NDT Method for Weld Defects Based on FMPVit Transformer Model

The primary NDT method for welding defects is the image-based detection. Currently, the best performance for image-based detection is based on the transformer model. However, with its high accuracy, it has many limitations, such as large model parameters, large data sample requirements, and expensive computer resources. This model has a weaker ability to capture local features compared with global features. In this study, an improved and optimized welding defect detection and identification framework named Fast Multi-Path Vision transformer (FMPVit) is proposed based on the transformer model. This model uses a multilayer parallel architecture and enhances the local information capture ability of the model through advanced multiscale convolution feature aggregation and the addition of a new local convolution module. Finally, a validation test is carried out using an open dataset of weld seams. The model is proven to exhibit an evident performance improvement over the mainstream model baseline.

[1]  Changhui Yang,et al.  Cas-VSwin transformer: A variant swin transformer for surface-defect detection , 2022, Comput. Ind..

[2]  Yang Liu,et al.  NDT Method for Line Laser Welding Based on Deep Learning and One-Dimensional Time-Series Data , 2022, Applied Sciences.

[3]  C. Taylor,et al.  Defect Classification and Detection Using a Multitask Deep One-Class CNN , 2022, IEEE Transactions on Automation Science and Engineering.

[4]  Guohua Liu,et al.  DRCDCT-net: a steel surface defect diagnosis method based on a dual-route cross-domain convolution-transformer network , 2022, Measurement Science and Technology.

[5]  Guitang Wang,et al.  Intelligent Welding Defect Detection Model on Improved R-CNN , 2022, IETE Journal of Research.

[6]  D. V. Kiran,et al.  In situ detection of welding defects: a review , 2022, Welding in the World.

[7]  Zhenmin Wang,et al.  Recognition of penetration state in GTAW based on vision transformer using weld pool image , 2022, The International Journal of Advanced Manufacturing Technology.

[8]  P. Biswas,et al.  Current status and development of external energy-assisted friction stir welding processes: a review , 2022, Welding in the World.

[9]  Ying-hong Peng,et al.  Deep learning approach for defective spot welds classification using small and class-imbalanced datasets , 2022, Neurocomputing.

[10]  Sung Ju Hwang,et al.  MPViT: Multi-Path Vision Transformer for Dense Prediction , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Fan Zhang,et al.  Automatic forgery detection for x-ray non-destructive testing of welding , 2021, Welding in the World.

[12]  Lu Yuan,et al.  Mobile-Former: Bridging MobileNet and Transformer , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Lu Yuan,et al.  Focal Self-attention for Local-Global Interactions in Vision Transformers , 2021, ArXiv.

[14]  Matthijs Douze,et al.  XCiT: Cross-Covariance Image Transformers , 2021, NeurIPS.

[15]  Xipeng Qiu,et al.  A Survey of Transformers , 2021, AI Open.

[16]  K. Santosh,et al.  Improved U-Net architecture with VGG-16 for brain tumor segmentation , 2021, Physical and Engineering Sciences in Medicine.

[17]  Zhuowen Tu,et al.  Co-Scale Conv-Attentional Image Transformers , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[18]  Matthijs Douze,et al.  LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[19]  Amjad J. Humaidi,et al.  Review of deep learning: concepts, CNN architectures, challenges, applications, future directions , 2021, Journal of Big Data.

[20]  N. Codella,et al.  CvT: Introducing Convolutions to Vision Transformers , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[21]  Mauricio Araya,et al.  Harnessing the power of CNNs for unevenly-sampled light-curves using Markov Transition Field , 2021, Astron. Comput..

[22]  Stefan Hinz,et al.  Review on Convolutional Neural Networks (CNN) in vegetation remote sensing , 2021, ISPRS Journal of Photogrammetry and Remote Sensing.

[23]  Enhua Wu,et al.  Transformer in Transformer , 2021, NeurIPS.

[24]  Xiang Li,et al.  Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Francis E. H. Tay,et al.  Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[26]  Z. Gizatullin,et al.  Classification of Defects in Welds Using a Convolution Neural Network , 2021, 2021 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus).

[27]  D. Tao,et al.  A Survey on Vision Transformer , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  S. Gelly,et al.  An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale , 2020, ICLR.

[29]  Matthieu Rauch,et al.  Towards defect monitoring for metallic additive manufacturing components using phased array ultrasonic testing , 2020, J. Intell. Manuf..

[30]  J. V. Gemert,et al.  On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Sen Jia,et al.  How Much Position Information Do Convolutional Neural Networks Encode? , 2020, ICLR.

[32]  R. Anand,et al.  Face Recognition and Classification Using GoogleNET Architecture , 2019, SocProS.

[33]  Guangrui Wen,et al.  Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding , 2019, Journal of Manufacturing Processes.

[34]  Bhaumik Vaidya,et al.  CNN based Traffic Sign Classification using Adam Optimizer , 2019, 2019 International Conference on Intelligent Computing and Control Systems (ICCS).

[35]  Dong-Joong Kang,et al.  Convolutional Neural Network Based Surface Inspection System for Non-patterned Welding Defects , 2019, International Journal of Precision Engineering and Manufacturing.

[36]  S. Kwong,et al.  An Underwater Image Enhancement Benchmark Dataset and Beyond , 2019, IEEE Transactions on Image Processing.

[37]  Hongjing Lu,et al.  Deep convolutional networks do not classify based on global object shape , 2018, PLoS Comput. Biol..

[38]  Yi Zhu,et al.  DenseNet for dense flow , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[39]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[40]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[42]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[44]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[45]  Xudong Kang,et al.  Interactformer: Interactive Transformer and CNN for Hyperspectral Image Super-Resolution , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[46]  Stephen Lin,et al.  Swin Transformer: Hierarchical Vision Transformer using Shifted Windows , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[47]  Abhishek Kumar Singh,et al.  ToLeD: Tomato Leaf Disease Detection using Convolution Neural Network , 2020, Procedia Computer Science.