Literatura académica sobre el tema "Testing Machine Company"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "Testing Machine Company".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Artículos de revistas sobre el tema "Testing Machine Company"
1
Sibarani, Prince, Tanika D. Sofianti y Aditya Tirta Pratama. "Improving the Overall Equipment Effectiveness (OEE) of Drum Testing Machine in Laboratory of Tire Manufacturing Using FMEA and PFMEA". Proceedings of The Conference on Management and Engineering in Industry 3, n.º 3 (4 de agosto de 2021): 56–61. http://dx.doi.org/10.33555/cmei.v3i3.84.
Texto completoResumen
Drum testing is equipment to test tire capability in the highway prototype in the tire company. Overall Equipment Effectiveness (OEE) is used to measure the productivity of the equipment. OEE has declined and has not achieved the target from Jun 2019 until June 2020. The objectives of this research are to determine the fixed parameter in the OEE calculation at the Drum Testing and to increase the OEE for achieving the company target. Process Failure Mode Effects Analysis (PFMEA) and Failure Mode Effects Analysis (FMEA) help to identify potential failure mode and its consequences, and formulate a solution to achieve the OEE target by improving the drum testing machine. Furthermore, an ideal target should be customized based on the manufacturing year and brand of the machine. This research showed PFMEA and FMEA successfully improve the OEE efficiency for five machines increases the average OEE from 53.6% to 67.2%.
2
C. M. Nalayani, Thanga Akilan .V, Hariharan .S, SaranArulnathan y Venkatanathan .S. "Placement Analysis for Students using Machine Learning". September 2023 5, n.º 3 (septiembre de 2023): 223–37. http://dx.doi.org/10.36548/jitdw.2023.3.001.
Texto completoResumen
Every University/College want their students to get placed in a good company with a better package. They create the syllabus so, that students will gain the most knowledge out of the study period. But they are not sure whether the students are getting trained with proper guidance and instruction to be placed. There is a need for metric to find the progress of the student’s placement. So, the student can speed up his/her preparation to meet the demands of the minimum criteria of placement. This metric is called the placement analysis system, it takes attributes like internships completed, papers published, aptitude scores, etc to predict where the individual will get placed i.e., Dream company, Core company, Normal company or not get placed. For this the machine learning algorithms are used to predict the results using three basic algorithms Random Forest, Decision tree and K-means clustering the accuracy of the algorithms are determined to find the optimal algorithm. The past data on the placement results were fed as the training dataset and a part of it is used for testing the accuracy of the model. Then if the accuracy is good, this can be used to predict the possibility of a student getting placed. If the student is unhappy with the result, then the model can be used to find the area where the student needs to improve to get to his desired goal. If properly implemented and the students work consistently, this aids in providing solutions to meet every student's goal.
3
Mustika, Nadya Intan, Bagus Nenda y Dona Ramadhan. "Machine Learning Algorithms in Fraud Detection: Case Study on Retail Consumer Financing Company". Asia Pacific Fraud Journal 6, n.º 2 (30 de diciembre de 2021): 213. http://dx.doi.org/10.21532/apfjournal.v6i2.216.
Texto completoResumen
This study aims to implement a machine learning algorithm in detecting fraud based on historical data set in a retail consumer financing company. The outcome of machine learning is used as samples for the fraud detection team. Data analysis is performed through data processing, feature selection, hold-on methods, and accuracy testing. There are five machine learning methods applied in this study: Logistic Regression, K-Nearest Neighbor (KNN), Decision Tree, Random Forest, and Support Vector Machine (SVM). Historical data are divided into two groups: training data and test data. The results show that the Random Forest algorithm has the highest accuracy with a training score of 0.994999 and a test score of 0.745437. This means that the Random Forest algorithm is the most accurate method for detecting fraud. Further research is suggested to add more predictor variables to increase the accuracy value and apply this method to different financial institutions and different industries.
4
Porter, S. J., J. P. Chadwick, M. G. Owen y S. J. Page. "Evaluation of seven ultrasonic machines for estimating carcase composition in live bulls". Proceedings of the British Society of Animal Production (1972) 1988 (marzo de 1988): 46. http://dx.doi.org/10.1017/s0308229600016846.
Texto completoResumen
The application of ultrasonics to the evaluation of live cattle has been carried out in bull performance testing for several years. The machine used for this was the Scanogram. The fact that this machine is no longer being produced and the emergence of several new machines has prompted this trial to evaluate seven ultrasonic machines.A total of 49 bulls, 27 Limousin x Friesian and 22 Charolais x Friesian, were evaluated and slaughtered in four batches of approximately equal size, over four weeks. Each batch was of one breed.Age, live weight at evaluation and subjective assessments of fatness and conformation were recorded together with fat and muscle measurements by the Delphi (Delphi Instruments Ltd, New Zealand), Meritronics (Merit, Lowson and French, England), Scanogram (Ithaco Incorporated, USA), Vetscan (Company no longer in existence), Kaijo Denki (Medata Systems Ltd, England), Velocity of Sound (Prototype developed at IFR-Bristol, England) and Warren (Prototype developed by J Warren) ultrasonic machines.
