TSFM in-context learning for time-series classification of bearing-health status
This enables AI-driven maintenance systems for bearing health monitoring, representing incremental progress beyond custom narrow AI solutions.
The paper tackles bearing health classification using time-series foundation models with in-context learning, achieving classification without fine-tuning by representing examples as targets and covariates in prompts, and demonstrates efficacy across varied operational conditions.
This paper introduces a classification method using in-context learning in time-series foundation models (TSFM). We show how data, which was not part of the TSFM training data corpus, can be classified without the need of finetuning the model. Examples are represented in the form of targets (class id) and covariates (data matrix) within the prompt of the model, which enables to classify an unknown covariate data pattern alongside the forecast axis through in-context learning. We apply this method to vibration data for assessing 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 probabilities how classified data corresponds to predefined labels. Leveraging the scalability of pre-trained models this method demonstrates efficacy across varied operational conditions. This marks significant progress beyond custom narrow AI solutions towards broader, AI-driven maintenance systems.