Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200065
Alankrita, S. Srivastava
Recent shift towards renewable energy resources has increased research for addressing shortcomings of these energy resources. As major issues are related to intermittency and uncertainty of renewable supply, new technologies like artificial intelligence and machine learning offers lot of opportunity to address these issues as they are basically meant for processing of uncertain data. This paper analyses application of machine learning in different areas of renewable energy system like forecasting where machine learning is used to build accurate models, maximum power point tracking where machine learning provides robust and smooth control which is not much susceptible to noise in input, inverter where machine learning can be used to provide high quality power without fluctuation even when input is intermittent. Even though machine learning has many prospects which can be used to address different issues associated with renewable system, whether to employ it as effective solution to problem for given system or not depends on host of factors. This paper analyses all these issues and present a methodical exploration of applications of machine learning, its advantages and challenges in hybrid renewable energy system.
{"title":"Application of Artificial Intelligence in Renewable Energy","authors":"Alankrita, S. Srivastava","doi":"10.1109/ComPE49325.2020.9200065","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200065","url":null,"abstract":"Recent shift towards renewable energy resources has increased research for addressing shortcomings of these energy resources. As major issues are related to intermittency and uncertainty of renewable supply, new technologies like artificial intelligence and machine learning offers lot of opportunity to address these issues as they are basically meant for processing of uncertain data. This paper analyses application of machine learning in different areas of renewable energy system like forecasting where machine learning is used to build accurate models, maximum power point tracking where machine learning provides robust and smooth control which is not much susceptible to noise in input, inverter where machine learning can be used to provide high quality power without fluctuation even when input is intermittent. Even though machine learning has many prospects which can be used to address different issues associated with renewable system, whether to employ it as effective solution to problem for given system or not depends on host of factors. This paper analyses all these issues and present a methodical exploration of applications of machine learning, its advantages and challenges in hybrid renewable energy system.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"20 1","pages":"327-331"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82727322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9199994
Pragya Sharma, Swet Chandan, B. P. Agrawal
This work is for developing a deep learning-based model for design and diagnosis of fault embedded in ball bearing. To overcome disadvantages of traditional methods for fault identification and diagnosis of ball bearing, method of 1-D Convolutional Neural Network (1-D CNN) is used in this work. 1-D CNN is developed for identification and classification of faults embedded in outer race of ball bearing. Adaptive design of 1-D CNN model presents an ability to fuse extraction of features and classification of fault in single learning body. Open source data "Society for Machinery Failure Prevention Technology (MFPT bearing fault dataset)" is used in this work for training and testing purpose. Main focus for using 1-D CNN approach is to get higher accuracy in fault diagnosis and less computational complexity for results.
{"title":"Vibration Signal-based Diagnosis of Defect Embedded in Outer Race of Ball Bearing using 1-D CNN","authors":"Pragya Sharma, Swet Chandan, B. P. Agrawal","doi":"10.1109/ComPE49325.2020.9199994","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9199994","url":null,"abstract":"This work is for developing a deep learning-based model for design and diagnosis of fault embedded in ball bearing. To overcome disadvantages of traditional methods for fault identification and diagnosis of ball bearing, method of 1-D Convolutional Neural Network (1-D CNN) is used in this work. 1-D CNN is developed for identification and classification of faults embedded in outer race of ball bearing. Adaptive design of 1-D CNN model presents an ability to fuse extraction of features and classification of fault in single learning body. Open source data \"Society for Machinery Failure Prevention Technology (MFPT bearing fault dataset)\" is used in this work for training and testing purpose. Main focus for using 1-D CNN approach is to get higher accuracy in fault diagnosis and less computational complexity for results.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"58 1","pages":"531-536"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88619849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200066
K. Kalita, A. Rai, Kunal Pandey, Rachana Garg
The determination of optimal power generation by generating units in an interconnected power system at the least possible cost, subject to power balance and limits of generation constraints, is called Economic Load Dispatch (ELD) problem. Different variants of Particle Swarm Optimization (PSO) applied on the problem of ELD are compared in this paper. The various methods viz - Conventional PSO, Simulated Annealing based PSO (SA-PSO), PSO with Time-Varying Acceleration Constant (PSO-TVAC) and Adaptive PSO (APSO). These methods are tested on a six-generator electrical power system. A comparative analysis of all these methods has been done on the basis of their ability to give an optimum solution, convergence
