Study Of PID Control Application On Electro-Hydraulic Servo Loading System

The electro-hydraulic servo system has many good characteristics such as: high precision, fast responsibility, the ratio of power and mass is big and it's easy to combine with electric control, so it is widely used in the industry. The electro-hydraulic load system is an important part of the electro-hydraulic servo system. The electro-hydraulic servo loading system studied in this thesis is significant equipment on structure testing for static performance, fatigue performance, detailed fatigue, and so on. This kind of testing provides theoretical basis for the design of structures and possesses advantages on reducing developing funds, shortening developing cycle, realizing diverse possible testing situations.PID control is widely used in industrial process because of simple structure and easy realization. But the PID controller must use the different PID parameters for different objects. Moreover, the PID control can't be adjusted conveniently, and it has poor anti-interference ability and big overshoot. Fuzzy control is a language control. It doesn't depend on mathematical model of controlled plant, and its algorithm can be easily realized. Because neural network is possessed of self-learning adaptive ability and mighty nonlinear match ability, it offers a effective solving method for nonlinear system modeling, but single neural network control has the defects such as : low rate of convergence and it is easy to trap in load minimum problem. Combining merits of fuzzy logic, BP neural network and PID control, taking full advantages of fuzzy logic nonfigurative ability, BP neural network self-study ability and the characteristic of simple PID control algorithm, the system can adjust parameters of PID controller through on-line by fuzzy BP neural network.In this paper, the mathematical model of electro-hydraulic servo loading system, which is based on the structure, working principle and technical requirements of the system, is set up by using the flow equation and force balance equation. And then, the fuzzy PID controller and fuzzy neural network PID controller are designed. Moreover, Using Simulink for system simulation, the parameters of fuzzy neural network PID controller, which can more effectively improve system performance such as overshoot, is obtained. The simulation results show that the fuzzy neural network PID control scheme is feasible.