Cited by An Improved VAE-Based Quality Prediction Method with Application to a Hot Strip Rolling Mill Process

Flatness prediction and optimization control of electronic aluminum foil based on MPSO-LightGBM DOI

Anrui He,

Haotang Qie,

Yuangai Zhang

et al.

The International Journal of Advanced Manufacturing Technology, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Language: Английский

Citations

Industrial Big Data‐Driven Modeling and Prediction for Hot‐Rolled Strip Crown with Multigrade and Multispecification Data DOI

Dewei Xu,

Chengyan Ding,

Yu Liu

et al.

steel research international, Journal Year: 2024, Volume and Issue: 95(7)

Published: April 25, 2024

In the field of hot rolling big data, presence different steel types, specifications, and data heterogeneity poses significant challenges to accuracy stability using single machine learning regression technology for prediction. Therefore, this study proposes a hot‐rolled strip crown prediction method that combines clustering fusion modeling. First, article introduces relevant mechanism designing cluster strategies. The optimal strategy is determined through comparative experiments process parameters, size, main material components as features. Subsequently, K‐Means++ algorithm used effectively training testing datasets based on strategy, generating multiple clusters both datasets. Finally, establishes seven models match most suitable model each cluster, matching between rigorous testing. evaluation shows an R 2 value 0.829 root mean square error 3.974. experimental results show proposed outperforms traditional methods in solving multiclass classification heterogeneity, providing strong support intelligent control future.

Language: Английский

Citations

Application of digital twin for industrial process control: A case study of gauge-looper-tension optimized control in strip hot rolling DOI

Jie Sun, Chen Shang,

Chengyan Ding

et al.

Digital Twin, Journal Year: 2024, Volume and Issue: 4, P. 10 - 10

Published: Oct. 14, 2024

Background During the hot rolling process, performance of most control systems gradually degrades due to equipment aging and changing process conditions. However, existing gauge-looper-tension method remain restricted by a lack intelligent parameter maintenance strategies. Methods To address this challenge enhance smart manufacturing capabilities strip rolling, based on digital twin method, paper proposes data-driven optimized for system rolling. First, model is constructed serve as an evaluation optimization platform. Subsequently, relevant data are collected calculate Hurst index identifying controller during process. Additionally, controllers with poor values, crayfish algorithm employed adjusting parameters maximum index. Results A real case steel production was used validate proposed method. Experimental results demonstrate that can effectively recognize state controller. Moreover, after optimizing through (COA), value showed significant improvement. Conclusions The -based capability maintain strategy production. Through increasing from 0.574 0.862.

Language: Английский

Citations

A novel cost-sensitive quality determination framework in hot rolling steel industry DOI

Chengyan Ding,

Jun-Cheng Ye,

L Wang

et al.

Information Sciences, Journal Year: 2024, Volume and Issue: 678, P. 121054 - 121054

Published: June 17, 2024

Language: Английский

Citations

Multi-dimension and multi-modal rolling mill vibration prediction model based on multi-level network fusion DOI

Shu-zong Chen,

Yunxiao Liu, Yunlong Wang

et al.

Journal of Central South University, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 12, 2024

Language: Английский

Citations

Application of novel interpretable machine learning framework for strip flatness prediction during tandem cold rolling DOI

Jingdong Li, Youzhao Sun,

Xiaochen Wang

et al.

Measurement, Journal Year: 2024, Volume and Issue: unknown, P. 116516 - 116516

Published: Dec. 1, 2024

Language: Английский

Citations

A Novel Model Based on PSO-GA-RBF Approach for Predicting Roll Gap During Unsteady Processes DOI

Ruixiao Zhang,

Chen-xue Mao,

Jinkai Hu

et al.

Published: Feb. 27, 2024

To enhance the control accuracy of strip thickness in non-stationary process cold continuous rolling, a PSO-GA-RBF based prediction model for roll gap is proposed. This combines big data algorithms with actual production data, including gap, rolling force, and speed. A 1450mm series line selected as research object. Pearson analysis utilized to perform correlation on original indicators, while principal component employed reduce dimensionality sample data. The optimization particle swarm enhanced by introducing crossover mutation operators from genetic algorithms. aims improve parameter selection mechanism radial basis function neural network, thereby enhancing model's generalization performance. performance different models analyzed, comparing them evaluation indicators such mean square error, average absolute error percentage. results indicate that demonstrates good predictive ability further validate effectiveness model, comparison drawn between obtained engineering practice. experimental show close correspondence trend period two, verifying strong model. validated offers benefits reducing workload automatic system improving steel thickness.

Language: Английский

Citations

Prediction and Analysis of Hot Rolling Strip Tension Based on Back Propagation Neural Network DOI

Hao Yuan, Yiwei Ma, Xu Li

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: April 5, 2024

Abstract In modern hot strip mill control systems, tension is the core function, and its performance will be directly reflected in product quality. A prediction model based on Back Propagation (BP) neural network proposed. To ensure that true value obtained, this paper proposes a four-dimensional judgment mode for contact time between looper steel establishes data set of parameters rolled steel. The traditional BP network, genetic algorithm optimized (GA-BP), whale (WOA-BP) models were used to predict tension, their was evaluated. results show proposed WOA-BP has best effect, with highest decision coefficient 0.9330. At same time, contribution rate each variable studied, showed angle roller force had greatest impact it, consistent physical laws. Propose improvement suggestions influence model.

Language: Английский

Citations

An Improved VAE-Based Quality Prediction Method with Application to a Hot Strip Rolling Mill Process DOI

Yundan Liu,

Kai Zhang, Xiaowen Zhang

et al.

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS), Journal Year: 2024, Volume and Issue: unknown, P. 783 - 788

Published: May 17, 2024

Language: Английский

Citations