Use Digital Twins to Support Fault Diagnosis From System-level Condition-monitoring Data

Killian Mc Court, Xavier Mc Court, Shijia Du, Zhiguo Zeng
11/2/2024
cs.LGcs.RO

No official code found. Best implementation: sonic160/dtr_digital_model_simulink (23 stars, MIT, last commit 2025-12-02).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

sonic160/dtr_digital_model_simulinkCommunity100%
MIT

This repo shows a digital model of a robot in simulink, and show how to use it to train an AI model for fault diagnosis.

236MATLABSep 30, 202410 months agoMIT
artificial-intelligencedigital-twinpredictive-maintenancereliability-engineeringrobot+1 more

Similar Papers

Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins

82% match2025

A Multimodal Lightweight Approach to Fault Diagnosis of Induction Motors in High-Dimensional Dataset

81% match2025

Bi-directional digital twin prototype anchoring with multi-periodicity learning for few-shot fault diagnosis

81% match2026

Fault Localization in Deep Learning-based Software: A System-level Approach

81% match1 repo2024

Uncertainty-aware deep learning for digital twin-driven monitoring: Application to fault detection in power lines

80% match2023

A new transformation for embedded convolutional neural network approach toward real-time servo motor overload fault-detection

80% match2023

Cite this paper

@article{court2024digital,
  title  = {Use Digital Twins to Support Fault Diagnosis From System-level Condition-monitoring Data},
  author = {Killian Mc Court and Xavier Mc Court and Shijia Du and Zhiguo Zeng},
  year   = {2024},
  eprint = {2411.01360},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.01360v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.01360.svg)](https://codeofpaper.com/paper/2411.01360)

Discussion