Process Integrated Computer Vision for Real-Time Failure Prediction in Steel Rolling Mill

TL;DR

This paper demonstrates a real-time, integrated computer vision system using deep learning for early failure prediction in steel mills, improving maintenance and reducing costs.

Contribution

It introduces a scalable, server-based vision system that combines visual and sensor data for proactive failure detection in industrial settings.

Findings

Early failure prediction reduces unplanned downtime.

Server-based inference minimizes computational load.

Joint analysis improves root cause identification.

Abstract

We present a long-term deployment study of a machine vision-based anomaly detection system for failure prediction in a steel rolling mill. The system integrates industrial cameras to monitor equipment operation, alignment, and hot bar motion in real time along the process line. Live video streams are processed on a centralized video server using deep learning models, enabling early prediction of equipment failures and process interruptions, thereby reducing unplanned breakdown costs. Server-based inference minimizes the computational load on industrial process control systems (PLCs), supporting scalable deployment across production lines with minimal additional resources. By jointly analyzing sensor data from data acquisition systems and visual inputs, the system identifies the location and probable root causes of failures, providing actionable insights for proactive maintenance. This integrated approach enhances operational reliability, productivity, and profitability in industrial manufacturing environments.