基于支持向量机α阶逆系统方法的无刷直流电机调速系统控制  

Control of speed-regulating system for BLDCM based on support vector machines α-th order inverse systems method

作　　者：金鹏[1] 刘国海[1] 董蓓蓓[1] 周大为[1] 

机构地区：[1]江苏大学电气信息工程学院,镇江212013

出　　处：《东南大学学报（自然科学版）》2009年第S1期82-86,共5页Journal of Southeast University：Natural Science Edition

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

摘　　要：针对无刷直流电机参数摄动与换相过程的非线性特点,在分析无刷直流电机换相区和传导区数学模型的基础上,提出了一种基于支持向量机α阶逆系统的控制策略.将通过支持向量机回归方法辨识出的逆系统串接在原系统之前构成伪线性复合系统,实现整体系统的近似线性化,简化了外环控制器的设计难度.支持向量机方法在小样本集上逼近效果好,同时能够避免训练中的过学习,因此该方法拓宽了逆系统理论在实际中的应用.仿真与实验表明,该方法不依赖于系统模型,在减小转速超调的同时保证了响应速度,弱化了电机参数摄动与换相扰动对系统造成的影响,使整个系统具有较强的鲁棒性.To deal with the problems of variation of parameters and nonlinear commutation process,a control approach based on the support vector machine(SVM) α-th order inverse system method is proposed by analyzing the mathematical model in the conduction region and the commutation region of brushless direct current motor(BLDCM).The inverse system of the BLDCM is identified by the support vector machine regression method.By cascading the inverse system with BLDCM,the nonlinear system is transformed into the pseudo-linear system,so it is easy to design the closed-loop linear regulator.Support vector machine which has a good approximation in fitting result on small sample set and avoids over learning widens the application scope of inverse system theory.Simulation and experimental results show that the controller has quick velocity response and strong robustness to both variations of parameters and nonlinear commutations.

关 键 词：无刷直流电机 支持向量机 Α阶逆系统 线性化 

分 类 号：TM33[电气工程—电机]