期刊名称：Advances in Science and Technology Research Journal
印刷版ISSN：2080-4075
电子版ISSN：2299-8624
出版年度：2019
卷号：13
期号：4
页码：70-86
DOI：10.12913/22998624/112542
语种：English
出版社：Society of Polish Mechanical Engineers and Technicians
摘要：The temperature of annealed steel coils is a determining variable of the future steel sheets quality. This variablealso determines the energy consumption in operation. Unfortunately, the monitoring of coil inner temperature isproblematic due to the furnace environment with high temperature, coil structure, and annealing principle. Currently, there are no measuring principles that can measure the temperature inside the heat-treated product in anon-destructive manner. In this paper, the soft sensing of inner temperature based on the theory of non-stationaryheat conduction and approach based on Support Vector Regression (SVR) was presented. The results showedthat a black-box approach based on the SVR could replace an analytic approach, though with lesser performance.Several annealing experiments were performed to create a training data set and model performance improvementin the estimation of inner coil temperatures. The proposed software based on non-stationary heat conduction cancalculate the behavior of inner coil temperature from the measured boundary temperatures that are measured bythermocouples. The soft-sensing principles presented in this paper were verifed under laboratory conditions andon the data obtained from a real annealing plant.
关键词：annealing; steel coil; temperature measurement; soft-sensing; fnite differences method; support vector
regression
