Condition-Based Monitoring and Anomaly Detection of Industrial Equipment using Autoencoder

Context. The problem of detecting anomalies from signals of cyber-physical systems based on spectrogram and scalogram images is considered. The object of the research is complex industrial equipment with heterogeneous sensory systems of different nature. Objective. The goal of the work is the development of a method for signal anomalies detection based on transfer learning with the extreme gradient boosting algorithm. Method. An approach based on transfer learning and the extreme gradient boosting algorithm, developed for detecting anomalies in acoustic signals of cyber-physical systems, is proposed. Little research has been done in this area, and therefore various pre-trained deep neural model architectures have been studied to improve anomaly detection. Transfer learning uses weights from a deep neural model, pre-trained on a large dataset, and can be applied to a small dataset to provide convergence without overfitting. The classic approach to this problem usually involves signal processing techniques that extract valuable information from sensor data. This paper performs an anomaly detection task using a deep learning architecture to work with acoustic signals that are preprocessed to produce a spectrogram and scalogram. The SPOCU activation function was considered to improve the accuracy of the proposed approach. The extreme gradient boosting algorithm was used because it has high performance and requires little computational resources during the training phase. This algorithm can significantly improve the detection of anomalies in industrial equipment signals. Results. The developed approach is implemented in software and evaluated for the anomaly detection task in acoustic signals of cyber-physical systems on the MIMII dataset. Conclusions. The conducted experiments have confirmed the efficiency of the proposed approach and allow recommending it for practical use in diagnosing the state of industrial equipment. Prospects for further research may lie in the application of ensemble approaches based on transfer learning to various real datasets to improve the performance and fault-tolerance of cyber-physical systems.

Download Full-text

An anomaly detection method to improve the intelligent level of smart articles based on multiple group correlation probability models

International Journal of Crowd Science ◽

10.1108/ijcs-09-2019-0024 ◽

2019 ◽

Vol 3 (3) ◽

pp. 333-347

Author(s):

Xudong Lu ◽

Shipeng Wang ◽

Fengjian Kang ◽

Shijun Liu ◽

Hui Li ◽

...

Keyword(s):

Anomaly Detection ◽

Probability Model ◽

Rapid Development ◽

Monitoring Data ◽

Distribution Model ◽

Industrial Equipment ◽

Data Set ◽

Content Type ◽

Multiple Group ◽

Correlation Probability

Purpose The purpose of this paper is to detect abnormal data of complex and sophisticated industrial equipment with sensors quickly and accurately. Due to the rapid development of the Internet of Things, more and more equipment is equipped with sensors, especially more complex and sophisticated industrial equipment is installed with a large number of sensors. A large amount of monitoring data is quickly collected to monitor the operation of the equipment. How to detect abnormal data quickly and accurately has become a challenge. Design/methodology/approach In this paper, the authors propose an approach called Multiple Group Correlation-based Anomaly Detection (MGCAD), which can detect equipment anomaly quickly and accurately. The single-point anomaly degree of equipment and the correlation of each kind of data sequence are modeled by using multi-group correlation probability model (a probability distribution model which is helpful to the anomaly detection of equipment), and the anomaly detection of equipment is realized. Findings The simulation data set experiments based on real data show that MGCAD has better performance than existing methods in processing multiple monitoring data sequences. Originality/value The MGCAD method can detect abnormal data quickly and accurately, promote the intelligent level of smart articles and ultimately help to project the real world into cyber space in CrowdIntell Network.

Download Full-text