Thèses sur le sujet « Motor Intelligence »
Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Motor Intelligence.
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleures thèses pour votre recherche sur le sujet « Motor Intelligence ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
1
Knight, Peter Robin. « Artificial intelligence and mathematical models for intelligent management of aircraft data ». Thesis, University of Southampton, 2012. https://eprints.soton.ac.uk/355717/.
Texte intégralRésumé :
Increasingly, large volumes of aircraft data are being recorded in an effort to adapt aircraft maintenance procedures from being time-based towards condition-based techniques. This study uses techniques of artificial intelligence and develops mathematical models to analyse this data to enable improvements to be made in aircraft management, affordability, availability, airworthiness and performance. In addition, it highlights the need to assess the integrity of data before further analysis and presents the benefits of fusing all relevant data sources together. The research effort consists of three separate investigations that were undertaken and brought together in order to provide a unified set of methods aimed at providing a safe, reliable, effective and efficient overall procedure. The three investigations are: 1. The management of helicopter Health Usage Monitoring System (HUMS) Condition Indicators (CIs) and their analysis, using a number of techniques, including adaptive thresholds and clustering. These techniques were applied to millions of CI values from Chinook HUMS data. 2. The identification of fixed-wing turbojet engine performance degradation, using anomaly detection techniques, applied to thousands of in-service engine runs from Tornado aircraft. 3. The creation of models to identify unusual aircraft behaviour, such as uncommanded flight control movements. Two Chinook helicopter systems were modelled and the models were applied to over seven hundred in-service flights. In each case, the existing techniques were directed toward a condition-based maintenance approach, giving improved detection and earlier warning of faults.
2
Gadoue, Shady Mostafa. « Artificial intelligence applied to speed sensorless induction motor drives ». Thesis, University of Newcastle Upon Tyne, 2009. http://hdl.handle.net/10443/1613.
Texte intégralRésumé :
During the last two decades there has been considerable development of sensorless vector controlled induction motor drives for high performance industrial applications. Such control strategies reduce the drive's cost, size and maintenance requirements while increasing the system's reliability and robustness. Parameter sensitivity, high computational effort and instability at low and zero speed can be the main shortcomings of sensorless control. Sensorless drives have been successfully applied for medium and high speed operation, but low and zero speed operation is still a critical problem. Much recent research effort is focused on extending the operating region of sensorless drives near zero stator frequency. Several strategies have been proposed for rotor speed estimation in sensorless induction motor drives based on the machine fundamental excitation model. Among these techniques Model Reference Adaptive Systems (MRAS) schemes are the most common strategies employed due to their relative simplicity and low computational effort. Rotor flux-MRAS is the most popular MRAS strategy and significant attempts have been made to improve the performance of this scheme at low speed. Artificial Intelligence (AI) techniques have attracted much attention in the past few years as powerful tools to solve many control problems. Common AI strategies include neural networks, fuzzy logic and genetic algorithms. The mam purpose of this work is to show that AI can be used to improve the sensorless performance of the well-established MRAS observers in the critical low and zero speed region of operation. This thesis proposes various novel methods based on AI combined with MRAS observers. These methods have been implemented via simulation but also on an experimental drive based around a commercial induction machine. Detailed simulations and experimental tests are carried out to investigate the performance of the proposed schemes when compared to the conventional rotor fluxMRAS. Various schemes are implemented and tested in real time using a 7.5 kW induction machine and a dSP ACE DS 1103 controller board. The results presented for these new schemes show the great improvement in the performance of the MRAS observer in both open loop and sensorless modes of operation at low and zero speed.
3
Shergold, Carol. « Sensory-motor coordination : adapting to disruptions ». Thesis, University of Sussex, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.341079.
Texte intégral
4
Ben, Amor Heni. « Imitation Learning of Motor Skills for Synthetic Humanoids ». Doctoral thesis, Technische Universitaet Bergakademie Freiberg Universitaetsbibliothek "Georgius Agricola", 2010. http://nbn-resolving.de/urn:nbn:de:bsz:105-qucosa-62877.
Texte intégralRésumé :
This thesis addresses the question of how to teach dynamic motor skills to synthetic humanoids. A general approach based on imitation learning is presented and evaluated on a number of synthetic humanoids, as well as a number of different motor skills. The approach allows for intuitive and natural specification of motor skills without the need for expert knowledge. Using this approach we show that various important problems in robotics and computer animation can be tackled, including the synthesis of natural grasping, the synthesis of locomotion behavior or the physical interaction between humans and robots.
5
Lucchetta, Linda. « La Business Intelligence per il monitoraggio delle vendite : il caso Ducati Motor Holding ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2016. http://amslaurea.unibo.it/11733/.
Texte intégralRésumé :
“La Business Intelligence per il monitoraggio delle vendite: il caso Ducati Motor Holding”.
L’obiettivo di questa tesi è quello di illustrare cos’è la Business Intelligence e di mostrare i cambiamenti verificatisi in Ducati Motor Holding, in seguito alla sua adozione, in termini di realizzazione di report e dashboard per il monitoraggio delle vendite.
L’elaborato inizia con una panoramica generale sulla storia e gli utilizzi della Business Intelligence nella quale vengono toccati i principali fondamenti teorici: Data Warehouse, data mining, analisi what-if, rappresentazione multidimensionale dei dati, costruzione del team di BI eccetera.
Si proseguirà mediante un focus sui Big Data convogliando l’attenzione sul loro utilizzo e utilità nel settore dell’automotive (inteso nella sua accezione più generica e cioè non solo come mercato delle auto, ma anche delle moto), portando in questo modo ad un naturale collegamento con la realtà Ducati.
Si apre così una breve overview sull’azienda descrivendone la storia, la struttura commerciale attraverso la quale vengono gestite le vendite e la gamma dei prodotti.
Dal quarto capitolo si entra nel vivo dell’argomento: la Business Intelligence in Ducati. Si inizia descrivendo le fasi che hanno fino ad ora caratterizzato il progetto di Business Analytics (il cui obiettivo è per l'appunto introdurre la BI i azienda) per poi concentrarsi, a livello prima teorico e poi pratico, sul reporting sales e cioè sulla reportistica basata sul monitoraggio delle vendite.
6
Baqqar, Mabrouka. « Machine performance and condition monitoring using motor operating parameters through artificial intelligence techniques ». Thesis, University of Huddersfield, 2015. http://eprints.hud.ac.uk/id/eprint/28315/.
Texte intégralRésumé :
Condition monitoring (CM) of gearboxes is a necessary activity due to the crucial importance of gearboxes in power transmission in most industrial applications. There has long been pressure to improve measuring techniques and develop analytical tools for early fault detection in gearboxes. This thesis develops new gearbox monitoring methods by demonstrating that operating parameters (static data) obtained from machine control processes can be used, rather than parameters obtained from vibration and acoustic measurements. Such a development has important implications for the future of CM techniques because it could greatly simplify the measurement process. To monitor the gearbox under different operating and fault conditions based on the static data, three artificial intelligence (AI) techniques: a general regression neural network (GRNN), a back propagation neural network (BPNN), and an adaptive neuro-fuzzy inference system (ANFIS) have been used successfully to capture nonlinear variations of the electric motor current and control parameters such as load settings and temperatures. The three AI systems are taught the expected values of current; load and temperature for the gearbox in a given condition, and then measured values obtained from the gearbox with a known fault introduced are assessed by each of the AI models to indicate the presence of this abnormal condition. The experimental results show that each of GRNN, BPNN and ANFIS are adequate and are able to serve as an effective tool for gearbox condition monitoring and fault detection. The main contributions of this study is to examine the performance of a model based condition monitoring approach by using just operating parameters for fault detection in a two stage gearbox. A model for current prediction is developed using an ANFIS, GRNN and BPNN which captures the complicated inter-relations between measured variables, and uses direct comparison between the measured and predicted values for fault detection.
7
PONTE, CHIARA. « Motor learning in Parkinson's Disease ». Doctoral thesis, Università degli studi di Genova, 2022. http://hdl.handle.net/11567/1094283.
Texte intégralRésumé :
The primary objective of these studies was to investigate motor learning processes through innovative approaches: (i) a new combined take that integrates motor sequence learning and motor adaptation; (ii) developing a computational model able to mimic real healthy subjects data. In this work, we first investigated the interaction of visuomotor adaptation and sequence learning in the early acquisition phase. Our results showed that simultaneous learning selectively affects both in different ways compared to sequence learning and rotation adaptation alone. Furthermore, our results showed significant differences in the number of anticipatory movements by comparing the combined task with the sequence learning alone. In particular, at the end of the training phase, subjects better anticipate the sequence in the explicit task alone. This finding corroborates a higher verbal score in the explicit task than combined. A second study aimed to understand motor learning processes in their early stage by computing a computational model that mimics the neurophysiological mechanism underpinning motor learning. We developed an integrated model (characterized by a combination of supervised and reinforcement learning) that exhibits a faster learning process concerning the classic reinforcement learning model.