5
Camille Merlin S. Tan y Lawrence Y. Materum. "Cleanroom Dashboard System for Time-Reduction Checking of Disk Tester Availability". Journal of Advanced Research in Applied Sciences and Engineering Technology 43, n.º 2 (17 de abril de 2024): 237–57. http://dx.doi.org/10.37934/araset.43.2.237257.
Texto completoResumen
With the vast amount of data being processed and reviewed in production and manufacturing industries nowadays, it takes a lot of time and effort to keep track of their performance metrics. Developing an automation system to improve the overall system performance and reduce man-machine interactions is necessary. Prior to the work, a computer disk drive manufacturing facility checked its fixed-tester availability manually, which made the company unable to optimize its man and machine hours as much as possible. This work proposes a system that displays all the critical information in a dashboard system to address the problem while enabling access to data history logs and further analytic insights. Moreover, the system enables readily accessible fixed-disk tester availability. The outcomes indicate significant improvements, especially in delay reductions, necessary for optimizing man and machine interactions in a fixed-disk testing facility at a leading computer disk drive manufacturer and data storage company at Laguna Technopark.
6
Sutrisno, Niantoro, Rizka Faradila, Rizka Faradila, Edison P. Sirait y Edison P. Sirait. "PENGARUH KAPASITAS MESIN DAN JUMLAH PERSEDIAAN BAHAN BAKU TERHADAP VOLUME PRODUKSI". Jurnal Akuntansi dan Bisnis 10, n.º 01 (25 de junio de 2024): 15. http://dx.doi.org/10.47686/jab.v10i01.680.
Texto completoResumen
Background of this research based on data’s observational at a company relating to capacity, amount of raw material inventory and production volume where the phenomena that occur still need to be optimized. This research uses a quantitative approach and uses primary data as a data source obtained from the results of questionnaires distributed to respondents related to activities in accordance with the specified research variables. The analytical methods used are instrument testing, classical assumption testing, multiple regression analysis, hypothesis testing and coefficient of determination (Adjusted R2). The results of this research show that:1. The machine capacity variable partially has a positive and significant effect on production volume at PT. Gema Graha Saran, Tbk Bekasi Regency.2. The raw material inventory variable partially has a positive and significant effect on production volume at PT. Gema Graha Sarana, Tbk Bekasi Regency.3. The variables of machine capacity and raw material inventory simultaneously have a positive and significant effect on production volume at PT. Gema Graha Sarana, Tbk Bekasi Regency Keywords :Raw Material Inventory, Machine Capacity, and Production Volume
7
Qu, Ju Bao y Shu Juan Wang. "Intelligent Quality Control System Based on Machine Vision of Multi-Line". Applied Mechanics and Materials 513-517 (febrero de 2014): 1192–96. http://dx.doi.org/10.4028/www.scientific.net/amm.513-517.1192.
Texto completoResumen
Testing for a variety of different industrial objects, this paper designed a multi on-line machine vision based on intelligent quality control system solutions. Microvision based on the company introduced the MV-8002 image acquisition card and the MV-VS1394 camera visual inspection of industrial software and hardware structure and the working principle of a high-speed online learning model of intelligent foreign recognition, it described the image acquisition card and the camera with the application and the software development. by the applications case, and the further evidence of the reliability of this system.
8
Siti Nur Syamimi Mat Zain, Nor Azuana Ramli y Rose Adzreen Adnan. "CUSTOMER SENTIMENT ANALYSIS THROUGH SOCIAL MEDIA FEEDBACK: A CASE STUDY ON TELECOMMUNICATION COMPANY". International Journal of Humanities Technology and Civilization 7, n.º 2 (14 de diciembre de 2022): 54–61. http://dx.doi.org/10.15282/ijhtc.v7i2.8739.
Texto completoResumen
Customer sentiment analysis is an automated way of detecting sentiments in online interactions in order to assess customer opinions about a product, brand or service. It assists companies in gaining insights and efficiently responding to their customers. This study presents a machine learning approach to analyse how sentiment analysis detects positive and negative feedback about a telecommunication company’s products. Customer feedback data were taken from Twitter through Streaming API (Application Programming Interface), where Tweets are retrieved in real time based on search terms, time, users and likes. Responses from the twitter API are parsed into tables and stored in a CSV file. Based on the analysis, it was found that there was no negative sentiment from the customers. The data were then split into training and testing to be tested on the three different supervised learning algorithms used in this study which are Support Vector Machine, Random Forest, and Naïve Bayes. Lasty, the performance of each model was compared to select the most accurate model and from the analysis, it can be concluded that Support Vector Machine gives the best performance in terms of accuracy, Mean Squared Error, Root Mean Squared Error and Area Under the ROC curve.
