AUTHOR=Sekhar  Ravi , Sharma  Deepak , Shah  Pritesh 

TITLE=Intelligent Classification of Tungsten Inert Gas Welding Defects: A Transfer Learning Approach

JOURNAL=Frontiers in Mechanical Engineering

VOLUME=Volume 8 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/mechanical-engineering/articles/10.3389/fmech.2022.824038

DOI=10.3389/fmech.2022.824038

ISSN=2297-3079

ABSTRACT=Automated and intelligent classification of defects can improve productivity, quality and safety of the numerous welded components used in industries. This paper presents a transfer learning approach for accurate classification of tungsten inert gas (TIG) welding defects while joining stainless steel parts. In this approach, eight pretrained deep learning models (VGG16, VGG19, ResNet50, InceptionV3, InceptionResNetV2, Xception, MobileNetV2, DenseNet169) were explored to classify welding images into two class (good weld/bad weld) and multi class (good weld/burn through/contamination/lack of fusion/lack of shielding gas/high travel speed) classifications. Moreover, four optimizers (SGD, Adam, Adagrad, Rmsprop) were applied separately to each of the deep learning models to maximize prediction accuracies. All models were evaluated based on testing accuracy, precision, recall, F1 scores as well as training/validation losses and accuracies over successive training epochs. Primary results show that the VGG19-SGD and DenseNet169-SGD architectures attained the best testing accuracies for two class (99.69 %) and multi class (97.28 %) defects classifications respectively. For 'burn through', 'contamination' and 'high travel speed' defects, most deep learning models ensured productivity over quality assurance of TIG welded joints. On the other hand, weld quality was promoted over productivity during classification of 'lack of fusion' and 'lack of shielding gas' defects. Thus, transfer learning methodology can help boost productivity and quality of welded joints by accurate classification of good and bad welds.