两电机调速系统的神经网络逆在线调整控制  

On-line Adjustment Control of Two Motor Variable Speed-regulating System based on Neural Network Inverse

作　　者：薛剑锋[1] 刘国海[1] 赵筱赫[1] 

机构地区：[1]江苏大学,江苏镇江212013

出　　处：《电力电子技术》2009年第5期42-44,共3页Power Electronics

基　　金：国家自然科学基金资助项目(60874014);江苏省自然科学基金资助项目(BK2007094)~~

摘　　要：针对MIMO非线性强耦合的两电机变频调速系统,在基于神经网络逆系统离线训练的基础上提出了在线调整的策略,通过静态神经网络加积分器来构造两电机变频调速系统的逆模型,在实际运行中不断地修正神经网络权值,更精确地逼近其逆系统,实现MIMO系统的线性化与解耦。仿真和实验结果表明,系统具有优良的动静态解耦性能和较强的抗负载扰动的能力。Two motor variable frequency speed-regulating system is a MIMO, nonlinear and high coupling control system.A strategy of controling on-line based on artificial neural network （ANN）inverse system is proposed,by which the MIMO nonlinear system can be transformed into a number of SISO linear subsystems.A static ANN and a integrator are used to construct the ANN inverse of the two motor variable frequency speed-regulating system,in which the connection value can be amended on-line in order to approach the inverse system exactly.The Simulation and experimental results show that the system has good static and dynamic decoupling performances and high-disturbance of load.

关 键 词：变频调速 交流电机/神经网络 解耦 

分 类 号：TM301.2[电气工程—电机]