{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T07:08:23Z","timestamp":1786086503183,"version":"3.56.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T00:00:00Z","timestamp":1771286400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T00:00:00Z","timestamp":1771286400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100016999","name":"Western Norway University Of Applied Sciences","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100016999","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Syst Assur Eng Manag"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Under the influence of various failure mechanisms \u2013 such as corrosion, erosion, fatigue, and deformation \u2013 process equipment (chemical, mechanical, and metallurgical) degrades over its service life. This degradation undermines equipment integrity and heightens the risk of failure. Although total elimination of failure risk is unattainable, robust asset management programs seek to maximize safety, reliability and availability through effective and efficient inspection and maintenance strategies. Designing and executing these programs, however, incurs significant complexity and cost. Risk-based methodologies, such as Risk-Based Inspection (RBI) and Reliability-Centered Maintenance (RCM), provide structured approaches for prioritizing resources and mitigating accident potential. Failure Modes and Effects Analysis (FMEA) remains a cornerstone of risk assessment. While FMEA can incorporate quantitative elements \u2013 such as estimating failure probabilities and consequences \u2013 it is fundamentally qualitative. Consequently, considerable time and effort are devoted to manually identifying hazards, failure modes, failure mechanisms, and failure causes, making traditional expert-driven FMEA processes time-consuming, error-prone, and inherently static. Advances in generative AI have the potential to automate aspects of the FMEA workflow. This study introduces a framework that combines open-source large language models (LLMs) with Retrieval-Augmented Generation (RAG) to extract insights from industry standards and authoritative literature for automated FMEA table generation. The paper describes the proposed architecture and presents initial evaluation results.<\/jats:p>","DOI":"10.1007\/s13198-026-03171-6","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T06:58:15Z","timestamp":1771311495000},"page":"1495-1509","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A framework for automating failure modes and effects analysis (FMEA) using large language models (LLMs) and retrieval-augmented generation (RAG)"],"prefix":"10.1007","volume":"17","author":[{"given":"Kamal V.","family":"Charan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3496-092X","authenticated-orcid":false,"given":"Maneesh","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Surender","family":"Redhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gunjan","family":"Soni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"3171_CR1","volume-title":"API 581: Risk-based inspection methodology","author":"American Petroleum Institute (API)","year":"2016","unstructured":"American Petroleum Institute (API) (2016) API 581: Risk-based inspection methodology. API, Washington, DC"},{"key":"3171_CR3","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.3390\/app14072946","volume":"14","author":"X Cao","year":"2024","unstructured":"Cao X, Xu W, Zhao J, Duan Y, Yang X (2024) Research on large Language model for coal mine equipment maintenance based on Multi-Source text. Appl Sci 14:2946. https:\/\/doi.org\/10.3390\/app14072946","journal-title":"Appl Sci"},{"issue":"7","key":"3171_CR4","doi-asserted-by":"publisher","first-page":"348","DOI":"10.3390\/systems11070348","volume":"11","author":"JJ Cardiel-Ortega","year":"2023","unstructured":"Cardiel-Ortega JJ, Baeza-Serrato R (2023) Failure mode and effect analysis with a fuzzy logic approach. Systems 11(7):348. https:\/\/doi.org\/10.3390\/systems11070348","journal-title":"Systems"},{"key":"3171_CR37","doi-asserted-by":"crossref","unstructured":"Es S, James J, Espinosa-Anke L, Schockaert S (2023) RAGAS: Automated evaluation of retrieval augmented generation. arXiv preprint arXiv:2309.15217","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"3171_CR5","doi-asserted-by":"crossref","unstructured":"Es S, James J, Anke LE, Schockaert S (2024), March Ragas: Automated evaluation of retrieval augmented generation. