Prediction technology for mechanical properties of hot-dip aluminum zinc plating unit products
WEI Baomin1, WANG Xiaojian1,2, BAI Zhenhua2,3
1. Meisteel Technology Center, Academia Sinica, Baosteel, Nanjing 210039, Jiangsu, China; 2. National Engineering Research Center for Equipment and Technology of Cold Strip Rolling, Yanshan University, Qinhuangdao 066004, Hebei, China; 3. State Key Laboratory of Metastable Materials Science and Technology, Yanshan University, Qinhuangdao 066004, Hebei, China
Abstract:Aiming at the issue of poor mechanical properties of hot-dip aluminum zinc plating unit products, based on the importance analysis and data sample clustering analysis of influencing parameters for product mechanical properties, a BP neural network prediction model for mechanical properties of the hot-dip aluminum zinc plating unit product was established. The calculation of mechanical properties parameters such as yield strength, tensile strength, and elongation after fracture of the strip steel was achieved in statistical sense. Based on the flat rolling mechanism model and using deformation resistance as a bridge, the fluctuation of deformation resistance at the exit of the strip steel was calculated based on the real-time rolling force data model during the flat rolling process. Thus the yield strength, tensile strength, and elongation after fracture predicted by the BP neural network model were modified, and a set of mechanical properties prediction technology of hot-dip products combining neural network model and physical metallurgy model was further formed. The application of this technology to the on-site production of hot-dip aluminum zinc plating unit in a steel plant provides theoretical basis for the formulation of the production process of the unit.
王孝建,钱胜,崔梦雨,等. 热镀锌机组沉没辊系刮刀力预报及影响因素[J]. 钢铁,2022,57(6):82. (WANG X J, QIAN S, CUI M Y, et al. Prediction and influencing factors of scraper force for sink roll system of hot dip galvanizing unit[J]. Iron and Steel, 2022, 57(6): 82.)
[2]
熊俊伟. 热镀锌改热镀铝锌机组工艺与设备选型[J]. 轧钢,2017,34(6):49. (XIONG J W. Process and equipment selection for hot dip galvanizing to hot dip aluminum zinc plating unit[J]. Steel Rolling, 2017, 34(6): 49.)
[3]
宋文钟,刘妍,路璐,等. 家电用热镀锌无铬耐指纹深冲钢DCJD2+Z研发[J]. 包钢科技,2022,48(4):29. (SONG W Z, LIU Y, LU L, et al. Research and development of DCJD2+Z hot-dip galvanized chromium free fingerprint resistant deep drawing steel for household appliances[J]. Baosteel Technology, 2022, 48 (4): 29.)
[4]
PAN Z S, ZHOU X H, CHEN P. Development and application of a neural network based coating weight control system for a hot-dip galvanizing line[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(7): 834.
[5]
曹晓恩,赵红旗,李守华,等. 980 MPa级冷轧超高强度双相钢边裂原因分析与工艺优化[J]. 中国冶金,2022,32(9):90. (CAO X E, ZHAO H Q, LI S H, et al. Cause analysis and process optimization of edge crack for 980 MPa cold rolled ultra high strength dual-phase steel[J]. China Metallurgy, 2022, 32(9): 90.)
[6]
金永清. 攀钢热镀铝锌钢板的开发[J]. 轧钢,2007,24(3):61. (JIN Y Q. Development of Panzhihua steel hot dipped aluminum zinc steel plate[J]. Rolling Steel, 2007, 24 (3): 61.)
[7]
秦兴祖,沈健,张雯. 汽车镀锌板表面缺陷的案例分析[J]. 北京汽车,2022(6):28. (QIN X Z, SHEN J, ZHANG W. Case analysis of surface defects in automotive galvanized sheets[J]. Beijing Automotive, 2022(6): 28.)
[8]
YANG D, CHEN J S, HAN Q, et al. Effects of lanthanum addition on corrosion resistance of hot-dipped galvalume coating[J]. Journal of Rare Earths, 2009, 27(1): 114.
[9]
徐烨明,张青树,白振华. 平整机组伸长率窜高形成机理及其控制技术[J]. 中国冶金,2020,30(10):41. (XU Y M, ZHANG Q S, BAI Z H. The formation mechanism and control technology of elongation escalation in leveling units[J]. China Metallurgy, 2020, 30(10): 41.)
[10]
马湧,王晓鹏,马莎莎. 基于Keras深度学习框架下BP神经网络的热轧带钢力学性能预测[J]. 冶金自动化,2019,43(2):6. (MA Y, WANG X P, MA S S. Prediction of mechanical properties of hot rolled strip steel based on BP neural network under Keras deep learning framework[J]. Metallurgical Automation, 2019, 43(2): 6.)
[11]
胡石雄,李维刚,杨威. 基于卷积神经网络的热轧带钢力学性能预报[J]. 武汉科技大学学报,2018,41(5):338. (HU S X, LI W G, YANG W. Prediction of mechanical properties of hot rolled strip steel based on convolutional neural networks[J]. Journal of Wuhan University of Science and Technology, 2018, 41(5): 338.)
[12]
王蕾. 热轧带钢的相变和力学性能模型研究及应用[D]. 北京:北京科技大学,2017. (WANG L. Research and Application of Phase Transformation and Mechanical Property Models for Hot Rolled Strip Steel[D]. Beijing: Beijing University of Science and Technology, 2017.)
[13]
贺俊光,文九巴,李俊. 用BP神经网络预测热镀锌钢板的拉伸强度[J]. 机械工程材料,2007,31 (3): 60. (HE J G, WEN J B, LI J. Predicting the tensile strength of hot-dip galvanized steel plates using BP neural network[J]. Mechanical Engineering Materials, 2007, 31 (3): 6).
[14]
LALAM S, TIWARI P K, SAHOO S, et al. Online prediction and monitoring of mechanical properties of industrial galvanized steel coils using neural networks[J]. Ironmaking & Steelmaking, 2017 (9):1.
[15]
JANANI S, THENMOZHI R, JAYAGOPAL L S. Theoretical investigations for the verification of shear centre and deflection of sigma section by back propagation neural network using Python[J]. Archives of Civil Engineering, 2019, 65(2):181.
[16]
CHENG Y H, YIN C, BAI L B, et al. Fault diagnostics of rolling bearings using feature fusion based BP, RBF and PNN neural networks[J]. International Journal of Applied Electromagnetics and Mechanics, 2016, 52(1/2):95.
[17]
白振华,刘宏民,李秀军,等. 平整轧制工艺模型[M]. 北京:冶金工业出版社,2010. (BAI Z H, LIU H M, LI X J, et al. Flat Rolling Process Model [M]. Beijing: Metallurgical Industry Press, 2010.)
[18]
白振华,康晓鹏,龙瑞兵. 工程实用平整轧制压力模型及其自学习技术研究[J]. 钢铁,2008,43(10):51. (BAI Z H, KANG X P, LONG R B. Research on the practical rolling pressure model for engineering flattening and its self learning technology[J]. Steel, 2008, 43(10): 51.)