无刷直流电机调速系统神经网络逆控制  

Neural Network Inverse Control of Speed Variable System for BLDCM

作　　者：刘国海[1] 金鹏[1] 魏海峰[2] 

机构地区：[1]江苏大学电气信息工程学院,镇江212013 [2]江苏大学现代农业装备与技术省部共建教育部重点实验室,镇江212013

出　　处：《电工技术学报》2010年第8期24-30,共7页Transactions of China Electrotechnical Society

基　　金：国家自然科学基金(60874014);教育部博士点基金(20050299009);江苏省自然科学基金(BK2007094)资助项目

摘　　要：无刷直流电机运行中参数摄动和换相过程的非线性,在一定程度上限制了其调速性能。针对这些特点,在分析无刷直流电机换相区和传导区数学模型的基础上,提出了一种基于神经网络逆的控制策略,采用静态神经网络加积分器来构造电机的逆系统,并将该逆系统与原电机系统串联复合构成伪线性系统,实现整体的近似线性化,从而简化了外环控制器的设计难度。仿真与实验结果均表明神经网络逆控制方法对负载扰动与电机参数摄动有较强的鲁棒性,且能在减小转速超调的同时保证了响应速度及跟踪精度,使整个系统具有优良的动静态性能。Variation of parameters and nonlinear commutation process limit the speed control performance of brushless DC motor（BLDCM）. A control approach based on neural network inverse system was developed for the brushless DC motor by analyzing the mathematical model in conduction region and commutation region. The inverse system of BLDCM consists of a static artificial neural network （ANN） and two integrators. By cascading the inverse system with BLDCM,the nonlinear system was transformed into pseudo-linear system and the whole system performance is improved. Simulation and experimental results show that the proposed scheme reduces overshoot,preserves fast speed response merit,and shows robust to load disturbance and motor parameters uncertainty. It effectively improves dynamic and static operation performance,and is a novel control method for BLDCM.

关 键 词：无刷直流电机 人工神经网络 逆系统 线性化 

分 类 号：TM383[电气工程—电机]