9
Srisattayakul, Parinya, Charnnarong Saikaew, Anurat Wisitsoraat y Naphatara Intanon. "Influence of MoN Sputtering Coating on Wear Resistance of a Fishing Net-Weaving Machine Component". Advanced Materials Research 1016 (agosto de 2014): 80–84. http://dx.doi.org/10.4028/www.scientific.net/amr.1016.80.
Texto completoResumen
Wear resistance of an upper hook, an important fishing net-weaving machine component manufactured from stainless steel, was improved by systematically investigating the influence of molybdenum nitride (MoN) sputtering coating using experimental design. Three factors of MoN coating on upper hooks including DC current, operating pressure, and Ar/N2ratio were studied and optimized for minimum wear of the machine component. After conducting wear testing on the fishing net-weaving machine in a participating company, it was found that the three coating factors influenced the wear of the machine component. In addition, the optimal operating condition for MoN sputtering coating that produced the minimum wear was obtained at DC current of 0.45 A, operating pressure of 0.01 mbar, and Ar/N2ratio of 0.5.
10
Weick, S., M. Grosse y M. Steinbrueck. "The INCHAMEL facility – a new device for in-situ neutron investigations under defined temperatures with applicable mechanical load". Journal of Physics: Conference Series 2605, n.º 1 (1 de septiembre de 2023): 012035. http://dx.doi.org/10.1088/1742-6596/2605/1/012035.
Texto completoResumen
Abstract In order to in-situ quantify the hydrogen diffusion in metals or more precisely in zircaloy cladding tubes with the influence of an applied stress field, a new device was constructed in cooperation with the company ZwickRoell - the transportable INCHAMEL facility. It is a modification of ZwickRoell’s Kappa Mini 1 kN tensile testing machine. The facility is equipped with all features of a tensile testing machine, additionally a defined temperature can be applied. The machine’s design was dedicated in detail to fulfil the requirements for the usage in facilities with neutron radiation. In this manner, neutron radiography investigations can be performed in-situ with the neutron beam passing through the sample without any disturbances by installations like beam windows, thermo-couples, furnace tubes, heater wires, clamps for strain measurements, etc.
Tesis sobre el tema "Testing Machine Company"
1
Olivier, Louis Petrus. "Psychomotor ability and learning potential as predictors of driver and machine operator performance in a road construction company". Diss., 2015. http://hdl.handle.net/10500/19687.
Texto completoResumen
The changing nature of work and its competitive characteristics are global phenomena and are mainly fuelled by ongoing technological advancement. This creates unique challenges for talent attraction and the retention of high performing individuals. In addition, the global workforce is becoming more diverse due to demographic, societal and cultural changes and companies are placing greater demands on employee competency and performance. Managing the human factor as a strategic asset in organisations remains a primary challenge in securing a competitive advantage.
The road construction industry in South Africa is no different. There is growing competition between civil engineering contractors to secure tenders and to maximise profitability. This is only possible with a sufficient and sustainable labour force. Valid selection processes are therefore required to ensure that the most productive individuals are selected for the most suitable jobs. Reliable and valid performance predictors will assist employers in making appropriate selection decisions. Selecting high performing individuals will support and enhance overall organisational performance.
ix
In this study the investigation focused on whether psychomotor ability and learning potential are statistically significant predictors of work performance - with specific reference to drivers and machine operators in a road construction company. A quantitative approach was followed to investigate the relationships between variables, or then the prediction of one dependent variable (driver and machine operator performance) by means of two independent variables (psychomotor ability and learning potential).
Results from the study did not indicate any statistically significant relationships between the variables. Only scientifically validated assessment instruments were used in the study - which means the findings led to a renewed focus on the importance of performance measurement and the psychometric quality (reliability and validity) of performance data.Industrial and Organisational Psychology
M.A. (Industrial and Organisational Psychology)
Capítulos de libros sobre el tema "Testing Machine Company"
1
Abaei, Golnoush y Ali Selamat. "Important Issues in Software Fault Prediction". En Advances in Systems Analysis, Software Engineering, and High Performance Computing, 510–39. IGI Global, 2014. http://dx.doi.org/10.4018/978-1-4666-6026-7.ch023.
Texto completoResumen
Quality assurance tasks such as testing, verification and validation, fault tolerance, and fault prediction play a major role in software engineering activities. Fault prediction approaches are used when a software company needs to deliver a finished product while it has limited time and budget for testing it. In such cases, identifying and testing parts of the system that are more defect prone is reasonable. In fact, prediction models are mainly used for improving software quality and exploiting available resources. Software fault prediction is studied in this chapter based on different criteria that matters in this research field. Usually, there are certain issues that need to be taken care of such as different machine-learning techniques, artificial intelligence classifiers, variety of software metrics, distinctive performance evaluation metrics, and some statistical analysis. In this chapter, the authors present a roadmap for those researchers who are interested in working in this area. They illustrate problems along with objectives related to each mentioned criterion, which could assist researchers to build the finest software fault prediction model.
