Diagnosis Solutions For Rolling Condition And Product Quality At Metal Plants*

The highly competitive business environment of the international metals industry is driving demand for more cost-effective operation of steel making facilities, rolling mills, and strip processing lines. Achieving stable operation is vital if the steel industry is to produce high-quality products constantly and productively. In recent years, advances in computer processing speeds, data acquisition rates, and data storage capacity have rapidly led to greater use of the new technologies of big data, analytics, the IoT, and AI by control system designers and process engineers, and the introduction of industrial applications. The “Smart Rolling Mill” solutions for hot strip mills have been developed by our group with the goal of achieving sophisticated, state of the art, and automated operation in steel rolling mills. The various solution engines improve process stability, increase the performance of mill equipment, and provide improved process control. These solution engines are based on extensive knowledge of the rolling process and the associated control systems. Two solution engines in particular are the diagnosis systems for rolling condition and for product quality that contribute to cost-effective operation and lower yield loss. This paper focuses on the diagnosis systems for rolling condition and for product quality in hot strip mills. Advanced information technologies using big data analytics and machine learning are applied to real-time data collected from the automation system that controls operation and the rolling process. We have developed diagnosis solutions for rolling condition and product quality utilizing predictive and clustering diagnosis. Predictive diagnosis prevents serious problems by detecting changes in the state of the plant or in the rolling condition. Clustering diagnosis classifies patterns of fluctuation in product quality trend charts, providing effective tuning guidance for improving product quality. This paper describes these applications with several examples.