{"title":"Comparative Analysis of different Variants of Particle Swarm Optimization for Economic Load Dispatch Problem","authors":"K. Kalita, A. Rai, Kunal Pandey, Rachana Garg","doi":"10.1109/ComPE49325.2020.9200066","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200066","url":null,"abstract":"The determination of optimal power generation by generating units in an interconnected power system at the least possible cost, subject to power balance and limits of generation constraints, is called Economic Load Dispatch (ELD) problem. Different variants of Particle Swarm Optimization (PSO) applied on the problem of ELD are compared in this paper. The various methods viz - Conventional PSO, Simulated Annealing based PSO (SA-PSO), PSO with Time-Varying Acceleration Constant (PSO-TVAC) and Adaptive PSO (APSO). These methods are tested on a six-generator electrical power system. A comparative analysis of all these methods has been done on the basis of their ability to give an optimum solution, convergence","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"51 1","pages":"475-479"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88341373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200015
Utpal Barman, Diganto Sahu, Golap Gunjan Barman, Jayashree Das
In recent times, the Convolution Neural Networks (CNNs) is widely used in agriculture fields such as plant disease detection, plant health issue prediction, etc. This paper also forwards a self-build CNN (SBCNN) for potato disease detection. The SBCNN is separately applied in the augmented and non-augmented potato leaf image dataset. The algorithm is used to train and test the potato leaves images. The best validation accuracy of SBCNN in the non-augmented and augmented datasets is 96.98% and 96.75% with the training accuracy of 99.71% and 98.75%, respectively. The errors of training and validation are reported in each epoch. The SBCNN model is performed well in an augmented dataset without having any overfitting in the model. The model is also compared with the performance of MobileNet architecture for the development of smartphone applications. Finally, the SBCNN (Augmented) is selected as the best model as compared to SBCNN (non-augmented) and MobileNet. The model is deployed in an android application for real-time testing of potato leaf diseases and it can be considered as a replica of agriculture pathological laboratory.
{"title":"Comparative Assessment of Deep Learning to Detect the Leaf Diseases of Potato based on Data Augmentation","authors":"Utpal Barman, Diganto Sahu, Golap Gunjan Barman, Jayashree Das","doi":"10.1109/ComPE49325.2020.9200015","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200015","url":null,"abstract":"In recent times, the Convolution Neural Networks (CNNs) is widely used in agriculture fields such as plant disease detection, plant health issue prediction, etc. This paper also forwards a self-build CNN (SBCNN) for potato disease detection. The SBCNN is separately applied in the augmented and non-augmented potato leaf image dataset. The algorithm is used to train and test the potato leaves images. The best validation accuracy of SBCNN in the non-augmented and augmented datasets is 96.98% and 96.75% with the training accuracy of 99.71% and 98.75%, respectively. The errors of training and validation are reported in each epoch. The SBCNN model is performed well in an augmented dataset without having any overfitting in the model. The model is also compared with the performance of MobileNet architecture for the development of smartphone applications. Finally, the SBCNN (Augmented) is selected as the best model as compared to SBCNN (non-augmented) and MobileNet. The model is deployed in an android application for real-time testing of potato leaf diseases and it can be considered as a replica of agriculture pathological laboratory.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"9 1","pages":"682-687"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78554931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9199998
Abhinaba Dattachaudhuri, S. Biswas, Sunita Sarkar, Arpita Nath Boruah, Manomita Chakraborty, B. Purkayastha
Nowadays credit risk evaluation is very crucial in financial domain. Whenever it is processed by an individual, it becomes controversial as the assessment may be prone to human error. Recently, to overcome this issue, some automated systems have been developed for credit risk evaluation. Most of the developed systems focused on the credit decision only and neglected the transparency of the systems; however, many cases require transparency of the credit decision to benefit financial organization as well as the potential customers. Therefore, this paper proposes an expert system named Transparent Neural based Expert System for Credit Risk (TNESCR) evaluation which uses a white box neural model Rule Extraction from Neural Network using Classified and Misclassified data (RxNCM) to generate rules from financial data. The generated rules are so transparent to justify the explanations for why applications are granted/rejected with a significant predictive accuracy. The proposed TNESCR is validated using 10 fold cross validation with 3 credit risk datasets. The experimental results show the proposed TNESCR can perform significantly with great transparency and accuracy.
