PID control incorporating RBF-neural network for servo mechanical systems

This paper presents a combined control scheme, comprising of the well-known PID controller augmented with a Radial Basis Function Neural Network (RBFNN) for the control of servo mechanical systems. A second-order linear dominant model is considered with an unmodeled part of dynamics that is possibly nonlinear and time-varying. The PID part of the controller is designed to stabilize the dominant model. The RBFNN is used to compensate for the deviation of the system characteristics from the dominant linear model to achieve performance enhancement. The advantage of this combined control scheme is that it can cope with strong nonlinearities in the system while still using the PID control structure which is well-known to many control engineers.