A new rail crack detection method using LSTM network for actual application based on AE technology

Zhang, Xin; Zou, Zhongxian; Wang, Kangwei; Hao, Qing; Wang, Yan; Shen, Yi; Hu, Hengshan

doi:10.1016/j.apacoust.2018.08.020

Cited by 38 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, wheel-rail contact rolling noise often leads to low signal-to-noise ratio (SNR) of AE signal; various advanced denoising algorithms have been developed to increase the SNR of rail AE signal, proving that it is possible to extract rail damage information in the field environment. [140][141][142][143][144] Furthermore, it is still a challenge to make a quantitative assessment of rail defect based on the AE technology, highlighting the need for more research in this area. 145…”

Section: Short-range Rail Ndt Technologiesmentioning

confidence: 99%

See 1 more Smart Citation

Guided wave–based rail flaw detection technologies: state-of-the-art review

Huat

Koh

et al. 2021

Structural Health Monitoring

View full text Add to dashboard Cite

The unavoidable increase in train speed and load, as well as the aging of railway facilities, is requiring more and more attention to rail defects detection. As a promising tool for rail, in-service high-speed inspection, guided wave–based detection technologies have been developed in succession by researches in the past two decades. However, there is a lack of a systematic review on the developments and performances of these technologies. This article reviews ultrasonic rail inspection methods comprehensively with the focus on the state-of-the-art technologies based on guided wave. Different excitation options, including train wheel, electromagnetic acoustic transducer, pulsed laser, air-coupled, and contact piezoelectric transducer, are described, respectively, along with their inspection sensitivities, regions, and potential speeds. Finally, future challenges and prospects are discussed to a certain extent to provide references for researchers in this area.

show abstract

Section: Short-range Rail Ndt Technologiesmentioning

confidence: 99%

“…Insensitive to surface defects less than 2 mm deep. Low ultrasound conversion efficiency 15 km/h 181,182 Pulse repetition frequency Crack initiation and propagation [136][137][138][139][140][141][142][143][144][145] In-service monitoring. Unnecessary artificial excitation.…”

Section: Concluding Remarks and Challenging Issuesmentioning

confidence: 99%

Guided wave–based rail flaw detection technologies: state-of-the-art review

Huat

Koh

et al. 2021

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…CNN, transfer learning [64] CNN, transfer learning, Bayesian optimization to tune hyperparameters [100] CNN-LSTM [87,103,107] Faster R-CNN [78,88] Faster R-CNN + CNN [73] FastNet, convolutional network-based [120] Fine-grained bilinear CNNs model [70] FCN [119] GAN for CNN [115] Inception-ResNet-v2 & CNN [113] LSTM-RNN [63,71,99] Mask R-CNN…”

Section: Review Of Rail Track Condition Monitoring With Deep Learningmentioning

confidence: 99%

Rail track condition monitoring: a review on deep learning approaches

Ji¹,

Woo²,

Wong³

et al. 2021

View full text Add to dashboard Cite

Rail track is a critical component of rail systems. Accidents or interruptions caused by rail track anomalies usually possess severe outcomes. Therefore, rail track condition monitoring is an important task. Over the past decade, deep learning techniques have been rapidly developed and deployed. In the paper, we review the existing literature on applying deep learning to rail track condition monitoring. Potential challenges and opportunities are discussed for the research community to decide on possible directions. Two application cases are presented to illustrate the implementation of deep learning to rail track condition monitoring in practice before we conclude the paper.

show abstract

“…It was shown that the proposed model does not require expert knowledge, and experimental results confirmed the excellent performance of the method for tool wear prediction. A bi-directional LSTM was also used by Zhang et al [ 9 ]. The developed model was designed to eliminate noise interference and detect rail cracks.…”

Section: Introductionmentioning

confidence: 99%

Model of the Austenite Decomposition during Cooling of the Medium Carbon Steel Using LSTM Recurrent Neural Network

2021

View full text Add to dashboard Cite

The motivation of the presented paper is the desire to create a universal tool to analyse the process of austenite decomposition during the cooling process of various steel grades. The presented analysis concerns the application of Recurrent Artificial Neural Networks (RANN) of the Long Short-Term Memory (LSTM) type for the analysis of the transition path of the cooling curve. This type of network was selected due to its ability to predict events in time sequences. The proposed generalisation allows for the determination of the austenite transformation during the continuous cooling process for various cooling curves. As training data for the neural network, values determined from the macroscopic model based on the analysis of Continuous Cooling Transformation (CCT) diagrams were used. All relations and analyses used to build training/testing or validation sets are presented in the paper. The modelling with the use of LSTM network gives the possibility to determine the incremental changes of phase transformation (in a given time step) with the assumed changes of temperature resulting from the considered cooling rate.

show abstract

A new rail crack detection method using LSTM network for actual application based on AE technology

Cited by 38 publications

References 16 publications

Guided wave–based rail flaw detection technologies: state-of-the-art review

Guided wave–based rail flaw detection technologies: state-of-the-art review

Rail track condition monitoring: a review on deep learning approaches

Model of the Austenite Decomposition during Cooling of the Medium Carbon Steel Using LSTM Recurrent Neural Network

Contact Info

Product

Resources

About