Data-Efficient Motor Condition Monitoring with Time Series Foundation Models

TL;DR

This paper introduces a data-efficient motor condition monitoring framework using pre-trained time series foundation models, significantly reducing labeled data requirements while maintaining high diagnostic accuracy.

Contribution

It leverages large-scale pre-training of time series models to improve fault diagnosis performance and data efficiency in motor condition monitoring.

Findings

MOMENT achieves nearly twice the performance of traditional models with only 1% of training data.

Mantis surpasses state-of-the-art baselines by 22%, reaching 90% accuracy with limited data.

The approach demonstrates strong generalization and scalability in fault diagnosis.

Abstract

Motor condition monitoring is essential for ensuring system reliability and preventing catastrophic failures. However, data-driven diagnostic methods often suffer from sparse fault labels and severe class imbalance, which limit their effectiveness in real-world applications. This paper proposes a motor condition monitoring framework that leverages the general features learned during pre-training of two time series foundation models, MOMENT and Mantis, to address these challenges. By transferring broad temporal representations from large-scale pre-training, the proposed approach significantly reduces dependence on labeled data while maintaining high diagnostic accuracy. Experimental results show that MOMENT achieves nearly twice the performance of conventional deep learning models using only 1% of the training data, whereas Mantis surpasses state-of-the-art baselines by 22%, reaching 90% accuracy with the same data ratio. These results demonstrate the strong generalization and data efficiency of time series foundation models in fault diagnosis, providing new insights into scalable and adaptive frameworks for intelligent motor condition monitoring.