Space-time characteristics and evolution rules of breakout during continuous casting
LIU Yu1, XU Zhi-qiang1, ZHANG Dong-dong1, WANG Xin-hua2
1. School of Mechanical Engineering, Northeast Electric Power University, Jilin 132012, Jilin, China; 2. School of Computer Science, Northeast Electric Power University, Jilin 132012, Jilin, China
Abstract:Breakout is a serious accident during continuous casting. It is very important for the steady and smooth continuous casting if the space-time characteristics and its evolution rules of breakout in mould are accurately recognized. Based on the visual characteristics, the characteristics of typical sticker breakout were analyzed from the aspect of time evolution. The spatial characteristics of hot and cold regions, such as the area, temperature velocity and location, were studied and analyzed in order to obtain the difference and critical condition of true and false sticker breakouts. The results show that the hot region area of sticker breakout is mainly concentrated in 1 973 to 7 795 pixels. The temperature velocity greater than 1.02 ℃/s is the necessary condition for sticker breakout. The temperature velocity of the cold region is in the range -0.57 to -4.22 ℃/s. When the temperature velocity is less than -2.52 ℃/s, there is no false sticker breakout, but there are 12 cases of true sticker breakout. The gathering location of hot and cold region of true sticker breakouts is concentrated in the range 46th-64th and 5th-47th, respectively. The research provides an easy way to distinguish true and false sticker breakouts and is helpful to recognize the instantaneous morphology of slab surface in mould more fully and accurately.
LIU Y, WANG X D, YAO M, et al. Effect of casting parameters on sticker breakout and its propagation behaviour during slab continuous casting[J].Ironmaking and Steelmaking, 2014, 41(10): 748.
QIN X, ZHU C F, ZHENG L W, et al. Molten steel breakout prediction based on thermal friction measurement[J].Journal of Iron and Steel Research International, 2011, 18(4): 24.
[12]
秦梦泽,张勇. 基于热-力信息融合的智能漏钢预报技术研究[J].炼钢,2020,36(4):65.
[13]
HE F, ZHANG L Y. Mold breakout prediction in slab continuous casting based on combined method of GA-BP neural network and logic rules[J].The International Journal of Advanced Manufacturing Technology, 2018, 95(9): 4081.
[14]
LIU Y, WANG X D, YAO M, et al. Computer vision detection of mold breakout in slab continuous casting using an optimized neural network[J].The International Journal of Advanced Manufacturing Technology, 2017, 88(1-4): 557.
[15]
DUAN H Y, WANG X D, BAI Y, et al. Integrated approach to density-based spatial clustering of applications with noise and dynamic time warping for breakout prediction in slab continuous casting[J].Metallurgical and Materials Transactions B, 2019, 50(5): 2343.
[16]
LIU Y, WANG X D, YAO M, et al. Visual detection based on computer vision for sticker breakout in slab continuous casting[J].Ironmaking and Steelmaking, 2015, 42(6): 417.