Grinding Particle Size Soft Mearsurement And Loop Optimization Control

In the grinding process,production equipment investment and consumption of steel energy are huge.It is of great significance to study how to improve the utilization rate of mineral resources,the production efficiency of grinding process,the economic and technical indexes of concentrator.Establishing the soft measurement model of grinding particle size and controlling the key variables in grinding process ensures the grinding particle size to be stable within the range of process requirements.And it makes the production equipment such as ball mill and classifier operate in the optimum working state to improve the grinding production efficiency.The main research contents of this paper are as follows:Firstly,in order to solve the problem of grinding particle size on-line detection,a soft measurement model of grinding particle size based on least squares support vector machine is established.The penalty coefficient and kernel function parameters of least squares support vector machine are iteratively optimized by using grey wolf optimization algorithm.Aiming at the shortcomings of the traditional grey wolf optimization algorithm,such as low precision,slow convergence rate and weak local search ability.An improved grey wolf optimization algorithm based on opposite learning strategy initializes population,nonlinear convergence factor,adaptive position updating and gaussian mutation is proposed.The simulation results show that the soft measurement model can achieve better on-line detection of grinding particle size for real-time control in the later stage.Secondly,according to the characteristics of the basic circuit in grinding process,the model free adaptive control strategy is adopted to optimize the loop control.Based on the basic universal model,the lag time is introduced and the output of the past time is increased,and the lead link is added to the feedback loop to improve the model free adaptive control.The improved grey wolf optimization algorithm is used to optimize the controller parameters.The simulation results show that the improved model free adaptive control strategy is adopted to control the grinding basic process loop,the control variables can track the set value quickly,and the control system has good anti-interference ability.Finally,in order to verify the feasibility and effectiveness of this research strategy,the simulation experiment is carried out on the grinding process semi-physical simulationplatform.The grinding particle size soft measurement model and the basic loop optimization control strategy are applied to the semi-physical simulation platform.The simulation results show that the proposed research strategy can control the grinding particle size within the technological requirements and has certain engineering application value.