View in EDS

Intelligent Operational Risk Management Using the Enhanced FMEA Method and Artificial Intelligence—A Case Study.

Saved in:
Bibliographic Details
Title: Intelligent Operational Risk Management Using the Enhanced FMEA Method and Artificial Intelligence—A Case Study.
Authors: Ratajszczak, Kinga, Oancea, Alexandru-Vasile, Misztal, Agnieszka, Ionescu, Nadia, Ionescu, Laurențiu Mihai, Wencek, Anna
Source: Applied Sciences (2076-3417); Dec2025, Vol. 15 Issue 24, p13199, 18p
Subject Terms: OPERATIONAL risk, FAILURE mode & effects analysis, MATHEMATICAL optimization, RISK assessment, LANGUAGE models, ARTIFICIAL intelligence, MANUFACTURING process management
Company/Entity: OPENAI Inc.
Abstract: The main purpose of the article is to demonstrate how large language models (LLMs) can enhance and automate the Failure Modes and Effects Analysis (FMEA) method to improve the identification, assessment, and management of operational risk in modern technological systems. The study aims to show that integrating AI into FMEA increases the efficiency, precision, and reliability of detecting potential failures and evaluating their consequences, provided that expert supervision and model transparency are maintained. The research combines a literature review with a case study using OpenAI's model to generate an automated FMEA for a manufacturing process. The methodology defines process components, identifies potential failure modes, and evaluates their risk impact. Five specialized libraries—structure, function, failure, risk, and optimization—serve as structured inputs for the LLM. A feedback mechanism allows the system to learn from previous analyses, improving future risk assessments and supporting continuous process optimization. The developed platform enables engineers to initiate projects, input data, generate and validate AI-based FMEA reports, and export results. Overall, the study demonstrates that the integration of LLMs into FMEA can transform operational risk management, making it more intelligent, adaptive, and data-driven. [ABSTRACT FROM AUTHOR]
Copyright of Applied Sciences (2076-3417) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:The main purpose of the article is to demonstrate how large language models (LLMs) can enhance and automate the Failure Modes and Effects Analysis (FMEA) method to improve the identification, assessment, and management of operational risk in modern technological systems. The study aims to show that integrating AI into FMEA increases the efficiency, precision, and reliability of detecting potential failures and evaluating their consequences, provided that expert supervision and model transparency are maintained. The research combines a literature review with a case study using OpenAI's model to generate an automated FMEA for a manufacturing process. The methodology defines process components, identifies potential failure modes, and evaluates their risk impact. Five specialized libraries—structure, function, failure, risk, and optimization—serve as structured inputs for the LLM. A feedback mechanism allows the system to learn from previous analyses, improving future risk assessments and supporting continuous process optimization. The developed platform enables engineers to initiate projects, input data, generate and validate AI-based FMEA reports, and export results. Overall, the study demonstrates that the integration of LLMs into FMEA can transform operational risk management, making it more intelligent, adaptive, and data-driven. [ABSTRACT FROM AUTHOR]
ISSN:20763417
DOI:10.3390/app152413199