AI Intelligent Recognition Early Warning System for Steel Mills

Yuan Jiang; Luyu Chen; Zhe Li; Xinchen Xu; Yuzhen Su; Xun Pei

doi:10.62051/ijcsit.v5n3.15

AI Intelligent Recognition Early Warning System for Steel Mills

Yuan Jiang, Luyu Chen, Zhe Li, Xinchen Xu, Yuzhen Su, Xun Pei

International Journal of Computer Science and Information Technology, (2025), Vol.5, No.3, pp.158-165

Published: April 10, 2025

DOI: 10.62051/ijcsit.v5n3.15

PDF: Download Full Text PDF

Abstract

The production environment of steel mills is complex, and the equipment is not allowed to stop. The traditional manual monitoring is inefficient, and it is impossible to always monitor data and equipment, which has great security risks. In this paper, an ai intelligent identification and early warning system for steel mills is designed, which integrates two subsystems: safety production early warning and equipment healthy operation early warning, and adopts computer vision (YOLOv5) and time series data analysis (LSTM, self-encoder) technologies respectively to realize workers' behavior monitoring and equipment fault prediction. Through real-time alarm and data visualization, the system can significantly improve the safety and operational efficiency of steel mills.

Keywords: Early Warning System, Steel Mills, Intelligent Recognition, AI

APA Citation: Yuan Jiang, Luyu Chen, Zhe Li, Xinchen Xu, Yuzhen Su, Xun Pei (2025). AI Intelligent Recognition Early Warning System for Steel Mills. International Journal of Computer Science and Information Technology, 5(3), 158-165. https://doi.org/10.62051/ijcsit.v5n3.15

References

Li Zhangping, Huang Yufen. Development of Intelligent Lighting Control System in Computer Vision Perspective [J]. China Lighting Electric Appliance, 2025(01):109-114.
Wu XY, Guo HW, Li NN, et al. A review of video-based detection of abnormal events in crowds [J]. Journal of Electronic Measurement and Instrumentation, 2014, 28(06):575-584. DOI:10.13382/j.jemi.2014.06.001.
Journal | [J] IEEE transactions on pattern analysis and machine intelligence. Volume 42, Issue 2. 2020. PP 318-327.
Du R, Chen H, Yu M, et al. 3DTCN-CBAM-LSTM short-term power multi-step prediction model for offshore wind power based on data space and multi-field cluster spatio-temporal correlation [J]. Applied Energy, 2024, 376(PA):124169-124169.
Zhao, C. 2024. Application of Reinforcement Learning in Complex Environmental Decision-making Problems [J]. Journal of Computing and Electronic Information Management. 15, 3 (Dec. 2024), 104–108.