(326b) Leveraging Generative Large Language Models for Automated Incident Analysis in the Process Industry

Incidents within the process industry pose significant threats, including economic losses, equipment damage, and adverse impacts on public safety and corporate reputation. Therefore, incident investigation, a key component of Process Safety Management (PSM), is essential for learning from past events and preventing recurrence, playing a pivotal role in risk mitigation, organizational learning, and continuous improvement. Recent advancements in machine learning (ML) and natural language processing (NLP) provide promising opportunities to automate and enhance the analysis of extensive incident records.

Transformer-based pretrained models (e.g., BERT) have recently emerged as effective tools for automated incident analysis but typically require extensive labeled datasets, leading to risks of overfitting and limited interpretability. To address these challenges, this study proposes a novel framework employing generative large language models (LLMs), enhanced with structured, domain-specific Chain-of-Thought (CoT) prompting and retrieval-augmented generation (RAG) strategies. Specifically, the framework integrates hierarchical root cause classification guidelines from the American Bureau of Shipping (ABS) with offshore platform incident reports published by the Bureau of Safety and Environmental Enforcement (BSEE). Preliminary results using GPT-4o-mini indicate that domain-specific CoT prompting significantly improves LLM classification accuracy, achieving notably higher precision compared to basic zero-shot and few-shot methods. Furthermore, incorporating RAG strategies leveraging local domain knowledge bases enhances model reliability and supports continuous refinement through accumulating incident data.

This research highlights the substantial potential of generative LLMs in automating and advancing incident analysis practices, providing a viable path toward digitalizing incident investigation processes and strengthening PSM practices. Ultimately, the proposed approach enables systematic learning from incidents, offering valuable opportunities to reduce both the frequency and severity of future events in the process industry.