KRAIL: A Knowledge-Driven Framework for Base Human Reliability Analysis Integrating IDHEAS and Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xiao, Xingyu, Chen, Peng, Qi, Ben, Zhao, Hongru, Liang, Jingang, Tong, Jiejuan, Wang, Haitao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912169387360256
author Xiao, Xingyu
Chen, Peng
Qi, Ben
Zhao, Hongru
Liang, Jingang
Tong, Jiejuan
Wang, Haitao
author_facet Xiao, Xingyu
Chen, Peng
Qi, Ben
Zhao, Hongru
Liang, Jingang
Tong, Jiejuan
Wang, Haitao
contents Human reliability analysis (HRA) is crucial for evaluating and improving the safety of complex systems. Recent efforts have focused on estimating human error probability (HEP), but existing methods often rely heavily on expert knowledge,which can be subjective and time-consuming. Inspired by the success of large language models (LLMs) in natural language processing, this paper introduces a novel two-stage framework for knowledge-driven reliability analysis, integrating IDHEAS and LLMs (KRAIL). This innovative framework enables the semi-automated computation of base HEP values. Additionally, knowledge graphs are utilized as a form of retrieval-augmented generation (RAG) for enhancing the framework' s capability to retrieve and process relevant data efficiently. Experiments are systematically conducted and evaluated on authoritative datasets of human reliability. The experimental results of the proposed methodology demonstrate its superior performance on base HEP estimation under partial information for reliability assessment.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18627
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KRAIL: A Knowledge-Driven Framework for Base Human Reliability Analysis Integrating IDHEAS and Large Language Models
Xiao, Xingyu
Chen, Peng
Qi, Ben
Zhao, Hongru
Liang, Jingang
Tong, Jiejuan
Wang, Haitao
Computation and Language
Human reliability analysis (HRA) is crucial for evaluating and improving the safety of complex systems. Recent efforts have focused on estimating human error probability (HEP), but existing methods often rely heavily on expert knowledge,which can be subjective and time-consuming. Inspired by the success of large language models (LLMs) in natural language processing, this paper introduces a novel two-stage framework for knowledge-driven reliability analysis, integrating IDHEAS and LLMs (KRAIL). This innovative framework enables the semi-automated computation of base HEP values. Additionally, knowledge graphs are utilized as a form of retrieval-augmented generation (RAG) for enhancing the framework' s capability to retrieve and process relevant data efficiently. Experiments are systematically conducted and evaluated on authoritative datasets of human reliability. The experimental results of the proposed methodology demonstrate its superior performance on base HEP estimation under partial information for reliability assessment.
title KRAIL: A Knowledge-Driven Framework for Base Human Reliability Analysis Integrating IDHEAS and Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2412.18627