RBF Neural Networks Control for Motor-driven Load Simulator

摘要

The motor-driven load system is highly nonlinear and includes delays in the control loop and extraneous force disturbance from load. These factors have many bad effects on the tracing accuracy and dynamic performance of the simulator. A motor-driven load simulator controller based on Radial Basis Function (RBF) networks is proposed in this paper. This controller is robust, efficient and simple. In this paper, the key problem discussed is to use the RBF neural networks as the feedforward compensator to eliminate the extraneous force, which can be adjusted adaptively. The input of the feedforward compensator is the output of the controller and the extraneous force. The simulation studies shows that the designed controller provides good control performance and adaptive feedforward compensation of the extraneous force.