Rozprawy doktorskie na temat „ANFIS CONTROLLER”

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2017-11-01T21:47:48Z No. of bitstreams: 1 JoseKleitonEwertonDaCostaMartins_DISSERT.pdf: 3450112 bytes, checksum: 43beab3e6259be22eeed518fd67eaefc (MD5)<br>Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2017-11-08T21:43:16Z (GMT) No. of bitstreams: 1 JoseKleitonEwertonDaCostaMartins_DISSERT.pdf: 3450112 bytes, checksum: 43beab3e6259be22eeed518fd67eaefc (MD5)<br>Made available in DSpace on 2017-11-08T21:43:16Z (GMT). No. of bitstreams: 1 JoseKleitonEwertonDaCostaMartins_DISSERT.pdf: 3450112 bytes, checksum: 43beab3e6259be22eeed518fd67eaefc (MD5) Previous issue date: 2017-06-23<br>Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior (CAPES)<br>O trabalho faz uma an?lise de diferentes t?cnicas de controle na estrutura do ANFIS modificado, m?todo recente que se originou a partir de uma altera??o na estrutura do ANFIS, para realizar identifica??o e controle de plantas com ampla faixa de opera??o e n?o linearidade acentuada. O ANFIS modificado ? dividido em dois grandes est?gios, o primeiro sendo a identifica??o e o segundo o controle. Para realizar a identifica??o pode-se utilizar quaisquer t?cnicas. Nesse trabalho foram exploradas as t?cnicas de identifica??o de sistemas lineares mais conhecidas na literatura e o m?todo dos m?nimos quadrados. Assim como no est?gio da identifica??o, o est?gio de controle tamb?m permite utilizar quaisquer t?cnicas de projeto. Nesse trabalho foram exploradas as t?cnicas de sintonia de controladores PID mais conhecidas na literatura, na qual os controladores projetados foram incorporados na estrutura do ANFIS modificado para a obten??o de um controlador global n?o linear. Foi escolhido um sistema de tanques com multisse??es como estudo de caso e assim foi realizada a sua identifica??o atrav?s do ANFIS modificado, mostrando as qualidades do m?todo. Em seguida foi realizada uma compara??o de desempenho do ANFIS modificado utilizando os diferentes m?todos de sintonia e ao final chegando a uma metodologia sistem?tica para utiliza??o do ANFIS modificado como controlador global.<br>This work makes an analysis of different control techniques in the modified ANFIS structure, this method is recent and originated from a change in the ANFIS structure for perform identification and control of plants with wide operating range and accentuated non-linearity. The modified ANFIS is divided into two major stages, the first is the identification and the second is the control. In order to perform the identification, it is possible to use any techniques. In this work was explored the linear system identification more known in the literature and the least square estimation. As in the identification stage, the control stage can also use any techniques. This work the tuning of PID controllers will be explored, in which the designed controllers will be incorporated into the modified ANFIS structure to obtain a non-linear controller. A system of tanks with multisections was chosen as a case study and its identification through the modified ANFIS was performed, showing the qualities of the method. Then a performance comparison of the modified ANFIS will be performed using the different tuning methods and show a systematic methodology for use the modified ANFIS as global controller.