2
"Front Matter". En Pendulum Impact Machines: Procedures and Specimens for Verification, FM1—FM10. ASTM International100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959, 1995. http://dx.doi.org/10.1520/stp14652s.
Texto completoResumen
Comprised of the most current and wide-ranging information available on metallic and nonmetallic pendulum impact machines. Experts from all over the world have contributed 18 papers covering four major areas: The Specimen; • The Anvils and the Striker; • Establishing Reference Energies; • and Testing Procedures and Other Topics. Three papers compare the merits of two different radius striker designs. Several presentations focus on the development of standardized specimens and their impact on verification of machine performance. Machine and specimen tolerances are explored in five papers, covering such topics as striker geometry tolerances, striker surface finish, specimen edge and reconstitution of specimens. Machine verification in plastic and polymeric materials is also discussed. Other papers deal with kinetic energy from the machines as well as the use of load-displacement curves for impact tests.
3
Anand, Mansimar, Irtibat Shaukat, Harnoor Kaler, Jai Narula y Prashant Singh Rana. "Hybrid Model for the Customer Churn Prediction". En SCRS Proceedings of International Conference of Undergraduate Students, 85–94. Soft Computing Research Society, 2023. http://dx.doi.org/10.52458/978-81-95502-01-1-9.
Texto completoResumen
The fast development of the showcase in each segment is driving to a prevalent endorser base for benefit suppliers. In such a quick setup, benefit suppliers have realized the significance of holding the on-hand clients. It is in this manner fundamental for the benefits suppliers to prevent churn - a phenomenon that states that the client wishes to quit the benefit of the company. The key here is to be motivated and have interaction with these clients. While simple, in theory, the realities worried about achieving this “proactive retention” goal are incredibly challenging. The most commitment of our work is to create a Churn expectation show that helps companies foresee clients who are most likely subject to churn. The model developed in this work employs machine learning strategies on the dataset and builds a robust training and testing model. The proposed model results are authenticated using K-fold cross-validation, and an accuracy of 91.48% is achieved. The main contribution is using K-means clustering to make clusters and then applying the Random Forest classifier for model prediction. The model was organized and tested operating on a data set created and supplied by a telecom organization from the United States of America. The model experimented with seven algorithms: Random Forest, Logistic Regression, Naive Bayes, K-nearest neighbors, Gradient Boosting, Ada Boosting, and K-means. However, the proposed model is experimented with by combining the K-means and Random Forest algorithm.
4
Kanatani, Kenichi. "Statistical Analysis of Geometric Computation, 2". En Geometric Computation for Machine Vision, 318–63. Oxford University PressOxford, 1993. http://dx.doi.org/10.1093/oso/9780198563853.003.0010.
Texto completoResumen
Abstract In this chapter, the techniques of statistical analysis established in Chapter 9 are applied to some of the most fundamental problems of machine vision. First, the reliability of focal length calibration is evaluated in statistical terms. We derive an optimal scheme for maximizing the reliability of the computed focal length and compute its confidence interval. Then, the error behaviours involved in 3-D motion estimation and conic fitting are analysed in detail. In each problem, the least-squares solution is shown to be statistically biased. We construct an unbiased estimation scheme and give numerical examples to demonstrate its effectiveness. Finally, a hypothesizing and testing approach is presented for making judgements concerning edge groupings, vanishing points, focuses of expansion, and vanishing lines. It is shown that the “credibility” of a given configuration can be computed by regarding “edges” as atomic elements and applying the X 2-test, which allows us to compare the credibilities of different configurations on the same basis.
5
Zhang, Xiang. "Financial Data Anomaly Recognition Model Based on Improved Support Vector Machine". En Advances in Transdisciplinary Engineering. IOS Press, 2024. http://dx.doi.org/10.3233/atde231272.
Texto completoResumen
In order to achieve unsupervised classification of enterprise financial transaction data and identify suspicious abnormal financial data, a financial data anomaly recognition model based on support vector machine is proposed. This article adopts sample testing and independence testing to reduce the dimensionality of the company’s indicators, and selects principal component indicators that can accurately measure the financial condition of the enterprise. When the SVM model is introduced to solve the financial anomaly identification problem, the parameter optimization module are improved. Then, a mixed kernel function through linear combination and optimized parameters using PSO is established. The experiment is performed in MATLAB environment to construct an improved SVM model for feature vector training based on training dataset algorithms. The results indicate that our scheme can detect suspicious values in actual financial account data and effectively avoid overfitting and underfitting phenomena. Compared to similar algorithms, the recognition accuracy and robustness have been improved, making it more suitable for financial crisis warning.
