Anomaly Detection for Industrial Time Series Data Based on Correlation Analysis and CNN-BiLSTM with Self-attention

Xinyi Yu

College of Engineering, Hangzhou Normal University, Hangzhou, 310018, China.

Bingbing Zeng

College of Engineering, Hangzhou Normal University, Hangzhou, 310018, China.

Lidong Wang *

College of Engineering, Hangzhou Normal University, Hangzhou, 310018, China.

*Author to whom correspondence should be addressed.


Abstract

This paper aims to propose an anomaly detection model for industrial time series data based on correlation analysis and CNN-BiLSTM with self-attention to solve the problem of abnormal data detection in the field of industrial data analysis. Industrial data anomaly detection is an important task in the industrial field, which can help people to timely understand the production operation status and real-time record and perception of the operating environment. This paper introduces two key technologies: correlation analysis and CNN-BiLSTM with self-attention, and how to combine them to build an effective anomaly detection model for industrial time series data. Through experimental evaluation, this paper proves the effectiveness and superiority of the proposed model in industrial data anomaly detection tasks.

Keywords: Anomaly detection, CNN-BiLSTM, self-attention, industrial time series data


How to Cite

Yu, X., Zeng, B., & Wang, L. (2024). Anomaly Detection for Industrial Time Series Data Based on Correlation Analysis and CNN-BiLSTM with Self-attention. Asian Journal of Mathematics and Computer Research, 31(2), 96–108. https://doi.org/10.56557/ajomcor/2024/v31i28697

Downloads

Download data is not yet available.

References

Zhang Jie, Qin Wei, Bao Jinsong,et al. Manufacturing big data. Shanghai: Shanghai Science and Technology Press; 2016.

Industrial Big Data AD Hoc group of industrial internet industry alliance. Industrial big data technology and application practice.Beijing: Publishing House of Electronics Industry; 2017.

National Manufacturing Power Building Strategy Advisory Committee. Made in China2025 Key Areas Technology Roadmap; 2015.

Wang Jianmin. White paper on China's industrial big data technology and application. Beijing: Industrial Internet Industry Alliance; 2017.

Wang Jianmin. Overview of industrial big data technology. Big Data. 2022,(6):3-14.

Ewusie JE, Soobiah C,Blondal E,et al. Methods,applica- tions and challenges in the analysis of interrupted time series data: A scoping review [J] .Journal of Multidisciplinary Healthcar. 2020;13:411.

Ding XO, Wang HZ, Su JX, et al. Cleanits: A data cleaning system for industrial time series. Proc, of the VLDB Endowment. 2019;12(12):1786-1789.

Golab L, Karloff H, Korn F, et al. Sequential dependencies. Proc, of the VLDB Endowment. 2019;2(1):574-585.

Song S, Zhang A, Wang J, et al. SCREEN: Stream data cleaning under speed constraints. In: Proc of the ACM SIGMOD International Conference on Management of Data. ACM. 2015;827-841.

Chandola V, Banerjee A, Kumar V. Anomaly detection: a survey. ACM Comput Surv. 2009;41:1-58.

Pang G, Shen C, Cao L, et al. Deep learning for anomaly detection: A review. 2020. ArXiv; 2007;02500.

Chalapathy R, Chawla S. Deep learning for anomaly detection: A survey. 2019.ArXiv:1901.03407.

Bulusu S, Kailkhura B, Li B, et al. Anomalous instance detection in deep learning: A survey. In: Proceedings of the 42nd lEEE Symposium on Security and Privacy Princeton; 2020.

Ruff L, Kauffmann JR, Vandermeulen R A, et al. A unifying review of deep and shallow anomaly detection.Proc IEEE. 2021;109:756-795.

Czimmermann T, Ciuti G, Milazzo M, et al. Visual-based defect detection and classification approaches for industrial applications--A survey. Sensors. 2020;20:1459.

Zhou DH, Wei MH, Si XS. A survey on anomaly detection, life prediction and maintenance decision for industrial processes. Acta Automatica Sin. 2013;39:711-722.

Tao X, Hou W, Xu D. A survey of surface defect detection methods based on deep learning. Acta Autom Sin. 2021;47:1017–1034.

Enders W, et al. Du Jiang, Yuan Jingan: Trans. Applied econometrics: Time series analysis. 2nd Ed. Beijing: Higher Education Press; 2006.

Eamoon JK, Kaushik C, Sharad M, Michael JP, Locally adaptive dimensionality reduction for indexing large time series databases. ACM Trans, on Database Systems. 2012;27(2):188-228.

Ma J, Ma J, Perkins S, et al. Time-series novelty detection using one-class support vector machines. In: Proc of the International Joint Conference on Neural Networks. IEEE; 2013.

Chandola V, Mithal V, Kumar V. Comparative evaluation of anomaly detection techniques fbr sequence data. In: Proc of the 8th IEEE International Conf on Data Mining. IEEE Computer Society; 2008.

Li X, Han J, Kim S, et al. ROAM: Rule- and motiAbased anomaly detection in massive moving object data sets. In: Proc, of the 7th SIAM Int'l Conf, on Data Mining. 2007;273-284.

Alex K,Ilya S,Geoffrey EH. Image Net classification with deep convolutional neural networks [J]. Neural Information Processing Systems. 2017;60(6):84-90.

Hochreiter S,Schmidhuber J. Long shortterm menory[J]. Neural Computation. 1997;9(9):1735-1780.