Retrieval-Augmented Generation with Covariate Time Series
This work provides a novel, training-free RAG framework for covariate time-series, addressing data scarcity and transient dynamics in high-stakes industrial predictive maintenance scenarios for engineers and operators.
This paper tackles the challenge of applying Retrieval-Augmented Generation (RAG) to Time-Series Foundation Models (TSFMs) for predictive maintenance, specifically for Pressure Regulating and Shut-Off Valves (PRSOVs). Their proposed RAG4CTS framework significantly outperforms state-of-the-art baselines in prediction accuracy and has successfully identified one PRSOV fault in two months with zero false alarms since deployment.
While RAG has greatly enhanced LLMs, extending this paradigm to Time-Series Foundation Models (TSFMs) remains a challenge. This is exemplified in the Predictive Maintenance of the Pressure Regulating and Shut-Off Valve (PRSOV), a high-stakes industrial scenario characterized by (1) data scarcity, (2) short transient sequences, and (3) covariate coupled dynamics. Unfortunately, existing time-series RAG approaches predominantly rely on generated static vector embeddings and learnable context augmenters, which may fail to distinguish similar regimes in such scarce, transient, and covariate coupled scenarios. To address these limitations, we propose RAG4CTS, a regime-aware, training-free RAG framework for Covariate Time-Series. Specifically, we construct a hierarchal time-series native knowledge base to enable lossless storage and physics-informed retrieval of raw historical regimes. We design a two-stage bi-weighted retrieval mechanism that aligns historical trends through point-wise and multivariate similarities. For context augmentation, we introduce an agent-driven strategy to dynamically optimize context in a self-supervised manner. Extensive experiments on PRSOV demonstrate that our framework significantly outperforms state-of-the-art baselines in prediction accuracy. The proposed system is deployed in Apache IoTDB within China Southern Airlines. Since deployment, our method has successfully identified one PRSOV fault in two months with zero false alarm.