Correlation-Based Anomaly Detection Method for Multi-sensor System
Open Access
- 31 May 2022
- journal article
- research article
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2022, 1-13
Abstract
In industry, sensor-based monitoring of equipment or environment has become a necessity. Instead of using a single sensor, multi-sensor system is used to fully detect abnormalities in complex scenarios. Recently, physical models, signal processing technology, and various machine learning models have improved the performance. However, these methods either do not consider the potential correlation between features or do not take advantage of the sequential changes of correlation while constructing an anomaly detection model. This paper firstly analyzes the correlation characteristic of a multi-sensor system, which shows a lot of clues to the anomaly/fault propagation. Then, a multi-sensor anomaly detection method, which finds and uses the correlation between features contained in the multidimensional time-series data, is proposed. The method converts the multidimensional time-series data into temporal correlation graphs according to time window. By transforming time-series data into graph structure, the task of anomaly detection is considered as a graph classification problem. Moreover, based on the stability and dynamics of the correlation between features, a structure-sensitive graph neural network is used to establish the anomaly detection model, which is used to discover anomalies from multi-sensor system. Experiments on three real-world industrial multi-sensor systems with anomalies indicate that the method obtained better performance than baseline methods, with the mean value of F1 score reaching more than 0.90 and the mean value of AUC score reaching more than 0.95. That is, the method can effectively detect anomalies of multidimensional time series.Keywords
Funding Information
- Foundation for Innovative Research Groups of the National Natural Science Foundation of China (61902051)
This publication has 22 references indexed in Scilit:
- A framework for scalable real‐time anomaly detection over voluminous, geospatial data streamsConcurrency and Computation: Practice and Experience, 2017
- A novel fault diagnosis technique for photovoltaic systems based on artificial neural networksRenewable Energy, 2016
- Anomaly Detection System in Cloud Environment Using Fuzzy Clustering Based ANNMobile Networks and Applications, 2015
- Design and Analysis of Multimodel-Based Anomaly Intrusion Detection Systems in Industrial Process AutomationIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015
- A Deep Learning-based Method for Machinery Health Monitoring with Big DataJournal of Mechanical Engineering, 2015
- A critical feature extraction by kernel PCA in stock trading modelSoft Computing, 2014
- FN-DFE: Fuzzy-Neural Data Fusion Engine for Enhanced Resilient State-Awareness of Hybrid Energy SystemsIEEE Transactions on Cybernetics, 2014
- Failure diagnosis using deep belief learning based health state classificationReliability Engineering & System Safety, 2013
- Efficient algorithms for mining outliers from large data setsACM SIGMOD Record, 2000
- Outliers in Statistical Data (3rd edition)Journal of the Operational Research Society, 1995