Dimension reduction method of cold rolling strip flatness data based on autoencoder
XU Yang-huan1, WANG Dong-cheng1,2, WANG Yong-mei1, YUAN Wen-yue3, YU Hua-xin1,2, LIU Hong-min1,2
1. National Engineering Research Center for Equipment and Technology of Cold Rolling Strip, Yanshan University, Qinhuangdao 066004, Hebei, China; 2. State Key Laboratory of Metastable Materials Science and Technology, Yanshan University, Qinhuangdao 066004, Hebei, China; 3. Northeastern University at Qinhuangdao, Qinhuangdao 066004, Hebei, China
Abstract：In order to realize the intelligent manufacturing of plate and strip rolling process, it is necessary to deeply explore the connotation of intelligent manufacturing. For specific problems, it is of great significance to apply the unsupervised learning and the reinforcement learning theory to production practice. The flatness detection data in the process of strip rolling is taken as the research object and the autoencoder in the unsupervised learning theory is used to automatically learn the basic flatness mode, so as to reduce the amount of storage and transmission of flatness data, realize the abstract representation of flatness distribution, and lay the foundation for the flatness anomaly detection, the intelligent prediction and the intelligent control. Compared with the traditional flatness data dimension reduction method based on Legendre polynomial, the accuracy of flatness reconstruction can be significantly improved and the approximate lossless compression of the flatness data can be realized applying the present method.
徐扬欢, 王东城, 汪永梅, 袁文越, 于华鑫, 刘宏民. 基于自编码器的冷轧带材板形数据降维方法[J]. 钢铁, 2021, 56(9): 26-35.
XU Yang-huan, WANG Dong-cheng, WANG Yong-mei, YUAN Wen-yue, YU Hua-xin, LIU Hong-min. Dimension reduction method of cold rolling strip flatness data based on autoencoder[J]. Iron and Steel, 2021, 56(9): 26-35.
[1] 王国栋. 高质量中厚板生产关键共性技术研发现状和前景[J]. 轧钢, 2019, 36(1): 1. (WANG Guo-dong. Status and prospects of research and development of key common technologies for high-quality heavy and medium plate production[J].Steel Rolling, 2019, 36(1): 1.) [2] 刘玠. 人工智能推动冶金工业变革[J]. 钢铁, 2020, 55(6): 1. (LIU Jie. Artificial intelligence drives changes in metallurgical industry[J]. Iron and Steel, 2020, 55(6): 1.) [3] 王龙, 冀秀梅, 刘玠. 人工智能在钢铁工业智能制造中的应用[J]. 钢铁, 2021, 56(4): 1. (WANG Long, JI Xiu-mei, LIU Jie. Application of artificial intelligence in intelligent manufacturing in steel industry[J]. Iron and Steel, 2021, 56(4): 1.) [4] 刘文仲. 中国轧钢自动化现状及实现轧钢智能化的思考[J]. 冶金自动化, 2016, 40(6): 1. (LIU Wen-zhong. Status of rolling automation in China and thinking about realization of intelligent rolling[J]. Metallurgical Industry Automation, 2016, 40(6): 1.) [5] 彭艳. 冶金轧制设备技术数字化智能化发展概述[J]. 燕山大学学报, 2020, 44(3): 218. (PENG Yan. Review on development of digital and intelligent metallurgical rolling equipment technology[J]. Journal of Yanshan University, 2020, 44(3): 218.) [6] 姚林, 王军生. 钢铁流程工业智能制造的目标与实现[J]. 中国冶金, 2020, 30(7): 1. (YAO Lin, WANG Jun-sheng. Goal and realization of smart manufacturing in steel industry[J]. China Metallurgy, 2020, 30(7): 1.) [7] 何安瑞, 荆丰伟, 刘超. 薄板坯连铸连轧过程控制技术的发展、应用及展望[J]. 轧钢, 2020, 37(3): 1. (HE An-rui, JING Feng-wei, LIU Chao. Development, application and prospect of process control technologies of thin slab continuous casting and rolling[J]. Steel Rolling, 2020, 37(3): 1.) [8] 李立刚, 孙文权, 李贤春, 等. 磨辊间智能管控一体化关键技术[J]. 冶金自动化, 2019, 43(6): 53. (LI Li-gang, SUN Wen-quan, LI Xian-chun, et al. Key technologies of intelligent management and integration of roll-shops[J]. Metallurgical Industry Automation, 2019, 43(6): 53.) [9] 邵健, 何安瑞, 孙文权, 等. 面向生产全过程的热轧带钢精准控制核心技术[J]. 