Anomaly Detection in Industrial Multivariate Time-Series Data With Neutrosophic Theory

Abstract

The Industrial Internet of Things (IIOT) plays an important role in the digital management process of industrial enterprises. It improves the productivity of enterprises and reduces the management cost of enterprises. Anomaly detection has gradually become an important tool in the field of IIoT security. Due to the complex topology network and randomness of IIOT, the increase in data dimension and information distortion makes it difficult to extract data neighborhood information effectively. This is a challenge for current detection methods. In this paper, a new multivariate time series (MTS) anomaly detection framework is proposed. The framework involves an intuition-based neutrosophic representation method for MTS and an automatic learning graph structure. Firstly, the data preprocessing and the data representation are performed. Then, the fuzzy features of the MTS data after dimensionality reduction and co-frequency processing are captured by using the intuition-based neutrosophic model. Finally, the graph model is used to identify rare events in the data and interpret the sensorlevel anomalies. Experiments on two public and available anomaly detection datasets prove that our method has better robustness and interpretability in the anomaly detection tasks of IIOT.