Predicting strip thickness of hot rolled sheet based on the combination of correlation analysis and Extreme Learning Machine

Based on Extreme Learning Machine (ELM) an new hot-rolled strip thickness model prediction method is proposed. Firstly, the input variables is determined through the correlation analysis to ensure the effectiveness of the model; then use ELM network forecasting model. The network uses live production data for training and testing, and compared with the BP network prediction model. Simulation results show that the model can predict the thickness more quickly and accurately, and is able to meet the needs of actual rolling production.