开关磁阻电机神经网络自适应PWM转速控制.pdfVIP

26 卷 13 期 中 国 电 机 工 程 学 报 Vol.26 No.13 Jul. 2006 2006 年7 月 Proceedings of the CSEE 2006 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2006) 13-0141-05 中图分类号：TM352 文献标识码：A 学科分类号：47040 开关磁阻电机神经网络自适应PWM 转速控制 夏长亮，陈自然，李 斌 (天津大学电气与自动化工程学院，天津市 南开区 300072) Neural Network Based Adaptive PWM Speed Control in Switched Reluctance Motors XIA Chang-liang, CHEN Zi-ran, LI Bin (School of Electrical Engineering and Automation, Tianji n University, Nankai District, Tianji n 300072, China) ABSTRACT: The switched reluctance motor drive(SRD) has 适应性强等优点。 obtained great attention as an AC stepless speed control system 关键词：开关磁阻电机；径向基函数神经网络；电压脉宽调 due to its large scale regulating scope, low cost and ruggedness. 制；在线辨识；正交最小二乘 However, its strong nonlinearity and multivariable 0 引言 characteristic make it difficult to control. To solve this problem, this paper presents an approach of adaptive pulse width 开关磁阻电机调速系统(SRD) 因其调速范围 modulation(PWM) speed control for switched reluctance 广，调速性能优越而引起了国内外学者的普遍关 motors based on RBF neural network. This method builds up a 注。SRD 也成为了继交流变频调速系统、直流调速 speed controller based on RBF neural network which has 系统之后，极具潜力的新一代交流无级调速系统。 powerful approximating ability and fast convergence property. 然而，开关磁阻电机电磁关系的高度非线性决定了 After being trained off-line, the speed controller regulates SRD 是一个时变的、非线性系统，采用常规的线性 network’s parameters at running to adapt the environment