Classification of Spot-Welded Joints in Laser Thermography Data Using Convolutional Neural Networks

Spot welding is a crucial process step in various industries. However, classification of spot welding quality is still a tedious process due to the complexity and sensitivity of the test material, which drain conventional approaches to its limits. In this paper, we propose an approach for quality inspection of spot weldings using images from laser thermography data.We propose data preparation approaches based on the underlying physics of spot welded joints, heated with pulsed laser thermography by analyzing the intensity over time and derive dedicated data filters to generate training datasets. Subsequently, we utilize convolutional neural networks to classify weld quality and compare the performance of different models against each other. We achieve competitive results in terms of classifying the different welding quality classes compared to traditional approaches, reaching an accuracy of more than 95 percent. Finally, we explore the effect of different augmentation methods.

[1]  Steven Delrue,et al.  Non-destructive ultrasonic examination of root defects in friction stir welded butt-joints , 2016 .

[2]  Dimitrios Giagopoulos,et al.  Non-destructive testing of welded fatigue specimens , 2020, MATEC Web of Conferences.

[3]  A. S. Sekhar,et al.  Non-destructive Evaluation of Friction Stir Welded Joints by X-ray Radiography and Infrared Thermography , 2014 .

[4]  Rik Van de Walle,et al.  Deep Learning for Infrared Thermal Image Based Machine Health Monitoring , 2017, IEEE/ASME Transactions on Mechatronics.

[5]  Zheng Fan,et al.  Detection of damage in welded joints using high order feature guided ultrasonic waves , 2019, Mechanical Systems and Signal Processing.

[6]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Guang Lin,et al.  Infrared Thermal Imaging-Based Crack Detection Using Deep Learning , 2019, IEEE Access.

[8]  Xinyi Le,et al.  Weld Defect Detection Based on Deep Learning Method , 2019, 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE).

[9]  Koen Faes,et al.  Analysis of the effect of structural defects on the fatigue strength of RFSSW joints using C‐scan scanning acoustic microscopy and SEM , 2019, Fatigue & Fracture of Engineering Materials & Structures.

[10]  Mahmoud Omid,et al.  Intelligent fault diagnosis of cooling radiator based on deep learning analysis of infrared thermal images , 2019, Applied Thermal Engineering.

[11]  Myriam Regattieri Delgado,et al.  Deep neural networks based approach for welded joint detection of oil pipelines in radiographic images with Double Wall Double Image exposure , 2019, NDT & E International.

[12]  Rhys Pullin,et al.  On the use of acoustic emission and digital image correlation for welded joints damage characterization , 2019 .

[13]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Nuno Vasconcelos,et al.  Cascade R-CNN: Delving Into High Quality Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Dietmar Meinel,et al.  Calibration of thermographic spot weld testing with X-ray computed tomography , 2017 .

[16]  Takayuki Okatani,et al.  A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks , 2019, Automation in Construction.

[17]  A. Haji-sheikh,et al.  Heat Conduction Using Green's Function , 1992 .

[18]  Gour Gopal Roy,et al.  X-ray tomography study on porosity in electron beam welded dissimilar copper–304SS joints , 2018 .

[19]  Bart De Schutter,et al.  Deep convolutional neural networks for detection of rail surface defects , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[20]  Chetan Patil,et al.  Investigation of Weld Defects in Similar and Dissimilar Friction Stir Welded Joints of Aluminium Alloys of AA7075 and AA6061 by X-ray Radiography , 2016 .

[21]  Ulrike Siemer,et al.  Einsatz der Thermografie als zerstörungsfreies Prüfverfahren in der Automobilindustrie : Entwicklung einer Ingenieurplattform , 2010 .

[22]  Philipp Myrach,et al.  Examination of Spot Welded Joints with Active Thermography , 2016 .

[23]  Xuefeng Tong,et al.  A Welding Defect Identification Approach in X-ray Images Based on Deep Convolutional Neural Networks , 2019, ICIC.

[24]  F C Cruz,et al.  Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing , 2017, Ultrasonics.

[25]  Salim Chaki,et al.  A review of non-destructive techniques used for mechanical damage assessment in polymer composites , 2018, Journal of Materials Science.