Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning
Welding is a vital joining process; however, occurrences of weld defects often degrade the quality of the welded part. The risk of occurrence of a variety of defects has led to the development of advanced weld defects detection systems such as automated weld defects detection and classification. The present work is a novel approach that proposes and investigates a unique image-centered method based on a deep learning model trained by a small X-ray image dataset. A data augmentation method able to process images on the go was used to offset the limitation of the small X-ray dataset. Fine-tuned transfer learning techniques were used to train two convolutional neural network based architectures with VGG16 and ResNet50 as the base models for the augmented sets. Out of the networks we fine-tuned, VGG16 based model performed well with a relatively higher average accuracy of 90%. Even though the small dataset was spread across 15 different classes in an unbalanced way, the learning curves showed acceptable model generalization characteristics.
Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning
Welding is a vital joining process; however, occurrences of weld defects often degrade the quality of the welded part. The risk of occurrence of a variety of defects has led to the development of advanced weld defects detection systems such as automated weld defects detection and classification. The present work is a novel approach that proposes and investigates a unique image-centered method based on a deep learning model trained by a small X-ray image dataset. A data augmentation method able to process images on the go was used to offset the limitation of the small X-ray dataset. Fine-tuned transfer learning techniques were used to train two convolutional neural network based architectures with VGG16 and ResNet50 as the base models for the augmented sets. Out of the networks we fine-tuned, VGG16 based model performed well with a relatively higher average accuracy of 90%. Even though the small dataset was spread across 15 different classes in an unbalanced way, the learning curves showed acceptable model generalization characteristics.
Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning
Int J Interact Des Manuf
Kumaresan, Samuel (Autor:in) / Aultrin, K. S. Jai (Autor:in) / Kumar, S. S. (Autor:in) / Anand, M. Dev (Autor:in)
01.12.2023
12 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Convolutional neural networks , Defects detection , Machine learning , Welding , Non-destructive testing , Machine vision Engineering , Engineering, general , Engineering Design , Mechanical Engineering , Computer-Aided Engineering (CAD, CAE) and Design , Electronics and Microelectronics, Instrumentation , Industrial Design
Deep Active Learning for Civil Infrastructure Defect Detection and Classification
| British Library Conference Proceedings | 2017