Retrieval-Augmented Generation with Covariate Time Series

TL;DR

This paper introduces RAG4CTS, a regime-aware retrieval-augmented generation framework for covariate time series, improving predictive maintenance in industrial settings with scarce, transient, and covariate-dependent data.

Contribution

We propose a novel, training-free RAG framework that uses a hierarchical knowledge base and dynamic context optimization for covariate time series.

Findings

Outperforms state-of-the-art baselines in prediction accuracy

Successfully deployed in industrial environment for fault detection

Identified a fault with zero false alarms in two months

Abstract

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.