TSFM in-context learning for time-series classification of bearing-health status

TL;DR

This paper presents a novel in-context learning approach using time-series foundation models for classifying bearing health status from vibration data without fine-tuning, enabling scalable AI-driven maintenance.

Contribution

It introduces a new method leveraging TSFMs for in-context classification of time-series data, bypassing traditional training or fine-tuning processes.

Findings

Effective classification across different operational conditions

No need for model fine-tuning or additional training

Potential for scalable AI maintenance solutions

Abstract

We introduce a classification method based on in-context learning using time-series foundation models (TSFMs). We demonstrate how data not included in the TSFM training can be classified without fine-tuning the foundation model or training a traditional classification model. Examples are represented as targets (class labels) and covariates (data matrices) within the TSFM prompt, enabling the classification of unknown covariate data patterns alongside the forecast horizon through in-context learning. We apply this method to vibration data to assess the health state of a bearing within a servo-press motor. The method transforms frequency-domain reference signals into pseudo time-series patterns, generates aligned covariate and target signals, and uses the TSFM to predict class-membership probabilities for predefined labels. Leveraging the scalability of pre-trained models, the proposed method demonstrates effectiveness across varying operational conditions. This represents significant progress beyond traditional, custom AI solutions towards broader AI-driven maintenance systems that could potentially be provided as Model- or Software-as-a-Service applications.