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations (pp. 150\u2013158)","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"3171_CR6","unstructured":"Ganesan K (2018) Rouge 2.0: Updated and improved measures for evaluation of summarization tasks. arXiv preprint arXiv:1803.01937"},{"key":"3171_CR7","doi-asserted-by":"publisher","unstructured":"Hassan FU, Nguyen T, Le T, Le C (2023) Automated prioritization of construction project requirements using machine learning and fuzzy failure mode and effects analysis (FMEA). Automation in construction https:\/\/doi.org\/10.1016\/j.autcon.2023.105013","DOI":"10.1016\/j.autcon.2023.105013"},{"issue":"DESIGN 2024","key":"3171_CR8","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1017\/pds.2024.204","volume":"4","author":"IE Hassani","year":"2024","unstructured":"Hassani IE, Masrour T, Kourouma N, Motte D, Tav\u010dar J (2024) Integrating large Language models for improved failure mode and effects analysis (FMEA): A framework and case study. Proc Des Soc 4(DESIGN 2024):2019\u20132028. https:\/\/doi.org\/10.1017\/pds.2024.204","journal-title":"Proc Des Soc"},{"key":"3171_CR9","unstructured":"https:\/\/huggingface.co\/meta-llama\/Llama-4-Scout-17B-16E-Instruct"},{"key":"3171_CR10","unstructured":"https:\/\/mistral.ai\/news\/mistral-saba"},{"key":"3171_CR11","unstructured":"International Organization for Standardization (2018) ISO 17359:2018 \u2013 Condition monitoring and diagnostics of Machines \u2013 General guidelines. ISO"},{"key":"3171_CR13","volume-title":"ISO 55000:2014 - Asset management \u2014 Overview, principles, and terminology","author":"International Organization for Standardization (ISO)","year":"2014","unstructured":"International Organization for Standardization (ISO) (2014) ISO 55000:2014 - Asset management \u2014 Overview, principles, and terminology. ISO, Geneva, Switzerland"},{"key":"3171_CR14","volume-title":"ISO 55002:2018 - Asset management \u2014 Management systems \u2014 Guidelines for the application of ISO 55001","author":"International Organization for Standardization (ISO)","year":"2018","unstructured":"International Organization for Standardization (ISO) (2018a) ISO 55002:2018 - Asset management \u2014 Management systems \u2014 Guidelines for the application of ISO 55001. ISO, Geneva, Switzerland"},{"key":"3171_CR15","volume-title":"ISO 31000:2018 - Risk management \u2014 Guidelines","author":"International Organization for Standardization (ISO)","year":"2018","unstructured":"International Organization for Standardization (ISO) (2018b) ISO 31000:2018 - Risk management \u2014 Guidelines. ISO, Geneva, Switzerland"},{"key":"3171_CR16","volume-title":"ISO 31010:2019 - Risk management \u2014 Risk assessment techniques","author":"International Organization for Standardization (ISO)","year":"2019","unstructured":"International Organization for Standardization (ISO) (2019) ISO 31010:2019 - Risk management \u2014 Risk assessment techniques. ISO, Geneva, Switzerland"},{"key":"3171_CR12","volume-title":"ISO\/IEC guide 73:2009 - Risk management \u2014 Vocabulary","author":"International Organization for Standardization (ISO) & International Electrotechnical Commission (IEC)","year":"2009","unstructured":"International Organization for Standardization (ISO) & International Electrotechnical Commission (IEC) (2009) ISO\/IEC guide 73:2009 - Risk management \u2014 Vocabulary. ISO, Geneva, Switzerland"},{"key":"3171_CR17","doi-asserted-by":"publisher","unstructured":"Ivan\u010dan J, Lisjak D (2021) New FMEA Risks Ranking Approach Utilizing Four Fuzzy Logic Systems. Machines 9(11):292. https:\/\/doi.org\/10.3390\/machines9110292","DOI":"10.3390\/machines9110292"},{"key":"3171_CR18","unstructured":"Jin R, Chen R, Lu S, Zhou S, Chen S, Ye S, Wang S, Yu S, Zhou S, Pan S, Li SS et al (2025) DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv"},{"issue":"1","key":"3171_CR19","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1504\/IJMCDM.2017.085154","volume":"7","author":"AJ Kolios","year":"2017","unstructured":"Kolios AJ, Umofia A, Shafiee M (2017) Failure mode and effects analysis using a fuzzy-TOPSIS method: a case study of subsea control module\u2019. Int J Multicriteria Decis Mak 7(1):29\u201353","journal-title":"Int J Multicriteria Decis Mak"},{"key":"3171_CR20","unstructured":"Lin CY (2004), July Rouge: A package for automatic evaluation of summaries. In Text summarization branches out (pp. 74\u201381)"},{"key":"3171_CR35","unstructured":"Meta AI (2024) Llama 4 technical report. Meta Platforms, Inc."},{"key":"3171_CR36","unstructured":"Mistral AI (2025) Mistral Saba: A 24B parameter language model tailored for the Middle East and South Asia. Mistral AI"},{"key":"3171_CR21","volume-title":"NORSOK Z-013: risk and emergency preparedness analysis","author":"Norwegian Petroleum Industry (NORSOK)","year":"2010","unstructured":"Norwegian Petroleum Industry (NORSOK) (2010) NORSOK Z-013: risk and emergency preparedness analysis. Standards Norway, Oslo, Norway"},{"key":"3171_CR22","doi-asserted-by":"crossref","unstructured":"Oluwatoyin SK, Hashim FM, Hussin HB (2014) Failure mode and effect analysis of subsea multiphase pump equipment. In MATEC Web of Conferences (Vol. 13, p. 05001). EDP Sciences","DOI":"10.1051\/matecconf\/20141305001"},{"key":"3171_CR23","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) July Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics (pp. 311\u2013318)","DOI":"10.3115\/1073083.1073135"},{"key":"3171_CR24","doi-asserted-by":"publisher","unstructured":"Peddi S, Lanka K, Gopal PRC (2023) Modified FMEA Using Machine Learning for Food Supply Chain, Materials Today: Proceedings. https:\/\/doi.org\/10.1016\/j.matpr.2023.04.353","DOI":"10.1016\/j.matpr.2023.04.353"},{"key":"3171_CR25","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1007\/s11668-023-01697-6","volume":"23","author":"PP