The Forward NN-PID Controllers Based on Chaos PSO-BP Hybrid Optimization Algorithms for Decoupling Control System of Ball Mill

As to the multi-variable, close coupling, nonlinear and time-varying characteristics of the ball mill pulverizing system, the forward NN-PID controller based on chaos PSO-BP hybrid optimization algorithms for decoupling control system of ball mill was proposed. In this controller, the control parameters of PID controller are adaptively adjusted by forward NN, the weights of NN are optimized by the mixed learning methods integrating the offline PSO algorithm combined with chaos strategies of global searching ability, with the online BP algorithm of local searching ability. The results of simulation of Matlab/Simulink show that the hybrid optimization algorithms could solve some problems effectively, such as BP algorithm or PSO algorithm with slow convergence rate and falling to partial minimum easily, and the new control method has better quality than the traditional PID decoupling control method, it has fast tracking ability, strong robustness, good decoupling ability, and it can solve the time-varying problem and the coupling problem of ball mill effectively.