铆接铝合金板铆钉失效缺陷检测方法研究

doi:10.19562/j.chinasae.qcgc.2024.02.019

Abstract

Abstract:

For the difficulties in feature extraction and low recognition rate in defect types and grades of rivet on aluminum alloy plates for car body， the diagnosis model and detection method for rivet failure defects are proposed based on the Gaussian convolutional deep belief network and long short-term memory network. Firstly， the specimens are designed for five types of fracture defects and an automatic detection system is constructed. The planned path and pose of the probe are set to lower lift-off effect on signals. Secondly， the dual network fusion diagnostic model is designed to extract and learn the multi-dimensional defect feature information， solving the problem of extracting defect information represented by temporal variation characteristics and spatial distribution state in detection curves. The experiments results show that the optimized model has an average recognition rate of 99.85%， with an increase of 14.54% compared with that of the traditional convolutional network and single deep belief network. The model has better compatibility and robustness， which can realize online diagnosis of internal defects of rivets.

Key words: defects in rivet, detection system, pattern recognition, feature fusion

Liang Liu,Ying Zhang,Chenyang Shi,Xinhua Zhao,Xianming Meng,Zengchang Liu. Research on Detection Method of Failure Defects of Rivet on Riveted Aluminum Alloy Plates[J].Automotive Engineering, 2024, 46(2): 366-374.