6
Iwata, Kazunori, Toyoshiro Nakashima, Yoshiyuki Anan y Naohiro Ishii. "Machine Learning Classification to Effort Estimation for Embedded Software Development Projects". En Research Anthology on Agile Software, Software Development, and Testing, 1652–65. IGI Global, 2022. http://dx.doi.org/10.4018/978-1-6684-3702-5.ch078.
Texto completoResumen
This paper discusses the effect of classification in estimating the amount of effort (in man-days) associated with code development. Estimating the effort requirements for new software projects is especially important. As outliers are harmful to the estimation, they are excluded from many estimation models. However, such outliers can be identified in practice once the projects are completed, and so they should not be excluded during the creation of models and when estimating the required effort. This paper presents classifications for embedded software development projects using an artificial neural network (ANN) and a support vector machine. After defining the classifications, effort estimation models are created for each class using linear regression, an ANN, and a form of support vector regression. Evaluation experiments are carried out to compare the estimation accuracy of the model both with and without the classifications using 10-fold cross-validation. In addition, the Games-Howell test with one-way analysis of variance is performed to consider statistically significant evidence.
7
Pai, Srinivasa P. y Nagabhushana T. N. "Tool Condition Monitoring Using Artificial Neural Network Models". En Handbook of Research on Emerging Trends and Applications of Machine Learning, 550–76. IGI Global, 2020. http://dx.doi.org/10.4018/978-1-5225-9643-1.ch026.
Texto completoResumen
Tool wear is a major factor that affects the productivity of any machining operation and needs to be controlled for achieving automation. It affects the surface finish, tolerances, dimensions of the workpiece, increases machine down time, and sometimes performance of machine tool and personnel are affected. This chapter deals with the application of artificial neural network (ANN) models for tool condition monitoring (TCM) in milling operations. The data required for training and testing the models studied and developed are from live experiments conducted in a machine shop on a widely used steel, medium carbon steel (En 8) using uncoated carbide inserts. Acoustic emission data and surface roughness data has been used in model development. The goal is for developing an optimal ANN model, in terms of compact architecture, least training time, and its ability to generalize well on unseen (test) data. Growing cell structures (GCS) network has been found to achieve these requirements.
8
Pai, Srinivasa P. y Nagabhushana T. N. "Tool Condition Monitoring Using Artificial Neural Network Models". En Research Anthology on Artificial Neural Network Applications, 400–426. IGI Global, 2022. http://dx.doi.org/10.4018/978-1-6684-2408-7.ch019.
Texto completoResumen
Tool wear is a major factor that affects the productivity of any machining operation and needs to be controlled for achieving automation. It affects the surface finish, tolerances, dimensions of the workpiece, increases machine down time, and sometimes performance of machine tool and personnel are affected. This chapter deals with the application of artificial neural network (ANN) models for tool condition monitoring (TCM) in milling operations. The data required for training and testing the models studied and developed are from live experiments conducted in a machine shop on a widely used steel, medium carbon steel (En 8) using uncoated carbide inserts. Acoustic emission data and surface roughness data has been used in model development. The goal is for developing an optimal ANN model, in terms of compact architecture, least training time, and its ability to generalize well on unseen (test) data. Growing cell structures (GCS) network has been found to achieve these requirements.
9
Deo, Ravinesh C., Sujan Ghimire, Nathan J. Downs y Nawin Raj. "Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model". En Research Anthology on Multi-Industry Uses of Genetic Programming and Algorithms, 116–47. IGI Global, 2021. http://dx.doi.org/10.4018/978-1-7998-8048-6.ch007.
Texto completoResumen
The precise prediction of windspeed is essential in order to improve and optimize wind power prediction. However, due to the sporadic and inherent complexity of weather parameters, the prediction of windspeed data using different patterns is difficult. Machine learning (ML) is a powerful tool to deal with uncertainty and has been widely discussed and applied in renewable energy forecasting. In this chapter, the authors present and compare an artificial neural network (ANN) and genetic programming (GP) model as a tool to predict windspeed of 15 locations in Queensland, Australia. After performing feature selection using neighborhood component analysis (NCA) from 11 different metrological parameters, seven of the most important predictor variables were chosen for 85 Queensland locations, 60 of which were used for training the model, 10 locations for model validation, and 15 locations for the model testing. For all 15 target sites, the testing performance of ANN was significantly superior to the GP model.
10
Deo, Ravinesh C., Sujan Ghimire, Nathan J. Downs y Nawin Raj. "Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model". En Advances in Computational Intelligence and Robotics, 328–59. IGI Global, 2018. http://dx.doi.org/10.4018/978-1-5225-4766-2.ch015.
