Predictive maintenance : an autoencoder anomaly-based approach for a 3 DoF delta robot

Fathi, Kiavash; van de Venn, Hans Wernher; Honegger, Marcel

doi:10.3390/s21216979

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-23821

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Predictive maintenance : an autoencoder anomaly-based approach for a 3 DoF delta robot
Authors:	Fathi, Kiavash van de Venn, Hans Wernher Honegger, Marcel
et. al:	No
DOI:	10.3390/s21216979 10.21256/zhaw-23821
Published in:	Sensors
Volume(Issue):	21
Issue:	21
Page(s):	6979
Issue Date:	21-Oct-2021
Publisher / Ed. Institution:	MDPI
ISSN:	1424-8220
Language:	English
Subjects:	Anomaly detection; Autoencoder; Data-driven maintenance; Deep learning; Gaussian processes; Predictive maintenance; Normal distribution; Probability; Robotics
Subject (DDC):	006: Special computer methods 621.3: Electrical, communications, control engineering
Abstract:	Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 DoF delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data are available. Due to the sequential nature of the data, nonlinearity of the system, and correlations between parameter time-series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method can calculate RUL using Gaussian process (GP), as a degradation model, given HI values as its input.
URI:	https://digitalcollection.zhaw.ch/handle/11475/23821
Fulltext version:	Published version
License (according to publishing contract):	CC BY 4.0: Attribution 4.0 International
Departement:	School of Engineering
Organisational Unit:	Institute of Mechatronic Systems (IMS)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2021_Fathi-etal_Predictive-maintenance_Sensors.pdf		3.08 MB	Adobe PDF	View/Open

Show full item record

Fathi, K., van de Venn, H. W., & Honegger, M. (2021). Predictive maintenance : an autoencoder anomaly-based approach for a 3 DoF delta robot. Sensors, 21(21), 6979. https://doi.org/10.3390/s21216979

Fathi, K., van de Venn, H.W. and Honegger, M. (2021) ‘Predictive maintenance : an autoencoder anomaly-based approach for a 3 DoF delta robot’, Sensors, 21(21), p. 6979. Available at: https://doi.org/10.3390/s21216979.

K. Fathi, H. W. van de Venn, and M. Honegger, “Predictive maintenance : an autoencoder anomaly-based approach for a 3 DoF delta robot,” Sensors, vol. 21, no. 21, p. 6979, Oct. 2021, doi: 10.3390/s21216979.

FATHI, Kiavash, Hans Wernher VAN DE VENN und Marcel HONEGGER, 2021. Predictive maintenance : an autoencoder anomaly-based approach for a 3 DoF delta robot. Sensors. 21 Oktober 2021. Bd. 21, Nr. 21, S. 6979. DOI 10.3390/s21216979

Fathi, Kiavash, Hans Wernher van de Venn, and Marcel Honegger. 2021. “Predictive Maintenance : An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot.” Sensors 21 (21): 6979. https://doi.org/10.3390/s21216979.

Fathi, Kiavash, et al. “Predictive Maintenance : An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot.” Sensors, vol. 21, no. 21, Oct. 2021, p. 6979, https://doi.org/10.3390/s21216979.