Industrial-Grade Smart Troubleshooting through Causal Technical Language Processing: a Proof of Concept

TL;DR

This paper introduces a causal diagnosis system for industrial troubleshooting using large language models to interpret technical language and causal relationships, demonstrated in a real-world predictive maintenance scenario.

Contribution

It presents a novel causality-aware retrieval augmented generation approach leveraging LLMs for industrial troubleshooting based on technical language analysis.

Findings

Effective causal diagnosis in industrial settings demonstrated

Utilizes vectorized linguistic knowledge from LLMs for fault detection

Discusses future improvements for robustness in complex scenarios

Abstract

This paper describes the development of a causal diagnosis approach for troubleshooting an industrial environment on the basis of the technical language expressed in Return on Experience records. The proposed method leverages the vectorized linguistic knowledge contained in the distributed representation of a Large Language Model, and the causal associations entailed by the embedded failure modes and mechanisms of the industrial assets. The paper presents the elementary but essential concepts of the solution, which is conceived as a causality-aware retrieval augmented generation system, and illustrates them experimentally on a real-world Predictive Maintenance setting. Finally, it discusses avenues of improvement for the maturity of the utilized causal technology to meet the robustness challenges of increasingly complex scenarios in the industry.