Texto completoResumen
The precise prediction of windspeed is essential in order to improve and optimize wind power prediction. However, due to the sporadic and inherent complexity of weather parameters, the prediction of windspeed data using different patterns is difficult. Machine learning (ML) is a powerful tool to deal with uncertainty and has been widely discussed and applied in renewable energy forecasting. In this chapter, the authors present and compare an artificial neural network (ANN) and genetic programming (GP) model as a tool to predict windspeed of 15 locations in Queensland, Australia. After performing feature selection using neighborhood component analysis (NCA) from 11 different metrological parameters, seven of the most important predictor variables were chosen for 85 Queensland locations, 60 of which were used for training the model, 10 locations for model validation, and 15 locations for the model testing. For all 15 target sites, the testing performance of ANN was significantly superior to the GP model.
Actas de conferencias sobre el tema "Testing Machine Company"
1
Abbas, Raafat, Aaron Simon, Doug Dunbar, Rodrigo Serrano, Andrew Creegan y Ernie Prochaska. "Automatic Driller Optimization Application Using Machine Learning and Artificial Intelligence Drives Consistent Performance in an Operator’s West Texas Drilling Program". En SPE Annual Technical Conference and Exhibition. SPE, 2023. http://dx.doi.org/10.2118/215087-ms.
Texto completoResumen
Abstract A large operator and drilling rig contractor worked collaboratively with a service company using a machine learning and artificial intelligence application to adjust setpoints on the auto driller to optimize performance in a West Texas drilling program. This application, which employed a novel usage of mud pulse telemetry, contributed to consistent performance in intermediate and lateral sections on multiple pads. The trial was conducted in the Midland Basin using Advisory Mode (manual) settings in the intermediate and lateral sections. The trial was considered successful with a decision made to move to the next level with Control Mode (automated) settings in the Delaware Basin. A unique aspect of this trial was the creation of an execution process that combined all the participating parties including the operator, drilling rig contractor, directional drilling company and the service company. This process involved documentation, training, testing, and communication with onsite, field and office personnel. Learnings were an integral part of this process and used to improve the performance on each section/well/pad. These lessons were used to update and optimize the engine’s logic as needed. The drilling rig contractor and service company worked together to integrate the rig control system and the auto driller application, performing lab testing and implementation at the rig site. After several development upgrades the operator wanted to test the system out on a second drilling rig in another area in the Delaware Basin. A drilling rig with a different control system was designated for testing, the same process was used to integrate the rig control system with the auto driller application, along with lab testing and implementation at the rig site. One of the objectives and focus was to match machine learning to human responses optimizing drilling parameters. During the testing, an accelerated development process was used adding functionality to the auto driller application that included active responses to downhole shocks and vibrations. Once the participants, operator, drilling rig contractor, directional drilling company, performance engineers, programmers and service support were satisfied with the reliability and repeatability with the application, six more drilling rigs were added to the program. There were initial measurable performance gains optimizing the drilling parameters, bottom hole assemblies and auto driller. The longer-term achievement of this application provided consistent enhanced performance using the auto driller. Automating this process aids the Driller by providing a tool that levels experience. The ongoing results of this program prove that long term sustainable performance is provided using this application on multiple control system drilling rigs. As a result of these efforts, a savings of approximately half a day when compared to manual operations was realized when drilling two mile lateral sections.
2
Valdiero, Antonio C., Ronei O. Ziech, Mauricio S. Pinto, Ivan J. Mantovani y Luiz A. Rasia. "Development and Construction of an Instrumentalized Workbench With a Hydraulic Motor for Farm Machine Testing". En 9th FPNI Ph.D. Symposium on Fluid Power. American Society of Mechanical Engineers, 2016. http://dx.doi.org/10.1115/fpni2016-1552.
Texto completoResumen
This work addresses the design and the construction of an instrumentalized workbench with hydraulic motor. The primary purpose of estimating the consumed power for farm machines, as for example the power consumption on the drive shaft of a variable rate fertilizer targeted for applications in precision agriculture. The estimate of the consumed power is important for the better design of the transmission elements and for machines control and design, collaborating for the reduction of the mass and the costs of the prototype. The instrumentalized workbench was used to estimate the actual consumed power in fertilizer dosing devices used in precision agriculture, allowing the correct specification of the power system to drive and the validation of modeling and variable rate control. The aim is to measure and to evaluate the power consumption of a commercial fertilizer in different fertilization rates with usual fertilizer. The used methodology is based on the needs analysis, design and construction of an instrumented bench with hydraulic motor for fertilizer prototype testing. The experimental prototype was tested at the Innovation Center for Automatic Machines and Servo Systems (NIMASS) in UNIJUÍ University with support by IMASA, FINEP and CNPq. Tests with fertilizer mounted allowed the calculation of the consumed volumetric flow rates and the load pressure of the hydraulic motor, thus enabling the estimated consumed power. This research intends to contribute for the modeling and design of hydraulic systems applications in farm machines and the innovations development to technology transfer to manufacturer national company.
3
Gerchman, Mark Craig. "The Single Point Diamond Turning (SPDT) Of Optical Surfaces For Visible Wavelength Applications". En Optical Fabrication and Testing. Washington, D.C.: Optica Publishing Group, 1990. http://dx.doi.org/10.1364/oft.1990.jtuc3.
