Temperature Prediction of Continuous Casting Slab Based on Improved Extreme Learning Machine

A fusion ELM model based on ensemble learning was proposed to predict slab temperatureTemperature. Combined with the actual production data of a steelSteel mill, the integrated ELM, ELM, ANN, BP networks are designed and the comparison test proves that the integrated ELM model has more advantages in the aspects of running time and prediction accuracy. The number of base models for integrating ELM model is determined to be 3, the number of hidden layer nodes is 20, and the neuron activation function Hardlim is the most suitable for steelSteel mill data set. The results show that the average hit rate of the predicted temperatureTemperature is 88.89% within ±5 ℃, and the MAE and RMSE of the predicted results are 2.46 and 2.85 ℃, respectively, indicating that the model has high accuracy and stability, and can be used to predict the casting slab temperatureTemperature.