Figures/Tables 24

References 23

1	LI D Z， CHRYSANTHOU A， PATEL I， et al. Self-piercing riveting-a review［J］. International Journal of Advanced Manufacturing Technology， 2017， 92： 1777-1824.
2	岁波，都东，常保华，等. 轻型车身自冲铆连接技术的发展［J］. 汽车工程， 2006， 28（1）： 85-89.
	SUI B，DU D，CHANG B H，et al. A review on the development of self-piercing riveting technology for lightweight vehicle body［J］. Automotive Engineering， 2006， 28（1）： 85-89.
3	李永兵，马运五，楼铭，等. 轻量化多材料汽车车身连接技术进展［J］. 机械工程学报， 2016， 52（24）： 1-23.
	LI Y B， MA Y W， LOU M， et al. Advances in welding and joining processes of multi-material lightweight car body［J］. Journal of Mechanical Engineering， 2016， 52（24）： 1-23.
4	CHERAGHI S H. Effect of variations in the riveting process on the quality of riveted joints［J］. The International Journal of Advanced Manufacturing Technology， 2008， 39（11）： 1144-1155.
5	ECKSTEIN J， ROOS E， ROLL K， et al. Experimental and numerical investigations to extend the process limits in self-pierce riveting［J］. American Institute of Physics， 2007， 907（1）： 279-286.
6	LIU F F， LIU S P， ZHANG Q L， et al. Quantitative non-destructive evaluation of drilling defects in SiCf/SiC composites using low-energy X-ray imaging technique［J］. NDT & E International， 2020， 116： 102364.
7	LE M， KIM J， KIM S， et al. B-scan ultrasonic testing of rivets in multilayer structures based on short-time Fourier transform analysis［J］. Measurement， 2018， 128： 495-503.
8	HE Y Z， LUO F L， PAN M C. Pulsed eddy current technique for defect detection in aircraft riveted structures［J］. NDT & E International， 2010， 43（2）： 176-181.
9	JANOVEC M， SMETANA M， BUGAJ M. Eddy current array inspection of Zlin 142 fuselage riveted joints［J］. Transportation Research Procedia， 2019， 40： 279-286.
10	武新军，张卿，沈功田. 脉冲涡流无损检测技术综述［J］. 仪器仪表学报， 2016， 37（8）： 1698-1712.
	WU X J， ZHANG Q， SHEN G T. Review on advances in pulsed eddy current nondestructive testing technology［J］. Chinese Journal of Scientific Instrument， 2016， 37（8）： 1698-1712.
11	胡祥超. 集成涡流无损检测系统设计与关键技术研究［D］. 长沙：国防科学技术大学， 2012.
	HU X C. Research on key technologies and design of integrated eddy current nondestructive testing system［D］. Changsha： National University of Defense Technology， 2012.
12	FU Y W， LEI M L， LI Z X， et al. Lift-off effect reduction based on the dynamic trajectories of the received-signal fast Fourier transform in pulsed eddy current testing［J］. NDT & E International， 2017（87）： 85-92.
13	SHAO H D， JIANG H K， ZHANG H Z， et al. Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing［J］. Mechanical Systems and Signal Processing， 2018， 100： 743-765.
14	YAN Hao， PENG Y M， SHANG W J， et al. Open-circuit fault diagnosis in voltage source inverter for motor drive by using deep neural network［J］. Engineering Applications of Artificial Intelligence， 2023， 120： 105866.
15	TERCAN H， MEISEN T. Machine learning and deep learning based predictive quality in manufacturing： a systematic review［J］. Journal of Intelligent Manufacturing， 2022， 33： 1879-1905.
16	XIE Q， LU D N， HUANG A Y， et al. RRCNet： rivet region classification network for rivet flush measurement based on 3-D point cloud［J］. IEEE Transactions on Instrumentation and Measurement， 2020， 70： 1-12.
17	AMOSOV O S， AMOSOVA S G， IOCHKOV I O. Detection and recognition of manufacturing defects of rivet joints by their video images using deep neural networks［C］. International Multi-Conference on Industrial Engineering and Modern Technologies （FarEastCon）， 2019： 1-4.
18	AMOSOV O S， AMOSOVA S G， IOCHKOV I O. Defects detection and recognition in aviation riveted joints by using ultrasonic echo signals of non-destructive testing［J］. IFAC-PapersOnLine， 2021， 54（1）： 484-489.
19	EBRAHIMKHANLOU A， DUBUC B， SALAMONE S. A generalizable deep learning framework for localizing and characterizing acoustic emission sources in riveted metallic panels［J］. Mechanical Systems and Signal Processing， 2019， 130： 248-272.
20	LEE H， GROSSE R， RANGANATH R， et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations［C］. Proceedings of the 26th Annual International Conference on Machine Learning， 2009： 609-616.
21	SALAKHUTDINOV R， HINTON G. Using deep belief nets to learn covariance kernels for gaussian processes［C］. Proceedings of Advances in Neural Information Processing Systems， 2008， 20： 1249-1256.
22	SHAO H D， JIANG H K， ZHANG H Z， et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network［J］. IEEE Transactions on Industrial Electronics， 2018， 65（3）： 2727-2736.
23	HOCHREITER S， SCHMIDHUBER J. Long short-term memory［J］. Neural Computation， 1997， 9（8）： 1735-1780.

铆钉缺陷类型	铆钉缺陷分布特征
钉脚一字裂纹	圆柱面底部裂纹呈现近似一字型分布
钉脚十字裂纹	圆柱面底部裂纹呈现近似十字型分布
轴向（分布）断裂	圆柱面沿轴向产生断裂的区域性缺损
径向（分布）断裂	钉帽根部及圆柱面沿径向产生断裂的区域性缺损
横向截面断裂	圆柱面横向截面整体产生腐蚀型缺损

缺陷类型	断裂尺寸/mm	断裂区域（长×宽）/mm²	缺陷等级
钉脚一字裂纹钉脚一字裂纹钉脚一字裂纹	长度0.5~1		轻度
	长度1~3		中度
	长度3~4		严重
钉脚十字裂纹钉脚十字裂纹钉脚十字裂纹	长度0.5~1		轻度
	长度1~3		中度
	长度3~4		严重
轴向（分布）断裂轴向（分布）断裂		（1~2）×（1~2）	中度
轴向（分布）断裂轴向（分布）断裂		（2~4）×（2~4）	严重
径向（分布）断裂径向（分布）断裂	深度0.5~1		轻度
径向（分布）断裂径向（分布）断裂	深度1~2		中度
横向截面断裂横向截面断裂	高度1~3		中度
横向截面断裂横向截面断裂	高度3~4		严重

