Welding defect detection: coping with artifacts in the production line

Visual quality inspection for defect detection is one of the main processes in modern industrial production facilities. In the last decades, artificial intelligence solutions took the place of classic computer vision techniques in the production lines and specifically in tasks that, for their complexity, were usually demanded to human workers yet obtaining similar or greater performance of their counterparts. This work exploits a Deep Neural Network for a smart monitoring system capable of performing accurate quality checks to detect welding defects in fuel injectors during the production stage. The contribution focuses on a novel approach to cope with unforeseen changes in production quality introduced by the alteration of a particular machine or process. Results suggest that pre-filtering could avoid the retraining of custom-designed networks. Moreover, the introduction of a weighting strategy on the confusion matrix allows obtaining good performance estimations even in the case of small and unbalanced datasets. Concerning a specific demanding case of an imbalanced dataset with very few positive examples, the system displayed a 96.30% accuracy on defect classification.

[1]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[2]  Youping Chen,et al.  Classification of surface defects on steel sheet using convolutional neural networks , 2017 .

[3]  Jingjing Zhao,et al.  Study on the application of acoustic emission testing technique in monitoring 16Mn steel welding defects , 2016, 2016 International Conference on Advanced Mechatronic Systems (ICAMechS).

[4]  Xinyu Li,et al.  A semi-supervised convolutional neural network-based method for steel surface defect recognition , 2020, Robotics Comput. Integr. Manuf..

[5]  Kincho H. Law,et al.  Automatic localization of casting defects with convolutional neural networks , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[6]  Guangjun Zhang,et al.  Simulation and controlling for weld shape process in P-GMAW based on fuzzy logic , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[7]  U. Natarajan,et al.  Vision inspection system for the identification and classification of defects in MIG welding joints , 2012 .

[8]  Noah Snavely,et al.  Material recognition in the wild with the Materials in Context Database , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Osama Zahran,et al.  Automatic weld defect identification from radiographic images , 2013 .

[10]  Tegoeh Tjahjowidodo,et al.  In-process virtual verification of weld seam removal in robotic abrasive belt grinding process using deep learning , 2019, Robotics and Computer-Integrated Manufacturing.

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[12]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[13]  Marizan Sulaiman,et al.  Butt welding joints recognition and location identification by using local thresholding , 2018, Robotics and Computer-Integrated Manufacturing.

[14]  Gregory Shakhnarovich,et al.  FractalNet: Ultra-Deep Neural Networks without Residuals , 2016, ICLR.

[15]  Primoz Podrzaj,et al.  The Application of LVQ Neural Network for Weld Strength Evaluation of RF-Welded Plastic Materials , 2016, IEEE/ASME Transactions on Mechatronics.

[16]  Carlo Alberto Avizzano,et al.  A study on picking objects in cluttered environments: Exploiting depth features for a custom low-cost universal jamming gripper , 2020, Robotics Comput. Integr. Manuf..

[17]  Jürgen Schmidhuber,et al.  Highway Networks , 2015, ArXiv.

[18]  Bibhuti Bhusan Biswal,et al.  Advances in weld seam tracking techniques for robotic welding: A review , 2019, Robotics and Computer-Integrated Manufacturing.

[19]  De Xu,et al.  A Vision-Based Self-Tuning Fuzzy Controller for Fillet Weld Seam Tracking , 2011, IEEE/ASME Transactions on Mechatronics.

[20]  Jun Xiong,et al.  Increasing stability in robotic GTA-based additive manufacturing through optical measurement and feedback control , 2019, Robotics Comput. Integr. Manuf..

[21]  M. Ahmadi,et al.  Intelligent Thermal Control of Resistance Welding of Fiberglass Laminates for Automated Manufacturing , 2015, IEEE/ASME Transactions on Mechatronics.

[22]  Carlo Alberto Avizzano,et al.  A Smart Monitoring System for Automatic Welding Defect Detection , 2019, IEEE Transactions on Industrial Electronics.

[23]  Yong Yan,et al.  Review of techniques for on-line monitoring and inspection of laser welding , 2005 .

[24]  Jeffrey P. Mower.  PREP-Mt: predictive RNA editor for plant mitochondrial genes , 2005, BMC Bioinformatics.

[25]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[27]  Jie Li,et al.  Two opposite sides synchronous tracking X-ray based robotic system for welding inspection , 2016, 2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP).

[28]  Euripides G. M. Petrakis,et al.  A survey on industrial vision systems, applications, tools , 2003, Image Vis. Comput..

[29]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Jürgen Schmidhuber,et al.  Steel defect classification with Max-Pooling Convolutional Neural Networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[31]  Kay Chen Tan,et al.  A Generic Deep-Learning-Based Approach for Automated Surface Inspection , 2018, IEEE Transactions on Cybernetics.