A computer vision based machine learning approach for fatigue crack initiation sites recognition

Wang, S.Y.; Zhang, Pingze; Zhou, Shaoqing; Wei, Dashun; Ding, Fei; Li, F.K.

doi:10.1016/j.commatsci.2019.109259

Cited by 26 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The three models are namely the VGG, ResNet, and FPN models. Remarkable improvements in the detection performance can be seen compared with our previous study on training a similar model from scratch using the DSOD algorithm (Wang et al, 2020). In the previous study, our best result was 22.1% in accurately detecting FCISs with just one bounding box and 24.0% for no valid results (i.e., FN results).…”

Section: Model Accuracysupporting

confidence: 48%

“…In a previous study (Wang et al, 2020), we employed machine learning approaches to recognize fatigue crack initiation sites (FCISs) in fractographic images of metallic compounds. The models were planned to be developed as an automatic FCIS detection module, which can be embedded with the observation systems attached to microscopes for a quick and accurate detection of FCISs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Wang

Guo

2021

Front. Mater.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Model Accuracysupporting

confidence: 48%

Section: Introductionmentioning

confidence: 99%

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

Wang

Guo

2021

Front. Mater.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine vision has been widely used in object positioning, pose detection, motion tracking, and 3D shape reconstruction [1][2][3][4][5]. However, the imaging blur effect of moving targets makes these tasks difficult.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] High‐Precision 3D Reconstruction of Cooperative Markers under Motion Blur

Shi

Tao

Wang

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The application of artificial intelligence and deep learning in the fields of wireless communication, image and speech recognition, and 3D reconstruction has successfully solved some difficult modeling problems. This paper focuses on the high-precision 3D reconstruction of the motion-blurred cooperative markers, including the Chinese character coded targets (CCTs) and the noncoded circular markers. A simulation-based motion-blurred image generation model is constructed to provide sufficient samples for training the convolutional neural network to identify and match the motion-blurred CCTs on the moving object. The blurred noncoded marker matching is performed through homography. The 3D reconstruction of the markers is realized via the optimization of the spatial moving path within the exposure period. The midpoint of the moving path of the markers is taken as the final reconstruction result. The experimental results show that the 3D reconstruction accuracy of the markers with a certain motion blur effect is about 0.08 mm.

show abstract

“…In this study, the AI system for fatigue fracture analysis is proposed and built up for the challenge of fatigue fracture analysis inspired by the previous researches. 18,19 In previous studies, generative adversarial network (GAN) was also adopted to analyze the fatigue fractography images. GAN can learn the features of microcrack and steel surface defect to generate new data samples for the AI-based classifier, 20,21 but the requirement of a large database for training hinders the commercialization application 22 of this network.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence‐assisted fatigue fracture recognition based on morphing and fully convolutional networks

Lyu

Yang

Liang

et al. 2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Fatigue fracture is one of the most common metallic component failure cases in manufacturing industries. The observation on fractography can provide direct evidence for failure analysis. In this study, an image semantic segmentation method based on fully convolutional networks (FCNs) was proposed to figure out the boundary between fatigue crack propagation and fast fracture regions from optical microscope (OM) fractography images. Furthermore, a novel morphing‐based data augmentation method was adopted to enable few‐shot learning of sample images. The proposed framework can successfully segment two categories, namely, the crack propagation and fast fracture regions, thus differentiating the boundary of two regions in one image. This artificial intelligence (AI)‐assisted fatigue analysis architecture can complete the failure analysis procedure in 0.5 s and prove the feasibility of fatigue failure analysis. The segmentation accuracy of self‐developed network achieves 95.4% for the fatigue crack propagation region, as well as 97.2% for the fast fracture region. Not only for semantic segmentation DNN, we also prove that our novel data augmentation method can applied at the instance segmentation DNN, such as mask regional convolutional neural network (mask R‐CNN), one state‐of‐the‐art deep learning network for instance segmentation, to achieve similar accuracy.

show abstract

A computer vision based machine learning approach for fatigue crack initiation sites recognition

Cited by 26 publications

References 12 publications

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

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

[Retracted] High‐Precision 3D Reconstruction of Cooperative Markers under Motion Blur

Artificial intelligence‐assisted fatigue fracture recognition based on morphing and fully convolutional networks

Contact Info

Product

Resources

About