摘要：Strip thickness prediction has importantcontribution to solve the problems of accurate strip thicknesscontrol and saving raw materials. Support vector regression(SVR) is presented to apply for strip thickness prediction, andthe key problem to be solved is determining parameters of SVR.A strip thickness prediction method is proposed based on SVRoptimized by improved differential gray wolf algorithm(denoted as HGWO-SVR). Firstly, the feature of the strip datais extracted by mutual information calculation method. Next,the differential evolution algorithm is introduced to enrich thediversity of the gray wolf population in gray wolf optimizer(GWO) and avoid falling into the local optimum, andcoefficient vector improved gray wolf optimizer (HGWO) isused to balance the ability of global search and local search.Then, HGWO is used to select optimal kernel coefficient σ andpenalty factor C in SVR model. Finally, establish HGWO-SVRmodel and input the characteristics of strip data into the modelto predict the strip thickness. The results state clearly thatHGWO-SVR has better predictive performance thanGWO-SVR and SVR.