This faster learning process of the integrated model was due to its improved exploration strategy. In particular, since the model gets the reward for the first time, the supervised component can learn a first coarse trajectory to reach the target. This trajectory affects the exploration by reducing its randomness and making it more focused on the target. The RL component then gradually improves the sub-optimal initial solution trial after trial while avoiding unneeded explorations as in the pure RL model. Similarly, the SL component gradually improves its behavior by receiving a better teaching signal (trajectories) from the RL processes. This mutual training between SL and RL thus produced a faster learning process.
8
Muñoz, Mauro Enrique de Souza. « Desenvolvimento artificial autônomo de um grafo sensório-motor auto-organizável ». Universidade de São Paulo, 2016. http://www.teses.usp.br/teses/disponiveis/3/3142/tde-28062016-081717/.
Texte intégralRésumé :
A teoria de Jean Piaget sobre o desenvolvimento da inteligência tem sido utilizada na área de inteligência computacional como inspiração para a proposição de modelos de agentes cognitivos. Embora os modelos propostos implementem aspectos básicos importantes da teoria de Piaget, como a estrutura do esquema cognitivo, não consideram o problema da fundamentação simbólica e, portanto, não se preocupam com os aspectos da teoria que levam à aquisição autônoma da semântica básica para a organização cognitiva do mundo externo, como é o caso da aquisição da noção de objeto. Neste trabalho apresentamos um modelo computacional de esquema cognitivo inspirado na teoria de Piaget sobre a inteligência sensório-motora que se desenvolve autonomamente construindo mecanismos por meio de princípios computacionais pautados pelo problema da fundamentação simbólica. O modelo de esquema proposto tem como base a classificação de situações sensório-motoras utilizadas para a percepção, captação e armazenamento das relações causais determiníscas de menor granularidade. Estas causalidades são então expandidas espaço-temporalmente por estruturas mais complexas que se utilizam das anteriores e que também são projetadas de forma a possibilitar que outras estruturas computacionais autônomas mais complexas se utilizem delas. O modelo proposto é implementado por uma rede neural artificial feed-forward cujos elementos da camada de saída se auto-organizam para gerar um grafo sensóriomotor objetivado. Alguns mecanismos computacionais já existentes na área de inteligência computacional foram modificados para se enquadrarem aos paradigmas de semântica nula e do desenvolvimento mental autônomo, tomados como base para lidar com o problema da fundamentação simbólica. O grafo sensório-motor auto-organizável que implementa um modelo de esquema inspirado na teoria de Piaget proposto neste trabalho, conjuntamente com os princípios computacionais utilizados para sua concepção caminha na direção da busca pelo desenvolvimento cognitivo artificial autônomo da noção de objeto.In artificial intelligence some cognitive agent models based on Jean Piaget\'s intelligence development theory have been proposed. Although the proposed models implement some fundamental aspects of this theory, like the cognitive schema struture, they do not consider the symbol grounding problem. Therefore, they are not concerned about the theoretical aspects that lead to the autonomous aquisition of the basic semantics needed by the cognitive organization of the agent\'s external world, as for the object concept aquisition. A computational cognitive scheme model inspired on Piaget\'s theory of the sensorimotor intelligence is presented. The scheme is autonomously built by computational mechanisms using principles considering the symbol grounding problem. The proposed scheme model uses sensory-motor situations to perceive, capture and store the finest grain deterministic causal relations. These causal relations are then expanded in time and space by more complex computational structures using the first ones. Those complex structures itselves are also designed in a way they can be used by more complex structures, expanding even further the causal relations in time and space. The proposed scheme model is implemented by an artificial neural network using feedforward architecture. The neural network output layer units progressively organized to compose a sensory-motor graph. Some known computational mechanisms from artificial inteligence were modified to fit to the zero semantic and the autonomous mental development paradigms, conceived in this work as the premises to handle the symbol grounding problem. The scheme model inspired by Piaget\'s theory implemented by the proposed self organizing sensorimotor graph in conjunction with the computational principles used, goes toward to the artificial autonomous cognitive development of the object concept.
9
Doss, Roger Ron. « The Relationship Between Low Achievement and Bodily-kinesthetic Intelligence in Fourth and Fifth Graders ». Thesis, University of North Texas, 1992. https://digital.library.unt.edu/ark:/67531/metadc332760/.
Texte intégralRésumé :
The problem of this study was an examination of the relationship between low achievement and physical abilities.This study focuses on the areas of musical, interpersonal, intrapersonal, spatial and bodily-kinesthetic abilities. This correlational study found that low achievers as a group, identified by achievement test scores, scored above the mean on a measure of motor ability. For children who are struggling to achieve in school, it would seem prudent to explore their strengths in other areas of intelligence. Further research is suggested in the areas of high and average achieving students' motor development.
10
Ogunoiki, Adebola Oluwaseyi. « Artificial road input data generation tool for vehicle durability assessment using artificial intelligence ». Thesis, University of Birmingham, 2015. http://etheses.bham.ac.uk//id/eprint/6156/.
Texte intégralRésumé :
Vehicle durability assessment in the automotive industry requires a good knowledge of the road load input the vehicle will experience while in service. This research explores the approach of artificial intelligence for predicting the road load input for road load simulation in the CAE environment prior to the development of a vehicle prototype. The multi-body dynamics (MBD) simulation of a quarter vehicle test rig, built with the specification of a commercial SUV, and the full vehicle of the same SUV were modelled and validated in SIMPACK using a simple tyre model developed using the tri-axial tyre test rig at the University of Birmingham. The models were used to carry out a road load data characterisation based on the variation in vehicle parameters. An artificial road input tool (ARIT) based on an optimised NARX artificial neural network architecture was developed to predict the road input for variants of vehicle for a particular vehicle behaviour over a road event. The results of the ARIT were used to run MBD simulations and compared with those from drive file iteration. The results of this research show a successful method of artificial intelligence for the generation of road load data from CAE simulations.
11
Miles, John Arthur Henry. « Artificial intelligence applied to data fusion and situation assessment for command and control ». Thesis, University of Southampton, 1988. https://eprints.soton.ac.uk/52251/.
Texte intégral
12
Bila, Hlengani Phanuel. « An assessment of application of intelligence-driven investigation in the combating of organised vehicle theft in Thohoyandou Cluster ». Thesis, University of Limpopo, 2015. http://hdl.handle.net/10386/1552.
Texte intégralRésumé :
Thesis (Ph. D. (Criminology)) -- University of Limpopo, 2015The research concerned with the aim of this study, was to assess the appli-cation of intelligence-driven investigation in combating organised motor vehicle theft. The strategic intelligence plan, information sharing and understanding of or-ganised vehicle theft, are some of approaches which will assist in dealing with the challenge of the illegal sale of vehicles and vehicle parts. There is indeed a need to address police corruption, if the battle against vehicle theft is to be realised. The objectives of this study were the following: to explain the strategic intelli-gence plan for investigating motor vehicle theft; to evaluate whether investiga-tions of organised motor vehicle theft in Thohoyandou cluster are intelligence-driven; to assess if the cluster uses intelligence offender profiling in investi-gations; to explore how intelligence-driven investigation assists in information sharing; and, to make recommendations for the improvement of intelligence-driven vehicle theft investigation. The researcher wanted to apply new research knowledge, in order to develop good practice in the field. This has been done by recommending new proced-ures to enhance performance and to improve the ways and means of combating organised vehicle theft. KEY TERMS Intelligence-driven investigation; strategic intelligence; intelligence cycle; crime investigations; modus operandi; offender profiling; organised crime; systems theory; motor vehicle theft; information sharing.
13
Kandarpa, Ramachandram. « REGS - a Regulatory Expert Guidance System for understanding and interpreting transportation regulations : application to Part 382 of the Federal Motor Carrier Safety Regulations / ». Thesis, This resource online, 1996. http://scholar.lib.vt.edu/theses/available/etd-09182008-063450/.
Texte intégral
14
Batista, Luciana [UNESP]. « A gênese da organização fonético-fonológica da fala ». Universidade Estadual Paulista (UNESP), 2005. http://hdl.handle.net/11449/91257.
Texte intégralRésumé :
Made available in DSpace on 2014-06-11T19:24:57Z (GMT). No. of bitstreams: 0
Previous issue date: 2005-09-19Bitstream added on 2014-06-13T20:52:54Z : No. of bitstreams: 1
batista_l_me_mar.pdf: 301132 bytes, checksum: cc34ffbc650427600130594a247e6d0a (MD5)A fala ou a necessidade de conversar não nasce bruscamente quando a criança emite suas primeiras palavras. O marco da aquisição dos fonemas, geralmente, é datado ao redor dos dezoito a vinte quatro meses, quando a criança é capaz de expressar-se oralmente de acordo com os padrões de uma língua. Mas, antes deste acontecimento, há uma etapa determinante na aquisição de tal conhecimento, denominada período sensório-motor. A evolução deste período é estudada quase sempre em função do meio social ou de estruturas inatas, independentes da evolução da inteligência, ou seja, da atividade da criança na interação com o meio. Com o objetivo de compreender a gênese da organização fonético-fonológica da fala na criança, realizou-se, neste trabalho, o estudo evolutivo das condutas vocais de crianças de três a dezoito meses, relacionando-as aos estágios do desenvolvimento sensório-motor descrito por Piaget. A pesquisa experimental demonstrou que as condutas sonoras produzidas no período sensório-motor evoluem correlativamente ao desenvolvimento da inteligência, em função da atividade e da interação da criança em seu meio, prolongando-se na fala estruturada de acordo com os padrões da língua.
