AET-based Pattern Recognition Technique for Rail Defect Detection

Liu, Xiao Zhou; Ni, Yi-Qing; Wu, Wang-Lin; Pei, Yifei; Hou, Yiling; Qin, Da-Yong

doi:10.12783/shm2015/252

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As demonstrated in authors' previous research work, for damage detection purpose, conventional time-frequency methods (e.g. power spectrum density (PSD) analysis, wavelet analysis) are able to identify large rail cracks before fractures at the point rail; 19,20 while detection of smaller cracks or damages may refer to a frequency domain Structural Health Index (SHI) updated under a Bayesian framework. 21 However, beyond damage detection, rail operators are keener on the condition evolvement of rail structures over a period of time before significant cracks literally take place, but both methods cannot well reveal the structural health conditions of rail tracks in a progressive manner using the AE data and are not sensitive enough to identify the early stages of rail deterioration when micro cracks are initializing.…”

Section: Introductionmentioning

confidence: 99%

An acoustic-homologous transfer learning approach for acoustic emission–based rail condition evaluation

Chen

Zhou

et al. 2020

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

This article presents a novel transfer learning approach for evaluating structural conditions of rail in a progressive manner, by using acoustic emission monitoring data and knowledge transferred from an acoustic-related database. Specifically, the low-level layers of a model pre-trained on large audio data are leveraged in our model for feature extraction. Compared with conventional transfer learning approaches that transfer knowledge from models pre-trained on normal images, the proposed approach can handle acoustic emission spectrograms more naturally in terms of both data inner properties and the way of data intaking. The training and testing data used for rail condition evaluation contains two months of acoustic emission recordings, which were acquired from an in situ operating rail turnout with an integrated acoustic emission –based monitoring system. Results show that the evolving stages of rail from intact to critically cracked are successfully revealed using the proposed approach with excellent prediction accuracy and high computation efficiency. More importantly, the study quantitatively shows that audio source data are more relevant to the acoustic emission monitoring data than Image data, by introducing a maximum mean discrepancy metric, and the transfer learning model with smaller maximum mean discrepancy does lead to better performance. As a by-product of the study, it has also been found that the features extracted by the proposed transfer learning model (“bottleneck” features) already exhibit a clustering trend corresponding to the evolving stages of rail conditions even in the training process before any label is annotated, indicating the potential unsupervised learning capability of the proposed approach. Through the study, it is suggested that selecting source data more correspondingly and flexibly would maximize the benefit of transfer learning in structural health monitoring area when facing heterogenous monitoring data under varying practical scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

An acoustic-homologous transfer learning approach for acoustic emission–based rail condition evaluation

Chen

Zhou

et al. 2020

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

show abstract

“…A moving load was exerted on rail segments by a motorized trolley running at a speed of 3 km/h, and the laboratory test showed that wheel rolling noise would not be an obstacle for crack identification and that AE is a promising technique for detecting crack growth in defective in‐service rails. An online AE monitoring system was devised and implemented on a freight railroad, and its capability for fault detection was verified by successful and timely detection of damage (Liu et al., ; Wang et al., ). Some other investigations in connection with AE technique were aimed at rail‐wheel interaction monitoring, including the identification of wheel and rail anomalies (Bruzelius and Mba, ; Thakkar et al., , , ).…”

Section: Introductionmentioning

confidence: 99%

A Bayesian Probabilistic Approach for Acoustic Emission‐Based Rail Condition Assessment

Wang

Liu

2017

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

The investigation described in this article aims at developing a Bayesian‐based approach for probabilistic assessment of rail health condition using acoustic emission monitoring data. It comprises the following three phases: (i) formulation of a frequency‐domain structural health index (SHI), via a linear transformation method, tailored to damage‐sensitive frequency bandwidth; (ii) establishment of data‐driven reference models, using Bayesian regression about the real and imaginary parts of the SHI derived with monitoring data from the intact rail; and (iii) quantitative evaluation of discrimination between the new observations representative of current rail health condition and the baseline model predictions in terms of Bayes factor. If the deviation of the new observations from the predictions is within an acceptable tolerance, no damage is flagged, and the new data are further used to update and refine the reference models. If the observations deviate substantially from the model predictions in a probabilistic sense, damage is signaled, damage severity is quantified, and damage location determined. The proposed approach is examined by using field monitoring data acquired from an instrumented railway turnout, and the coincidence between the assessment results and the actual health conditions demonstrates its effectiveness in damage detection, localization, and quantification.

show abstract

Literature Review

Li¹

2018

Rail Crack Monitoring Using Acoustic Emission Technique

View full text Add to dashboard Cite

AET-based Pattern Recognition Technique for Rail Defect Detection

Cited by 4 publications

References 0 publications

An acoustic-homologous transfer learning approach for acoustic emission–based rail condition evaluation

An acoustic-homologous transfer learning approach for acoustic emission–based rail condition evaluation

A Bayesian Probabilistic Approach for Acoustic Emission‐Based Rail Condition Assessment

Literature Review

Contact Info

Product

Resources

About