A Comparison of Deep Learning Techniques for Corrosion Detection

Bolton, Tom; Bass, Julian M.; Gaber, Tarek

doi:10.1007/978-3-031-20601-6_18

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, they primarily operate within a supervised framework, which poses challenges when accessing signals or images from compromised structures that are not easily accessible. In particular, deep learning ANN models that rely on images [18] face practical difficulties in confined spaces like the inner sections of generators. Moreover, hydropower plants experience significant variations in environmental conditions (temperature, humidity) and operational conditions (loads) throughout their operational phases.…”

Section: Related Work On Corrosion Detectionmentioning

confidence: 99%

An Artificial Intelligence and Industrial Internet of Things-Based Framework for Sustainable Hydropower Plant Operations

Fera,

Spandonidis

2024

Smart Cities

View full text Add to dashboard Cite

Hydropower plays a crucial role in supplying electricity to developed nations and is projected to expand its capacity in various developing countries such as Sub-Saharan Africa, Argentina, Colombia, and Turkey. With the increasing demand for sustainable energy and the emphasis on reducing carbon emissions, the significance of hydropower plants is growing. Nevertheless, numerous challenges arise for these plants due to their aging infrastructure, impacting both their efficiency and structural stability. In order to tackle these issues, the present study has formulated a specialized real-time framework for identifying damage, with a particular focus on detecting corrosion in the conductors of generators within hydropower plants. It should be noted that corrosion processes can be highly complex and nonlinear, making it challenging to develop accurate physics-based models that capture all the nuances. Therefore, the proposed framework leverages autoencoder, an unsupervised, data-driven AI technology with the Mahalanobis distance, to capture the intricacies of corrosion and automate its detection. Rigorous testing shows that it can identify slight variations indicating conductor corrosion with over 80% sensitivity and a 5% false alarm rate for ‘medium’ to ‘high’ severity damage. By detecting and resolving corrosion early, the system reduces disruptions, streamlines maintenance, and mitigates unscheduled repairs’ negative effects on the environment. This enhances energy generation effectiveness, promotes hydroelectric facilities’ long-term viability, and fosters community prosperity.

show abstract

Section: Related Work On Corrosion Detectionmentioning

confidence: 99%

An Artificial Intelligence and Industrial Internet of Things-Based Framework for Sustainable Hydropower Plant Operations

Fera,

Spandonidis

2024

Smart Cities

View full text Add to dashboard Cite

show abstract

“…The authors of [ 24 ] developed a shallow convolutional neural network to predict corrosion in visual images using sliding windows of different sizes and scored a 98% recall value for a window size of 128 × 128 megapixels. Bolton et al [ 25 ] tested five image classification models to detect corrosion in steel structures by initializing the random weights, including VGG16, ResNet50, AlexNet, Bastian Net, and ZF Net. VGG16 and ResNet50 were used in both transfer learning and fully trained modes.…”

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

Application of Machine Learning and Deep Learning Techniques for Corrosion and Cracks Detection in Nuclear Power Plants: A Review

Allah,

Toor,

Shams

et al. 2024

Arab J Sci Eng

View full text Add to dashboard Cite

A Comparison of Deep Learning Techniques for Corrosion Detection

Cited by 3 publications

References 18 publications

An Artificial Intelligence and Industrial Internet of Things-Based Framework for Sustainable Hydropower Plant Operations

An Artificial Intelligence and Industrial Internet of Things-Based Framework for Sustainable Hydropower Plant Operations

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

Application of Machine Learning and Deep Learning Techniques for Corrosion and Cracks Detection in Nuclear Power Plants: A Review

Contact Info

Product

Resources

About