Made available in DSpace on 2016-04-25T20:22:29Z (GMT). No. of bitstreams: 1 Marcia Cristina Lazzari.pdf: 1055866 bytes, checksum: 7e37be836bb85dd4fd0ae4f8dfcf4fae (MD5) Previous issue date: 2008-10-08<br>This work analyze the practices and the discourses of so-called Protection Network, defined as a group of institutions that confront the violations of the rights of children and young people, taking as parameter the Tutelary Councils (TC) and its association with different advisory body. Sustained by the power from the integration of public and private institutions, were mapped movements, and technologies of power disruption, analyzing information about the attendance provided to the community, by TCs in association with schools, and under supervision and guidance of the Law and the State. The analyses about the continuities and ruptures of the devices of attendance and protection of children and young people, raised approaches around the society of control announced by Deleuze, promoting a investigation about the regimes of disguised truth, found in institutional pathways. It is possible to map the practice of control through researches on the reports and documents relatives to the attendance provided by the CTs. The flows of power, present in the CTs, which manage the conflicts, prevent the access to data and scandalize the defense of rights, reaffirm the discourses of the government, put in movement the power and support the control all sectors related to children and young people. These are indications that participatory democracy favored ripples of catches of resistance and also, starts to acquire another meaning relative to the deterritorialization of space without jurisdiction. The questioning of the intolerable habits and actions reinforces the notion of inadequacy and isolation, and allows the review of the concentration camps, established under practice of snapshot control and police control, exercised by everybody<br>Neste trabalho são analisadas as práticas e os discursos da chamada Rede de Proteção, definida como o conjunto de instituições que compõem o enfrentamento às violações dos direitos das crianças e dos jovens, tendo como parâmetro os Conselhos Tutelares e suas articulações com outras instâncias. No interior de um fluxo de poderes emanados pela integração de instituições estatais e não estatais, são mapeados movimentos, rupturas e tecnologias de poder, examinando informações sobre atendimentos prestados à comunidade, pelos CTs em articulação com a escola, sob a supervisão e orientação da Lei e do Estado. As análises relativas às continuidades e rupturas dos dispositivos de atendimento e defesa de crianças e de jovens, suscitaram abordagens em torno da sociedade de controle anunciada por Deleuze, impulsionando a investigação dos regimes de verdade subjacentes, encontrados nas trajetórias institucionais. Tornou-se possível mapear práticas de controle por meio da pesquisa realizada junto aos relatórios e documentos relativos a atendimentos prestados. Os fluxos de controle, presentes nos CTs, que administram os conflitos, inviabilizam o acesso aos dados e alardeiam a defesa de direitos, reafirmam os discursos do governo, exercitam poderes e corroboram para a policialização de setores ligados às crianças e aos jovens. Tais elementos indicam que a democracia participativa favoreceu ondulações de capturas de resistências e também, passou a adquirir outro significado relativo à reterritorizaliação do espaço não jurisdicional. O questionamento de hábitos e ações insuportáveis reforça a noção de inadequação e isolamento, e permite a releitura do campo de concentração, instituído sob o exercício do controle instantâneo e policial exercido por todos

Este trabalho apresenta uma alternativa ao controle vetorial de motores de indução, sem a utilização de sensores para realimentação da velocidade mecânica do motor. Ao longo do tempo, diversas técnicas de controle vetorial têm sido propostas na literatura. Dentre elas está a técnica de controle por orientação de campo (FOC), muito utilizada na indústria e presente também neste trabalho. A principal desvantagem do FOC é a sua grande sensibilidade às variações paramétricas da máquina, as quais podem invalidar o modelo e as ações de controle. Nesse sentido, uma estimativa correta dos parâmetros da máquina, torna-se fundamental para o acionamento. Este trabalho propõe o desenvolvimento e implementação de um estimador baseado em um sistema de inferência neuro-fuzzy adaptativo (ANFIS) para o controle de velocidade do motor de indução trifásico em um acionamento sem sensores. Pelo fato do acionamento em malha fechada admitir diversas velocidades de regime estacionário para o motor, uma nova metodologia de treinamento por partição de frequência é proposta. Ainda, faz-se a validação do sistema utilizando a orientação de campo magnético no referencial de campo de entreferro da máquina. Simulações para avaliação do desempenho do estimador mediante o acionamento vetorial do motor foram realizadas utilizando o programa Matlab/Simulink. Para a validação prática do modelo, uma bancada de testes foi implementada; o acionamento do motor foi realizado por um inversor de frequência do tipo fonte de tensão (VSI) e o controle vetorial, incluindo o estimador neuro-fuzzy, foi realizado pelo pacote de tempo real do programa Matlab/Simulink, juntamente com uma placa de aquisição de dados da National Instruments.<br>This work presents an alternative sensorless vector control of induction motors. Several techniques for induction motor control have been proposed in the literature. Among these is the field oriented control (FOC), strongly used in industries and also in this work. The main drawback of the FOC technique is its sensibility to deviations of the parameters of the machine, which can deteriorate the control actions. Therefore, an accurate determination of the machines parameters is mandatory to the drive system. This work proposes the development of an adaptive neuro-fuzzy inference system (ANFIS) estimator to control the angular speed of a three-phase induction motor in a sensorless drive. In a closed loop configuration, several speed commands can be imposed to the motor. Thus, a new frequency partition training of ANFIS is proposed. Moreover, the ANFIS speed estimator is validated in a magnetizing flux oriented control scheme. Simulations to evaluate the performance of the estimator considering the vector drive system were done by the Matlab/Simulink. To determine the benefits of the proposed model a practical system was implemented using a voltage source inverter (VSI) and the vector control including the ANFIS estimator, carried out by the Real Time Toolbox from Matlab/Simulink and a data acquisition card from National Instruments.

