Cleaning Maintenance Logs with LLM Agents for Improved Predictive Maintenance

TL;DR

This paper investigates how large language model agents can improve the cleaning of maintenance logs, addressing data quality issues to enhance predictive maintenance in the automotive industry.

Contribution

It demonstrates the effectiveness of LLM agents in cleaning maintenance logs and discusses potential for future industrial applications and improvements.

Findings

LLMs effectively handle generic cleaning tasks.

Domain-specific errors remain challenging.

LLMs offer a promising foundation for industrial use.

Abstract

Economic constraints, limited availability of datasets for reproducibility and shortages of specialized expertise have long been recognized as key challenges to the adoption and advancement of predictive maintenance (PdM) in the automotive sector. Recent progress in large language models (LLMs) presents an opportunity to overcome these barriers and speed up the transition of PdM from research to industrial practice. Under these conditions, we explore the potential of LLM-based agents to support PdM cleaning pipelines. Specifically, we focus on maintenance logs, a critical data source for training well-performing machine learning (ML) models, but one often affected by errors such as typos, missing fields, near-duplicate entries, and incorrect dates. We evaluate LLM agents on cleaning tasks involving six distinct types of noise. Our findings show that LLMs are effective at handling generic cleaning tasks and offer a promising foundation for future industrial applications. While domain-specific errors remain challenging, these results highlight the potential for further improvements through specialized training and enhanced agentic capabilities.