Speech or the need to talk doesn't just suddenly start when a child says its first words. The period that phonetic sounds are acquired by a child, is usually about the time it starts to speak, that is when it is eighteen to twenty four months of age, when a child is able to express itself orally, by the standards of a language. But, before this happens, there is a phase that is important in speech acquisition, known as the motor-sensorial phase. The evolution of the speech acquisition period, is nearly always studied considering factors such as the child's social background and innate structures, independently of the evolution of the child's intelligence, that is, interaction with what surrounds it. In order to better understand the phonetic-phonological organization of children's speech, this study of the vocal evolution of children aged three to eighteen months, was made to determine the stages of motor-sensory development, described by Piaget. Experimental research work showed that the sounds emitted prior to the motor sensory phase, evolve towards intelligence development, and the amount of interaction the child has with it's surroundings, leads to speech that is structured by the standards of a language.
15
Gonçalves, Claudia Maria Ribeiro Martins. « Evolução do desenvolvimento motor e cognitivo de pré-escolares nascidos pré-termo de muito baixo peso egressos do método canguru ». Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/5/5141/tde-05062014-164359/.
Texte intégralRésumé :
INTRODUÇÃO: O Método Canguru é um tipo de assistência neonatal que consiste no contato precoce pele a pele entre a mãe e o recém-nascido de baixo peso, de forma crescente e pelo tempo que ambos entenderem ser prazeroso e suficiente, permitindo dessa forma, uma maior participação dos pais no cuidado a seu recém-nascido, acompanhado de suporte assistencial, por uma equipe de saúde treinada adequadamente. Tem como premissa a interação dinâmica e continua entre fatores biomédicos e ambientais. OBJETIVO: Descrever a evolução do desenvolvimento motor e cognitivo de pré-escolares de muito baixo peso egressos do Método Canguru, que receberam leite humano durante o período de internação. MÉTODOS: Foram estudadas 54 crianças prematuras, no período de Janeiro de 2004 a Janeiro de 2011 que participaram do Método Canguru e acompanhadas no Ambulatório de Seguimento, até a idade pré-escolar. Essas crianças foram submetidas ao teste Denver II, com um ano e novamente na idade préescolar quando foi aplicada a Escala de Maturidade Mental Colúmbia. METODOLOGIA ESTATÍSTICA: As variáveis contínuas serão descritas através de suas médias e desvios-padrão. Aquelas com comportamento não paramétrico, serão descritas através da mediana e do intervalo inter-quartil. As variáveis categóricas serão descritas através de suas proporções e intervalos de confiança de 95%. Para descartar a hipótese de nulidade será utilizado o nível de corte de 5%. RESULTADOS: Na amostra houve predominância do sexo feminino de 65%, e cerca de 30% dos RNPT foram PIG. As medianas do peso de nascimento e idade gestacional foram 1316g e 32 semanas, respectivamente. A mediana da idade materna foi de 28 anos, ensino fundamental completo com nove anos de estudo e a renda per capita de R$150,00. Entre as 54 crianças do estudo, 15% tiveram Hemorragia Perintraventricular grau I, 19% desenvolveram displasia broncopulmonar e nenhuma apresentou retinopatia da prematuridade. No teste Denver II de 54 crianças na idade de um ano corrigida, constatamos um risco no desempenho do desenvolvimento motor grosso de 31%, na linguagem 7%, psicossocial 6% e motor adaptativo 2%. Na idade pré-escolar observamos uma diminuição significativa do risco no desempenho do desenvolvimento para 4% em linguagem, 3% em motor grosso e 0% em psicossocial e motor adaptativo. Na idade pré-escolar o desempenho cognitivo se assemelhou a normalidade, quando comparado com a população brasileira, de acordo com a padronização da Escala Colúmbia. Os fatores de risco para o desempenho no desenvolvimento neuropsicomotor das crianças com um ano de idade corrigida estão associados ao tempo de internação e inicio da posição Canguru e foram estatisticamente significantes (p=0,009), (p=0,013), mesmo depois de ajustar à análise para as variáveis da idade gestacional, peso de nascimento, idade materna e sexo. Embora não tenha havido significância estatística, as crianças que foram amamentadas por mais tempo (meses) tiveram percentualmente menor risco para o desempenho neuropsicomotor. Nesta amostra constatamos em relação ao aleitamento materno total a mediana de sete meses e para o aleitamento exclusivo a mediana de três meses. CONCLUSÃO: A análise da evolução do desenvolvimento motor e cognitivo de pré-escolares nascidos pré-termo de muito baixo peso e egressos do Método Canguru, mostrou que, as crianças com um ano de idade corrigida, apresentaram 38% de risco no desempenho neuropsicomotor e ao atingirem a idade pré-escolar, apenas 5% demonstraram este risco. No que diz respeito ao desenvolvimento cognitivo, os valores obtidos foram percentualmente acima da média da população brasileira. Estes achados sugerem que as crianças que foram RNPT MBP alimentadas com leite humano durante sua internação e egressas do Método Canguru podem apresentar um desempenho no desenvolvimento tanto motor como cognitivo semelhante ao padrão de normalidadeINTRODUCTION: The Kangaroo Method is a perinatal care concerning skin contact between the mother and the low birth weight (LBW) newborn as long as both consider it pleasant and necessary. It allows greater parental participation in the care of their low birth weight newborn closely followed by properly trained healthcare professionals. The dynamic and continuous interaction between biomedical and environmental factors is its premise. OBJECTIVE: To describe the cognitive and motor development of children at preschool age that were born with very low birth weight (VLBW), former patients of the Kangaroo Method that were breastfed during hospital stay. METHOD: Fifty four preterm infants were studied between January 2004 and January 2011. The infants participated in the Kangaroo Method and they were followed up to preschool age by trained professionals in a followup ambulatory. These children were submitted to Denver II test by the time they were one year old and again at preschool age. Columbia Mental Maturity scale was applied to the children at preschool age. STATISTICAL ANALYSIS: The continual variables will be described by their averages and standard deviations. The nonparametric variables will be described by the medians and the interquartile interval. The categorical variables will be described by their proportions and the confidence interval of 95%. A 5% cutoff point will be applied to discard the null hypothesis. RESULTS: In the sample 65% were female, approximately 30% of the preterm newborn were small for the gestational age. Birth weight and gestational age medians were respectively 1316g and 32 weeks. Maternal age median was 28 years old. The mothers completed elementary school in nine years and their per capita income was R$ 150,00. The fifty four children involved in the study 15% had peri-intraventricular hemorrhage level 1, 19% had bronchopulmonary dysplasia and none had retinopathy of prematurity. The fifty four children were assessed at one year old, corrected age, to Denver II test and the following development risks were detected, 31% gross motor, 7% language, 6% psychosocial and 2% adaptive motor. At preschool age there was a considerable decrease in those parameters, 4% for language and 3% for gross motor 0% for psychosocial and adaptive motor. According to the Columbia scale standardization cognitive performance at preschool age resembled normality when compared with Brazilian population. Our study identified that the children involved had a higher performance than the population of reference (Brazilian population). Hospitalization period and the beginning of the Kangaroo position determined the risks factors for psychomotor development at one year old, corrected age, even after the adjustments in the analysis for gestational age, birth weight, mother\'s age and gender (p=0,009), (p=0,013) had been made. Although there was no statistical significance children breastfed for longer period had a lower psychomotor development risk. For the sample enrolled the median for total breastfeeding was 7 months and the exclusive breastfeeding 3 months. CONCLUSION: The Kangaroo Method had an impact on motor and cognitive developmental performance of the preschool age children born preterm with very low birth weight. At one year old, corrected age, the children concerned presented a 38% risk in psychomotor performance, however at preschool age the percentage dropped to 5%. The measured values for cognitive development were above the average for the Brazilian population. These findings suggest that very low birth weight preterm newborn that were breastfed during hospital stay and submitted to Kangaroo Method may present motor as well as cognitive developmental performances similar to normal standard
16
De, La Bourdonnaye François. « Learning sensori-motor mappings using little knowledge : application to manipulation robotics ». Thesis, Université Clermont Auvergne (2017-2020), 2018. http://www.theses.fr/2018CLFAC037/document.