Made available in DSpace on 2014-12-17T14:55:48Z (GMT). No. of bitstreams: 1 MarconiCR.pdf: 3477416 bytes, checksum: 7bf9d3b9014c2ba726d8694085022188 (MD5) Previous issue date: 2006-02-17<br>Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior<br>A neuro-fuzzy system consists of two or more control techniques in only one structure. The main characteristic of this structure is joining one or more good aspects from each technique to make a hybrid controller. This controller can be based in Fuzzy systems, artificial Neural Networks, Genetics Algorithms or rein forced learning techniques. Neuro-fuzzy systems have been shown as a promising technique in industrial applications. Two models of neuro-fuzzy systems were developed, an ANFIS model and a NEFCON model. Both models were applied to control a ball and beam system and they had their results and needed changes commented. Choose of inputs to controllers and the algorithms used to learning, among other information about the hybrid systems, were commented. The results show the changes in structure after learning and the conditions to use each one controller based on theirs characteristics<br>Neste trabalho ? mostrado tanto o desenvolvimento quanto as caracter?sticas de algumas das principais t?cnicas utilizadas para o controle inteligente de sistemas. Partindo de um controlador fuzzy foi poss?vel aplicar t?cnicas de aprendizagem, similares ?s utilizadas pelas Redes Neurais Artificiais (RNA's), evoluir para os modelos neuro-fuzzy ANFIS e NEFCON. Estes modelos neuro-fuzzy foram aplicados a uma planta real do tipo ball and beam e tiveram tanto suas adapta??es quanto seus resultados comentados. Para cada controlador desenvolvido s?o especificadas as vari?veis de entrada, os par?metros utilizados para a adapta??o das vari?veis e os algoritmos aplicados em cada um deles. J? os resultados est?o voltados para a obten??o de um comparativo entre a fase inicial e a final da evolu??o dos controladores neuro-fuzzy, assim como, a aplicabilidade de cada um deles de acordo com suas caracter?sticas intr?nsecas

Made available in DSpace on 2014-12-17T14:55:11Z (GMT). No. of bitstreams: 1 CarlosAGF_TESE.pdf: 1739972 bytes, checksum: 7401db4e68ede642dc9d65e00bd935e6 (MD5) Previous issue date: 2012-12-21<br>In this work a modification on ANFIS (Adaptive Network Based Fuzzy Inference System) structure is proposed to find a systematic method for nonlinear plants, with large operational range, identification and control, using linear local systems: models and controllers. This method is based on multiple model approach. This way, linear local models are obtained and then those models are combined by the proposed neurofuzzy structure. A metric that allows a satisfactory combination of those models is obtained after the structure training. It results on plant s global identification. A controller is projected for each local model. The global control is obtained by mixing local controllers signals. This is done by the modified ANFIS. The modification on ANFIS architecture allows the two neurofuzzy structures knowledge sharing. So the same metric obtained to combine models can be used to combine controllers. Two cases study are used to validate the new ANFIS structure. The knowledge sharing is evaluated in the second case study. It shows that just one modified ANFIS structure is necessary to combine linear models to identify, a nonlinear plant, and combine linear controllers to control this plant. The proposed method allows the usage of any identification and control techniques for local models and local controllers obtaining. It also reduces the complexity of ANFIS usage for identification and control. This work has prioritized simpler techniques for the identification and control systems to simplify the use of the method<br>Neste trabalho prop?e-se uma modifica??o na estrutura neurofuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) para a obten??o de um m?todo sistem?tico para identifica??o e controle de plantas com ampla faixa de opera??o e n?o linearidade acentuada, a partir de t?cnicas lineares de identifica??o e controle. Este m?todo se baseia na metodologia de m?ltiplos modelos. Dessa forma, obt?m-se modelos lineares locais e esses s?o combinados pela estrutura neurofuzzy proposta. Uma m?trica que permite combinar adequadamente esses modelos ? obtida ap?s o treinamento dessa estrutura, resultando na identifica??o global da planta. Para cada um desses modelos ? projetado um controlador. O controle global ? obtido a partir da combina??o dos sinais dos controladores locais. Essa mistura ? feita pelo ANFIS modificado. A modifica??o na arquitetura do ANFIS permite o compartilhamento do conhecimento adquirido pelo treinamento da estrutura empregada na combina??o de modelos locais. Assim n?o se faz necess?rio o treinamento da estrutura empregada na mistura de controladores. Avaliaram-se as estruturas modificadas atrav?s de dois estudos de caso. Verificou-se que ? poss?vel treinar apenas um ANFIS, para a obten??o de uma m?trica que permita a combina??o adequada dos modelos lineares, v?lidos localmente, e essa estrutura, j? ajustada, pode ser aplicada na combina??o de controladores lineares, projetados para cada um dos modelos, resultando em um sistema de controle que satisfaz as especifica??es de desempenho previamente estabelecidas. O m?todo proposto possibilita a utiliza??o de quaisquer t?cnicas de identifica??o e controle para a obten??o dos modelos e controladores locais, e a redu??o da complexidade de utiliza??o do ANFIS para identifica??o e controle. Neste trabalho priorizaram-se as t?cnicas mais simples de identifica??o e controle de sistemas de forma a simplificar a utiliza??o do m?todo

Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2017-01-27T12:26:54Z No. of bitstreams: 1 JoseSoaresBatistaLopes_TESE.pdf: 3701361 bytes, checksum: 945caee9725d682534c235543f919e4b (MD5)<br>Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2017-01-30T13:07:29Z (GMT) No. of bitstreams: 1 JoseSoaresBatistaLopes_TESE.pdf: 3701361 bytes, checksum: 945caee9725d682534c235543f919e4b (MD5)<br>Made available in DSpace on 2017-01-30T13:07:29Z (GMT). No. of bitstreams: 1 JoseSoaresBatistaLopes_TESE.pdf: 3701361 bytes, checksum: 945caee9725d682534c235543f919e4b (MD5) Previous issue date: 2016-06-17<br>Este trabalho descreve o estudo e a implementa??o digital embarcado em um DSP TMS 3208F28335 para o controle vetorial de velocidade do motor-mancal com bobinado dividido de 4 p?los com 250W de pot?ncia. As t?cnicas inteligentes: ANFIS e as Redes Neurais foram investigadas e implementadas computacionalmente para a avalia??o do desempenho do motor-mancal nas seguintes condi??es: operando como estimador de par?metros incertos, e como controlador de velocidade, respectivamente. Para isso, utilizou-se o programa MATLAB? e seu toolbox para as simula??es e os ajustes dos par?metros envolvendo a estrutura ANFIS, e tamb?m para as simula??es com a Rede Neural. Os resultados simulados mostraram um bom desempenho para as duas t?cnicas aplicadas, de forma diferente: como estimador, e como controlador de velocidade utilizando ambas um modelo do motor de indu??o operando como um motor-mancal. A parte experimental para o controle vetorial de velocidade utiliza tr?s malhas de controles: corrente, posi??o radial e velocidade, onde foram investigados a configura??o dos perif?ricos, as interfaces ou drivers para o acionamento do motor-mancal. Detalhes de configura??o dos perif?ricos do DSP TMS 3208F335 s?o descritas neste trabalho, assim como, as interfaces respons?veis pela aquisi??o da corrente, posi??o radial e velocidade do rotor. Por ?ltimo, s?o mostrados os resultados experimentas do motor-mancal comparando o funcionamento do controle vetorial cl?ssico com o controle neural.

