Adaptive PID Control for Cement Particle Size System Based on Data-driven Technology

In order to solve the problem that the controlled system depends on the mathematical model in the cement particle size control, and further to improve the robustness and stability of the controled system, a data-driven online adaptive PID control method is proposed. Firstly, the cement mill process is briefly introduced, and a relevance is reached that the speed of the posterior separator is the key factor to influence the cement particle size. Secondly, the nonlinear cement mill system is linearized by using compact form dynamic linearization (CFDL) method. Then, the pseudo-partial derivative (PPD) of CFDL is estimated only by using the I/O data of the controlled system. Thirdly, the parameters of PID controller are dynamically updated according to PPD. Finally, the simulation results show the effectiveness of the proposed method.