Saved in:
Bibliographic Details
Main Authors: Court, Killian Mc, Court, Xavier Mc, Du, Shijia, Zeng, Zhiguo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.01360
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916466018746368
author Court, Killian Mc
Court, Xavier Mc
Du, Shijia
Zeng, Zhiguo
author_facet Court, Killian Mc
Court, Xavier Mc
Du, Shijia
Zeng, Zhiguo
contents Deep learning models have created great opportunities for data-driven fault diagnosis but they require large amount of labeled failure data for training. In this paper, we propose to use a digital twin to support developing data-driven fault diagnosis model to reduce the amount of failure data used in the training process. The developed fault diagnosis models are also able to diagnose component-level failures based on system-level condition-monitoring data. The proposed framework is evaluated on a real-world robot system. The results showed that the deep learning model trained by digital twins is able to diagnose the locations and modes of 9 faults/failure from $4$ different motors. However, the performance of the model trained by a digital twin can still be improved, especially when the digital twin model has some discrepancy with the real system.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01360
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Use Digital Twins to Support Fault Diagnosis From System-level Condition-monitoring Data
Court, Killian Mc
Court, Xavier Mc
Du, Shijia
Zeng, Zhiguo
Machine Learning
Robotics
Deep learning models have created great opportunities for data-driven fault diagnosis but they require large amount of labeled failure data for training. In this paper, we propose to use a digital twin to support developing data-driven fault diagnosis model to reduce the amount of failure data used in the training process. The developed fault diagnosis models are also able to diagnose component-level failures based on system-level condition-monitoring data. The proposed framework is evaluated on a real-world robot system. The results showed that the deep learning model trained by digital twins is able to diagnose the locations and modes of 9 faults/failure from $4$ different motors. However, the performance of the model trained by a digital twin can still be improved, especially when the digital twin model has some discrepancy with the real system.
title Use Digital Twins to Support Fault Diagnosis From System-level Condition-monitoring Data
topic Machine Learning
Robotics
url https://arxiv.org/abs/2411.01360