Texte intégralRésumé :
La thèse consiste en l'apprentissage d'une tâche complexe de robotique de manipulation en utilisant très peu d'aprioris. Plus précisément, la tâche apprise consiste à atteindre un objet avec un robot série. L'objectif est de réaliser cet apprentissage sans paramètres de calibrage des caméras, modèles géométriques directs, descripteurs faits à la main ou des démonstrations d'expert. L'apprentissage par renforcement profond est une classe d'algorithmes particulièrement intéressante dans cette optique. En effet, l'apprentissage par renforcement permet d’apprendre une compétence sensori-motrice en se passant de modèles dynamiques. Par ailleurs, l'apprentissage profond permet de se passer de descripteurs faits à la main pour la représentation d'état. Cependant, spécifier les objectifs sans supervision humaine est un défi important. Certaines solutions consistent à utiliser des signaux de récompense informatifs ou des démonstrations d'experts pour guider le robot vers les solutions. D'autres consistent à décomposer l'apprentissage. Par exemple, l'apprentissage "petit à petit" ou "du simple au compliqué" peut être utilisé. Cependant, cette stratégie nécessite la connaissance de l'objectif en termes d'état. Une autre solution est de décomposer une tâche complexe en plusieurs tâches plus simples. Néanmoins, cela n'implique pas l'absence de supervision pour les sous tâches mentionnées. D'autres approches utilisant plusieurs robots en parallèle peuvent également être utilisés mais nécessite du matériel coûteux. Pour notre approche, nous nous inspirons du comportement des êtres humains. Ces derniers généralement regardent l'objet avant de le manipuler. Ainsi, nous décomposons la tâche d'atteinte en 3 sous tâches. La première tâche consiste à apprendre à fixer un objet avec un système de deux caméras pour le localiser dans l'espace. Cette tâche est apprise avec de l'apprentissage par renforcement profond et un signal de récompense faiblement supervisé. Pour la tâche suivante, deux compétences sont apprises en parallèle : la fixation d'effecteur et une fonction de coordination main-oeil. Comme la précédente tâche, un algorithme d'apprentissage par renforcement profond est utilisé avec un signal de récompense faiblement supervisé. Le but de cette tâche est d'être capable de localiser l'effecteur du robot à partir des coordonnées articulaires. La dernière tâche utilise les compétences apprises lors des deux précédentes étapes pour apprendre au robot à atteindre un objet. Cet apprentissage utilise les mêmes aprioris que pour les tâches précédentes. En plus de la tâche d'atteinte, un predicteur d'atteignabilité d'objet est appris. La principale contribution de ces travaux est l'apprentissage d'une tâche de robotique complexe en n'utilisant que très peu de supervisionThe thesis is focused on learning a complex manipulation robotics task using little knowledge. More precisely, the concerned task consists in reaching an object with a serial arm and the objective is to learn it without camera calibration parameters, forward kinematics, handcrafted features, or expert demonstrations. Deep reinforcement learning algorithms suit well to this objective. Indeed, reinforcement learning allows to learn sensori-motor mappings while dispensing with dynamics. Besides, deep learning allows to dispense with handcrafted features for the state spacerepresentation. However, it is difficult to specify the objectives of the learned task without requiring human supervision. Some solutions imply expert demonstrations or shaping rewards to guiderobots towards its objective. The latter is generally computed using forward kinematics and handcrafted visual modules. Another class of solutions consists in decomposing the complex task. Learning from easy missions can be used, but this requires the knowledge of a goal state. Decomposing the whole complex into simpler sub tasks can also be utilized (hierarchical learning) but does notnecessarily imply a lack of human supervision. Alternate approaches which use several agents in parallel to increase the probability of success can be used but are costly. In our approach,we decompose the whole reaching task into three simpler sub tasks while taking inspiration from the human behavior. Indeed, humans first look at an object before reaching it. The first learned task is an object fixation task which is aimed at localizing the object in the 3D space. This is learned using deep reinforcement learning and a weakly supervised reward function. The second task consists in learning jointly end-effector binocular fixations and a hand-eye coordination function. This is also learned using a similar set-up and is aimed at localizing the end-effector in the 3D space. The third task uses the two prior learned skills to learn to reach an object and uses the same requirements as the two prior tasks: it hardly requires supervision. In addition, without using additional priors, an object reachability predictor is learned in parallel. The main contribution of this thesis is the learning of a complex robotic task with weak supervision
17
De, Scalzi Marika. « An embodied approach to language comprehension in probable Alzheimer's Disease : could perceptuo-motor processing be a key to better understanding ? » Thesis, University of Sussex, 2013. http://sro.sussex.ac.uk/id/eprint/47190/.
Texte intégralRésumé :
One of the central tenets of the embodied theory of language comprehension is that the process of understanding prompts the same perceptuo-motor activity involved in actual perception and action. This activity is a component of comprehension that is not memory–dependent and is hypothesized to be intact in Alzheimer's Disease (AD). Each article in this thesis is aimed at answering the question whether individuals with probable AD, healthy older adults and younger adults show differences in their performance on tests where perceptual and motoric priming take place during language comprehension. The second question each article asks is whether language comprehension in AD can be facilitated by the specific use of this perceptual and motoric priming. Article I examines whether the way individuals with pAD represent verbs spatially matches the way healthy older and younger adults do, and how stable these representations are. It also explores in what way spatial representations may relate to verb comprehension, more specifically, whether representations matching the norms translate into a better quality of verb comprehension. Article II tests the interaction between the verbs' spatial representations taking place during comprehension and perceptual cues - compatible and incompatible to the representations - in order to investigate whether individuals with pAD show differences in susceptibility to perceptual cues, compared to healthy older and younger participants. The second aim of this article is to explore in what way performance on a word-picture verification task can be affected, with reference to the fact that in previous studies on young participants, both priming and interference have resulted from the interaction of linguistic and perceptual processing. Article III explores the Action Compatibility Effect (ACE) (Glenberg & Kaschak, 2002) with the aim of finding out whether the ACE exists for volunteers with pAD and whether it can facilitate language comprehension. The order of presentation of language and movement is manipulated to establish whether there is a reciprocal relationship between them. This information could be crucial in view of possible applications to individuals with pAD. These articles test, for the first time, the effects of the manipulation of the perceptuo-motor component during language comprehension in individuals with pAD; they are intended as a methodological exploration contributing to a better understanding of the potential of embodiment principles to support language comprehension changes associated with pAD. Embodiment effects need to be studied further with a view to putting them to use in either clinical or real-life applications.
18
Liu, Dan. « Computational and psychophysical studies of goal-directed arm movements ». Diss., [La Jolla] : University of California, San Diego, 2008. http://wwwlib.umi.com/cr/ucsd/fullcit?p3331228.
Texte intégralRésumé :
Thesis (Ph. D.)--University of California, San Diego, 2008.Title from first page of PDF file (viewed June 1, 2009). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 124-131).
19
Sunčica, Poček. « Specifičnosti antropološkog statusa mladih odbojkašica Vojvodine ». Phd thesis, Univerzitet u Novom Sadu, Fakultet sporta i fizičkog vaspitanja u Novom Sadu, 2015. https://www.cris.uns.ac.rs/record.jsf?recordId=95381&source=NDLTD&language=en.
Texte intégralRésumé :
Na uzorku od 358 devojčica sa teritorije Vojvodine, uzrasta od 11,50 – 16 decimalnih godina, od kojih 186 odbojkašica (najmanje tri godine u trenažnom procesu),i 172 devojčice koje se ne bave organizovanom fizičkom aktivnošću, sprovedeno je istraživanje morfoloških karakteristika, motoričkih i intelektualnih sposobnosti. Cilj istraživanja je bio da se utvrde specifičnosti mladih odbojkašica u odnosu na devojčice koje se ne bave organizovanom fizičkom aktivnošću, testiranjem kako kvantitativnih, tako i razlika u strukturi sposobnosti definisanih predmetom istraživanja. Uvidom u rezultate, možemo zaključiti da se devojčice koje se bave odbojkom odlikuju većim vrednostima telesne visine i telesne mase, obima grudi,nadlaktice i podlaktice u odnosu na devojčice koje se ne bave organizovanom fizičkom aktivnošću. Iako u varijablama za procenu potkožnog masnog tkiva nijedošlo do statistički značajnih razlika, u dve od tri grupe vidimo da su kod odbojkašica manje vrednosti varijabli kožnih nabora, ali ne i statistički značajno manje.Navedene razlike grupa devojčica u prostoru morfoloških karakteristika su proizašle na osnovu procesa selekcije i rasta i razvoja (telesna visina, volumen i masa tela), dok se manje vrednosti u potkožnom masnom tkivu odbojkašica mogu pripisatitrenažnom tretmanu bavljenja odbojkom. Na osnovu rezultata primenjene kongruencije ekstrahovanih faktora, možemo zaključiti da se grupe devojčica nerazlikuju u strukturi prvih izolovanih faktora – koji definišu strukturu morfološkog prostora, ali da postoji razlika u strukturi drugih i trećih faktora koji definišuvarijable za procenu motoričkih sposobnosti i inteligencije. Posebno je važno sagledati razliku u strukturi drugih faktora po uzrastu, odnosno važnostpojedinih motoričkih varijabli gde se vidi da je na uzorku odbojkašica motorički prostor mnogo homogeniji, jasnije definisan, sa dominacijom varijabliza procenu intenziteta i trajanja ekscitacije i struktuiranja kretanja. Na osnovu sprovedenog istraživanja o specifičnostima antropološkog prostoradve grupe devojčica starijeg školskog uzrasta, a u skladu sa postavljenim ciljevima i zadacima i u kome su proveravane definisane hipoteze, može se generalnozaključiti da se devojčice koje su u trenažnom programu – odbojkašice statistički značajno razlikuju u morfološkom i motoričkom prostoru od ispitanica kojese ne bave organizovanom fizičkom aktivnošću, dok u intelektualnom funkcionisanju dve grupe ispitanica nisu uočene statistički značajne razlike.A research of morphological features, motor abilities and intelligence was carried out on the sample of 358 girls from the territory of Vojvodina, 11, 50 – 16 years old, out of which 186 female volleyball players (at least three years in training process) and 172 girls that do not practice organized physical activities. The aim of this study was to determine the specificity of young volleyball players compared to girls who are not involved in physical activity, testing of quantitative as well as differences in the structure of skills defined by the subject of research. After examining the results, we can conclude that girls engaged in volleyball are characterized by higher values of body height and body weight, chest circumference, upper arm and forearm girth inrelation to girls who are not involved in physical activity. Although there were no statistically significant differences in the variables for estimating body fat, on the basis of the differences in two of the three groups, we see lower skin fold values of volleyball players, but not significantly lower. These differences of girls in the area of morphological characteristics are derived on the basis of the selection processand the growth and development (height, volume and mass of the body), while the lower values in the subcutaneous adipose tissue of volleyball players can be attributed to the training treatment practicing volleyball. Based on the results of applied congruence of factors extracted, it can be concluded that groups ofgirls do not differ in the structure of the first isolated factors - that define the structure of the morphological space, but there is a difference in the structure of the second and third factors that define the variables of motor abilities and intelligence. It is particularly important to see the difference in the structure of other factors,by age or importance of certain motor variables by which can be seen that the sample of volleyball players in the motor space is far more homogeneous, more clearly defined, with the domination of variables regarding the intensity and duration of excitation and structuring of movement. On the basis of the research on thespecificity of the anthropological area, two groups of girls of school age, in line with the set goals and tasks in which they checked defined hypotheses, a general conclusion is that girls who are in the training program - volleyball players differ significantly in morphology and motor area in respect of girls who are notinvolved in physical activity, while in the intellectual functioning of two groups ofsubjects were not observed statistically significant differences.
