Prediction model of hot strip crown based on industrial data and hybrid PCA-SDWPSO-ELM approach

Abstract The accurate prediction of strip crown is the precondition of the shape pre-set model in hot strip rolling. In this study, a new data-driven model of strip crown based on extreme learning machine (ELM) optimized by S-curve decreasing inertia weight PSO (SDWPSO) algorithm and industrial data is proposed. In order to simplify the model structure and save modeling time, principal component analysis (PCA) is used to reduce the dimension of the input data for modeling samples. The comprehensive performance of the proposed hybrid PCA-SDWPSO-ELM prediction model is evaluated by several error indexes. The superiority of the proposed model is also proved by comparing the prediction results with other three comparison models. The research shows that the hybrid PCA-SDWPSO-ELM method can solve the problem of nonlinear and strong coupling in the traditional engineering. It is suitable for the parameters prediction and optimization of the iron and steel manufacturing industry, especially in the process of shape control in hot strip rolling.