A signal-based fault detection and classification method for heavy haul wagons

Li, Chunsheng; Luo, Shan; Cole, Colin; Spiryagin, Maksym; Sun, Yanquan

doi:10.1080/00423114.2017.1334929

Cited by 7 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The output V (1) of the first convolutional layer can be expressed as where X is the input matrix, W is the convolution kernel, and superscript (1) indicates the layer number. n is the number of the convolution kernel; herein n (1) = 32. The size of the convolution kernel W (1) is 3 × 3.…”

Section: Data-driven Methodsmentioning

confidence: 99%

“…The activation function is the "ReLU" function, which is defined as The stride of the first pooling layer is 2 × 2. The pooling function is defined as Through the pooling process, V (1) becomes V (2) . The output V (3) of the second convolutional layer can be expressed as (8) (1) = conv2d (1) , (1) , n (1) , "relu" ,…”

Section: Data-driven Methodsmentioning

confidence: 99%

“…At present, the axle load of heavy-haul trains has reached 40 tons in Australia [1]. The Ministry of Railways in China has put forward a plan to improve the axle load to 30 tons [2].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ballasted Track Behaviour Induced by Absent Sleeper Support and its Detection Based on a Convolutional Neural Network Using Track Data

Zhang

Tian

et al. 2023

Urban Rail Transit

View full text Add to dashboard Cite

With development of the heavy-haul railway, the increased axle load and traction weight bring a significant challenge for the service performance and safety maintenance of the railway track. Conducting defect recognition on concrete sleepers and ballast using big data is vital. This paper focused on the detection of absent sleeper support in a ballasted track with an emphasis on the integration of model-based and data-driven methods. To this end, a mathematical model consisting of the wagon, track and wheel–rail contact subsystems was first established to acquire the necessary raw data for the data-driven method, in which the wagon was regarded as a 47-degree-of-freedom multi-body subsystem, and the track was treated as a multi-layer discrete-elastic support beam subsystem with absent sleeper support. Then, an architectural hierarchy of a three-layer convolutional neural network (TLCNN) was developed, which includes three convolutional layers and two pooling layers, and a method for reconstructing one-dimensional sleeper vertical displacement to a two-dimensional time–space matrix was also proposed. Thirdly, verification was carried out by comparing the simulation and experimental results to illustrate the accuracy and reliability of the mathematical model, and the dynamic behaviour of the track with absent sleeper support was investigated. Lastly, the established TLCNN was used to train the raw data of the sleeper vertical displacement and detect the existence of absent sleeper support. Results show that the integration of model-based and data-driven methods was a reliable and effective approach for the detection of absent sleeper support. The proposed TLCNN can acquire and extract robust characteristics in a noisy environment. To handle more complex recognition tasks and further improve performance, deeper CNN models and larger sample sizes should be preferentially considered in practical applications.

show abstract

Section: Data-driven Methodsmentioning

confidence: 99%

Section: Data-driven Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Ballasted Track Behaviour Induced by Absent Sleeper Support and its Detection Based on a Convolutional Neural Network Using Track Data

Zhang

Tian

et al. 2023

Urban Rail Transit

View full text Add to dashboard Cite

show abstract

“…This method is very sensitive to different fault conditions. Li [25,26] developed a fully detailed dynamic model of 40t axle load heavy haul wagon. With the help of auto-correlation and cross-correlation analysis, the fault diagnosis for secondary bolster spring was studied, and an online fault diagnosis strategy was proposed.…”

Section: Introductionmentioning

confidence: 99%

“…The work described in this paper starts from some ideas described in [23][24][25][26] concerning the application of cross-correlation techniques to detect suspensions faults in railway vehicles and making use of measurement coming from axle-box, bogie and carbody, and tries to extend and apply such ideas to a new field, the detection of the hunting instability.…”

Section: Introductionmentioning

confidence: 99%

A signal analysis based hunting instability detection methodology for high-speed railway vehicles

Sun

Meli

Cai

et al. 2020

Vehicle System Dynamics

View full text Add to dashboard Cite

Hunting stability is a long-standing research topic and has been deeply investigated due to its great influence on railway vehicle dynamic performances. Most of the existing hunting monitoring methods detect only the large amplitude hunting instability (LAHI). However, the small amplitude hunting instability (SAHI) is still hard to be detected accurately and efficiently. To face this challenging problem, this paper describes a signal analysis based hunting instability detection methodology. The proposed method is based on crosscorrelation techniques and is able to detect both SAHI and LAHI in a simple, efficient and effective way. Eight cross-correlation indicators (CCIs) are exploited to detect anomalous SAHI and LAHI conditions. A fully detailed dynamic model of one typical high-speed railway vehicle is developed to test the methodology and to compare the CCIs under different vehicle operating conditions. The most effective CCI and its critical values are determined on the basis of the statistics and comparisons of the simulation results. Furthermore, the robustness of the proposed method to distinguish hunting instability and periodic excitations coming from track irregularities has been verified. Finally, the proposed instability detection methodology has been validated by detecting the SAHI successfully on field test data coming from specific experimental campaigns.

show abstract

Maneuver-based deep learning parameter identification of vehicle suspensions subjected to performance degradation

Pan

Sun

Min

et al. 2022

Vehicle System Dynamics

View full text Add to dashboard Cite

A signal-based fault detection and classification method for heavy haul wagons

Cited by 7 publications

References 32 publications

Ballasted Track Behaviour Induced by Absent Sleeper Support and its Detection Based on a Convolutional Neural Network Using Track Data

Ballasted Track Behaviour Induced by Absent Sleeper Support and its Detection Based on a Convolutional Neural Network Using Track Data

A signal analysis based hunting instability detection methodology for high-speed railway vehicles

Maneuver-based deep learning parameter identification of vehicle suspensions subjected to performance degradation

Contact Info

Product

Resources

About