Abstract
The continuously growing amount of monitored data in the Industry 4.0 context requires strong and reliable anomaly detection techniques. The advancement of Digital Twin technologies allows for realistic simulations of complex machinery, therefore, it is ideally suited to generate synthetic datasets for the use in anomaly detection approaches when compared to actual measurement data. In this paper, we present novel weakly-supervised approaches to anomaly detection for industrial settings. The approaches make use of a Digital Twin to generate a training dataset which simulates the normal operation of the machinery, along with a small set of labeled anomalous measurement from the real machinery. In particular, we introduce a clustering-based approach, called Cluster Centers (CC), and a neural architecture based on the Siamese Autoencoders (SAE), which are tailored for weakly-supervised settings with very few labeled data samples. The performance of the proposed methods is compared against various state-of-the-art anomaly detection algorithms on an application to a real-world dataset from a facility monitoring system, by using a multitude of performance measures. Also, the influence of hyper-parameters related to feature extraction and network architecture is investigated. We find that the proposed SAE based solutions outperform state-of-the-art anomaly detection approaches very robustly for many different hyper-parameter settings on all performance measures.
Highlights
I n recent years, there has been a strong tendency to equip technical machinery, ranging from single machines to complete buildings and manufacturing plants with sensors to constantly monitor their operation, especially in the context of Industry 4.0 strategies [1]
One category of deep anomaly detection methods is based on reducing the dimension of the input by mapping it to a low dimensional manifold followed by reconstruction
For completeness, we show the usefulness of the Digital Twin simulation data, by reporting the performance of the anomaly detection algorithms by using only the real-world data
Summary
I n recent years, there has been a strong tendency to equip technical machinery, ranging from single machines to complete buildings and manufacturing plants with sensors to constantly monitor their operation, especially in the context of Industry 4.0 strategies [1]. Depending on the effort spent to create the Digital Twin, it can be realistic simulation which captures the qualitatively correct behavior of the machinery, or an almost perfect digital copy whose output can be directly compared to the real-world machinery The former can be at least used to create a large dataset containing data samples of normal operation conditions which can be utilized in machine learning approaches. The main contributions of this work are: (i) novel approaches to anomaly detection using data from a Digital Twin simulation for the normal operational state of a machinery, (ii) a clustering-based algorithm capable to solve the anomaly detection task in both unsupervised and weakly-supervised settings, (iii) a Siamese Autoencoder architecture for weaklysupervised anomaly detection where very few labelled training samples are needed to improve the performance over unsupervised anomaly detection methods, (iv) a thorough comparison of experimental results of the proposed methods and their performance to state-of-the-art algorithms for anomaly detection.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.