An Intelligent Framework for Implementing AIAG–VDA FMEA and Action Priority (AP) Assessment
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index; 6 of the 18 sources its claims cite were checked for support.
Abstract
The paper presents the Failure Mode and Effects Analysis (FMEA) method applied to a process-based case study, together with an approach for implementing the AIAG & VDA harmonized FMEA standard by using modern digital tools. While classical FMEA is widely used in the industry, risk assessment based on the Risk Priority Number (RPN) often leads to the inconsistent ranking of failures and unclear prioritization of corrective actions. This paper explores the shift from the traditional Risk Priority Number (RPN) approach to the Action Priority (AP) concept introduced in the AIAG & VDA FMEA Handbook and explains why this change leads to clearer, more consistent risk-based decisions. Rather than focusing only on the methodological differences, the paper also outlines a practical framework for full implementation, showing how Industry 4.0 technologies can strengthen traceability, improve response time, and ensure greater consistency in PFMEA development. It also examines how Artificial Intelligence (AI) and Large Language Models (LLMs) can support engineers in everyday practice—for example, by helping identify potential failure modes, standardizing documentation, and guiding the definition of prevention and detection controls. In parallel, IoT-based monitoring and real-time data collection can provide valuable feedback to validate occurrence and detection ratings. Over time, this data-driven feedback loop can improve the accuracy and reliability of risk assessments. The proposed framework contributes to improved responsiveness in process optimization activities, reduces the probability of recurring failures, and supports continuous quality improvement in manufacturing organizations. The solution is discussed in relation to classical FMEA practices and recent trends in the digital transformation of quality management systems.
Overview
CoChat Summary
TL;DR
The paper presents an AI/LLM-based framework for automating AIAG–VDA FMEA and Action Priority assessment, piloted on a 3D laser cutting process using a Prima Power Laser Next LN1530. Initial risk assessment classified 67% Low, 29% Medium, and 4% High risks; after corrective and preventive actions, all failure modes were reclassified as Low (100%).
Key findings
- The most significant failure modes were missing holes and unsatisfactory cutting edge surface quality, with direct impact on assembly capability and customer acceptance.
- Initial risk distribution was Low 67%, Medium 29%, and High 4%; High-priority cases were primarily associated with improper cutting parameter settings and inadequate base material conditions.
- After optimization, all identified failure modes were classified as Low risk (L-100%), attributed to standardized cutting parameters, automated controls/poka-yoke, updated maintenance plans, and reinforced inspections.
- The pilot automated solution handled 319 requests over 6 months: 98 Low (31%), 172 Medium (54%), and 49 High (15%); response time was max ~30 s versus previous ~5–10 min data collection, ~1–3 h analysis, and up to 24 h response generation. Cumulated total response time was 9570 s for full AI LLM pilot versus 4199 s with automated FMEA (AI LLM) pre-analysis.
Methods
- Case study on 3D laser cutting of S235JRH steel rectangular hollow tube (60 × 40 × 4 mm) using a Prima Power Laser Next LN1530, following the AIAG & VDA FMEA (2019) seven-step framework.
- A web-based pilot platform was developed with HTML/CSS/JS/Jinja frontend, Python 3.12 backend, JSON knowledge base, and ChatGPT/GPT-5.1 via OpenAI API; non-AI threshold pre-analysis classified Low risks, while Medium/High risks triggered LLM analysis.
- S-O-D ratings were assigned per AIAG & VDA grids; AP thresholds used monthly internal nonconformities (0–5 parts/month ≤500 ppm Low; 6–20 parts/month 600–2000 ppm Medium; >20 parts/month >2000 ppm High), external nonconformities, customer complaints, and defect trend.
Limitations
- Stated: the solution was implemented as a pilot for one specific production process (3D laser cutting) and can be extended to other manufacturing processes; future work includes completing the knowledge base and expanding the industrial domain.
- Stated: the solution does not replace specialists or modify the risk evaluation methodology itself; AI responses are restricted to an expert-created knowledge base to reduce hallucinations.
- Evident: the study is a single-case pilot with a small user group (six plus one receptionist), no control group or statistical validation, and results rely on expert review and operational implementation rather than independent replication.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
6 Valid · 10 Not valid · 7 Not checked · 73 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The implementation of a complete framework covering the entire workflow, from defining the production process and recording defects at batch level to the automatic generation of the FMEA report.”
§ An Intelligent Framework for Implementing AIAG-VDA FMEA and Action Priority (AP) Assessment > 1. Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Before implementing the optimization measures, the distribution of risk levels (Figure 4) showed a predominance of Low risks (L-67%), a significant proportion of Medium risks (M-29%), and a small but critical percentage of High risks (H-4%).”
- Also stated in: § 5. Results · plain
“The initial risk assessment indicated that most of the identified risks were classified as Low (67%), followed by Medium (29%), while only 4% were categorized as High.”
