Zhang Jiansheng

Research on PID controller based on RBF neural network

RBF neural network is a kind of feedforward neural network with good performance, which is proposed based on the brains neurons to external reaction and it has the capability of strong nonlinear mapping, it can with arbitrary precision approaches a nonlinear function global, it has the advantage of simple structure, fast learning etc. Neural network with arbitrary nonlinear expression ability can realize the best PID control by system performance study, by RBF network, the self-learning PID controller can been built with parameters Kp, Ki, Kd, the simulation results show that the system has good dynamic and static performance.

Application of intelligent control method in magnetic bearing

Active magnetic bearing (AMB) is a new kind of base mechanical component that can supply contactless support. Its working principle involves contactless support of the axle by the bearings through electrical magnetic force. So, AMB has some good features, such as no touch friction and wear, small motion resistance, lower power supply and long utility time. Overseas, AMB technology has reached mature level and increasingly products, which set up with AMB, can be found. The ways of design and process AMB rotor system are described. Here a number of design methods of AMB are dealt with, mainly includes the features in the systematic design, methods of design for the system controller, rigid shaft system and flexible shaft system. Some numeric results are presented also.