Optimization for steel grade family of model based on measured data during hot continuous rolling
LI Wei-gang1,2,XU Wen-sheng1,MA Wei1,LIU Ao2,3
(1. Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, Hubei, China 2. National-Provincial Joint Engineering Research Center of High Temperature Materials and Lining Technology, Wuhan University of Science and Technology, Wuhan 430081, Hubei, China 3. Center for Service Science and Engineering, Wuhan University of Science and Technology, Wuhan 430065, Hubei, China)
Abstract:The steel grade family is one of the most important basic configuration data for the process control during hot continuous rolling. It has an important influence on the setting precision of rolling models. The existing divisions of the steel grade family are mainly based on the artificial experience, mainly relying on the carbon equivalent, which is unreasonable and difficult to meet the actual production needs. In view of this, a new line clustering algorithm to optimize the classification of steel grade family is proposed. First, collect a large number of rolling historical data from a certain steel grade family. Then, draw a scatter diagram of the strip steel about the deformation rate and the deformation resistance, and observe the distribution characteristics of the data. Finally, use the linear clustering algorithm to optimize the classification of the steel grade family, and select the steel with larger separation degree to an new steel group. At present, the technology has been used in the commissioning of several hot rolling models such as Baosteel 1 880, which has played an important role in the standard production and the product verification of the hot rolling engineering.
收稿日期: 2018-03-21
出版日期: 2018-10-26
引用本文:
李维刚,徐文胜,马 威,刘 翱,. 基于热连轧实测数据的模型钢族层别优化[J]. , 2018, 53(10): 54-60.
LI Wei-gang,,XU Wen-sheng,MA Wei,LIU Ao,. Optimization for steel grade family of model based on measured data during hot continuous rolling. Iron and Steel, 2018, 53(10): 54-60.