Automatic Rail Flaw Localization and Recognition by Featureless Ultrasound Signal Analysis

Sulimova, Valentina; Zhukov, Alexander; Krasotkina, Olga; Mottl, Vadim; Markov, А. A.

doi:10.1007/978-3-319-96136-1_2

Cited by 6 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…38 Researchers have conducted various trials combining texture traits of B-scan images and traditional machine learning classifiers to classify internal rail defects. 39,40 Based on the pattern of human visual perception, researchers designated six textural features known as Tamura texture features: coarseness, contrast, directionality, line-likeness, regularity, and roughness. 38 However, the texture features of images in the industry are not smooth enough to process.…”

Section: Experiments and Discussionmentioning

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

Section: Experiments and Discussionmentioning

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

show abstract

“…The article describes the application of signal processing using neural networks to recognize patterns in measurement data from a defectoscope wagon examining railroad rails using ultrasonic methods. This has also been described in publications [15,16]. The wagon's measurement apparatus uses digital signal processing, enabling the recording of a large data volume.…”

Section: Introductionmentioning

confidence: 99%

Selected aspects of the diagnostic process in rail transport

Chrzan,

Ciszewski,

Nowakowski

2023

Rail Vehicles/Pojazdy Szynowe

View full text Add to dashboard Cite

The article presents selected results of research in the area of reducing the risk of defects in railway infrastructure and traffic control devices. The first part of the article will discuss selected topics used in a defectoscope car for automated ultrasonic rail inspections related to the identification of joints and flaws. A method based on the identification of joints and flaws using a neural network will be presented. The second part of the article will cover research on the automatic collection of diagnostic data from railway traffic control devices. The solutions presented concern a simulator of railway traffic control device malfunctions, from which data is extracted to populate a database of malfunctions and then used in the inference process. The article will present partial results of research on both systems.

show abstract