Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot

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, ca...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kiavash Fathi, Hans Wernher van de Venn, Marcel Honegger
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	predictive maintenance anomaly detection autoencoder gaussian processes deep learning data-driven maintenance Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/1856716ed8b4492c9ba6bfe0a5e7cb2f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1856716ed8b4492c9ba6bfe0a5e7cb2f
record_format	dspace
spelling	oai:doaj.org-article:1856716ed8b4492c9ba6bfe0a5e7cb2f2021-11-11T19:01:42ZPredictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot10.3390/s212169791424-8220https://doaj.org/article/1856716ed8b4492c9ba6bfe0a5e7cb2f2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/6979https://doaj.org/toc/1424-8220Performing 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.Kiavash FathiHans Wernher van de VennMarcel HoneggerMDPI AGarticlepredictive maintenanceanomaly detectionautoencodergaussian processesdeep learningdata-driven maintenanceChemical technologyTP1-1185ENSensors, Vol 21, Iss 6979, p 6979 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	predictive maintenance anomaly detection autoencoder gaussian processes deep learning data-driven maintenance Chemical technology TP1-1185
spellingShingle	predictive maintenance anomaly detection autoencoder gaussian processes deep learning data-driven maintenance Chemical technology TP1-1185 Kiavash Fathi Hans Wernher van de Venn Marcel Honegger Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot
description	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.
format	article
author	Kiavash Fathi Hans Wernher van de Venn Marcel Honegger
author_facet	Kiavash Fathi Hans Wernher van de Venn Marcel Honegger
author_sort	Kiavash Fathi
title	Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot
title_short	Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot
title_full	Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot
title_fullStr	Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot
title_full_unstemmed	Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot
title_sort	predictive maintenance: an autoencoder anomaly-based approach for a 3 dof delta robot
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1856716ed8b4492c9ba6bfe0a5e7cb2f
work_keys_str_mv	AT kiavashfathi predictivemaintenanceanautoencoderanomalybasedapproachfora3dofdeltarobot AT hanswernhervandevenn predictivemaintenanceanautoencoderanomalybasedapproachfora3dofdeltarobot AT marcelhonegger predictivemaintenanceanautoencoderanomalybasedapproachfora3dofdeltarobot
_version_	1718431629353943040

Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot

Ejemplares similares