基于软测量模型的粗轧厚度预测方法  

Prediction Method of Rough Rolling Thickness Based on the Soft Sensor Model

作　　者：彭文[1] 马更生[1] 龚殿尧[1] 张殿华[1] 

机构地区：[1]东北大学轧制技术及连轧自动化国家重点实验室,辽宁沈阳110819

出　　处：《东北大学学报（自然科学版）》2017年第3期366-369,共4页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(51504061)

摘　　要：为提高热连轧粗轧过程各道次厚度控制精度,满足道次动态修正的要求,提出了一种简单有效的厚度软测量模型.基于典型粗轧区的仪表配置,模型从轧件跟踪、数据处理等方面进行了针对性的研究,提出了偶数道次立辊辊缝渐变的策略用于可逆轧制过程中的宽度测量,并通过模型预测得到了轧制过程中各道次的出口厚度.现场实际应用表明,通过软测量模型预报的各道次厚度与实际测量结果吻合较好,各道次的厚度预报偏差在±0.10 mm范围内达到95.2%,满足了现场生产需求.In order to improve the thickness control precision and meet the demand of the pass dynamic correction in rough rolling process,a simple and effective thickness soft sensor model was proposed. The study of rolling tracking and data processing was carried out based on the instrument arrangement in typical rough rolling. The strategy of gradual vertical roll-gap was proposed to measure the width in the even pass. And the thickness of each pass was obtained by the soft sensor model. The application results showed that the thickness is in a good agreement with the actual measured ones. The predicted precision error in the range of ± 0. 10 mm reaches95. 2%,which can meet the demand of the production.

关 键 词：热连轧 粗轧 软测量模型 厚度预测 控制精度 

分 类 号：TG335.5[金属学及工艺—金属压力加工]