PID-ANN decoupling controller of ball mill pulverizing system based on particle swarm optimization method

Ball mill coal pulverizing system of pelletizing plant is a complex nonlinear multivariable process with strongly coupling and time-delay, whose operations often varies violently. The automatic control of such systems is a research focus in the process control area. Decoupling control technology based on the PID-ANN (artificial neural network) was used to eliminate the coupling between the two loops. Particle swarm optimization algorithm is also adopted to optimize weights of neural networks. Simulation results show the validity of the model obtained and the control method proposed in this paper, the new method can overcome nonlinear and strong coupling features of the system in a wide range, and it has strong robustness and adaptability.