Neuron Decoupling and Adaptive PID Control of Three-motor Variable Frequency Speed-regulation System
Three-motor variable frequency speed-regulation system is a multi-input multi-output (MIMO), nonlinear, and high coupling complex control system. Focusing on the system of induction motors powered by current-tract SPWM transducers, the mathematic model of the system of three motors is established. Three adaptive PID controllers based on RBF neural network are adopted to be used in the velocity loop and two tension loop respectively, which makes the system possess stronger adaptive capability and perform better. In order to minimize the coupling effect, combining decoupling technology of adaptive neuron decoupling compensation, a neuron decoupling compensator is designed. It integrates the coupling effects of the three loops and realizes the decoupling control between velocity and tension by training the weights of networks to compensate the coupling effects, realizing the decoupling between speed and tension of the system. The experiment results show that the three-motor system is decoupled based on neural network control, and it can be extended to the usual multi-motor (n>3) system.
Three-motor neural networks RBF networks decoupling control tension control
Shen Cuifeng
Yancheng Institute of Technology,Yancheng 224002 China
国际会议
厦门
英文
47-52
2010-05-22（万方平台首次上网日期，不代表论文的发表时间）