Kai Sato;Koutaro Hachiya;Toshiki Kanamoto;Atsushi Kurokawa
{"title":"利用人工神经网络对无线电力传输系统进行补偿电容调整","authors":"Kai Sato;Koutaro Hachiya;Toshiki Kanamoto;Atsushi Kurokawa","doi":"10.23919/comex.2023XBL0165","DOIUrl":null,"url":null,"abstract":"This letter proposes a new method for tuning compensation capacitances of wireless power transfer (WPT) systems using an artificial neural network (ANN). A field solver is used to analyze the compensation capacitances that maximize the output power at a set resonant frequency in a WPT system with ferrite shields. The compensation capacitances can be tuned using the ANN learned from the results acquired by the field solver. The electrical parameters for tuning the compensation capacitances acquired by the proposed method have maximum errors within 3.40% and mean absolute errors within 1.38%.","PeriodicalId":54101,"journal":{"name":"IEICE Communications Express","volume":"13 3","pages":"88-92"},"PeriodicalIF":0.3000,"publicationDate":"2024-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10400566","citationCount":"0","resultStr":"{\"title\":\"Compensation capacitance tunings of wireless power transfer systems using artificial neural network\",\"authors\":\"Kai Sato;Koutaro Hachiya;Toshiki Kanamoto;Atsushi Kurokawa\",\"doi\":\"10.23919/comex.2023XBL0165\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This letter proposes a new method for tuning compensation capacitances of wireless power transfer (WPT) systems using an artificial neural network (ANN). A field solver is used to analyze the compensation capacitances that maximize the output power at a set resonant frequency in a WPT system with ferrite shields. The compensation capacitances can be tuned using the ANN learned from the results acquired by the field solver. The electrical parameters for tuning the compensation capacitances acquired by the proposed method have maximum errors within 3.40% and mean absolute errors within 1.38%.\",\"PeriodicalId\":54101,\"journal\":{\"name\":\"IEICE Communications Express\",\"volume\":\"13 3\",\"pages\":\"88-92\"},\"PeriodicalIF\":0.3000,\"publicationDate\":\"2024-01-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10400566\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEICE Communications Express\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10400566/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEICE Communications Express","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10400566/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
摘要
本文提出了一种利用人工神经网络(ANN)调整无线功率传输(WPT)系统补偿电容的新方法。在带铁氧体屏蔽的 WPT 系统中,使用场求解器分析在设定谐振频率下能使输出功率最大化的补偿电容。补偿电容可利用从场求解器获得的结果中学习到的 ANN 进行调整。通过拟议方法获得的用于调整补偿电容的电气参数的最大误差在 3.40% 以内,平均绝对误差在 1.38% 以内。
Compensation capacitance tunings of wireless power transfer systems using artificial neural network
This letter proposes a new method for tuning compensation capacitances of wireless power transfer (WPT) systems using an artificial neural network (ANN). A field solver is used to analyze the compensation capacitances that maximize the output power at a set resonant frequency in a WPT system with ferrite shields. The compensation capacitances can be tuned using the ANN learned from the results acquired by the field solver. The electrical parameters for tuning the compensation capacitances acquired by the proposed method have maximum errors within 3.40% and mean absolute errors within 1.38%.