{"title":"Transparent Neural based Expert System for Credit Risk (TNESCR): An Automated Credit Risk Evaluation System","authors":"Abhinaba Dattachaudhuri, S. Biswas, Sunita Sarkar, Arpita Nath Boruah, Manomita Chakraborty, B. Purkayastha","doi":"10.1109/ComPE49325.2020.9199998","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9199998","url":null,"abstract":"Nowadays credit risk evaluation is very crucial in financial domain. Whenever it is processed by an individual, it becomes controversial as the assessment may be prone to human error. Recently, to overcome this issue, some automated systems have been developed for credit risk evaluation. Most of the developed systems focused on the credit decision only and neglected the transparency of the systems; however, many cases require transparency of the credit decision to benefit financial organization as well as the potential customers. Therefore, this paper proposes an expert system named Transparent Neural based Expert System for Credit Risk (TNESCR) evaluation which uses a white box neural model Rule Extraction from Neural Network using Classified and Misclassified data (RxNCM) to generate rules from financial data. The generated rules are so transparent to justify the explanations for why applications are granted/rejected with a significant predictive accuracy. The proposed TNESCR is validated using 10 fold cross validation with 3 credit risk datasets. The experimental results show the proposed TNESCR can perform significantly with great transparency and accuracy.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"19 1","pages":"013-017"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73086592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200080
Athira Mv, D. M. Khan
The area, object detection has seen a drastic development of algorithms and techniques over the past years. The arrival of deep learning has boosted the improvement in accuracy and performance of systems. This paper is a brief survey of several works developed so far in the field of image classification and object detection and a relative study of different methods. Survey is divided in three sub areas as Machine Learning based approach, Deep Learning based approach and object detection for night vision applications. A comparative table with the discussed works is also given.
{"title":"Recent Trends on Object Detection and Image Classification: A Review","authors":"Athira Mv, D. M. Khan","doi":"10.1109/ComPE49325.2020.9200080","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200080","url":null,"abstract":"The area, object detection has seen a drastic development of algorithms and techniques over the past years. The arrival of deep learning has boosted the improvement in accuracy and performance of systems. This paper is a brief survey of several works developed so far in the field of image classification and object detection and a relative study of different methods. Survey is divided in three sub areas as Machine Learning based approach, Deep Learning based approach and object detection for night vision applications. A comparative table with the discussed works is also given.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"153 1","pages":"427-435"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73710682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200086
Avishek Nandi, P. Dutta, Md. Nasir
Human face emotions are generally classified in six different expressions such as Anger, Disgust, Fear, Happiness, Sadness, and Surprise. The authors propose a novel method for selecting an expression specific set of salient landmark points out of 68 landmark points produced by applying an Active Appearance Model (AAM) on an input face image. The salient Landmark points are selected by training a MultiLayer Perceptron network using a Histogram oriented Gradient (HoG) feature of neighboring pixels of a Landmark point. Next, a shape signature vector is constructed by forming triangulation using those salient landmarks for each expression. This is trained with six Multilayered Perceptron (MLP) network for classification of each of the six basic expressions. The suggested algorithm is tested on CK+, JAFFE, MMI, and MUG database. The outcomes are found extremely promising.
{"title":"Human Emotion Classification: An Expression Specific Geometric Approach","authors":"Avishek Nandi, P. Dutta, Md. Nasir","doi":"10.1109/ComPE49325.2020.9200086","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200086","url":null,"abstract":"Human face emotions are generally classified in six different expressions such as Anger, Disgust, Fear, Happiness, Sadness, and Surprise. The authors propose a novel method for selecting an expression specific set of salient landmark points out of 68 landmark points produced by applying an Active Appearance Model (AAM) on an input face image. The salient Landmark points are selected by training a MultiLayer Perceptron network using a Histogram oriented Gradient (HoG) feature of neighboring pixels of a Landmark point. Next, a shape signature vector is constructed by forming triangulation using those salient landmarks for each expression. This is trained with six Multilayered Perceptron (MLP) network for classification of each of the six basic expressions. The suggested algorithm is tested on CK+, JAFFE, MMI, and MUG database. The outcomes are found extremely promising.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"51 1","pages":"217-221"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74426229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200168
Sangeeta Sarkar, Meenakshi Agarwalla, S. Agarwal, M. Sarma
Deep Neural Networks have progressed significantly over the past few years and they are growing better and bigger each day. Thus, it becomes difficult to compute as well as store these over-parameterized networks. Pruning is a technique to reduce the parameter-count resulting in improved speed, reduced size and reduced computation power. In this paper, we have explored a new pruning strategy based on the technique of Incremental Pruning with less pre-training and achieved better accuracy in lesser computation time on MNIST, CIFAR-10 and CIFAR-100 datasets compared to previous related works with small decrease in compression rates. On MNIST, CIFAR-10 and CIFAR-100 datasets, the proposed technique prunes 10x faster than conventional models with similar accuracy.
