Use Digital Twins to Support Fault Diagnosis From System-level Condition-monitoring Data
This addresses the data scarcity issue in fault diagnosis for industrial systems like robots, though it is incremental as it builds on existing digital twin and deep learning methods.
The paper tackled the problem of reducing the need for large labeled failure data in deep learning-based fault diagnosis by using a digital twin to support model training, achieving diagnosis of 9 faults from 4 motors with system-level data.
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.