Ray","year":"2023","unstructured":"Ray PP (2023) Transforming industrial reliability: the intersection of failure modes and effects analysis with artificial intelligence. J Fail Anal Prev 23:1383\u20131384. https:\/\/doi.org\/10.1007\/s11668-023-01697-6","journal-title":"J Fail Anal Prev"},{"key":"3171_CR26","unstructured":"Riviere M, Banks J, Dragan A, Petrov S, Vinyals O, Dean J, Hassabis D, Kavukcuoglu K, Farabet C, Buchatskaya E, Borgeaud S, Fiedel N, Joulin A, Kenealy K, Dadashi R, Andreev A, Kenealy K, Dadashi R, Andreev A (2024) Gemma 2. Improving Open Language Models at a Practical Size"},{"issue":"2","key":"3171_CR27","doi-asserted-by":"publisher","first-page":"224","DOI":"10.3390\/pr8020224","volume":"8","author":"S Sader","year":"2020","unstructured":"Sader S, Husti I, Dar\u00f3czi M (2020) Enhancing failure mode and effects analysis using auto machine learning: A case study of the agricultural machinery industry. Processes 8(2):224. https:\/\/doi.org\/10.3390\/pr8020224","journal-title":"Processes"},{"key":"3171_CR28","doi-asserted-by":"publisher","unstructured":"Stewart M, Hodkiewicz M, Li S (2023) Large Language models for failure mode classification: an investigation. ArXiV 1\u20138. https:\/\/doi.org\/10.48550\/arXiv.2309.08181","DOI":"10.48550\/arXiv.2309.08181"},{"key":"3171_CR29","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1007\/s11668-023-01659-y","volume":"23","author":"D Thomas","year":"2023","unstructured":"Thomas D (2023) Revolutionizing failure modes and effects analysis with chatgpt: unleashing the power of AI Language models. J Fail Anal Prev 23:911\u2013913. https:\/\/doi.org\/10.1007\/s11668-023-01659-y","journal-title":"J Fail Anal Prev"},{"key":"3171_CR30","doi-asserted-by":"crossref","unstructured":"Wang H, Li Y (2023) Large Language Model Empowered by Domain-Specific Knowledge Base for Industrial Equipment Operation and Maintenance. 5th International Conference on System Reliability and Safety Engineering (SRSE), 474\u2013479","DOI":"10.1109\/SRSE59585.2023.10336112"},{"issue":"2","key":"3171_CR31","doi-asserted-by":"publisher","first-page":"567","DOI":"10.3390\/app11020567","volume":"11","author":"L Wang","year":"2021","unstructured":"Wang L, Sun L, Kang J, Wang Y, Wang H (2021) Risk identification of FPSO oil and gas processing system based on an improved FMEA approach. Appl Sci 11(2):567. https:\/\/doi.org\/10.3390\/app11020567","journal-title":"Appl Sci"},{"key":"3171_CR32","doi-asserted-by":"crossref","unstructured":"Xia Y, Jazdi N, Weyrich M (2024) Enhance FMEA with Large Language Models for Assisted Risk Management in Technical Processes and Products, International Conference on Emerging Technologies and Factory Automation, 10th -13th September 2024, Padova, Italy","DOI":"10.36227\/techrxiv.172254395.58219170\/v1"},{"key":"3171_CR33","doi-asserted-by":"crossref","unstructured":"Yu H, Gan A, Zhang K, Tong S, Liu Q, Liu Z (2024) August Evaluation of retrieval-augmented generation: A survey. In CCF Conference on Big Data (pp. 102\u2013120). Singapore: Springer Nature Singapore","DOI":"10.1007\/978-981-96-1024-2_8"},{"key":"3171_CR34","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1007\/s40747-021-00279-z","volume":"7","author":"M Yucesan","year":"2021","unstructured":"Yucesan M, Gul M, Celik E (2021) A holistic FMEA approach by Fuzzy-based bayesian network and Best\u2013worst method. Complex Intell Syst 7:1547\u20131564. https:\/\/doi.org\/10.1007\/s40747-021-00279-z","journal-title":"Complex Intell Syst"}],"container-title":["International Journal of System Assurance Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13198-026-03171-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13198-026-03171-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13198-026-03171-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T08:33:15Z","timestamp":1778747595000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13198-026-03171-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,17]]},"references-count":36,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["3171"],"URL":"https:\/\/doi.org\/10.1007\/s13198-026-03171-6","relation":{},"ISSN":["0975-6809","0976-4348"],"issn-type":[{"value":"0975-6809","type":"print"},{"value":"0976-4348","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,17]]},"assertion":[{"value":"9 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"None.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Informed consent"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research involving human participants and\/or animals"}},{"value":"During the preparation of this paper, AI tool (specifically ChatGPT) was used solely to correct grammar and improve clarity. The tool was applied conscientiously and in line with ethical guidelines. No AI was used to generate original ideas, analyses, or references. All research, analysis, interpretations, and conclusions are entirely the authors\u2019 own, and the authors takes full responsibility for the content.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration on the use of AI tools in manuscript Preparation"}}]}}