缺陷类型	缺陷等级	训练样本数	测试样本数	标签
无缺陷	无	248	89	1
钉脚一字裂纹	轻度	212	74	2
	中度	210	75	3
	严重	201	72	4
钉脚十字裂纹	轻度	212	74	5
	中度	210	75	6
	严重	201	72	7
轴向分布断裂	中度	210	75	8
轴向分布断裂	严重	201	72	9
横向截面断裂	中度	210	75	10
横向截面断裂	严重	201	72	11
径向分布断裂	轻度	212	74	12
径向分布断裂	中度	212	74	13

GCRBM结构层数	第1层	第2层
卷积核个数	9	16
卷积核大小	3×3	3×3
池化大小	2×2	2×2
训练批次	10	10
学习率	0.005	0.001
权重更新动量	0.9	0.9

[1]	Lei Ma, Shunqing Yang, Huanhuan Wang, Jiachen Zhai, Jianao Xu. Lightweight Object Detection Algorithm Based on Image Saliency Feature Fusion [J]. Automotive Engineering, 2024, 46(1): 84-91.
[2]	Yingxiang Cui, Youtong Zhang, Hongqian Wei. An Intrusion Detection System for In-vehicle CAN Network Based on Sample Entropy [J]. Automotive Engineering, 2023, 45(7): 1184-1191.
[3]	Yuxin Guan,Haojie Ji,Zhe Cui,He Li,Liwen Chen. An Overview of Intrusion Detection Methods for In-Vehicle CAN Network of Intelligent Networked Vehicles [J]. Automotive Engineering, 2023, 45(6): 922-935.
[4]	Long Chen,Chen Yang,Yingfeng Cai,Hai Wang,Yicheng Li. Pedestrian Crossing Intention Prediction Method Based on Multimodal Feature Fusion [J]. Automotive Engineering, 2023, 45(10): 1779-1790.
[5]	Teng Cheng,Lei Sun,Dengchao Hou,Qin Shi,Junning Zhang,Jiong Chen,He Huang. Multi-level and Multi-modal Target Detection Based on Feature Fusion [J]. Automotive Engineering, 2021, 43(11): 1602-1610.
[6]	Liu Zhiqiang, Zhang Guanglin, Zheng Yuewen, He Xiaoyu. Multi-Sensor Fusion Method Based on Checking Unscented Information Fusion Algorithm [J]. Automotive Engineering, 2020, 42(7): 854-859.
[7]	Zhang Yangyang, Jia Yunxian, Wu Weiyi, Su Xiaobo, Shi Xiaowen. Application of Probabilistic Neural Network to Typical Fault Diagnosis of Vehicle Gearbox [J]. Automotive Engineering, 2020, 42(7): 972-977.
[8]	Chen Wenqiang, Xiong Hui, Li Keqiang, Li Xiaofei& Zhang Dezhao. Concurrent Pedestrian and Cyclist Detection Based on Deep Neural Networks [J]. , 2018, 40(6): 726-.

Research on Detection Method of Failure Defects of Rivet on Riveted Aluminum Alloy Plates

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 24

References 23

Related Articles 8

Metrics

Comments

Recommended 10

标签	识别率/%
标签	GCDBN	LSTM	GCDBN- LSTM	GCDBN- Bi-LSTM	PSO+GCDBN- Bi-LSTM
1	100	100	100	100	100
2	90.54	81.08	100	100	100
3	100	100	96	98.67	100
4	95.83	51.39	95.83	95.83	100
5	87.84	79.73	100	100	98.65
6	88	100	100	100	100
7	100	55.56	95.83	95.83	100
8	98.67	85.33	100	100	100
9	100	100	100	100	100
10	88	97.33	100	100	100
11	100	100	100	100	100
12	98.65	87.84	100	100	100
13	100	100	100	100	100
总识别率	96	87.87	99	99.28	99.9