I. Introduction
As one of the indispensable raw materials for the manufacturing industry, the quality of hot-rolled coil is crucial for many types of end products, especially high-end products in aerospace, automotive, and precision instruments fields. In addition to surface and shape defect, end-face defect (including edge crack, thorn, damage, and scratch) is another important affecting factor, such as corrosion resistance, wear resistance, and fatigue strength [1]. Therefore, the end-face defect control (EF-DC) is getting more and more attention in Baowu, Nippon, Posco, Nucor, and other major steel enterprises. The core of EF-DC is to recognize defects, analyze causes, predict developing trend in advance, and take corresponding measures timely to prevent similar defects in subsequent production. EF-DC mainly includes the following three aspects:
Defect recognition: Identify whether there is a defect and its type. The current recognition method mainly focuses on surface or shape defect of hot-rolled coil, lacking standard end-face defect feature set, and related identification algorithm.
Defect analysis and prediction: Count the defects in the same batch (such as type, quantity, severity, etc.), analyze the cause of defects, and predict whether defect is controllable through data. It indicates that defects are most likely to occur in subsequent production if out of control.
Defect control: Formulate control methods and take corresponding measures to optimize and adjust production to prevent similar defects in subsequent production based on defect analysis and prediction.