IoT-based framework for digital twins in steel production: A case study of key parameter prediction and optimization for CSR

Expert Systems with Applications, Год журнала: 2024, Номер 250, С. 123909 - 123909

Опубликована: Апрель 4, 2024

Язык: Английский

---

Explainable machine learning for predicting mechanical properties of hot-rolled steel pipe

Journal of Iron and Steel Research International, Год журнала: 2025, Номер unknown

Опубликована: Фев. 24, 2025

Язык: Английский

---

基于混合多阶集成模型的非平衡热轧带钢凸度智能诊断

Journal of Central South University, Год журнала: 2024, Номер 31(3), С. 762 - 782

Опубликована: Март 1, 2024

Язык: Английский

---

An interpretable framework for high-precision flatness prediction in strip cold rolling

Journal of Materials Processing Technology, Год журнала: 2024, Номер 329, С. 118452 - 118452

Опубликована: Май 24, 2024

Язык: Английский

---

A novel deep ensemble reinforcement learning based control method for strip flatness in cold rolling steel industry

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 134, С. 108695 - 108695

Опубликована: Май 31, 2024

Язык: Английский

---

Novel shape control system of hot-rolled strip based on machine learning fused mechanism model

Expert Systems with Applications, Год журнала: 2024, Номер 255, С. 124789 - 124789

Опубликована: Июль 14, 2024

Язык: Английский

---

Modeling and Simulation of Shape Control Based on Digital Twin Technology in Hot Strip Rolling

Sensors, Год журнала: 2024, Номер 24(2), С. 614 - 614

Опубликована: Янв. 18, 2024

Focusing on the problem of strip shape quality control in finishing process hot rolling, a model based metal flow and stress release with application varying contact rolling parameters is introduced. Combined digital twin technology, framework proposed, which realizes deep integration between physical time–space virtual time–space. With utilization historical data, are optimized iteratively to complete model. According schedule, raw material information taken as input obtain simulation shape, shows variety export conditions. The prediction absolute error crown flatness less than 5 μm I-unit, respectively. results prove that proposed strong performance can be effectively applied production. In addition, provides operators reference for parameter settings actual production promotes intelligent strategy.

Язык: Английский

---

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

Digital Twin, Год журнала: 2025, Номер 4, С. 10 - 10

Опубликована: Фев. 7, 2025

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. 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 maximize index. Experimental results demonstrate that effectively recognized state successfully enhances system. Therefore, platform, proposed can maintain performance-degraded systems.

Язык: Английский

---

Predictive modeling of strip width based on incremental learning and adaptive-weight fusion during the hot rolling process

Journal of Manufacturing Processes, Год журнала: 2025, Номер 142, С. 157 - 176

Опубликована: Апрель 1, 2025

Язык: Английский

---

Two-stream neural network for the prediction of multiple defects in continuous casting

Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 113116 - 113116

Опубликована: Апрель 1, 2025

Язык: Английский

---