Texto completoResumen
Recent advances in machine tools for single point diamond turning have significantly improved the quality of machined surfaces available. The most recent generation of SPDT machines are producing optical surfaces suitable for many visible wavelength applications. This presentation will examine the quality of current SPDT surfaces and compare them with reasonable criteria for visible wavelength surface specifications.
4
Al Radhi, Mohammed, Fernando Angel Bermudez, Wael Al Madhoun, Khaled Al Blooshi, Noor Nasser Al Nahhas y Mohammed Nazeih Shono. "Unlocking the Potential of Electrical Submersible Pumps: the Successful Testing and Deployment of a Real-Time Artificially Intelligent System, for Failure Prediction, Run Life Extension, and Production Optimization". En SPE Symposium: Artificial Intelligence - Towards a Resilient and Efficient Energy Industry. SPE, 2021. http://dx.doi.org/10.2118/208647-ms.
Texto completoResumen
Abstract This paper is a summary of the collaborative work between ADNOC (Abu Dhabi National Oil Company) and nybl, a deep tech development company, and the results of applying nybl's proprietary "Science-Based Artificial Intelligence" to ADNOC Electrical Submersible Pump (ESP) wells in real-time applications. The paper demonstrates the potential benefits of the real-life application of Artificial Intelligence (AI) / Machine Learning (ML) in conjunction with traditional Petroleum Engineering concepts and algorithms to predict imminent and future failures, extend and monitor run life, and maximize the production of ESPs. This paper will highlight ADNOC's innovative approach to pilot new technology through successful deployment on 27 wells, spread onshore and offshore, in real-time, with prescriptive actions.
5
Bermudez, Fernando, Noor Al Nahhas, Hafsa Yazdani, Michael LeTan y Mohammed Shono. "Unlocking the Potential of Electrical Submersible Pumps: The Successful Testing and Deployment of a Real-Time Artificially Intelligent System, for Failure Prediction, Run Life Extension, and Production Optimization". En Abu Dhabi International Petroleum Exhibition & Conference. SPE, 2021. http://dx.doi.org/10.2118/207839-ms.
Texto completoResumen
Abstract This paper is a summary of the collaborative work between a Gulf Cooperation Council (GCC) national oil company (NOC) and Nybl, a deep tech development company, and the results of applying Nybl's proprietary science-based AI to the GCC NOC ESP wells in real-time applications. The paper demonstrates the potential benefits of the real-life application of AI / Machine Learning in conjunction with traditional Petroleum Engineering concepts and algorithms to predict imminent and future failures, extend and monitor run life, and maximize the production of Electrical Submersible Pumps (ESP's). This paper will highlight the NOC's innovative approach to pilot new technology through successful deployment on 27 wells, spread onshore and offshore, in real-time, with prescriptive actions.
6
Miller, Richard J. y Reginald D. Conner. "Field Validation Testing of New HEAT™ Steam Turbine". En ASME 2006 Power Conference. ASMEDC, 2006. http://dx.doi.org/10.1115/power2006-88202.
Texto completoResumen
The field validation and launch unit performance testing of a new high efficiency steam turbine design is described. The HEAT™ (High Efficiency Advanced Technology) steam turbine utilizes a new line of high efficiency steam path components developed by the author’s company [1], [2]. The extensive field test program, executed at the customer’s plant, included all major aspects of steam turbine operation and performance. Data was gathered continuously using multiple automated systems. Careful indexing of this data provided a multi-faceted view of operating phenomena during the test period. Overall machine performance was tested using ASME PTC 6.2 protocol. HP and IP individual section thermodynamic performance was quantified with a series of enthalpy drop tests. In addition, all leakage flows were measured to confirm end seal performance. HP section pressure ratio tests and internal leakage blowdown tests were done to determine the HP steam path aerodynamic characteristics. Various pressure measurements were used to quantify LP bucket aerodynamics and overall LP hood/diffuser performance. Validation testing of thermal-mechanical transient behavior of major components during all normal operating modes was achieved using lasers, thermocouples and strain gauges. In addition, thermal imaging was used to increase understanding of these transients. The validation instrumentation had an additional benefit to this customer, as it assisted the site team to successfully commission this A14 code type turbine, which achieved world-class efficiency.
7
Black, J. T. "Lean Manufacturing Cell Design". En ASME 1996 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 1996. http://dx.doi.org/10.1115/imece1996-0773.
Texto completoResumen
Abstract In the lean production company, the manufacturing engineers are responsible for designing, building, testing, and implementing the manufacturing equipment for the manufacturing cells. These cells are designed for flexibility — they can handle changes in product design as well as external customer demand. This means the manufacturing engineer must have machine design skills in addition to system design skills. The key here is that the manufacturing equipment is custom designed and custom built for the manufacturing system and for the users of the equipment (the internal customer). However, many companies have designed interim cells using machine tools designed for stand-alone applications in the job shop. Industrial examples of these two kinds of cells are presented.
