The Multi Inductive Motor Decoupling Control Based Artificial Neural Networks α-th Order Inverse System Method

With the financial aid of Natural Science Fund of Jiangsu Education Department, the paper focuses on the multi-variable decoupling control of synchronization system of the AC induction motors-decoupling the synchronically modulating velocity system composed of two AC induction motors and transducers into velocity and tension subsystems by the application ofα- th ANN inverse system method.On the basis of theoretic invertibility analysis of that system, the methods,the steps,the design principles and the cautions are proposed to fabricate theα-th ANN inverse system of original system. Through training the network with the advanced BP arithmetic and make it convergent, theα-th ANN inverse system composed of two AC induction motors and the transducers is constructed. The digital control arithmetic programmed according to the ANN and the synthesis controller of pseudolinear integrated system, which is designed on the basis of the ANN inverse system, works well in the controlling experiment on the platform of multi-motor synchronization system.The online execution of ANN controller after its training convergence is subject to not reference model of controlled object (the platform of the multi-motor synchronization system) or inverse dynamic model but the direct control of the object. Lots of experiments results manifest that the method designed successfully decouples the system into the velocity and the tension subsystem completely, and the system has good robustance against the disturbance of the load, and the dynamic and static attributions improve obviously, and the system can trace any defined route and almost has the same effect even if under the condition of alteration of the working methods of system transducer (constant ratio of voltage to frequency or the method of vector control) without alteration of other parameters (for example, the structure of controller and control parameters). The control method proposed in the paper is promising and can be applied in many industrial control environments.