Orientador: Maria Cecília Calani Baranauskas<br>Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Computação<br>Made available in DSpace on 2018-08-16T23:18:27Z (GMT). No. of bitstreams: 1 Miranda_LeonardoCunhade_D.pdf: 4387805 bytes, checksum: b138e75ab0fe002567c99b3af4fd3a50 (MD5) Previous issue date: 2010<br>Resumo: A digitalização da transmissão da televisão terrestre no Brasil e, consequentemente, a possibilidade de oferta de interatividade na televisão estabelece um novo paradigma de interação do telespectador com essa mídia com extremo potencial de impacto social, especialmente para a população brasileira. Entretanto, a existência de artefatos digitais comumente utilizados para a interação com o sistema de televisão hoje praticado não garante que esses dispositivos sejam os mais adequados aos avanços propostos com a Televisão Digital Interativa (TVDI). Além disso, a convivência de um número cada vez maior de equipamentos que fazem uso de controle remoto leva a interfaces mais complexas considerando os problemas existentes com o controle remoto já discutido na literatura por vários autores. O foco desta pesquisa de doutorado foi, portanto, investigar o design da interação nessa nova mídia com o objetivo de propor, desenvolver e validar novas formas de interação entre os usuários e a TVDI. Com base no entendimento de que uma interação mais direta com a TVDI passa pela necessidade de fazer com que o foco da interação se dirija mais à interface das aplicações interativas do que ao artefato físico de interação, chegamos a alguns resultados desta pesquisa. A tecnologia resultante desta pesquisa de doutorado saiu do plano das ideias, passando pelo seu projeto conceitual, de forma participativa, até sua implementação e validação junto a representantes do público-alvo. Podemos destacar algumas contribuições decorrentes da realização desta pesquisa no contexto dos artefatos físicos de interação com a TVDI: i) taxonomia para os artefatos físicos de interação; ii) recomendações de uso dos artefatos físicos de interação conhecidos na literatura; iii) análise sócio-técnica do domínio/contexto de novos artefatos físicos de interação; iv) diretrizes para novos artefatos físicos de interação; v) modelo de interação baseado em gestos via artefato físico de interação; vi) guidelines de design para novos artefatos físicos de interação; vii) especificações do design do produto e da linguagem de interação de um novo artefato digital para a TVDI; viii) implementações de protótipos de hardware e software do novo artefato digital para a TVDI; e ix) validação das especificações e dos protótipos do novo artefato digital para a TVDI junto ao público-alvo.<br>Abstract: The digitalization of terrestrial television broadcasting in Brazil and consequently the possibility of offering interactivity on television establish a new paradigm of interaction for the spectator with the media that has great potential to make a social impact, especially for the Brazilian population. However, the existence of digital artifacts commonly used to interact with current television system does not guarantee that those devices are adequate to the developments with the Interactive Digital Television (iDTV). Moreover, the coexistence of an increasing number of devices that make use of the remote control could result in more complex interfaces, considering the problems with remote control already discussed in the literature by several authors. The objective of this Ph.D. research was to investigate the interaction design in the iDTV with the purpose of proposing, developing and validating new ways of interaction with this new media. The research results are grounded in the understanding that a more direct interaction with iDTV involves making the focus of the interaction more on the interface of the interactive applications than on the physical artifact of interaction itself. The technology resulting from this research involved since its conceptual design, with a participatory approach, to its implementation and validation with real users from the target audience. Some contributions of this research in the context of physical artifacts of interaction with the iDTV can be highlighted: i) taxonomy for the physical artifacts of interaction; ii) use recommendations of physical artifacts of interaction known in the literature; iii) socio-technical analysis of the domain/context of new physical artifacts of interaction; iv) guidelines for new physical artifacts of interaction; v) gesture based interaction model via physical artifact of interaction; vi) design guidelines for new physical artifacts of interaction; vii) product design and interaction language specifications for new digital artifact for iDTV; viii) implementations of hardware and software prototypes for the new digital artifact for iDTV; and ix) validation of the specifications and prototypes of the new digital artifact for iDTV with the target audience.<br>Doutorado<br>Interação Humano-Computador<br>Doutor em Ciência da Computação

O protocolo Token Ring sem o (WTRP) é um protocolo distribuído de controle de acesso ao meio que provê qualidade de serviço em termos de uso de largura de banda e latência limitada. WTRP consiste de nós (estações) que formam topologicamente um anel. Contudo, quando o número de nós em um anel aumenta a latência aumenta e o tempo de reuso de token por parte de um nó em anel também aumenta. Neste trabalho, apresentamos uma versão extendida de WTRP com foco em reduzir a latência, tempo de reuso de token e permitir encaminhamento de dados entre anéis sem aumentar signicativamente o consumo de energia. Para provar o conceito que propomos, implementamos e testamos a nossa versão de WTRP usando simulador de rede - NS.<br>Wireless Token Ring Protocol (WTRP) is a distributed Medium Access Control protocol that provides quality of service in terms of reserved bandwidth and limited latency]. It consists of nodes or stations structured in ring topology. However, when the number of nodes in a ring increases latency and time of a node reuse token increases. In this work, we present an extended version WTRP that focus on reducing latency, time of token reuse and data forwarding among the rings in a MANet , without suggestive increasing of energy consumption. We have implemented and tested our version of WTRP in network simulator - NS.

