|
|
Defect detection of billet macrostructure based on machine learning |
HAN Zhan-guang, ZHOU Gan-shui, XIE Chang-chuan |
Research Institute, WISDRI CCTEC Engineering Co., Ltd., Wuhan 430073, Hubei, China |
|
|
Abstract Aiming at the problem of low magnification defect rating of continuous casting billets, a system solution based on deep learning framework was established. Based on the defect target detection algorithm of YOLO V4, the detection and recognition of defects of detection class are carried out. The standard Average Precision (AP) index is used as the evaluation index. The AP of “central pipe”, “central porosity”, “nonmetallic inclusion”, “subsurface blowhole” and “central segregation” reached 82.19%, 97.63%, 54.27%, 66.20% and 29.29% respectively. The defect instance segmentation algorithm based on MASK RCNN was used to detect and identify segmented defects. Taking the standard AP(0.5-0.95) as the evaluation index, the AP(0.5-0.95) for detecting and segmentation of four types of defects, namely, “central crack”, “corner crack”, “middle crack” and “subcutaneous crack”, reached 0.78. In particular, From the perspective of production and application, AP(0.5) reaches 0.96, which can better meet the needs of defect detection.
|
Received: 21 June 2022
|
|
|
|
[1] |
马飞跃. 连铸坯低倍检验工艺发展现状及展望[J]. 连铸,2022(1):9.
|
[2] |
郑伟栋,唐志军,郝强,等. 铸坯酸蚀检验法在板坯连铸生产中的应用[J]. 连铸,2011(2):44.
|
[3] |
张静. 基于图像处理的连铸方坯低倍缺陷裂纹和缩孔的识别与评级[D]. 沈阳:东北大学,2016.
|
[4] |
贾永坡. 基于深度学习的板坯低倍质量评级系统[C]//第十一届钢铁年会论文集. 北京:中国金属学会,2017:1.
|
[5] |
CHEN T, CHENG M M, TAN P, et al. Sketch2Photo: Internet image montage[J]. ACM Trans Graph, 2009, 28(5):1.
|
[6] |
Wang L, Hua G, Sukthankar R, et al. Video object discovery and Co-segmentation with extremely weak supervision[J]. European Conference on Computer Vision, 2014: 640.
|
[7] |
Ren Z, Gao S, Chia L T, et al. Region-based saliency detection and its application in object recognition[J]. IEEE Trans Circuits Syst Video Technol, 2014, 24(5):769.
|
[8] |
Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Trans Pattern Anal Mach Intell, 1998, 20(11):1254.
|
[9] |
Treisman A M, Gelade G. A feature-integration theory of attention[J]. Cogn Psychol, 1980,12(1):97.
|
[10] |
Walther D,Koch C. 2006 Special Issue: Modeling attention to salient proto-objects[J]. Neural Networks, 2006, 19(9):1395.
|
[11] |
Gao D, Vasconcelos N. Bottom-up saliency is a discriminant process[J]. IEEE Int Conf Comput Vis, 2007: 1.
|
[12] |
LIU T, YUAN Z J, SUN J, et al. Learning to detect a salient object[J]. IEEE Trans Pattern Anal Mach Intell, 2011, 33(2):353.
|
[13] |
JIANG H, WANG J, YUAN Z, et al. Salient object detection: A discriminative regional feature integration approach[J]. IEEE Conf Comput Vis Pattern Recognit, 2013: 2083.
|
[14] |
Lu S, Mahadevan V, Vasconcelos N. Learning optimal seeds for diffusion-based salient object detection[J]. IEEE Conf Comput Vis Pattern Recognit, 2014:2790.
|
[15] |
陈琴,朱磊,后云龙,等. 基于深度中心邻域金字塔结构的显著目标检测[J]. 模式识别与人工智能,2020,33(6):496.
|
[16] |
KUEN J, WANG Z, WANG G. Recurrent attentional networks for saliency detection[J]. IEEE Conf Comput Vis Pattern Recognit, 2016: 3668.
|
[17] |
WANG L, LU H, ZHANG P, et al. Saliency detection with recurrent fully convolutional networks[J]. European Conference on Computer Vision, 2016:825.
|
[18] |
Viola P, Jones M. Robust real-time object detection[J]. Int J Comput Vis, 2001(4):34.
|
[19] |
Messom C, Barczak A. Fast and efficient rotated haar-like features using rotated integral images[J]. Proc 2006 Australas Conf Robot Autom, 2006:1.
|
[20] |
Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997,55(1):119.
|
[21] |
Dalal N, Triggs B. Histograms of oriented gradients for human detection[J]. IEEE Conf Comput Vis Pattern Recognit, 2005:886.
|
[22] |
Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Trans Pattern Anal Mach Intell, 2010(9):162.
|
[23] |
Zhou X, Wang D, Krähenbühl P.Objects as points[J]. arXiv,2019: 12.
|
[24] |
Bochkovskiy A, Wang C Y, Liao M. YOLOv4: Optimal speed and accuracy of object detection[J]. arXiv, 2020:10934.
|
[1] |
XIAO Jiong1,XIANG Junliang1,XU Guodong2,WANG Yingchun2,ZHONG Honggang1,ZHAI Qijie1. Thermal simulation of microstructure evolution in surface layer of 0.1 mass%C low carbon steel slab[J]. JOURNAL OF IRON AND STEEL RESEARCH , 2023, 35(3): 255-263. |
[2] |
DAI Zhang-jie, HUANG Cheng-yong, LIU Wei, XIA Jian-chao, YANG Shu-feng, LI Jing-she. Morphology detection of converter mouth based on Mask-RCNN[J]. Iron and Steel, 2023, 58(3): 73-78. |
[3] |
ZHOU Guo-tao, CHEN Jin, HUANG Biao-cai, YAN Wei, LI Jing. Numerical simulation of solidification and heat transfer of Q355B slab during continuous casting[J]. CONTINUOUS CASTING, 2023, 42(2): 43-51. |
[4] |
ZHANG Ya-bing, WANG Dong-xing, ZHAO Li, ZUO Xiao-tan, HUANG Yan, YANG Wei-yong. Solute distribution of 35CrMnSi structural alloy steel billet under the effect of PMO[J]. CONTINUOUS CASTING, 2023, 42(2): 78-83. |
[5] |
SHI Wei-ning. Effect of mold water flow rate in 40Cr billet continuous casting on surface crack[J]. CONTINUOUS CASTING, 2023, 42(2): 84-89. |
[6] |
ZHOU Ye-lian, JIANG Zhong-kuai, ZHANG Fa-bin. Control process and mechanism analysis for tundish fluxes to form the solidified crusts[J]. CONTINUOUS CASTING, 2023, 42(2): 113-119. |
|
|
|
|