Experimental Research on Decoupling Control of Multi-motor Variable Frequency System Based on Neural Network Generalized Inverse

摘要

Multi-motor variable frequency speed-regulating system is a MIMO, nonlinear, and high coupling control system. Being rightly designed, the generalized inverse can transform the MIMO nonlinear system into a number of SISO linear subsystems with open-loop stability, and then benefits the integration of this tension control system. The generalized reversibility of this multi-motor system working on vector control mode was testified. Consequently, a pseudo-linear system was completed by constructing a neural network generalized inverse system and combining it with two-motor system. Both the open-loop and the closed-loop characteristics of this pseudo-linear system were studied based on S7-300 PLC experiment platform. The experiment results demonstrate that decoupling control with open-loop stability can be reached by neural network generalized inverse (NNGI) control method.