Study On The Parameters Self-Adjustment PID Control Algorithm Based On Neural Network

The PID control is a general control technology which is applied in many fields now. However there are a lot of complex, nonlinear control systems and many objects that can not be established with accurate mathematics model on industry, if these systems are controlled with the traditional PID controller, it is impossible to get ideal control effect. In recent years, the artificial neural network (ANN) control method which combined with the genetic algorithm (GA) is gradually attended. ANN can describe arbitrary nonlinear function and has some virtues of self-learning adaptability, parallel processing and so on, while GA has the global random searching ability, therefore a kind of NNPID control method is proposed in which genetic algorithm and neural networks are mixed. The weighs of neural networks are trained and optimized by GA, then a group of optimal BP neural networks initial weights is obtained, based on which the object's sensitive information is acquired through RBF identifiable network, and BP neural networks' weights is modified by BP algorithm to achieve PID parameters' self-adjustment on line. The method remains the global random searching ability of genetic algorithm and the robustness and self-learning ability of neural networks. The simulation results indicate the GA's capability in fast learning of neural networks and guarantee a rapid global convergence. Moreover, the learning efficiency and the convergent precision for the weights of the multi-layer forward neural networks are improved greatly. The motivation of this approach is to overcome the shortcomings of traditional error back propagation algorithm for updating the weights of the multi-layer forward neural networks, such as the low precision of the solutions, the slow search speed and easy convergence to the local minimum points. These results show the proposed method in this paper is feasible and effective.