Mohammad Ali Labbaf Khaniki, Mohammad Behzad Hadi, M. Manthouri
{"title":"基于RMSprop和Salp群算法的自动调压系统反馈误差学习控制器","authors":"Mohammad Ali Labbaf Khaniki, Mohammad Behzad Hadi, M. Manthouri","doi":"10.1109/ICCKE50421.2020.9303718","DOIUrl":null,"url":null,"abstract":"The primary goal of the Automatic Voltage Regulator (AVR) is to control the terminal voltage at the desired level. The controller used in AVR must be capable of maintaining generator terminal voltage in various operating conditions and also withstand uncertainty. In this paper, Feedback Error Learning (FEL) controller has been proposed to control the AVR system. FEL structure consists of the classical controller (PD controller) and the intelligent controller (MLP neural network controller). This control strategy has been employed to control unknown and uncertain plant model. Salp Swarm Algorithm (SSA) has been used to obtain the initial weights, biases and the number of neurons of the MLP neural network. The training methods used in this research are Stochastic Gradient Descend (SGD) and Root Mean Square propagation (RMSprop) that in particular; these methods are used in deep learning. The robustness and effectiveness of the proposed method has been studied in different operating conditions. The results demonstrate that the proposed strategy outperforms other methods.","PeriodicalId":402043,"journal":{"name":"2020 10th International Conference on Computer and Knowledge Engineering (ICCKE)","volume":"31 3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Feedback Error Learning Controller based on RMSprop and Salp Swarm Algorithm for Automatic Voltage Regulator System\",\"authors\":\"Mohammad Ali Labbaf Khaniki, Mohammad Behzad Hadi, M. Manthouri\",\"doi\":\"10.1109/ICCKE50421.2020.9303718\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The primary goal of the Automatic Voltage Regulator (AVR) is to control the terminal voltage at the desired level. The controller used in AVR must be capable of maintaining generator terminal voltage in various operating conditions and also withstand uncertainty. In this paper, Feedback Error Learning (FEL) controller has been proposed to control the AVR system. FEL structure consists of the classical controller (PD controller) and the intelligent controller (MLP neural network controller). This control strategy has been employed to control unknown and uncertain plant model. Salp Swarm Algorithm (SSA) has been used to obtain the initial weights, biases and the number of neurons of the MLP neural network. The training methods used in this research are Stochastic Gradient Descend (SGD) and Root Mean Square propagation (RMSprop) that in particular; these methods are used in deep learning. The robustness and effectiveness of the proposed method has been studied in different operating conditions. The results demonstrate that the proposed strategy outperforms other methods.\",\"PeriodicalId\":402043,\"journal\":{\"name\":\"2020 10th International Conference on Computer and Knowledge Engineering (ICCKE)\",\"volume\":\"31 3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-10-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 10th International Conference on Computer and Knowledge Engineering (ICCKE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCKE50421.2020.9303718\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 10th International Conference on Computer and Knowledge Engineering (ICCKE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCKE50421.2020.9303718","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Feedback Error Learning Controller based on RMSprop and Salp Swarm Algorithm for Automatic Voltage Regulator System
The primary goal of the Automatic Voltage Regulator (AVR) is to control the terminal voltage at the desired level. The controller used in AVR must be capable of maintaining generator terminal voltage in various operating conditions and also withstand uncertainty. In this paper, Feedback Error Learning (FEL) controller has been proposed to control the AVR system. FEL structure consists of the classical controller (PD controller) and the intelligent controller (MLP neural network controller). This control strategy has been employed to control unknown and uncertain plant model. Salp Swarm Algorithm (SSA) has been used to obtain the initial weights, biases and the number of neurons of the MLP neural network. The training methods used in this research are Stochastic Gradient Descend (SGD) and Root Mean Square propagation (RMSprop) that in particular; these methods are used in deep learning. The robustness and effectiveness of the proposed method has been studied in different operating conditions. The results demonstrate that the proposed strategy outperforms other methods.