20
Parchemal, Yannick. « Sepiar : un systeme a base de connaissance qui apprend a utiliser efficacement une expertise ». Paris 6, 1988. http://www.theses.fr/1988PA066465.
Texte intégral
21
Åström, Emil. « AI-motor : Artificiell intelligens för spel ». Thesis, Mittuniversitetet, Avdelningen för informations- och kommunikationssystem, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-22234.
Texte intégralRésumé :
Artificiell intelligens (AI) är en stor del i dagens datorspel. För att få inblick i komplexiteten runt AI i spelutveckling och för att förstå delar som AI består av har detta projekt genomförts. Målet var att skapa en AI-motor från grunden med bra grundplattform som är enkel att bygga vidare på. Innan projektet startade utfördes en förundersökning där olika alternativ för kartrepresentationer och grafsökningsalgoritmer togs fram. Utvecklingen av AI-motorn har haft ett starkt beroende till projektet där en spelmotor utvecklats av Niklas Ekman och Christian Mesch. Detta projekt har utförts enligt den agila systemutvecklingsmetoden Scrum. Ett versionshanteringssystem har använts för att enkelt kunna dela källkod mellan projekten. AI-motorn har utvecklats i C++ och för operativsystemen Ubuntu och OSX. AI-motorn består av fyra huvuddelar; logik, navigering, kommunikation och AI-objekt. Logiken är hjärnan i AI-motorn, navigeringen använder sig av navmesh som kartrepresentation och A*-algoritmen är den grafsökningsalgoritm som har valts. Kommunikation sker mellan AI-motorn och spelmotorn för att kunna dela på funktionalitet. AI-objekten är främst informationsklasser som t.ex. håller reda på antalet registrerade datorstyrda spelare. Valet av metod för kartrepresentation avgjordes av att navmesh enkelt kunde genereras automatiskt med hjälp av verktyg vilket var svårare för de andra alternativen. A* valdes som grafsökningsalgoritm eftersom den gav en korrekt väg med minst antal beräkningar. AI-motorn uppfyller de krav som ställdes innan utvecklingen påbörjades och är en bra grund för att lätt kunna utöka motorn med mer avancerad funktionalitet, men det finns så klart förbättringar som kan göras.
22
Guimarães, ádller de Oliveira. « Algoritmo genético aplicado no controle de posição do rotor de um motor de corrente contínua com rejeição a distúrbios por ação feedforward ». Universidade Federal Rural do Semi-Árido, 2013. http://bdtd.ufersa.edu.br:80/tede/handle/tede/517.
Texte intégralRésumé :
Made available in DSpace on 2016-08-31T13:33:36Z (GMT). No. of bitstreams: 1
AdllerOG_DISSERT.pdf: 1624176 bytes, checksum: b3a8115396f3b1d6c0110178978f22e3 (MD5)
Previous issue date: 2013-12-27The versatility of direct current machines combined with the relative simplicity of their drive systems ensures its continued use in a wide variety of applications in industrial electrical systems, more specifically in applications that requiring a wide range of speed and position control of the rotor. In this work, a new method for tuning Proportional-Integral-Derivative (PID) controllers with disturbance rejection using Genetic Algorithm (GA) is proposed. The proportional, integral and derivative gains, designed to control the rotor position of DC motor are optimized using GA in group with Ziegler - Nichols technique, and the rejection of disturbances is obtained from the implementation of feedforward control in the algorithm. Preliminary results show that the proposed GA gave a satisfactory response, both in transitional regime as at steady state, and shows good performance in disturbance rejection. To validate this technique, the results obtained were compared with other methods in literature
A versatilidade das máquinas de corrente contínua, combinada com a relativa simplicidade dos seus respectivos sistemas de acionamento, assegura a sua contínua utilização numa ampla variedade de aplicações em sistemas elétricos industriais, mais especificamente, em aplicações que exigem uma vasta gama de controle da velocidade e posição do rotor. Neste trabalho, um novo método de sintonia de controladores Proporcional-Integral-Derivativo (PID) com rejeição a distúrbios usando Algoritmo Genético (AG) é proposto. Os ganhos proporcional, integral e derivativo, projetados para controlar a posição do rotor do motor CC, são otimizados utilizando AG em conjunto com a técnica de Ziegler-Nichols, e a rejeição a distúrbios é obtida a partir da implementação no algoritmo do controle por ação Feedforward. Resultados preliminares mostram que o AG proposto, apresentou desempenho satisfatório da resposta, tanto em regime transitório quanto no estado estacionário, além de apresentar boa performance na rejeição a distúrbios. Para validar a técnica utilizada, os resultados obtidos foram comparados com outros métodos publicados na literatura
23
Fouet, Jean-Marc. « Utilisation de connaissances pour améliorer l'utilisation de connaissances : la machine Gosseyn ». Paris 6, 1987. http://www.theses.fr/1987PA066378.
Texte intégralRésumé :
Le double problème de l'acquisition de connaissances et de leur utilisation efficace est abordé. Sont ensuite établies les contraintes qui portent d'une part sur la représentation externe et d'autre part sur la représentation interne, en étudiant la nécessité et les limites du développement incrémental. Dans une deuxième partie, la simulation d'une machine d'inférence censée répondre à ces exigences est étudiée. Fondée sur une architecture à "flot de données", cette machine met à profit des connaissances diverses pour, d'une part, assurer le contrôle de l'interprétation de connaissances et, d'autre part, procéder à la compilation incrémentale, sous forme de nouveaux circuits, de ces mêmes connaissances
24
Batista, Luciana. « A gênese da organização fonético-fonológica da fala / ». Marília : [s.n.], 2005. http://hdl.handle.net/11449/91257.
Texte intégralRésumé :
Orientador: Adrian Oscar Dongo MontoyaBanca: Lourenço Chacon Jurado Filho
Banca: Jaime Luiz Zorzi
Resumo: A fala ou a necessidade de conversar não nasce bruscamente quando a criança emite suas primeiras palavras. O marco da aquisição dos fonemas, geralmente, é datado ao redor dos dezoito a vinte quatro meses, quando a criança é capaz de expressar-se oralmente de acordo com os padrões de uma língua. Mas, antes deste acontecimento, há uma etapa determinante na aquisição de tal conhecimento, denominada período sensório-motor. A evolução deste período é estudada quase sempre em função do meio social ou de estruturas inatas, independentes da evolução da inteligência, ou seja, da atividade da criança na interação com o meio. Com o objetivo de compreender a gênese da organização fonético-fonológica da fala na criança, realizou-se, neste trabalho, o estudo evolutivo das condutas vocais de crianças de três a dezoito meses, relacionando-as aos estágios do desenvolvimento sensório-motor descrito por Piaget. A pesquisa experimental demonstrou que as condutas sonoras produzidas no período sensório-motor evoluem correlativamente ao desenvolvimento da inteligência, em função da atividade e da interação da criança em seu meio, prolongando-se na fala estruturada de acordo com os padrões da língua.
