Particle Swarm Optimization PID Neural Network Control Method in the Main Steam Temperature Control System

摘要

BP algorithm based on the gradient descent depends on initial weight selection with slow convergence rate and easily falling into local optimum. This paper presents the PSO algorithm and BP algorithm respectively in the global and local search advantage for the neural network weights optimization, The algorithm was used for the main steam temperature control system. The control strategy improved the control performance, and had a good anti-jamming performance and strong robustness, it achieved good control effect for large delay and variable object.