An anomaly detection method based on random convolutional kernel and isolation forest for equipment state monitoring

• Autorzy: Shu Xinhao , Zhang Shigang , Li Yue , Chen Mengqiao

Identyfikatory

DOI

10.17531/ein.2022.4.16

• Języki publikacji: EN

Abstrakty

EN

Anomaly detection plays an essential role in health monitoring and reliability assurance of complex system. However, previous researches suffer from distraction by outliers in training and extensively relying on empiric-based feature engineering, leading to many limitations in the practical application of detection methods. In this paper, we propose an unsupervised anomaly detection method that combines random convolution kernels with isolation forest to tackle the above problems in equipment state monitoring. The random convolution kernels are applied to generate cross-dimensional and multi-scale features for multi-dimensional time series, with combining the time series decomposing method to select abnormally sensitive features for automatic feature extraction. Then, anomaly detection is performed on the obtained features using isolation forests with low requirements for purity of training sample. The verification and comparison on different types of datasets show the performance of the proposed method surpass the traditional methods in accuracy and applicability.

Słowa kluczowe

EN

anomaly detection; random convolutional kernel; isolation forest; multi-dimensional time; series; equipment state monitoring

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2022
• Tom: Vol. 24, no. 4
• Strony: 758--770
• Opis fizyczny: Bibliogr. 25 poz., rys., tab.

Twórcy

autor

Shu Xinhao

• National University of Defense Technology, Laboratory of Science and Technology on Integrated Logistics Support, College of Intelligence Science and Technology, Deya str., Changsha, 410073, Hunan, China

• https://orcid.org/0000-0003-3326-0573

autor

Zhang Shigang

• National University of Defense Technology, Laboratory of Science and Technology on Integrated Logistics Support, College of Intelligence Science and Technology, Deya str., Changsha, 410073, Hunan, China

autor

Li Yue

• National University of Defense Technology, Laboratory of Science and Technology on Integrated Logistics Support, College of Intelligence Science and Technology, Deya str., Changsha, 410073, Hunan, China

autor

Chen Mengqiao

• National University of Defense Technology, Laboratory of Science and Technology on Integrated Logistics Support, College of Intelligence Science and Technology, Deya str., Changsha, 410073, Hunan, China

Bibliografia

• 1. Bengio Y, Courville A, Vincent P. Representation Learning: A Review and New Perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence 2013; 35(8): 1798–1828, https://doi.org/10.1109/TPAMI.2013.50.
• 2. Calheiros R N, Ramamohanarao K, Buyya R et al. On the effectiveness of isolation-based anomaly detection in cloud data centers: On the effectiveness of isolation-based anomaly detection in cloud data centers. Concurrency and Computation: Practice and Experience 2017; 29(18): e4169, https://doi.org/10.1002/cpe.4169.
• 3. Chalapathy R, Chawla S. Deep Learning for Anomaly Detection: A Survey. 2019. http://arxiv.org/abs/1901.03407
• 4. Cheng Z, Wang S, Zhang P et al. Improved autoencoder for unsupervised anomaly detection. International Journal of Intelligent Systems 2021; 36(12): 7103–7125, https://doi.org/10.1002/int.22582.
• 5. Dempster A, Petitjean F, Webb G I. ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery 2020; 34(5): 1454–1495, https://doi.org/10.1007/s10618-020-00701-z.
• 6. Dempster A, Schmidt D F, Webb G I. MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual Event Singapore, ACM: 2021: 248–257, https://doi.org/10.1145/3447548.3467231.
• 7. Guo K, Liu D, Peng Y, Peng X. Data-Driven Anomaly Detection Using OCSVM with Boundary Optimzation. 2018 Prognostics and System Health Management Conference (PHM-Chongqing), Chongqing, IEEE: 2018: 244–248, https://doi.org/10.1109/PHMChongqing. 2018.00048.
• 8. Hinton G E, Salakhutdinov R R. Reducing the Dimensionality of Data with Neural Networks. Science 2006; 313(5786): 504–507, https://doi.org/10.1126/science.1127647.
• 9. Jahromi A F, Hajiloei M, Dehghani Y, Lahoninezhad S. Improved subspace-based and angle-based outlier detections for fuzzy datasets with a real case study. Journal of Intelligent & Fuzzy Systems 2022; 42(6): 5471–5481, https://doi.org/10.3233/JIFS-211955.
• 10. Jimenez A, Raj B. Time Signal Classification Using Random Convolutional Features. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, IEEE: 2019: 3592–3596, https://doi.org/10.1109/ICASSP.2019.8682489.
• 11. Kingma D P, Welling M. Auto-Encoding Variational Bayes. 2014. http://arxiv.org/abs/1312.6114
• 12. Lei Z, Zhu L, Fang Y et al. Anomaly detection of bridge health monitoring data based on KNN algorithm. Journal of Intelligent & Fuzzy Systems 2020; 39(4): 5243–5252, https://doi.org/10.3233/JIFS-189009.
• 13. Li Y, Wang Y, Ma X. Variational autoencoder-based outlier detection for high-dimensional data. Intelligent Data Analysis 2019; 23(5): 991–1002, https://doi.org/10.3233/IDA-184240.
• 14. Liu F T, Ting K M, Zhou Z-H. Isolation Forest. 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy, IEEE: 2008: 413–422, https://doi.org/10.1109/ICDM.2008.17.
• 15. Mensi A, Bicego M. Enhanced anomaly scores for isolation forests. Pattern Recognition 2021; 120: 108115, https://doi.org/10.1016/j.patcog.2021.108115.
• 16. Puggini L, McLoone S. An enhanced variable selection and Isolation Forest based methodology for anomaly detection with OES data. Engineering Applications of Artificial Intelligence 2018; 67: 126–135, https://doi.org/10.1016/j.engappai.2017.09.021.
• 17. Saxe A M, Koh P W, Chen Z et al. On Random Weights and Unsupervised Feature Learning. International Conference on Machine Learning (ICML 2011), Bellevue, Washington, USA, 2011.
• 18. Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study.Mechanical Systems and Signal Processing 2015; 64–65: 100–131, https://doi.org/10.1016/j.ymssp.2015.04.021.
• 19. Tan C W, Dempster A, Bergmeir C, Webb G I. MultiRocket: multiple pooling operators and transformations for fast and effective time series classification. Data Mining and Knowledge Discovery 2022. doi:10.1007/s10618-022-00844-1, https://doi.org/10.1007/s10618-022-00844-1.
• 20. Tian H D, Khoa N, Anaissi A et al. Concept Drift Adaption for Online Anomaly Detection in Structural Health Monitoring. PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM ’19) 2019:2813–2821, https://doi.org/10.1145/3357384.3357816.
• 21. Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th international conference on Machine learning - ICML ’08, Helsinki, Finland, ACM Press: 2008: 1096–1103, https://doi.org/10.1145/1390156.1390294.
• 22. Zhang L, Lin J, Karim R. Adaptive kernel density-based anomaly detection for nonlinear systems. Knowledge-Based Systems 2018; 139: 50–63, https://doi.org/10.1016/j.knosys.2017.10.009.
• 23. Zhao J, Itti L. Decomposing time series with application to temporal segmentation. 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, IEEE: 2016: 1–9, https://doi.org/10.1109/WACV.2016.7477722.
• 24. Zhong S, Fu S, Lin L et al. A novel unsupervised anomaly detection for gas turbine using Isolation Forest. 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), San Francisco, CA, USA, IEEE: 2019: 1–6, https://doi.org/10.1109/ICPHM.2019.8819409.
• 25. Zong B, Song Q, Min M R et al. Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection. ICLR, 2018.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).