BP network modified by particle swarm optimization and its application to online-tuning PID parameters in idle-speed engine control system

PID control systems are widely used in many fields, and many methods to tune parameters of PID controller are known. When the characteristics of the object are changed, the traditional PID control should be adjusted by empirical knowledge. It may bring a worse performance to the system. In this paper, a new method to tune PID parameters called as the modified back propagate network by particle swarm optimization is proposed. This algorithm combines the conventional PID control with the back propagate neural network (BPNN) and the particle swarm optimization (PSO). This method is demonstrated in the engine idle-speed control problem, and the proposed method provides prominent performance benefits over the traditional controller in this simulation.