Grinding Control System Design And Particle Size Prediction Study

With the rapid development of modern science and technology and the new chemical material industry,the demand for ultra-fine materials in traditional industries and high-tech industries has gradually increased.Therefore,the ultrafine powder grinding technology has gradually attracted widespread attention in recent years.The design of grinding control systems and the predictive analysis of particle size are two important topics in powder grinding.This paper takes the Jiangsu Disirui Company powder grinding project as the background,studies on the design of grinding control systems and its particle size prediction.In this paper,combined with the requirements of the powder grinding control system,the system design scheme is determined.With Siemens S7-1200 as the core controller,the control of inverters,sand mills,sensors and other equipment is realized.Based on the TIA Portal V16 platform,PLC program development.The control program includes the control of the rough grinding and fine grinding process.The software part adopts the Force Contral configuration software,and designs the host computer monitoring program to monitor the operation status of the equipment.Finally,the grinding control system is used for alumina powder grinding.Test to verify the effectiveness of the system.In view of the complex influencing factors of powder grinding,it is difficult to accurately predict the output particle size.This paper introduces the sparrow search algorithm(SSA)and proposes improved strategy for the sparrow search algorithm.For the shortcomings of the original sparrow search algorithm’s lack of global search ability and easy to fall into local optimum,the Tent chaotic map is introduced to initialize the population and enhance the global search ability.The nonlinear weight factor and the Cauchy variation factor disturbance the update sparrow position,improving the algorithm is easy to fall into the local optimization problem,and improve the algorithm’s search ability.The new algorithm is combined with the BP neural network to form a prediction model to predict output particle size of the material grinding.Simulation results show that,the proposed improved sparrow search algorithm optimizes the weights and biases of the BP neural network,which effectively improves the training accuracy of the BP neural network.Experimental results show that the proposed New-SSA-BP neural network model has obvious effect on the regression prediction of material grinding output particle size.