Research on Optimization of Strip Steel Process Parameters Based on Random Forest Model

Haotong Wang; Xijun Gao; Mingze Gao

doi:10.54097/vac6nh17

Authors

Haotong Wang
Xijun Gao
Mingze Gao

DOI:

https://doi.org/10.54097/vac6nh17

Keywords:

Cold Rolled Strip Steel, Process Parameter Optimization, Random Forest Regression, Data-Driven, Hardness Prediction.

Abstract

Aiming at the problem that it is difficult to accurately model the complex nonlinear relationship between process parameters and hardness in continuous annealing process of cold-rolled strip steel, a data-driven optimization method based on random forest regression model is proposed in this paper. Firstly, Pearson correlation coefficient analysis was used to quantify the correlation between process parameters and hardness, and the key influencing factors such as fast cooling furnace temperature, carbon content and soaking furnace temperature were identified. Secondly, a random forest regression model is established, and the prediction performance of the model is improved by grid search optimization. Finally, the data are preprocessed (including Z-score standardization and outlier processing), and the validity of the model is verified based on simulation experiments. The results show that the mean square error (MSE) of the optimized model on the test set is 285.97, and the coefficient of determination (R²) is 0.384, which can better predict the hardness of the strip. This method provides theoretical support and decision-making basis for iron and steel enterprises to optimize production process and improve product quality.

References

[1]Wang P, Yan Z, Li X, et al. Edge drop control of cold rolled silicon steel strip based on model predictive control[J]. Journal of Manufacturing Processes, 2022, 82: 88-95.

[2]Chen H, Nie Z, Xu Q, et al. Intelligent detection and classification of surface defects on cold-rolled galvanized steel strips using a data-driven faulty model with attention mechanism[J]. Journal of Computing and Information Science in Engineering, 2023, 23(4): 041001.

[3]Chen Y, Peng L, Wang Y, et al. Prediction of tandem cold-rolled strip flatness based on Attention-LSTM model[J]. Journal of Manufacturing Processes, 2023, 91: 110-121.

[4]Šverko Z, Vrankić M, Vlahinić S, et al. Complex Pearson correlation coefficient for EEG connectivity analysis[J]. Sensors, 2022, 22(4): 1477.

[5]Hu J, Szymczak S. A review on longitudinal data analysis with random forest[J]. Briefings in bioinformatics, 2023, 24(2): bbad002.

[6]Costa V G, Pedreira C E. Recent advances in decision trees: An updated survey[J]. Artificial Intelligence Review, 2023, 56(5): 4765-4800.

[7]Zhang Y, Liu J, Shen W. A review of ensemble learning algorithms used in remote sensing applications[J]. Applied Sciences, 2022, 12(17): 8654.

[8]Schober P, Mascha E J, Vetter T R. Statistics from A (agreement) to Z (z score): a guide to interpreting common measures of association, agreement, diagnostic accuracy, effect size, heterogeneity, and reliability in medical research[J]. Anesthesia & Analgesia, 2021, 133(6): 1633-1641.

[9]Chicco D, Warrens M J, Jurman G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. Peerj computer science, 2021, 7: e623.

[10]Ahmad G N, Fatima H, Ullah S, et al. Efficient medical diagnosis of human heart diseases using machine learning techniques with and without GridSearchCV[J]. Ieee Access, 2022, 10: 80151-80173.

[11]Soydaner D. Attention mechanism in neural networks: where it comes and where it goes[J]. Neural Computing and Applications, 2022, 34(16): 13371-13385.

Veličković P. Everything is connected: Graph neural networks[J]. Current Opinion in Structural Biology, 2023, 79: 102538.