Neural networks predictive control using AEPSO

In order to improve the global convergence of the basic particle swarm optimization, an adaptive expanded particle swarm optimization method was provided in this paper firstly, where particle is refreshed by multi-particle strategy; at the same time, the parameter c₀ is self-adaptively adjusted. Then improved PSO was used as the optimizer of the neural network predictive control and optimized the control serial in the finite time field. The stability of predictive control of neural network using improved PSO as optimizer is proofed. Simulation results show that the method has better track performance.