{"title":"An Incremental Pruning Strategy for Fast Training of CNN Models","authors":"Sangeeta Sarkar, Meenakshi Agarwalla, S. Agarwal, M. Sarma","doi":"10.1109/ComPE49325.2020.9200168","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200168","url":null,"abstract":"Deep Neural Networks have progressed significantly over the past few years and they are growing better and bigger each day. Thus, it becomes difficult to compute as well as store these over-parameterized networks. Pruning is a technique to reduce the parameter-count resulting in improved speed, reduced size and reduced computation power. In this paper, we have explored a new pruning strategy based on the technique of Incremental Pruning with less pre-training and achieved better accuracy in lesser computation time on MNIST, CIFAR-10 and CIFAR-100 datasets compared to previous related works with small decrease in compression rates. On MNIST, CIFAR-10 and CIFAR-100 datasets, the proposed technique prunes 10x faster than conventional models with similar accuracy.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"46 1","pages":"371-375"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78896518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200039
Abhishek Chauhan, Pritam Rout, Ksh Milan Singh
A closed loop modulated Hopping Discrete Fourier Transform (mHDFT) based quadrature detector is proposed to estimate the various vibration parameters. The modulated hopping DFT is efficient way of calculating DFT of N samples. The system poles always reside on the unit circle and as there is no twiddle factor involved in feedback of the filter so there is no accumulation of error while calculating the DFT of N samples. This algorithm is implemented in Phase Locked Loop design for non contact type vibration estimation. The detection accuracy of the proposed estimator is very high even for low frequency signals.
{"title":"Vibration Parameters Estimation using mHDFT Filter in PLL Technique","authors":"Abhishek Chauhan, Pritam Rout, Ksh Milan Singh","doi":"10.1109/ComPE49325.2020.9200039","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200039","url":null,"abstract":"A closed loop modulated Hopping Discrete Fourier Transform (mHDFT) based quadrature detector is proposed to estimate the various vibration parameters. The modulated hopping DFT is efficient way of calculating DFT of N samples. The system poles always reside on the unit circle and as there is no twiddle factor involved in feedback of the filter so there is no accumulation of error while calculating the DFT of N samples. This algorithm is implemented in Phase Locked Loop design for non contact type vibration estimation. The detection accuracy of the proposed estimator is very high even for low frequency signals.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"45 1","pages":"649-653"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79022792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1109/ComPE49325.2020.9200186
Robin Wilson, R. Gandhi, Amit Kumar, Rakesh Roy
This paper analyzes the performance of dual-rotor axial flux permanent magnet synchronous motor for its application in electric motor drive. Dual-rotor single-stator topology is employed for analysis due to its superior features compared to other topologies of the motor for electric drive application. Constant torque angle control strategy with hysteresis current controller for inverter switching is implemented with the axial flux motor and is analyzed for validation. To enhance the robustness of the control strategy, the coefficients of proportional-integral controller are optimized with particle swarm optimization algorithm using Matlab/Simulink software to minimize the torque and speed ripples obtained from the conventional setting of proportional-integral controller. The performance analysis of the motor drive with optimized controller coefficients is carried out using Ansys co-simulation with Maxwell and Simplorer softwares. The simulation analysis of the motor with optimized constant torque angle strategy shows good motor performance and robustness which is inferred from results.
{"title":"Optimized Vector Control Strategy for Dual-Rotor Axial Flux Permanent Magnet Synchronous Motor for in-Wheel Electric Drive Applications","authors":"Robin Wilson, R. Gandhi, Amit Kumar, Rakesh Roy","doi":"10.1109/ComPE49325.2020.9200186","DOIUrl":"https://doi.org/10.1109/ComPE49325.2020.9200186","url":null,"abstract":"This paper analyzes the performance of dual-rotor axial flux permanent magnet synchronous motor for its application in electric motor drive. Dual-rotor single-stator topology is employed for analysis due to its superior features compared to other topologies of the motor for electric drive application. Constant torque angle control strategy with hysteresis current controller for inverter switching is implemented with the axial flux motor and is analyzed for validation. To enhance the robustness of the control strategy, the coefficients of proportional-integral controller are optimized with particle swarm optimization algorithm using Matlab/Simulink software to minimize the torque and speed ripples obtained from the conventional setting of proportional-integral controller. The performance analysis of the motor drive with optimized controller coefficients is carried out using Ansys co-simulation with Maxwell and Simplorer softwares. The simulation analysis of the motor with optimized constant torque angle strategy shows good motor performance and robustness which is inferred from results.","PeriodicalId":6804,"journal":{"name":"2020 International Conference on Computational Performance Evaluation (ComPE)","volume":"20 1","pages":"676-681"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75429555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：