Transfer Learning-Based Algorithms for the Detection of Fatigue Crack Initiation Sites: A Comparative Study

Abstract

The identification of fatigue crack initiation sites (FCISs) is routinely performed in the field of engineering failure analyses; this process is not only time-consuming but also knowledge-intensive. The emergence of convolutional neural networks (CNNs) has inspired numerous innovative solutions for image analysis problems in interdisciplinary fields. As an explorative study, we trained models based on the principle of transfer learning using three state-of-the-art CNNs, namely VGG-16, ResNet-101, and feature pyramid network (FPN), as feature extractors, and a faster R-CNN as the backbone to establish models for FCISs detection. The models showed application-level detection performance, with the highest precision reaching up to 95.9% at a confidence threshold of 0.6. Among the three models, the ResNet model exhibited the highest accuracy and lowest training cost. The performance of the FPN model closely followed that of the ResNet model with an advantage in terms of the recall.