基于FNN的SRM调节器参数自整定的研究  

Research on Parameter Self-tuning of SRM Speed Regulator Based on FNN

作　　者：邹洪建 栾茹[1,2] ZOU Hongjian;LUAN Ru(School of Electrical and Information Engineering,Beijing University of Civil Engineering and Architecture,Beijing 100044,China;Beijing Key Laboratory of Intelligent Processing for Building Big Data,Beijing 100044,China)

机构地区：[1]北京建筑大学电气与信息工学院,北京100044 [2]建筑大数据智能处理方法研究北京市重点实验室,北京100044

出　　处：《微电机》2022年第11期75-81,共7页Micromotors

摘　　要：开关磁阻电机因独特的双凸极结构和运行原理而具有较强的非线性,难以在整个调速区间内获得最优的控制器参数组合。神经网络控制算法和传统控制器的结合实现了控制参数的自适应调节,提高了开关磁阻电机的调速性能,抑制了转矩脉动。但是传统BP神经网络的激活函数常采用单参数的Sigmoid函数,容易陷入局部最优,影响到了控制器参数自整定的准确性。本文构建柔性神经网络以提高控制器参数自整定能力,同时结合转矩分配函数控制,提高开关磁阻电机的调速性能,抑制转矩脉动。通过和带有转矩分配函数控制的,PI控制、模糊PID控制、普通BP神经网路PID控制进行仿真对比,结果表明柔性神经网络控制方式下,开关磁阻电机具有更好的调速性能、更快的恢复速度以及更低的转矩脉动。Switched reluctance motor has strong nonlinearity due to its unique double salient pole structure and operation principle, so it is difficult to obtain the optimal controller parameter combination in the whole speed range.The combination of neural network control algorithm and traditional controller realizes the adaptive adjustment of control parameters, improves the speed regulation performance of switched reluctance motor and restages the torque ripple.However, the activation function of traditional BP neural network usually adopts Sigmoid function with single parameter, which is easy to fall into local optimum and affects the accuracy of controller parameter self-tuning.In this paper, a flexible neural network was constructed to improve the parameter self-tuning ability of the controller, and the torque distribution function control was combined to improve the speed regulation performance of the Switched reluctance motor and suppress the torque ripple.Compared with PI control, fuzzy PID control and general BP neural network PID control with torque distribution function control, the simulation results show that under the flexible neural network control mode, switched reluctance motor has better speed regulation performance, faster recovery speed and lower torque ripple.

关 键 词：开关磁阻电机 转速控制 参数自整定 柔性神经网络 

分 类 号：TM352[电气工程—电机] TP273[自动化与计算机技术—检测技术与自动化装置] TH39[自动化与计算机技术—控制科学与工程]