Coiling temperature model self-learning method suitable for fast-paced rolling

• Main Authors: CUI SHUJIE, XIN XIAOBING, LI CHENGCHENG, CHEN TONG, LINGHU KEZHI, QIN HONGBO, LI XIAOGANG, ZHANG ZAIXING, YU HAIYAN
• Format: Patent
• Language: Chinese; English
• Published: 29.07.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVINGMATERIAL; PERFORMING OPERATIONS; PHYSICS; PUNCHING METAL; ROLLING OF METAL; TRANSPORTING

The invention relates to a coiling temperature model self-learning method suitable for fast-paced rolling, and belongs to the technical field of hot rolling methods in the metallurgical industry. According to the technical scheme, a water-cooling self-learning target point of a coiling temperature model is configured, after the self-learning target point passes through a pyrometer, actual temperature data are obtained and are immediately compared with predicted temperature, a water-cooling self-learning coefficient is calculated, upper and lower limits and data are subjected to smoothing processing, and then the data are updated to a model database for coiling temperature model calculation. The method has the beneficial effects that the problem that in an original design, the model self-learning coefficient is updated only after the hot-rolled strip steel completely passes through a pyrometer before coiling, and during fast-paced production, the updated model self-learning coefficient cannot be used for setti