Abstract: Speech or the need to talk doesn't just suddenly start when a child says its first words. The period that phonetic sounds are acquired by a child, is usually about the time it starts to speak, that is when it is eighteen to twenty four months of age, when a child is able to express itself orally, by the standards of a language. But, before this happens, there is a phase that is important in speech acquisition, known as the motor-sensorial phase. The evolution of the speech acquisition period, is nearly always studied considering factors such as the child's social background and innate structures, independently of the evolution of the child's intelligence, that is, interaction with what surrounds it. In order to better understand the phonetic-phonological organization of children's speech, this study of the vocal evolution of children aged three to eighteen months, was made to determine the stages of motor-sensory development, described by Piaget. Experimental research work showed that the sounds emitted prior to the motor sensory phase, evolve towards intelligence development, and the amount of interaction the child has with it's surroundings, leads to speech that is structured by the standards of a language.
Mestre
25
Beldiceanu, Nicolas. « Langage de regles et moteur d'inferences bases sur des contraintes et des actions : application aux reseaux de petri ». Paris 6, 1988. http://www.theses.fr/1988PA066053.
Texte intégral
26
Martin-Clouaire, Roger. « Representation et utilisation de meta-connaissances et d'informations imprecises ou incertaines ». Toulouse 3, 1986. http://www.theses.fr/1986TOU30246.
Texte intégralRésumé :
Dans l'approche developpee, les meta connaissances sont exprimees declarativement via des metaregles ayant pour role de: suggerer comment utiliser les connaissances de base; orienter le systeme sur les donnees adequates; permettre de hierarchiser les etapes du raisonnement et restructurer les donnees suivant des considerations spatiales. Quant au moteur d'inference spii (systeme de propagation de l'imprecision et de l'incertitude), il permet un traitement homogene, dans le cadre de la theorie des possibilites, des informations (regles ou faits) tant imprecises qu'incertaines
27
Ho, Tu Bao. « Systemes experts et analyse de donnees ». Paris 6, 1987. http://www.theses.fr/1987PA066128.
Texte intégralRésumé :
Le travail concerne: 1) la construction d'un moteur d'inference adapte aux logiciels statistiques avec une contribution au formalisme de raisonnement; 2) la mise en oeuvre d'un systeme expert guidant l'utilisation du logiciel sicla, permettant aux non statisticiens d'utiliser facilement les methodes d'analyse des donnees; 3) la construction d'une base de regles a partir de donnees observees par la methode de classification conceptuelle cabro; 4) la simplification d'une base de regles a l'aide du tableau rpcb et de regles intermediaires detectees
28
Lennartsson, Alexander, et Martina Blomberg. « Fault Detection in Permanent Magnet Synchronous Motors using Machine Learning ». Thesis, Luleå tekniska universitet, Institutionen för system- och rymdteknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-84909.
Texte intégralRésumé :
In the aviation industry, safety and robustness are the number one priorities, which is why they use well-tested systems such as hydraulic actuators. However, drawbacks such as high weight and maintenance have pushed the industry toward newer, electrical, actuators that are more efficient and lighter. Electrical actuators, on the other hand, have some reliability issues. In particular, short circuits in the stator windings of Permanent-Magnet SynchronousMotors (PMSMs), referred to as Inter-Turn Short Faults (ITSFs), are the dominating faults, and is the focus of this thesis. ITSFs are usually challenging to detect and often do not become noticeable until the fault has propagated, and the motor is on the verge of being destroyed. This thesis investigates the possibility of detecting ITSFs in a PMSM, at an early stage when only one turn is shorted. The method is limited to finding the faults using ML algorithms. Both an experiential PMSM and a simulated model of the experimental PMSM, with the ability to induce an ITSF, were used to collect the data. Several Machine Learning (ML) models were developed, and then trained and tested with the collected data. The results show that four of the tested ML models, being: Random Forest, Gaussian SVM, KNN, and the CNN, all achieve an accuracy exceeding 95%, and that the fault can be found at an early stage in a PMSM with three coils connected in parallel in each phase. The results also show that the ML models are able to identify the ITSF when the simulated data is downsampled to the same frequency as the experimental data. We conclude that the ML models, provided in this study, can be used to detect an ITSF in a simulated PMSM, at an early stage when only one turn is shorted, and that there is great potential for them to detect ITSFs in a physical motor as well.
29
Wen, Xin. « A hybrid intelligent technique for induction motor condition monitoring ». Thesis, University of Portsmouth, 2011. https://researchportal.port.ac.uk/portal/en/theses/a-hybrid-intelligent-technique-for-induction-motor-condition-monitoring(bafbf73a-0813-44f8-8f00-9212cc54c890).html.
Texte intégralRésumé :
The objective of this research is to advance the field of condition monitoring and fault diagnosis for induction motors. This involves processing the signals produced by induction motors, classifying the types and estimating the severity of induction motors faults. A typical process of condition monitoring and fault diagnosis for induction motors consists of four steps: data acquisition, signal analysis, fault detection and post-processing. A description of various kinds of faults that can occur in induction motors is presented. The features reflecting faults are usually embedded in transient motor signals. The signal analysis is a very important step in the motor fault diagnosis process, which is to extract features which are related to specific fault modes. The signal analysis methods available in feature extraction for motor signals are discussed. The wavelet packet decomposition results consist of the time-frequency representation of a signal in the same time, which is inherently suited to the transient events in the motor fault signals. The wavelet packet transform-based analysis method is proposed to extract the features of motor signals. Fault detection has to establish a relationship between the motor symptoms and the condition. Classifying motor condition and estimating the severity of faults from the motor signals have never been easy tasks and they are affected by many factors. AI techniques, such as expert system (ES), fuzzy logic system (FLS), artificial neural network (ANN) and support vector machine (SVM), have been applied in fault diagnosis of very complex system, where accurate mathematical models are difficult to be built. These techniques use association, reasoning and decision making processes as would the human brain in solving diagnostic problems. ANN is a computation and information processing method that mimics the process found in biological neurons. But when ANN-based methods are used for fault diagnosis, local minimums caused by the traditional training algorithms often result in large approximation error that may destroy their reliability. In this research, a novel method of condition monitoring and fault diagnosis for induction motor is proposed using hybrid intelligent techniques based on WPT. ANN is trained by improved genetic algorithm (IGA). WPT is used to decompose motor signals to extract the feature parameters. The extracted features with different frequency resolutions are used as the input of ANN for the fault diagnosis. Finally, the proposed method is tested in 1.5 kW and 3.7 kW induction motor rigs. The experimental results demonstrate that the proposed method improves the sensitivity and accuracy of the ANN-based methods of condition monitoring and fault diagnosis for induction motors.
30
Allaith, Noori A. « Intelligent power module for variable speed AC motor drives ». Thesis, University of Bristol, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.361134.
Texte intégral
31
Uddin, Mohammad Nasir. « Intelligent control of an interior permanent magnet synchronous motor drive ». Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0021/NQ55128.pdf.
Texte intégral
32
Trewin, S. M. « Towards intelligent, adaptive input devices for users with motor disabilities ». Thesis, University of Edinburgh, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.663035.
Texte intégralRésumé :
This thesis presents an unusual application of user modelling, the domain of interest being the physical abilities of a user. Specifically, a model which identifies aspects of keyboard use with which a user has difficulty is presented. An empirical study of keyboard and mouse use by people with and without motor disabilities is described. The study focuses on common input errors due to physical innacuracies in using these devices. For the majority of these errors, there exist keyboard or mouse configuration facilities intended to reduce or eliminate them. While such facilities are now integrated into the majority of modern operating systems, there is little published data describing their effect on keyboard or mouse usability. This thesis offers evidence that they can be extremely useful, even essential, but that further research and interface development are required. The user model focuses on four of the most commonly observed keyboard difficulties, and makes recommendations for settings for three keyboard configuration facilities. As a user modelling task, this application presents a number of interesting challenges for which traditional user modelling techniques are inadequate . The users to be modelled may tire easily, and may have cognitive disabilities in addition to physical ones. This makes it difficult to gain information by questioning users, or requiring them to perform given tasks. On shared machines many different users with very different requirements will be encountered, while individuals may also have varying requirements. This calls for a dynamic technique. This thesis attempts to show that it is feasable to draw accurate conclusions about a user's keyboard configuration requirements without questioning them, or requiring them to perform controlled tasks. The model presented records for a user's input unintrusively, and examines this input for evidence of physical errors or difficulties. Conclusions are based on the assumption that the user is typing English text. Any other textual language could be used.
33
Kubba, Ammar Issam Salih. « Intelligent tyre technologies ». Thesis, University of Birmingham, 2018. http://etheses.bham.ac.uk//id/eprint/8363/.
Texte intégralRésumé :
This thesis reports an investigation about range of intelligent tyre technologies. A piezoelectric transducer was utilized to measure tyre inner liner strain in the longitudinal direction. Tyre driving condition can be recognized from different tyre strain pattern data which is collected from the piezoelectric transducers. Tyre load, slip angle, and rolling speed can be identified from the tyre strain pattern throughout the tyre contact patch area strain pattern. A novel circumferential four-chamber tyre concept was designed, manufactured and tested in this study. These four-chamber prototypes can have independent inflation pressure in each chamber to provide wide range of tyre behavior which is suitable for different road surfaces and driving conditions. The multi-chamber tyre has a range of modes to accommodate urban and motorway driving for rolling resistance and grip control. A multi-chamber tyre finite element model using ABAQUS software was developed from a conventional tyre model to design and validate these tyre prototypes. These multi-chamber tyre prototypes were manufactured with the assistance of Fusion Innovations Ltd and tested in the University of Birmingham tyre test rig. Finally, a shape memory alloy valve design was investigated to control the air flow in the multi-chamber tyre.
