{"title":"递归四元数神经网络在伺服控制系统中的应用","authors":"Kazuhiko Takahashi","doi":"10.1109/ANZCC.2018.8606573","DOIUrl":null,"url":null,"abstract":"This paper investigates the control system application of a fully connected recurrent neural network in which all network parameters and signals are expressed in quaternion numbers, and the training of the network is conducted using a real–time recurrent learning algorithm. The recurrent quaternion neural network (RQNN), which synthesises the control input to track the outputs of the non–linear system to the desired outputs, assumes the role of an adaptive–type servo controller in the control system. A feedback error learning method is used to train the RQNN using an online method in the control system. Numerical simulations for controlling discrete–time non–linear plants are performed to evaluate the characteristics of the RQNN–based adaptive–type controller. The simulation results demonstrate the feasibility and effectiveness of the proposed controller.","PeriodicalId":358801,"journal":{"name":"2018 Australian & New Zealand Control Conference (ANZCC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Remarks on a Recurrent Quaternion Neural Network with Application to Servo Control Systems\",\"authors\":\"Kazuhiko Takahashi\",\"doi\":\"10.1109/ANZCC.2018.8606573\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper investigates the control system application of a fully connected recurrent neural network in which all network parameters and signals are expressed in quaternion numbers, and the training of the network is conducted using a real–time recurrent learning algorithm. The recurrent quaternion neural network (RQNN), which synthesises the control input to track the outputs of the non–linear system to the desired outputs, assumes the role of an adaptive–type servo controller in the control system. A feedback error learning method is used to train the RQNN using an online method in the control system. Numerical simulations for controlling discrete–time non–linear plants are performed to evaluate the characteristics of the RQNN–based adaptive–type controller. The simulation results demonstrate the feasibility and effectiveness of the proposed controller.\",\"PeriodicalId\":358801,\"journal\":{\"name\":\"2018 Australian & New Zealand Control Conference (ANZCC)\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 Australian & New Zealand Control Conference (ANZCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ANZCC.2018.8606573\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 Australian & New Zealand Control Conference (ANZCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ANZCC.2018.8606573","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Remarks on a Recurrent Quaternion Neural Network with Application to Servo Control Systems
This paper investigates the control system application of a fully connected recurrent neural network in which all network parameters and signals are expressed in quaternion numbers, and the training of the network is conducted using a real–time recurrent learning algorithm. The recurrent quaternion neural network (RQNN), which synthesises the control input to track the outputs of the non–linear system to the desired outputs, assumes the role of an adaptive–type servo controller in the control system. A feedback error learning method is used to train the RQNN using an online method in the control system. Numerical simulations for controlling discrete–time non–linear plants are performed to evaluate the characteristics of the RQNN–based adaptive–type controller. The simulation results demonstrate the feasibility and effectiveness of the proposed controller.