The thesis deals with artificial neural networks theory. Subsequently, fuzzy sets are being described and fuzzy logic is explained. The hybrid neuro-fuzzy system stemming from ANFIS system is designed on the basis of artificial neural networks, fuzzy sets and fuzzy logic. The upper-mentioned systems' functionality has been demonstrated on an inverted pendulum controlling problem. The three controllers have been designed for the controlling needs - the first one is on the basis of artificial neural networks, the second is a fuzzy one, and the third is based on ANFIS system.  The thesis is aimed at comparing the described systems, which the controllers have been designed on the basis of, and evaluating the hybrid neuro-fuzzy system ANFIS contribution in comparison with particular theory solutions. Finally, some experiments with the systems are demonstrated and findings are assessed.

碩士<br>國立成功大學<br>系統及船舶機電工程學系<br>103<br>In practical, most of physical systems are nonlinear, and the feedback linearization method may be utilized to control the system. However, the system uncertainties and disturbances will affect the feasibility of the controller and make the closed-loop system hard to match the desired performance. To solve this problem, in this thesis, the ANFIS-based H_∞ Fuzzy Sliding Mode Controller is derived to form the proposed robust controller and to meet the pre-specified specifications. The proposed controller is composed of two control components. One component is the feedback-linearization based sliding mode controller, in which the control gains and the observer gains are optimally chosen from the standard H_∞ control problem. The other component is the fuzzy-based controller, whose membership functions are optimally tuned by the Adaptive-Network Based Fuzzy Inference System (ANFIS). With the proposed controller, the system tracking errors will be forced to the sliding surface by the first component. To ensure the achievement of tracking performance and desired specifications, the errors resulted from system uncertainties will be eliminated by the second component. The closed-loop system stability of the proposed controller is proved by the Lyapunov’s stability criterion. The largest allowable scale of uncertainties is then explored by an inequality proposed in this research. Finally, a robot manipulator with uncertainties is simulated to prove the feasibilities of the proposed composite controller.

碩士<br>明志科技大學<br>電機工程研究所<br>100<br>This paper aims to study the intelligent control approach on the speed control of an automatic guided vehicle (AGV). An adaptive neural fuzzy Inference System (ANFIS) with PID controller is adopted according to the features of motor and vehicle. Through training ANFIS controller, the rising time and settling time can be decreased to minimum values. Further, particle swarm optimization (PSO) is used to optimize the parameters of fuzzy rules, membership function and normalization gaining of ANFIS controller. It can be shown that the better performance such as the shortest rising time and settling time can be achieved by the proposed PSO-ANFIS with PID control scheme.

碩士<br>國立交通大學<br>電機與控制工程系所<br>96<br>The objective of the thesis is to use the intelligent ANFIS controller and to build the discrete PM DC motor by using the Runge-Kutta method, then use the back propagation learning algorithm to find the near-optimal parameters in ANFIS based controller. When the sampling time h is too large or the plant has fast dynamics, the linear approximation may not be a suitable estimate of the next state [5]. In order to solve this problem, the so-called Runge-Kutta method with higher order can be used to implement the plant block. However, the use of higher order Runge-Kutta method often results in more complicated adaptive network and slows down the learning process accordingly. In this thesis, there are used the third order Runge-Kutta formula because the second order is too easy if the model become complex and the fourth order will result complicated adaptive network for the modeling. Then by using the regulation learning of motor to find the parameters in controller applied to angle tracking of one motor and to track the moving object by controlling the humanoid vision system which is three axis actuated by three motors.

In general speed control is essential in drive system. This involves variable frequency and voltage. Many pulse width modulation techniques are used for obtaining variable frequency and voltage from an inverter. The space vector pulse width modulation method with proportional integral control of induction motor drive is widely used in high performance drive system. It is due to its characteristics like good power factor and high efficiency. In this dissertation the voltage source inverter type space vector pulse width modulation using proportional integral control, ANN control and ANFIS control model design and implementation has been done through MATLAB/Simulink software for the speed control of induction motor. The performance of speed is increased by PI controller, ANN controller and ANFIS controller. The simulation results provide a smooth speed response and high performance under various dynamic operations. Space vector pulse width modulation (SVPWM) is more efficient among all other pulse width modulation (PWM) techniques due to its key characteristics like better DC voltage utilization, switching losses reduction and easiness in digital implementation. The complete mathematical model of the system is described and simulated in MATLAB/Simulink.

