Networked Control System Based on PSO-RBF Neural Network Time-Delay Prediction Model

To satisfy the requirement of real-time and accurate control system, a time-delay prediction system based on PSO-RBF neural network model is established to solve effect time delay system’s performance. Firstly, with predict output uncertainty delay. Secondly, an improved offline RBF networks proposed problem low accuracy in networks. that PSO algorithm prone fall into local optimality, nonlinear adjustment formula for parameters number iterations proposed, TS used make optimal global solution. Finally, order compensate delay, online controller designed, are adjusted by gradient descent method, target function differential component evaluate optimization rolling stage. The results from true-time simulation platform show this paper improves IAE 59.9% 31.7%, respectively, compared traditional PID fuzzy under influence disturbances. Therefore, has good capability compensation output.