The Study Of Modeling And Optimal Control For Products Quality In Rolled Steel Production Process

Complex industrial process of steel rolling is complicated large-scale system composed of multi-subsystem,which has the characteristic of severe non-linearity, uncertainty,time-varying,large-delay,strong coupling and multiple-parameter.It is necessary to establish the quality model and optimize and control of the steel rollling process,however,quality modeling and optimal control of steel rolling process may have much difficulty because of its complexity with many influnce factors and the pollution of industrial noise.In recent years,many domestic and foreign scholars have carried out the quality modeling using various neural network and their work has got certain effect.But it still has certain distance in the aspect of using the estiblished model to guide the production practice and implement optimal control.In this paper,the research on the.quality-modeling and optimal control of steel rolling process is studied and has got some practical significance result. The main work and Contents are as follows:(1) Based on the analysis of steel rolling production process,the product quality indicators and its infulunce factors is studied and analyzed,Then the main infulunce factors is determined. Finally,the quality modeling and quality optimal control problem of steel rolling process is analyzed and discussed which established the foundation of quality modeling and implement the quality optimal control of steel rolling process.(2) Firstly,the sample data of steel rolling production process is selected and pretreated. Secondly based on the analysis of the Hierarchical Fuzzy Neural Network and its modeling,the modeling approach of steel rolling process using Hierarchical Fuzzy Neural Network is given,then the simulation and analysis are carried out.The simulation results show the validity and reliability of this modeling approach.(3) Firstly,Based on the built quality model,the product quality optimal control is analyzed and discussed deeply,the product quality optimal control approach of steel rolling process is given.Secondly,the quality optimization model of steel rolling process is built,then this optimization model is optimized by penalty function and particle swarm algorithm.The simulation results show the validity and reliability of the given method.