This dissertation deals with, “Improvement of BLDC motor performance through intelligent controllers”. Implementation of different control strategies for Permanent Magnet Brushless DC Motor in different modes of operation is carried out through MATLAB/simulation. The controlled electric motors play a vital role in the industrial automation. It is well known that electrical motors consume a significant percentage of electrical energy and even small improvement in operating efficiency could result in large reduction in consumption of energy. Therefore new techniques are required to extract ultimate performance from these drives. There has also been tremendous research for providing suitable speed controller for PMBLDC motor. Many control strategies have been proposed in literature. The main drawback of fixed gain controllers is that their performance deteriorates as a result of changes in motor parameters & its operating conditions. In recent times hybrid controllers such as Fuzzy Logic and Adaptive neuro-fuzzy (ANFIS) have emerged as one of the most attractive non-linear controller for application in the industrial processes giving robust performance in the face of parameter variation and load disturbance effects. The main objective is to compensate for overshoots and oscillation in the response of the PMBLDC motor for wide speed range of opearation. The performance is defined in terms of accuracy, smooth operation and simplicity. The controller performance is defined in terms of rise time, Settling time, overshoot, undershoot and behavior with non-linarites. In this thesis, the PMBLDCM drive is modeled and simulated in MATLAB/SIMULINK environment. The controller such as Proportional Integral controller, Fuzzy logic controller, Adaptive- Neuro controller (ANFIS), series hybrid controller(known as Fuzzy precompensated PI controller) and self-tuning PI controller(Fuzzy tuned PI controller) are implemented for speed controller in the MATLAB/SIMULINK environment and drive performance using these controllers is observed and compared. The performance comparison is done in terms of several performance measures such as settling time, peak time, rise time, overshoot, undershoot, and load variations and stable performance under all operating conditions. iv Every controller has their own merits and demerits. It is observed that PI controller would be a good choice for simplicity and ease of application. PI controllers are observed to have no steady state error but are slow in response. The Fuzzy logic controller offer good performance in the presence of nonlinearity but Fuzzy logic controller has offset at steady state. Adaptive neuro fuzzy controller provides excellent transient response in terms of quickness of the response. Series hybrid and self- tuning PI controller offer good response in different operating conditions but main drawback is that, processing time of controllers are high.

Renewable energy are a key and powerful alternative sources widely used having many advantages comparing to the conventional power generation. Most known alternative power generation sources are solar, wind geothermal, hydro, and biomass. Therefore energy generated naturally from the sunlight as is it called solar energy in particular has been used now for years as an optional way to power multiple devices. However the energy generated depends proportionally on the amount of the radiation that varies constantly during the day because of the weather which influence negatively in voltage stability. Using a converter such as boost converter is an ideal option to step-up the power so that the usage requirement can be met. Hence ANFIS based MPPT controller is designed to control the duty cycle of the generated pulses and track the maximum power generated by the entire system plant.

碩士<br>聖約翰科技大學<br>電機工程系碩士班<br>94<br>Because in real application, original ANFIS inverse learning method can not represent the inverse dynamic model of induction motor effectively. Thus in this thesis, a modified ANFIS inverse learning method is proposed. A modified training phase by introducing an overall transfer function and a modified application phase by introducing a feedback configuration which combines the ANFIS inverse model and the integral controller are proposed. This new design method gives us a simple and powerful way to design a speed controller for a servo-motor. An experimental result for a 3-phase induction motor is also given to illustrate the effectiveness of the proposed design method. Moreover, in this thesis, a way to realize the modified ANFIS inverse learning method by XSCALE PXA255 embedded system is also proposed. In realizing the embedded intelligent controller, we use LINUX C language to implement the modified ANFIS control rules. The proposed program can gather the input and output data set of the plant, and send the data set to us via the TCP/IP protocol. In this way, we can easily get the required input and output data set using the host PC and obtain the inverse dynamic model using the off-line training method. While obtaining the inverse dynamic model, we also show a way to produce a text file which contains the parameter set of the model and transmit it to the embedded system via the TCP/IP protocol. Hence in this thesis, we have successful realized an embedded intelligent controller which combines the modified ANFIS control law and the TCP/IP communication program.