8
Kasim, Fadzlin Hasani, Nurul Nadhira Idris, Saeed Majidaie, Budi Priyatna Kantaatmadja, Numair Ahmed Siddiqui, Akhmal Sidek y Nur Aqilah Nabila Yahaya. "The Utilization of Machine Learning Method to Predict Hydrocarbon Flow Rate for a Better Reservoir Potential Evaluation". En International Petroleum Technology Conference. IPTC, 2022. http://dx.doi.org/10.2523/iptc-22025-ms.
Texto completoResumen
Abstract The numbers of machine learning technologies used in subsurface characterization work is increasing with more company rely on data driven to assist in performing any evaluation. In this study, a supervised random forest machine learning approach was utilized in two stages; first stage was to predict static reservoir using well logs and core as inputs. The output is then used as the basis in the second stage to predict initial oil rate (Qi) and subsequently to determine estimated ultimate recovery (EUR) at targeted interval as proposed in the first stage. Static reservoir machine learning prediction outputs were benchmark with available routine core analysis with the result showed R2 of 88% respectively. For initial oil rate (Qi) prediction, a total of 9000 observation points from 20 wells were extracted for training and blind testing process by using variables such as permeability, net thickness, well choke size, well flowing pressure, average pressure, water cut, irreducible water saturation (Swi), and historical production rate. The estimated ultimate recovery (EUR) is then predicted utilizing the thickness of that unit and the decline rate that is obtained from the neighboring wells that has produced from the said reservoir as the analogue. The Qi and EUR results from machine learning is compared with the estimated Qi and EUR using conventional methods for verification purpose. The results from machine learning dynamic properties prediction showed 97% R2 for training while the testing score mean is 87% against the historical data. High R2 from static and dynamic machine learning prediction indicated that the method was reliable and able to assist petroleum engineer in reservoir potential evaluation process.
9
Liao, Leo y Ang Li. "An Intelligent System to Automate the Inquery in Logistics Industry using AI and Machine Learning". En 8th International Conference on Natural Language Processing (NATP 2022). Academy and Industry Research Collaboration Center (AIRCC), 2022. http://dx.doi.org/10.5121/csit.2022.120109.
Texto completoResumen
Operator and sales employees in the logistics industry often have to submit the same inquiry repetitively to different vendors and opt in for the quotation that will generate the greatest profit for the company [4]. This process can be very laborious and tedious. Meanwhile, for smaller companies that do not have a well-constructed database for quotation information, monitoring employee’s work is simply difficult to achieve [5]. To increase the efficiency of sales’ workflow in this particular industry, this application devises a platform that automates the inquiry process, analyzes quotations from different vendors, retrieves the most profitable one, and documents all inquiries an employee has committed [6]. The results, after a series of intensive testing, prove to be promising and satisfying. The machine learning model can successfully fetch the most cost-effective price after analyzing a list of emails containing common languages used in the industry. All histories of an employee’s inquiry can be correctly displayed on any front-end device. Overall, the obstacle presented above is largely solved.
10
Anderson, Joel, Nathan Switzner, Jeffrey Kornuta y Peter Veloo. "Incorporating Measurement Uncertainty Into Machine Learning-Based Grade Predictions". En 2022 14th International Pipeline Conference. American Society of Mechanical Engineers, 2022. http://dx.doi.org/10.1115/ipc2022-87347.
Texto completoResumen
Abstract As part of the regulations published in October of 2019, PHMSA requires operators that do not have reliable records to conduct material verification in accordance with §192.607. As part of the material verification process, §192.607(d)(2) compels the operator to “[c]onservatively account for measurement inaccuracy and uncertainty using reliable engineering tests and analyses” when utilizing nondestructive examination (NDE) methods. The Pacific Gas and Electric Company (PG&E) has completed extensive testing to develop approaches that utilize nondestructive measurements to estimate grade. As part of this work, a supervised classification machine learning (ML) model was developed to predict pipe grade using NDE chemical composition measurements as inputs. While using the ML-based model provides substantial improvement over yield strength (YS) in predicting pipe grade, measurement uncertainty from NDE tools must be considered per §192.607(d)(2). Moreover, some amount of uncertainty is present in any measurement regardless of precision, and this measurement uncertainty may ultimately affect the ML model’s pipe grade classification. This paper presents a methodology for incorporating this variability into the authors’ ML classification model using a Monte Carlo-based simulation approach. In addition, this study will discuss the various metrics that were developed for interpreting the most probable pipe grade from the large number of simulation results, including the average probability, range of probability, and the number of simulations where each grade was identified as having the highest probability. Since any ML model can misclassify a sample and there are such slight differences between adjacent grades, it is necessary to have a method of systematically validating the results based on prior knowledge. Several case studies using field data will be presented to illustrate this approach, including validation cases where the pipe grade is known.