A Unified Detection Approach for Point and Subsequence Anomaly Data From Train Axle Temperature Sensors
- 25 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (20) , 24772-24786
Abstract
The train axle temperature sensor data exhibit two distinct abnormal patterns: point anomalies and subsequence anomalies, which reflect the intricate operational state of the axle and train. Precise detection of multi-category anomalies within the axle temperature data is crucial for ensuring the safe and stable operation of trains. However, the coexistence of multiple anomaly types leads to diminished accuracy in existing anomaly detection methods. Hence, we propose an unsupervised unified detection model, leveraging the power of the prediction model, targeting both point and subsequence anomalies. Our model begins by utilizing long short-term memory (LSTM) networks to predict the axle temperature, thereby generating a residual sequence. To ameliorate the error accumulation effect of LSTM, a weighting mechanism is introduced during the prediction process. Subsequently, the kernel density estimation (KDE) method is adopted to perform piecewise non-parametric fitting on the distribution of the residual sequence, enabling the determination of non-parametric dynamic thresholds for point anomalies. Finally, using the detected point anomalies as boundary points, the residual sequence is partitioned into multiple subsequences of varying lengths. The improved local outlier factor (ILOF) method is applied to compute the anomaly score of each subsequence, enabling the recognition of subsequence anomalies. The evaluation experiments for anomaly detection were conducted on two axle temperature datasets. The F 1 -scores were all above 0.975, which verified the effectiveness of the model. Compared with the baseline models, the F 1 -score of the proposed model has increased by more than 5%, which verified the superiority of the proposed model.Keywords
Funding Information
- Beijing Natural Science Foundation (L191008)
- Key Project of China State Railway Group Co., Ltd (N2020Z006)
This publication has 23 references indexed in Scilit:
- Use of CdTe Quantum Dots as Heat Resistant Temperature Sensor for Bearing Rotating Elements MonitoringIEEE Journal on Selected Areas in Communications, 2020
- Probabilistic Deep Autoencoder for Power System Measurement Outlier Detection and ReconstructionIEEE Transactions on Smart Grid, 2019
- Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding2018
- Density Estimation for Statistics and Data Analysis2018
- A Model-Based Diagnosis System for a Traction Power Supply SystemIEEE Transactions on Industrial Informatics, 2017
- Improving Spacecraft Health Monitoring with Automatic Anomaly Detection Techniques2016
- An Improved ARIMA-Based Traffic Anomaly Detection Algorithm for Wireless Sensor NetworksInternational Journal of Distributed Sensor Networks, 2016
- Rényi Entropy Filter for Anomaly Detection With Eddy Current Remote Field SensorsIEEE Sensors Journal, 2015
- LOFACM SIGMOD Record, 2000
- Long Short-Term MemoryNeural Computation, 1997