A channel attention based deep neural network for automatic metallic corrosion detection

Sheng, Zhang; Deng, Xinling; Lu, Yue; Hong, Shaozheng; Kong, Zhengyi; Peng, Yongli; Luo, Ye

doi:10.1016/j.jobe.2021.103046

Cited by 19 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We then classify them as HIGH, MEDIUM, and LOW based on the severity of corrosion present on the surface of the sample. A similar classification of corroded samples has been performed by Bastian et al [22], Soares et al [23], Zhang et al [24], and Munawar et al [25]. All the aforementioned experiments involve classification into 4 levels: no corrosion, low corrosion, medium corrosion, and high corrosion.…”

Section: Introductionmentioning

confidence: 77%

Corrosion characterization of engine connecting rods using fringe projection profilometry and unsupervised machine learning

Lakshman S,

Delzendehrooy,

Balasubramaniam

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The consequences associated with corrosion, a global industrial peril, cost an estimated $ 2.5 trillion annually to inspect, rectify, and prevent. In addition to significant economic losses, corrosion-induced failure of critical components in transport systems, like automobiles, may also lead to loss of human life. Hence, it is essential to eradicate corrosion in its early stages. The most vital automobile component is its engine, whose failure can cause fatal accidents. Regular quality inspection and maintenance by skilled personnel is essential to prevent this. Automating this task will address this domain's personnel shortage while mitigating the risk of human error. To enable the performance of this task without the need for human intervention, we determine the morphological parameters affected by corrosion in automotive engine components, namely connecting rods, using Fringe Projection Profilometry (FPP), a high-speed 3D profiling technique capable of achieving sub-millimeter accuracy. We then perform classification using k-means clustering into low, medium, and high corrosion bands, based on the parameters obtained from 3D imaging. The model was able to achieve a high accuracy of 88.57%. The accuracy was determined by considering the visual classification performed by a Material Science Expert as the ground truth.

show abstract

Section: Introductionmentioning

confidence: 77%

Corrosion characterization of engine connecting rods using fringe projection profilometry and unsupervised machine learning

Lakshman S,

Delzendehrooy,

Balasubramaniam

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In the research of deep learning algorithms, the channel attention (CA) mechanism is a resource allocation mechanism that can make the model training of neural network focus on the important features of the image and improve the efficiency and accuracy of the neural network. Each channel of a feature map is a feature detector, and the channel attention mechanism pays different attention to different image channels [45]. The channel attention module is shown in Figure 5.…”

Section: Channel Attentionmentioning

confidence: 99%

Intelligent Identification and Prediction Mineral Resources Deposit Based on Deep Learning

Gao,

Wang,

Zhang

et al. 2023

Sustainability

View full text Add to dashboard Cite

In recent years, the intelligent identification and prediction of ore deposits based on deep learning algorithm and image processing technology has gradually become one of the main research frontiers in the field of geological and metallogenic prediction. However, this method also has many problems that need to be solved. For example: (1) There are very few trainable image samples containing mineral point labels; (2) the geological image features are small and irregular, and the image similarity is high; (3) it is difficult to calculate the influence of different geological prospecting factors on ore mineralization. Based on this, this paper constructs a deep learning network model multiscale feature attention framework (MFAF) based on geoimage data. The results show that the MFCA-Net module in the MFAF model can solve the problem of scarce mine label images to a certain extent. In addition, the channel attention mechanism SE-Net module can quantify the difference in influence of different source factors on mineralization. The prediction map is obtained by applying the MFAF model in the study of deposit identification and prediction in the research area of the southern section of the Qin-hang metallogenic belt. The experimental results show that the areas numbered 5, 9, 16, 28, 34, 41, 50, 72, 74, 75, 80, 97, 101, 124, and 130 have great metallogenic potential and this method would be a promising tool for metallogenic prediction. A large number of experimental results show that this method has obvious advantages over other state-of-the-art methods in the prediction of prospecting target areas, and the prediction effect in the samples with mines is greatly improved. The multi-scale feature fusion and attention mechanism MFAF in this paper can provide a new way of thinking for geologists in mineral exploration. The research of this paper also provides resource guarantees and technical support for the sustainable exploitation of mineral resources and the sustainable growth of society and economy.

show abstract

“…Some already developed model architectures, such as Faster RCNN [ 19 , 20 ] and Mask RCNN [ 21 ], have been used by researchers to detect corrosion in the structural elements of steel bridges for this reason. Other deep convolution neural networks, such as ResNet50 [ 22 , 23 ], AlexNet [ 23 ], VGG-16 [ 23 ], and GoogleNet [ 23 ], have been used to detect metallic corrosion. AlexNet outperformed the other models in terms of correct corroded image predictions; however, the training dataset was imbalanced, and the proportion of damage in the test dataset was not reported.…”

Section: Introductionmentioning

confidence: 99%

Autonomous Image-Based Corrosion Detection in Steel Structures Using Deep Learning

Das,

Dorafshan,

Kaabouch

2024

Sensors

View full text Add to dashboard Cite

Steel structures are susceptible to corrosion due to their exposure to the environment. Currently used non-destructive techniques require inspector involvement. Inaccessibility of the defective part may lead to unnoticed corrosion, allowing the corrosion to propagate and cause catastrophic structural failure over time. Autonomous corrosion detection is essential for mitigating these problems. This study investigated the effect of the type of encoder–decoder neural network and the training strategy that works the best to automate the segmentation of corroded pixels in visual images. Models using pre-trained DesnseNet121 and EfficientNetB7 backbones yielded 96.78% and 98.5% average pixel-level accuracy, respectively. Deeper EffiecientNetB7 performed the worst, with only 33% true-positive values, which was 58% less than ResNet34 and the original UNet. ResNet 34 successfully classified the corroded pixels, with 2.98% false positives, whereas the original UNet predicted 8.24% of the non-corroded pixels as corroded when tested on a specific set of images exclusive to the investigated training dataset. Deep networks were found to be better for transfer learning than full training, and a smaller dataset could be one of the reasons for performance degradation. Both fully trained conventional UNet and ResNet34 models were tested on some external images of different steel structures with different colors and types of corrosion, with the ResNet 34 backbone outperforming conventional UNet.

show abstract

A channel attention based deep neural network for automatic metallic corrosion detection

Cited by 19 publications

References 14 publications

Corrosion characterization of engine connecting rods using fringe projection profilometry and unsupervised machine learning

Corrosion characterization of engine connecting rods using fringe projection profilometry and unsupervised machine learning

Intelligent Identification and Prediction Mineral Resources Deposit Based on Deep Learning

Autonomous Image-Based Corrosion Detection in Steel Structures Using Deep Learning

Contact Info

Product

Resources

About