34
Adjaoute, Akli. « Rylm : générateur de systèmes experts pour les problèmes d'aide aux diagnosticsYkra : système d'enseignement ». Paris 6, 1988. http://www.theses.fr/1988PA066005.
Texte intégral
35
León, Jessica (Jessica E. ). « Manufacturing of the motor mount of the uBox, an intelligent pillbox ». Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/45330.
Texte intégralRésumé :
Thesis (S.B.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, 2008.Includes bibliographical references (leaf 25).
The uBox has been developed to be a solution to the medication adherence problems for a multitude of applications. The box offers a way to collect and formulate patient and volunteer adherence data for use in the field while offering a critical locking feature for the pills inside the box. The uBox is currently transitioning to production on the order of hundreds. A rig was designed to reduce error in the assembly of the locking mechanism. This includes a device to mount the motor accurately and repeatably which is critical to the function of the uBox. In addition, the strengths of different glues for the mounting of the motor were analyzed and optimal glue was determined.
by Jessica León.
S.B.
36
Sangha, Mahavir Singh. « Intelligent fault diagnosis for automative engines and real data evaluation ». Thesis, Liverpool John Moores University, 2008. http://researchonline.ljmu.ac.uk/5867/.
Texte intégral
37
Sekar, Booma Devi. « Hybrid intelligent technology based fault diagnosis system for squirrel cage induction motor ». Thesis, University of Macau, 2007. http://umaclib3.umac.mo/record=b1678023.
Texte intégral
38
Li, Li Wang Fei-Yue. « Advanced motion control and sensing for intelligent vehicles ». New York : Springer, 2007. http://www.myilibrary.com?id=113830.
Texte intégral
39
Lanzoni, Diego. « Realizzazione di un sistema di Social Business Intelligence basato sul motore SPSS ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2013. http://amslaurea.unibo.it/5013/.
Texte intégral
40
Zhao, Gui Quan. « Design, control and experimental testing of intelligent variable dual-fuel automotive engines ». Thesis, University of Macau, 2017. http://umaclib3.umac.mo/record=b3691635.
Texte intégral
41
Andrade, Eduardo Filipe Ferreira. « Desenvolvimento de motor de BI (Business Intelligence) ». Master's thesis, 2007. http://hdl.handle.net/10451/4662.
Texte intégralRésumé :
Trabalho de projecto de mestrado em Engenharia Informática, apresentado à Universidade de Lisboa, através da Faculdade de Ciências, 2007A informação, como factor que sustenta o conhecimento e o seu tratamento, é de extrema importância pois esta constitui parte integrante de processos de trabalho e decisões que aproximam as organizações dos seus propósitos. Os sistemas de Business Intelligence utilizam os dados disponíveis nas organiza-ções para disponibilizar informação relevante para a tomada de decisão, combinando um conjunto de ferramentas de interrogação e exploração dos dados com ferramentas que permitem a geração de relatórios, para produzir informação que será posteriormente utilizada pela gestão de topo das organizações, no suporte à tomada de decisão. Este projecto consiste no estudo de alguns produtos de exploração de dados que utilizam a tecnologia OLAP (On-line Analytical Processing) e posterior integração destes produtos (Mondrian & jPivot) numa aplicação comercial. O objectivo desta integração é enriquecer a aplicação dotando-a de funcionalidades de exploração de dados que permitem aos utilizadores da aplicação ter um acesso facilitado à informação contida no sistema operacional.
Information play a role of high importance in the process of knowledge aquisition, so that good decisions can be taken to evolve in a positive manner. Business Intelligence systems use the data available in the organizations to share relevant information, combining a set of query and analysis tools, in order to produce information that may be used afterwards by the higher levels of the organization supporting the decision making processes. This project relies on the study of some analysis software tools that use OLAP (On-line Analytical Processing) and subsequent integration of this tools (Mondrian & jPivot) in another software product. The main purpose of this integration is to enrich the application, endowing it with features of data analysis allowing users to access information that relies on the operational system.
42
Simão, Carolina Gonçalves Silva. « Artificial intelligence for fraud detection in motor insurance sector ». Master's thesis, 2022. http://hdl.handle.net/10362/133845.
Texte intégralRésumé :
Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data ScienceOne of the major problems in the insurance sector is related to fraud, aside from tax fraud, insurance fraud is the most practiced fraud in the world since insurance, by its nature is very susceptible to it. Fraud could be minimized by investigating each claim that occurs but that also means an increase of the costs for the insurance companies. The fraudulent clients or agents that will be caught with the investigation and the amount of money spent by looking into every new claim is not worth it. Insurance fraud is usually caught only when the fraudsters get greedy and it becomes obvious that they are involved in a scheme. To minimize the investigation costs by only looking at suspicious claims, this project tries to identify the ones that are worth to scrutinize, through machine learning techniques. Five different predictive models will be used: Logistic Regression, Decision Tree, Random Forest, Neural Network and Gradient Boosting. The goal is to build an optimal model that will determine which automobile claims have higher probability of being fraudulent. An efficient fraud management can reduce costs, minimize claims and increase profits. This goal was accomplished with a Gradient Boosting classifier with 400 estimators, that is able to predict correctly 49% of the fraudulent claims, with 75% less investigated claims. There is still room for improvement by introducing the expected claim and investigation costs in the model. Since only the ones with significant costs would be worth to open an investigation, an even greater decrease in the number of investigated claims would be possible and, consequently, a decrease in the company’s costs with claims. Also, it would be expected that the claims with higher costs are more likely fraudulent than the ones with small indemnities; hence, this variable could lead to a higher precision of the model. These two features will be available in the future.
43
Lin, Shou-Chuang, et 林首壯. « Study on Intelligence Controller for Induction Motor Drive Systems ». Thesis, 2018. http://ndltd.ncl.edu.tw/handle/8dfv6w.
Texte intégralRésumé :
博士國立臺北科技大學
電機工程系
106
This study presents the implementation of an adaptive supervisory sliding fuzzy cerebellar model articulation controller (FCMAC) in the speed sensorless vector control of an induction motor (IM) drive system. The proposed adaptive supervisory sliding FCMAC consists of a supervisory controller, an integral sliding surface, and an adaptive FCMAC. The integral sliding surface is employed to eliminate steady-state errors and enhance the response of the system. The adaptive FCMAC incorporates an FCMAC with a compensating controller to perform a desired control action. The proposed controller is derived using the Lyapunov approach, which guarantees learning-error convergence. The implementation of three intelligent control schemes—the adaptive supervisory sliding FCMAC, adaptive sliding FCMAC, and adaptive sliding CMAC—are experimentally investigated under various conditions in a realistic sensorless vector-controlled IM drive system. The root mean square error (RMSE) is used as a performance index to evaluate the experimental results of each control scheme. The analysis results indicate that the proposed adaptive supervisory sliding FCMAC substantially improves the system performance compared with the other control schemes.
44
Hsieh, Wen-Cheng, et 謝文政. « Study and Implementation of Intelligence Drive System for Switched Reluctance Motor ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/94k5km.
Texte intégralRésumé :
碩士國立臺北科技大學
電機工程系所
93
This thesis adopts Neural Network (NN) technique in Intelligent Control to design the controller for the switch reluctance motors (SRMs) drive system. System with the designed controller acquires superior performance in speed response. SRMs are being considered for variable speed drive applications due to their high power density, high torque, high efficiency, no rotor windings, and low cost. However, the inherent nonlinear characteristics make SRM difficult to control. Since the Neural Network technique provides a good capability to deal with nonlinear characteristics, we propose a Neural Network based online self-tuning PI controller with the aid of projection algorithm used in the adaptive control theory, named Neural Network PI controller (NNPIC), which integrates the SRM drive system with the Neural Network technology. Furthermore, the projection algorithm is embedded into the cerebellar model articulation controller (CMAC) to improve the convergence speed of the traditional CMAC in the real-time applications. Consequently, the proposed controller structure can on-line adjust PI parameters to make the dynamic behavior of the system better than that uses the conventional fix-parameter PI controller. Also the controller structure is sample and thus takes the advantage of integrated circuit implementation. To verify the feasibility and practicality of the controller, a dSPACE-DS1104 platform is used to implement the proposed control scheme. From the experimental results, it is seen that the dynamic performance of the SRM driver system is improved by our proposed scheme as comparing to the conventional fix-parameter PI controller.
45
Rosenstein, Michael T. « Learning to exploit dynamics for robot motor coordination ». 2003. https://scholarworks.umass.edu/dissertations/AAI3096312.
