High-Speed Railway Bogie Fault Diagnosis Using LSTM Neural Network

Fu, Yuanzhe; Huang, Deqing; Qin, Na; Liang, Kaiwei; Yang, Yang

doi:10.23919/chicc.2018.8483987

Cited by 25 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research effort explores the application of a multivariate Long Short-Term Memory (LSTM) model as a data-driven approach for multivariate topology under an immense sample size of more than a million samples per vehicle. LSTMs employ deep-learning, artificial recurrent neural network techniques (Fu, Huang, Qin, Liang, & Yang, 2018). Deployed on preliminary data, the LSTM model observed multiple channels of sensor data and provided fault detection and diagnosis.…”

Section: Long Short-term Memory Modelmentioning

confidence: 99%

A Hybrid Learning Approach to Prognostics and Health Management Applied to Military Ground Vehicles Using Time-Series and Maintenance Event Data

et al. 2020

View full text Add to dashboard Cite

Attempts to leverage operational time-series data in Condition Based Maintenance (CBM) approaches to optimize the life cycle management and Reliability, Availability, and Maintainability (RAM) of military vehicles have encountered several obstacles over decades of data collection. These obstacles have beset similar approaches on civilian ground vehicles, as well as on aircraft and other complex systems. Analysis of operational data is critical because it represents a continuous recording of the state of the system. Applying rudimentary data analytics to operational data can provide insights like fuel usage patterns or observed reliability of one vehicle or even a fleet. Monitoring trends and analyzing patterns in this data over time, however, can provide insight into the health of a vehicle, a complex system, or a fleet, predicting mean time to failure or compiling logistic or life cycle needs. Such High-Performance Data Analytics (HPDA) on operational time-series datasets has been historically difficult due to the large amount of data gathered from vehicle sensors, the lack of association between clusters observed in the data and failures or unscheduled maintenance events, and the deficiency of unsupervised learning techniques for time-series data. We present an HPDA environment and a method of discovering patterns in vehicle operational data that determines models for predicting the likelihood of imminent failure, referred to as Parameter-Based Indicators (PBIs). Our method is a data-driven approach that uses both time-series and relational maintenance data. This hybrid approach combines both supervised and unsupervised machine learning and data analytic techniques to correlate labeled, relational maintenance event data with unlabeled operational time-series data utilizing the DoD High Performance Computing (HPC) capabilities at the U.S. Army Engineer Research and Development Center. In leveraging both time-series and relational data, we demonstrate a means of fast, purely data-driven model creation that is more broadly applicable and requires less a priori information than physics informed, data-driven models. By blending these approaches, this system will be able to relate some lifecycle management goals through the workflow to generate specific PBIs that will predict failures or highlight appropriate areas of concern in individual or collective vehicle histories.

show abstract

Section: Long Short-term Memory Modelmentioning

confidence: 99%

A Hybrid Learning Approach to Prognostics and Health Management Applied to Military Ground Vehicles Using Time-Series and Maintenance Event Data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…[24,[32][33][34][35] use convolutional neural networks (CNN), Refs. [36][37][38] use LSTM, and [39] uses a combination of both CNN and RNN called convolutional-recurrent neural network (CRNN). In transfer learning approaches, Refs.…”

Section: Related Workmentioning

confidence: 99%

“…The LSTM model is used for the detection which shows its feasibility of detection faults at the speed of 15 km/h. Fu et al [37] worked to detect the structural damage. They used LSTM for classification.…”

Section: Related Workmentioning

confidence: 99%

Railway Track Inspection Using Deep Learning Based on Audio to Spectrogram Conversion: An on-the-Fly Approach

Hashmi

Ibrahim

Bajwa

et al. 2022

Sensors

View full text Add to dashboard Cite

The periodic inspection of railroad tracks is very important to find structural and geometrical problems that lead to railway accidents. Currently, in Pakistan, rail tracks are inspected by an acoustic-based manual system that requires a railway engineer as a domain expert to differentiate between different rail tracks’ faults, which is cumbersome, laborious, and error-prone. This study proposes the use of traditional acoustic-based systems with deep learning models to increase performance and reduce train accidents. Two convolutional neural networks (CNN) models, convolutional 1D and convolutional 2D, and one recurrent neural network (RNN) model, a long short-term memory (LSTM) model, are used in this regard. Initially, three types of faults are considered, including superelevation, wheel burnt, and normal tracks. Contrary to traditional acoustic-based systems where the spectrogram dataset is generated before the model training, the proposed approach uses on-the-fly feature extraction by generating spectrograms as a deep learning model’s layer. Different lengths of audio samples are used to analyze their performance with each model. Each audio sample of 17 s is split into 3 variations of 1.7, 3.4, and 8.5 s, and all 3 deep learning models are trained and tested against each split time. Various combinations of audio data augmentation are analyzed extensively to investigate models’ performance. The results suggest that the LSTM with 8.5 split time gives the best results with the accuracy of 99.7%, the precision of 99.5%, recall of 99.5%, and F1 score of 99.5%.

show abstract

“…A deep belief network (DBN) hierarchical ensemble was presented to automatically learn the hierarchical features of the bogie vibration signals by combining the deep learning with classification ensemble technology [24]. For time series prediction problems, the long-short-term memory (LSTM) neural network shows superior performance, and a LSTMbased bogie fault prediction method was studied in [25], where the spatial and temporal correlation of fault features can be learned from the original time series signals without any prior knowledge. In [26], a convolutional recurrent neural network (CRNN) was proposed for the HST bogie fault diagnosis, which can simultaneously achieve high accuracy and save time as it inherits the advantages of CNN and Simple Recurrent Unit.…”

Section: Bogie System Fault Diagnosismentioning

confidence: 99%

Advances in Fault Diagnosis for High-Speed Railway: A Review

Yin

et al. 2019

2019 6th International Conference on Frontiers of Industrial Engineering (ICFIE)

View full text Add to dashboard Cite

The high speed railway (HSR) is a complex system with many subsystems and components. The reliability of its core subsystems is a key consideration in ensuring the safety and operation efficiency of the whole system. As the service time increases, the degradation of these subsystems and components may lead to a range of faults and deteriorate the whole system performance. To ensure the operation safety and to develop reasonable maintenance strategies, fault detection and isolation is an indispensable functionality in high speed railway systems. In this paper, the traction power supply system, bogie system, civil infrastructure system, and control and signaling system of HSR are briefly summarized, and then different fault diagnosis methods for these subsystems are comprehensively reviewed. Finally, some future research topics are discussed.Keywords-High-speed railway (HSR); fault diagnosis; traction power supply system (TPSS); bogie system I.

show abstract

High-Speed Railway Bogie Fault Diagnosis Using LSTM Neural Network

Cited by 25 publications

References 9 publications

A Hybrid Learning Approach to Prognostics and Health Management Applied to Military Ground Vehicles Using Time-Series and Maintenance Event Data

A Hybrid Learning Approach to Prognostics and Health Management Applied to Military Ground Vehicles Using Time-Series and Maintenance Event Data

Railway Track Inspection Using Deep Learning Based on Audio to Spectrogram Conversion: An on-the-Fly Approach

Advances in Fault Diagnosis for High-Speed Railway: A Review

Contact Info

Product

Resources

About