A CNN-Based Crack Analysis Model for Metal Specimens
DOI:
https://doi.org/10.54097/zg2fm992Keywords:
Convolutional Neural Network, strain field, Image Recognition.Abstract
In the field of engineering, the combination of deep learning and traditional simulation has become a research hotspot. In healthy structure monitoring problems, strain sensors are spaced and spatially arranged to collect strains. However, methods such as strain gauges can only capture single-point strains, and in many cases these more discrete strain information is insufficient to determine the damage of the target. In this paper, we combine the strain field with deep learning methods to propose a novel damage detection method based on strain image inversion to perform crack information of workpieces. The method defines the type and location of cracks on the specimen as labels, a large number of simulated strain images as datasets, and uses CNN networks to train the model. The results show that the obtained crack inversion model for metal specimens can achieve 93.99% accuracy.
Downloads
References
Katunin A, Dragan K, Dziendzikowski M. Damage identification in aircraft composite structures: A case study using various non-destructive testing techniques [J]. Composite structures, 2015, 127: 1 - 9.
Capriotti M, Kim H E, Lanza di Scalea F, et al. Non-Destructive inspection of impact damage in composite aircraft panels by ultrasonic guided waves and statistical processing [J]. Materials, 2017, 10 (6): 616.
Liang T, Ren W, Tian G Y, et al. Low energy impact damage detection in CFRP using eddy current pulsed thermography [J]. Composite Structures, 2016, 143: 352 - 361.
Lin M, Guo S, He S, et al. Structure health monitoring of a composite wing based on flight load and strain data using deep learning method [J]. Composite Structures, 2022, 286: 115305.
Yin F, Ye D, Zhu C, et al. Stretchable, highly durable ternary nanocomposite strain sensor for structural health monitoring of flexible aircraft [J]. Sensors, 2017, 17 (11): 2677.
He K, Gkioxari G, Dollár P, et al. Mask r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2961 - 2969.
Gang Z, Jingyu H U, Wenlei X, et al. A mask R-CNN based method for inspecting cable brackets in aircraft [J]. Chinese Journal of Aeronautics, 2021, 34 (12): 214 - 226.
Doğru A, Bouarfa S, Arizar R, et al. Using convolutional neural networks to automate aircraft maintenance visual inspection [J]. Aerospace, 2020, 7 (12): 171.
Brandoli B, de Geus a R, Souza J R, et al. Aircraft fuselage corrosion detection using artificial intelligence [J]. Sensors, 2021, 21 (12): 4026.
Wang Y, Luo Q, Xie H, et al. Digital image correlation (DIC) based damage detection for CFRP laminates by using machine learning based image semantic segmentation [J]. International Journal of Mechanical Sciences, 2022, 230: 107529.
Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-resnet and the impact of residual connections on learning [C]//Proceedings of the AAAI conference on artificial intelligence. 2017, 31 (1).
He F, Liu T, Tao D. Why resnet works? residuals generalize [J]. IEEE transactions on neural networks and learning systems, 2020, 31 (12): 5349 - 5362.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
