Prediction and Online Optimization of Strip Shape in Hot Strip Rolling Process Using Sparrow Search Algorithm‐Online Sequential‐Deep Multilayer Extreme Learning Machine Algorithm

Abstract

In the hot strip process, the prediction of strip shape is a key factor to improve the quality of products. However, strip‐shape prediction models based on traditional machine learning algorithms with relatively simple network structures often rely on data preprocessing and feature selection. Herein, five strip‐shape prediction models are proposed by combining sparrow search algorithm (SSA), particle swarm optimization algorithm (PSO), extreme learning machine (ELM), and deep multilayer extreme learning machine (DELM). The prediction experiments show that the SSA‐DELM model has highest accuracy, and the determination coefficient (R2) of crown prediction and flatness prediction of SSA‐DELM model is 0.971 and 0.979. 100% of the samples have a prediction error of less than ±7 μm and ±7 IU. Furthermore, to solve the problem of concept drift affecting prediction accuracy in industrial processes, online optimization method is proposed. Especially, online sequential deep ELM model (OS‐DELM) optimized by SSA and guided by double window drift detection is proposed to fill the gap. Compared with other online optimization methods, the update time with this method can be reduced by up to 83.05% averagely, which is more suitable for online strip‐shape prediction in hot rolling process.

Stacking ensemble learning fused with whale optimisation algorithm based method for crown prediction of hot-rolled strip

“…Zhang et al proposed a deep multilayer extreme learning machine fused with the sparrow algorithm to predict the flatness and crown of hot-rolled strip, which was guided by doublewindow drift detection to solve concept drift. 18 Dong et al used machine vision technology to generate the dataset and established a data-driven model based on XGBoost to predict the length of medium thickness plates, whose hyperparameters optimised by the improved bald eagle search algorithm. 19 Sun et al proposed a strip crown prediction model based on random forest (RF), which correct the decision tree to alleviate overfitting.…”