Incipient anomaly detection for railway vehicle door system based on adaptive mean shift clustering

Han, Guangyang; Zhang, Y.; Lu, Ningyun; Jiang, Bin; Xu, Zhixing; Cao, Jingzhi; Shi, Xiaohu

doi:10.1109/cac.2017.8242967

Cited by 6 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results are shown in Tables 2 and 3. The accuracy of fault identification calculation formula is shown in formula (12), and the statistical results are shown in Table 2. From the results in the table, it can be clearly seen that the accuracy of the fault diagnosis for the four groups of the fault data could reach 100% before and after adding the decision model.…”

Section: Resultsmentioning

confidence: 99%

“…At the same time, the temperature data of train bearings obtained using the WTDS system was used to monitor the condition of an axle box bearing. Han et al 12 proposed an adaptive mean shift clustering algorithm in which the common and frequent anomalies in a train door system could be successfully detected and isolated.…”

Section: Abnormal Bearing Temperature Detection Based On Outlier Dete...mentioning

confidence: 99%

“…Correctly distinguish the number of fault samples Number of fault samples in test set (12) Another case was a false alarm, where the normal state of the bearing was judged as a fault state, as shown in Figure 10. A false alarm not only affects the user experience but may also cause economic losses, which should be avoided as much as possible.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A novel abnormal detection method for bearing temperature based on spatiotemporal fusion

Liu

Zou

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part F:

View full text Add to dashboard Cite

The existing bearing temperature fault detection and early warning system has a high false alarm rate and insufficient early warning ability. For this reason, in this study, a method for detecting the abnormal bearing temperature of high-speed trains based on spatiotemporal fusion decision-making was proposed. First, the temperature characteristics of similar bearings were compared and analyzed with different spatial distributions. Then, a bearing abnormal temperature rise detection model based on the analytic hierarchy process (AHP) entropy method was proposed. Second, the temperature characteristics of the same bearings were compared and analyzed with different time distributions. A real-time prediction model of high-speed train bearing temperature anomalies based on Bi-directional Long Short-Term Memory (BILSTM) was proposed. Finally, the D-S evidence theory was used to combine the anomaly detection model based on the AHP entropy method and the anomaly detection model based on BILSTM real-time prediction. Through the comprehensive diagnosis and decision-making of high-speed train bearings from two dimensions of space and time, a more comprehensive and accurate anomaly detection model was realized. The experimental results showed that the spatiotemporal comparison fusion decision model successfully eliminated the misjudgment phenomenon of single-dimension model diagnosis and that it has good early warning ability.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Abnormal Bearing Temperature Detection Based On Outlier Dete...mentioning

confidence: 99%

See 1 more Smart Citation

A novel abnormal detection method for bearing temperature based on spatiotemporal fusion

Liu

Zou

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part F:

View full text Add to dashboard Cite

show abstract

“…Traditional detection methods can be subdivided into classification-based [2], density-based [11], statistically based [13] and spectrum-based anomaly detection algorithms [20]. Although these methods are mathematically simple and easy to implement [33], they are difficult to adapt to dynamic changes in passenger flow data.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Advanced monitoring technologies leveraging big data analytics and intelligent algorithms offer a promising approach to achieving high accuracy and reliability in detecting anomalies in URTNs [7]. Many automatic anomaly detection models are widely studied in passenger flow anomaly detection, such as the Z-score [8], 3-sigma [9], K-nearest neighbour (KNN) [10], density-based spatial clustering of application with noise (DBSCAN) [11], autoencoder (AE) [12] and principal component analysis algorithms [13]. However, it is difficult for these models to capture the temporal and spatial dependencies in passenger flows, especially for anomaly detection at the network level [14].…”

Section: Introductionmentioning

confidence: 99%

Passenger flow anomaly detection in urban rail transit networks with graph convolution network–informer and Gaussian Bayes models

Liu

Tan

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Passenger flow anomaly detection in urban rail transit networks (URTNs) is critical in managing surging demand and informing effective operations planning and controls in the network. Existing studies have primarily focused on identifying the source of anomalies at a single station by analysing the time-series characteristics of passenger flow. However, they ignored the high-dimensional and complex spatial features of passenger flow and the dynamic behaviours of passengers in URTNs during anomaly detection. This article proposes a novel anomaly detection methodology based on a deep learning framework consisting of a graph convolution network (GCN)–informer model and a Gaussian naive Bayes model. The GCN–informer model is used to capture the spatial and temporal features of inbound and outbound passenger flows, and it is trained on normal datasets. The Gaussian naive Bayes model is used to construct a binary classifier for anomaly detection, and its parameters are estimated by feeding the normal and abnormal test data into the trained GCN–informer model. Experiments are conducted on a real-world URTN passenger flow dataset from Beijing. The results show that the proposed framework has superior performance compared to existing anomaly detection algorithms in detecting network-level passenger flow anomalies. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

show abstract

An Unsupervised Anomaly Detection Method Based on Density Peak Clustering for Rail Vehicle Door System

Shi¹,

Lu²,

Jiang

et al. 2019

2019 Chinese Control and Decision Conference (CCDC)

View full text Add to dashboard Cite

Incipient anomaly detection for railway vehicle door system based on adaptive mean shift clustering

Cited by 6 publications

References 11 publications

A novel abnormal detection method for bearing temperature based on spatiotemporal fusion

A novel abnormal detection method for bearing temperature based on spatiotemporal fusion

Passenger flow anomaly detection in urban rail transit networks with graph convolution network–informer and Gaussian Bayes models

An Unsupervised Anomaly Detection Method Based on Density Peak Clustering for Rail Vehicle Door System

Contact Info

Product

Resources

About