Texte intégralRésumé :
Humans exploit dynamics—gravity, inertia, joint coupling, elasticity, and so on—as a regular part of skillful, coordinated movements. Such movements comprise everyday activities, like reaching and walking, as well as highly practiced maneuvers as used in athletics and the performing arts. Robots, especially industrial manipulators, instead use control schemes that ordinarily cancel the complex, nonlinear dynamics that humans use to their advantage. Alternative schemes from the machine learning and intelligent control communities offer a number of potential benefits, such as improved efficiency, online skill acquisition, and tracking of nonstationary environments. However, the success of such methods depends a great deal on structure in the form of simplifying assumptions, prior knowledge, solution constraints and other heuristics that bias learning. My premise for this research is that crude kinematic information can supply the initial knowledge needed for learning complex robot motor skills—especially skills that exploit dynamics as humans do. This information is readily available from various sources such as a coach or human instructor, from theoretical analysis of a robot mechanism, or from conventional techniques for manipulator control. In this dissertation I investigate how each type of kinematic information can facilitate the learning of efficient “dynamic” skills. This research is multidisciplinary with contributions along several dimensions. With regard to biological motor control, I demonstrate that motor synergies, i.e. functional units that exploit dynamics, evolve when trial-and-error learning is applied to a particular model of motor skill acquisition. To analyze the effects of velocity on dynamic skills and motor learning, I derive an extension to the notion of dynamic manipulability that roboticists use to quantify a robot's capabilities before specification of a task. And along the machine learning dimension, I develop a supervised actor-critic architecture for learning a standard of correctness from a conventional controller while improving upon it through trial-and-error learning. Examples with both simulated and real manipulators demonstrate the benefits that this research holds for the development of skillful, coordinated robots.
46
James, Cohen Erez. « Motor Intelligence The study of simple motor tasks as indicators for inter-individual differences Implications for clinical practice and sport excellence ». Doctoral thesis, 2020. http://hdl.handle.net/2158/1189130.
Texte intégralRésumé :
This thesis aims to bridge between the theoretical concept of motor intelligence and its practice. Particularly, I seek to affront the problematic regarding to its quantification. As any transition between theory and practice, the theoretical framework must first be established. When it comes to Motor Intelligence specifically, though the theoretical groundwork had existed for a long time, the practicality of which had remained behind. This thesis begins by first examining the reasons for the discrepancy between theory and practice for motor intelligence, continuing by a proposal for a practical approach based on the successful implementation of the concepts of intelligence (Chapter 1).
The approach presented here is made on two fronts; the first front consists of the identification of suitable tasks for quantification of various aspects of motor control (Chapters 2-4). Specifically, Chapter 2 examines the potential of drawing and tracing tasks as tools for assessment of fine motor control, tested on a large number of subjects with specific attention to individual differences and the implications of these tasks to motor control. The results evidence that there is no correlation in terms of precision between the two tasks and that this lack of correlation is task dependent and not shape dependent. This allows for a classification of subjects, based on their level of tasks precision, as either drawers or tracers. Results obtained from the study suggest that for an accurate evaluation of fine motor control, both tasks should be used integrating their results. Chapter 3, extends the findings in Chapter 2 to elementary children, investigating the development of components of fine motor control using a tracing and a drawing task. The study demonstrates that, while tracing capacity improves greatly with age, drawing capacity improves only slightly. This trend may be due to possible involvement of attention as well as maturation patterns of the nervous system. The tasks, by being simple, economic and rapid, may represent a good instrument for motor control quantification during development, especially for population screening of eventual delays in maturation of motor control. Chapter 4, assesses the sensitivity of a tracing task following specific interventions, examining how the manipulation of objects, specifically fidget spinner, may influence fine motor control using a spiral tracing task. Results suggest that while fidget spinners do improve precision in tracing, it does not appear to be due to any inherent characteristic of the spinners themselves, as Sham group also demonstrated improvements.
The second front consists of the creation of instruments and methodological approaches that could be used for quantification (Chapters 5-7). Chapter 5 introduces a novel quantification method for 3D analysis of movement using a single camera, with a specific attention to the widespread implementation of movement analysis. Chapter 6, introduces a novel approach for the quantification of motor adaptation, using a simple continuous task which seeks to facilitate testing, and consequently used also in clinical settings. The adequacy of the task was evaluated by examining for aftereffects and generalizations (considered as indicators for motor adaptation). Results affirm the suitability of the task for examining adaptation, specifically, long-lasting after effects and generalization both for size and shift were found. Chapter 7 introduces a novel quantification approach during motor learning which is aimed to evidence individual differences in strategy selection during learning. This execution-centric approach is able to predict behavior during learning, regardless of outcome.
Finally, Chapter 8 closes this thesis by discussing the approach presented here in a general context along with some concluding remarks and possible future directions.
47
Hildreth, Ellen C., et John M. Hollerbach. « The Computational Approach to Vision and Motor Control ». 1985. http://hdl.handle.net/1721.1/5606.
Texte intégralRésumé :
Over the past decade it has become increasingly clear that to understand the brain, we must study not only its biochemical and biophysical mechanisms and its outward perceptual and physical behavior. We also must study the brain at a theoretical level that investigated the computations that are necessary to perform its functions. The control of movements such as reaching, grasping and manipulating objects requires complex mechanisms that elaborate information form many sensors and control the forces generated by a large number of muscles. The act of seeing, which intuitively seems so simple and effortless, requires information processing whose complexity we are just beginning to grasp. A computational approach to the study of vision and motor tasks. This paper discusses a particular view of the computational approach and its relevance to experimental neuroscience.
48
Chen, Jih-Sheng, et 陳志昇. « The Design of High Power Motor Driver with Soft-switching and Intelligence Protection Functions ». Thesis, 2003. http://ndltd.ncl.edu.tw/handle/83551917025649843511.
Texte intégralRésumé :
碩士國立交通大學
電機與控制工程系
91
In the thesis we propose a structure of high power motor driver. The structure includes an inverter with six legs for driving brushless DC motor, a quasi- resonant DC link circuit notches the bus voltage and forces the switches of the inverter switching at zero voltage, a circuit with current limit, over - temperature and short - circuit protection functions, and a six-step square waveform generator for motor driver testing. Considering traditional hard-switching, during power devices switching on or off the load current still flows through the device . Therefore, high switching losses and EMI caused by dv/dt 、di/dt will occur when devices switch in high power operation, and both of them will influence the efficiency and stability of the driver. Soft-switching techniques applying to power inverter can reduce the switching losses, limit dv/dt and di/dt to minimize EMI. The driver is monitored through the whole operation period. The experimental results have shown the protection circuits can protect the power devices from being damaged in dangerous situation.
49
Hwung, Hong-Rong, et 黃烘榮. « Optimal Position Control Of Induction Motor Using Aritificial Intelligence and Indirect Vector-control Techniques ». Thesis, 1996. http://ndltd.ncl.edu.tw/handle/64404718390974769318.
Texte intégralRésumé :
碩士國立中正大學
電機工程學系
84
This thesis proposes a novel method using artificial intelligence and indirectvector-control techniques for position control of induction motor.The fuzzy phase-plane theory is employed for the design of the controllers.Five controllers are proposed, which are able to achieve good performance underchanges of operating conditions of wide range. The proposed controllers applythe method of genetic algorithms of evolutionary direction operator of improvementtype to requirement of exerting multifarious experiences of expert and proceduresof defuzziness, the controllers can attain more quick response than that of theconventonal fuzzy controllers. What is more, since the output signal of thecontrolls is operated by continues nonlinear function, it is in favor of thedesign of optimal control and the analysis of stability.The control technique using artificial intelligence and indirect vector- controlwere successfully explored and simulated. Simulation results show that theapproach is computationally efficient and has exceedingly good control performance.Furthermore, because of employing the fuzzy phase-plane technique, no transferfunction development is required for the implementation of the method. Thusethe proposed controllers have the advantages of easiness and flexibility fordesign.
50
Chien, Shao-Chuan, et 簡劭全. « Study and Implementation of Intelligence Indirect Torque Control Drive System for Switched Reluctance Motor ». Thesis, 2006. http://ndltd.ncl.edu.tw/handle/3c5uf9.
Texte intégralRésumé :
碩士國立臺北科技大學
電機工程系所
94
This thesis adopts intelligent control technique to design the controller and using the torque sharing strategy to implement the intelligent indirect torque control drive system for switched reluctance motors (SRMs). The proposed control scheme can improve system response. The merits of SRMs include high torque, high efficiency, no rotor windings, and low cost. However, the structure of salient poles on both the rotor and the stator brings about high nonlinearity of the output torque and makes SRM difficult to control. Since both the Neural Network (NN) technique and the Cerebellar Model Articulation Controller (CMAC) provide a good capability to deal with nonlinear characteristics, we propose a NN-based and a CMAC-based controller respectively with the grey prediction theory and the projection algorithm used in the adaptive control theory. The proposed controller structure can on-line adjust PI parameters to make the dynamic behavior of the proposed system superior to that of the system using the conventional fix-parameter PI controller. To verify the feasibility and practicality of the controller, a dSPACE-DS1104 platform is used to implement the proposed control scheme. From the experimental results, it is seen that the dynamic performance of the SRM driver system is improved by the proposed scheme.