中国冶金, 2017, 27(5): 45. (SHAO Jian, HE An-rui, SUN Wen-quan, et al. Precise control core technology of hot rolling strip in whole production process[J]. China Metallurgy, 2017, 27(5): 45.) [10] 张殿华, 彭文, 孙杰, 等. 板带轧制过程中的智能化关键技术[J]. 钢铁研究学报, 2019, 31(2): 174. (ZHANG Dian-hua, PENG Wen, SUN Jie, et al. Key intelligent technologies of steel strip rolling process[J]. Journal of Iron and Steel Research, 2019, 31(2): 174.) [11] 张殿华, 孙杰, 陈树宗, 等. 高精度薄带材冷连轧过程智能优化控制[J]. 钢铁研究学报, 2019, 31(2): 180. (ZHANG Dian-hua, SUN Jie, CHEN Shu-zong, et al. Intelligent optimization control of tandem cold rolling process for high precision thin strip[J]. Journal of Iron and Steel Research, 2019, 31(2): 180.) [12] 刘晔, 闫博, 刘长鑫. 基于厚板生产大数据的智能监控系统研究[J]. 控制工程, 2020, 27(12): 2204. (LIU Ye, YAN Bo, LIU Chang-xin. Research on intelligent monitoring system based on big data of heavy plate production[J]. Control Engineering of China, 2020, 27(12): 2204.) [13] 焦四海, 丁建华, 闫博, 等. 厚板数据中心和智能制造的实践与探索[J]. 宝钢技术, 2020(6): 8. (JIAO Si-hai, DING Jian-hua, YAN Bo, et al. Practice and explorationon data center and intelligent manufacture of plate mill[J]. Baosteel Technology, 2020(6): 8.) [14] 刘相华, 赵启林, 黄贞益. 人工智能在轧制领域中的应用进展[J]. 轧钢, 2017, 34(4): 1. (LIU Xiang-hua, ZHAO Qi-lin, HUANG Zhen-yi. Prospect of artificial intelligent application in rolling[J]. Steel Rolling, 2017, 34(4): 1.) [15] 刘振宇, 曹光明, 周晓光, 等. 组织性能预测技术及其在智能热轧中的核心作用[J]. 轧钢, 2019, 36(2): 1. (LIU Zhen-yu, CAO Guang-ming, ZHOU Xiao-guang, et al. The predicting technologies for microstructure and properties and their core roles in smart hot rolling processes[J]. Steel Rolling, 2019, 36(2): 1.) [16] 刘阳, 郜志英, 周晓敏, 等. 工业数据驱动下薄板冷轧颤振的LSTM智能预报[J]. 机械工程学报, 2020, 56(11): 121. (LIU Yang, GAO Zhi-ying, ZHOU Xiao-min, et al. Industrial data-driven intelligent forecast for chatter of cold rolling of thin strip with LSTM recurrent neural network[J]. Journal of Mechanical Engineering, 2020, 56(11): 121.) [17] SONG Ke-chen, YAN Yun-hui. A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects[J]. Applied Surface Science, 2013, 285(21): 858. [18] HE Yu, SONG Ke-chen, MENG Qing-guang, et al. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 64(4): 1493. [19] 王东城, 徐扬欢, 段伯伟, 等. 数据驱动的热轧带钢边部线状缺陷智能预报模型[J]. 钢铁, 2020, 55(11): 82. (WANG Dong-cheng, XU Yang-huan, DUAN Bo-wei, et al. Data-driven intelligent prediction model of edge seam defects for hot rolling strip[J]. Iron and Steel, 2020, 55(11): 82.) [20] David Silver, Aja Huang, Chris J Maddison, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587): 484. [21] 袁文越. 冷轧带材板形测控数据远程采集系统研究及应用[D]. 秦皇岛: 燕山大学, 2018. (YUAN Wen-yue. Research and Application of Remote Acquisition System for Measured Shape Data of Cold Rolled Strip[D]. Qinhuangdao: Yanshan University, 2018.) [22] Tomas Mikolov, Kai Chen, Greg Corrado, et al. Efficient estimation of word representations in vector space[C]//Proceedings of the International Conference on Learning Representations (ICLR 2013). Scottsdale: arXiv preprint. 2013: https://arxiv.org/abs/1301.3781. [23] 宋明明, 王东城, 张帅, 等. 基于循环神经网络的板形模式识别模型[J]. 钢铁, 2018, 53(11): 56. (SONG Ming-ming, WANG Dong-cheng, ZHANG Shuai, et al. Flatness pattern recognition model based on recurrent neural network[J]. Iron and Steel, 2018, 53(11): 56.) [24] 单修迎, 刘宏民, 贾春玉. 含有三次板形的新型板形模式识别方法[J]. 钢铁, 2010, 45(8): 56. (SHAN Xiu-ying, LIU Hong-min, JIA Chun-yu. A recognition method of new flatness pattern containing the cubic flatness[J]. Iron and Steel, 2010, 45(8): 56.) [25] 邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社, 2021. (QIU Xi-Peng. Neural Network and Deep Learning[M]. Beijing: Mechanical Industry Press, 2021.) [26] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504.
2021, Vol. 56 
