Magnetic Levitation Neural Network PID Control Algorithm Research

As a perfect vehicle on land, maglev train is characterized by high velocity, small energy consuming, low noise, safety and comfort, and it has been successfully put into practice. Due to the inherent nonlinearities and instability of the electromagnetic suspension system, suspension control is key point. So it is needed active control in order to keep steady suspension.First, this paper describes the composition of magnetic suspension system and working principle and establishes the model of magnetic suspension system in a single magnetic suspension system as the research object.Second, for the way of electromagnetic suspension train, because the electromagnetic suction and nonlinear inverse relationship between the suspended clearance, Making the electromagnetic suspension system itself inherent instability. And in order to achieve the stability of the suspension, the control device must be used. This paper will use the current common PID control algorithm applied to industrial areas, and make the object of study has simple structure, easy to understand and implement, the advantages of good control effect and robustness is strong.At last, using self-learning, adaptive features of RBF neural networks, a adaptive PID controller is designed based on the traditional PID controller.The results showed that the improved adaptive PID controller based on RBF on-line identification has better dynamic and static performance requirements compared with conventional PID controller and possesses the advantages of high precision, quick response speed and is of great adaptability and robustness.