Rail Defect Detection Method Based on BP Neural Network

Xu, Qinhua; Zhao, Qinjun; Wang, Liguo; Shen, Tao

doi:10.1007/978-981-15-8462-6_8

Cited by 4 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the results showed the efficiency and the robustness of the proposed configuration in the detection of cracks regardless its size, orientation and location. As future work, in order to realize the automatic recognition of rail defect detection data by computer, the existing methods are mainly to select the features of rail flaw detection data manually, and then use relevant algorithms to recognize and classify from the perspective of image [12][13][14][15]. On the other hand, the effects of detection speed on eddy current testing (ECT) signals need to be investigated as well as the quantitative evaluation method of rail surface cracks at different speeds [16].…”

Section: Discussionmentioning

confidence: 99%

Eddy Current Probe Configuration for Full Rail Top Surface Inspection

Aouf¹,

Bouchala²,

Abdou³

et al. 2021

I2M

View full text Add to dashboard Cite

In this paper, we have carried out an experimental study of the detection of top rail surface cracks. Firstly, we have highlighted the inability to inspect the entire rail head surface by a single sensor with a single scan. To overcome this inspection inability, we have proposed a multisensor system composed of three differential probes arranged within a specific configuration. The yielded results showed the efficiency and the robustness of the proposed configuration in the detection of cracks regardless its size, orientation and location.

show abstract

Section: Discussionmentioning

confidence: 99%

Eddy Current Probe Configuration for Full Rail Top Surface Inspection

Aouf¹,

Bouchala²,

Abdou³

et al. 2021

I2M

View full text Add to dashboard Cite

show abstract

“…The traditional method extracts ultrasonic image features by manually designing a rail ultrasonic image data feature extractor and then classifying rail defects using machine learning classifiers. 22–24 Researchers have attempted to customize feature extraction of B-scan images and integrate them with machine learning techniques to classify rail defects. Wu 22 extracted the color, contour, and other features in the algorithm and put them into the perceptron model for rail defect classification.…”

Section: Literature Reviewmentioning

confidence: 99%

Artificial intelligence-aided detection of rail defects based on ultrasonic imaging data

Li,

Wang,

Qin

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part F:

View full text Add to dashboard Cite

Railroads are one of society’s fundamental infrastructures, facilitating the transportation of passengers and goods over vast distances. Rail status data is immensely important for ensuring the safe and efficient operation of railroad networks. However, analyzing ultrasonic inspection data is a labor-intensive process and relies heavily on the expertise of experienced inspectors. To detect internal defects of the rail accurately and automatically, this paper proposes a customized image recognition method based on a convolutional neural network with limited B-scan rail image data collected within the industry. The proposed method uses EfficientNet-b7 as the backbone network to fully extract the B-scan rail image data features. With the help of transfer learning and data augmentation techniques, the backbone network is substantially enhanced so that it can understand high-level features of the object without being trained with large-scale B-scan image data. We establish a real-world internal rail defect dataset with 280 B-scan images and test our proposed method. The results reveal that the highest accuracy of the other mainstream CNN-based methods is 76.25% and the accuracy of the traditional method based on a support vector machine classifier trained with Tamura texture and LBP features is 60.00%. Our proposed EfficientNet-b7 model classifies rail defect B-scan images with an accuracy of 85.00%, precision of 84.71%, and recall of 85.00%. Compared to other rail internal defect detection methods, this method is more accurate. With the help of transfer learning and data augmentation, our proposed method achieves better performance and requires less data.

show abstract