Abstract
With growing dependence of industrial robots, a failure of an industrial robot may interrupt current operation or even overall manufacturing workflows in the entire production line, which can cause significant economic losses. Hence, it is very essential to maintain industrial robots to ensure high-level performance. It is widely desired to have a real-time technique to constantly monitor robots by collecting time series data from robots, which can automatically detect incipient failures before robots totally shut down. Model-based methods are typically used in anomaly detection for robots, yet explicit domain knowledge and accurate mathematical models are required. Data-driven techniques can overcome these limitations. However, a major difficulty for them is the lack of sufficient fault data of industrial robots. Besides, the used technique for anomaly detection of robots should be required to not only capture the temporal dependency in collected time series data, but also the inter-correlations between different metrics. In this paper, we introduce an unsupervised anomaly detection for industrial robots, sliding-window convolutional variational autoencoder (SWCVAE), which can realize real-time anomaly detection spatially and temporally by coping with multivariate time series data. This method has been verified by a KUKA KR6R 900SIXX industrial robot, and the results prove that the proposed model can successfully detect anomaly in the robot. Thus, this work presents a promising tool for condition-based maintenance of industrial robots.
Highlights
Nowadays, industrial robots are playing an increasingly important role in manufacturing as they greatly improve productivity and quality
Statistical methods are frequently used due to their computational efficiency. They detect data points that deviate from the distribution of the historical data. These methods used for robots include Statistical Control Charts (SCCs) [9], Principal Component Analysis (PCA) based method [10], Partial Least Squares (PLS) based approach [11] and so on
We introduce an online unsupervised anomaly detection method for industrial robots by an unsupervised method based on sliding-window convolutional variational autoencoder (SWCVAE)
Summary
Industrial robots are playing an increasingly important role in manufacturing as they greatly improve productivity and quality. An unsupervised anomaly detection method based on sliding-window convolutional variational autoencoder (SWCVAE) for industrial robots is proposed, which automatically learns normal patterns from time series data in training. These methods used for robots include Statistical Control Charts (SCCs) [9], Principal Component Analysis (PCA) based method [10], Partial Least Squares (PLS) based approach [11] and so on Most of these methods require that all the data have to be accumulated before faults can be detected, which make them unsuitable for real-time anomaly detection. They assume that normal data are generated from a known distribution. Unlike some unsupervised methods which only focus on spatial anomalies, this method can detect spatial and temporal anomalies in data by dealing with time series data, and may help for recognizing the deviation of workflow under repetitive operation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