§ An Intelligent Framework for Implementing AIAG-VDA FMEA and Action Priority (AP) Assessment > 4.1. FMEA Implementation: The Seven Stages of Risk Analysis
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. Results · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“After the implementation of the optimization actions, the FMEA reassessment demonstrated a significant reduction in the overall risk level, with all failure modes being classified as Low risk (L-100%), confirming the effectiveness of the implemented control system.”
- Also stated in: § 5. Results · plain
“The subsequent FMEA reassessment showed that all identified failure modes were classified in the Low-risk category (L-100%).”
§ An Intelligent Framework for Implementing AIAG-VDA FMEA and Action Priority (AP) Assessment > 4.1. FMEA Implementation: The Seven Stages of Risk Analysis
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. Results · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The High-priority cases were primarily associated with improper cutting parameter settings and inadequate base material conditions.”
§ An Intelligent Framework for Implementing AIAG-VDA FMEA and Action Priority (AP) Assessment > 5. Results
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The use of a preprocessing stage before involving the AI component.In this approach, a group of experts (engineers, management, and quality specialists) defined the risk classifications and the corresponding indicators for each failure mode, as is typically done in a traditional risk analysis.”
§ An Intelligent Framework for Implementing AIAG-VDA FMEA and Action Priority (AP) Assessment > 1. Introduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
24 more claims
Create a free account to see all 96 claims and to verify the 1 reference still open.
- Probably not a substantial claim. 47
- It may state two separate claims as one. 40
- The quote only partly states this claim. 3
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ An Intelligent Framework for Implementing AIAG-VDA FMEA and Action Priority (AP) Assessment > 4.2. Development of an Automated Solution for the Assessment of the AP Index in FMEA
“the number involved users is six: two members of the quality assurance team, two production engineers, and one member of the management team.In addition, a receptionist responsible for complaint emails is involved in monitoring this input channel.”
§ An Intelligent Framework for Implementing AIAG-VDA FMEA and Action Priority (AP) Assessment > 6. Conclusions
“| Number of users involved | 6 + 1 (2 quality eng., 3 production eng., 1 management team + 1 reception operator) |”
Citations
Cites
Fault Tree Analysis Improvements: A Bibliometric Analysis and Literature Review
Yazdi, M., Mohammadpour, J., Li, H., Huang, H., Zarei, E., Pirbalouti, R. G., & Adumene, S. (2023) · Quality and Reliability Engineering International · doi:10.1002/qre.3271 · Cited by 199
Li, Y., Liu, P., & Li, G. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109196 · Cited by 50
Hybrid Intelligence Failure Analysis for Industry 4.0: A Literature Review and Future Prospective
Mokhtarzadeh, M., Rodríguez-Echeverría, J., Semanjski, I., & Gautama, S. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02376-5 · Cited by 35
Failure Mode and Effect Analysis (FMEA)
(2002) · Six Sigma and Beyond · doi:10.1201/9781420000290.ch6 · Cited by 32
A Concept of Risk Prioritization in FMEA Analysis for Fluid Power Systems
Fabis-Domagala, J., Domagala, M., & Momeni, H. (2021) · Energies · doi:10.3390/en14206482 · Cited by 31
A Concept of Risk Prioritization in FMEA of Fluid Power Components
Fabiś-Domagała, J., & Domagała, M. (2022) · Energies · doi:10.3390/en15176180 · Cited by 22
Gao, F., & Zhou, D. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.12.025 · Cited by 16
Nechita, R.-M., Stochioiu, F.-P.-G., & Grecu, I. (2025) · Systems · doi:10.3390/systems13080687 · Cited by 15
Smart Machine Vision System to Improve Decision-Making on the Assembly Line
Silva, C. A. D. S., & Paladini, E. P. (2025) · Machines · doi:10.3390/machines13020098 · Cited by 13
Optimization of PFMEA Team Composition in the Automotive Industry Using the IPF-RADAR Approach
Komatina, N., & Marinković, D. (2025) · Algorithms · doi:10.3390/a18060342 · Cited by 13
Aleksić, A., Tadić, D., Komatina, N., & Nestić, S. (2025) · Mathematics · doi:10.3390/math13132216 · Cited by 11
Practical Application of the New Approach To FMEA Method according to AIAG and VDA Reference Manual
Plinta, D., Golińska, E., & Dulina, Ľ. (2021) · Communications - Scientific letters of the University of Zilina · doi:10.26552/com.c.2021.4.b325-b335 · Cited by 11
Sun, J.-J., Yeh, T.-M., & Pai, F.-Y. (2022) · Mathematics · doi:10.3390/math10152596 · Cited by 10
Kluse, C. (2020) · Journal of Management and Engineering Integration · doi:10.62704/10057/24747 · Cited by 9
Investigation into a Potential Reduction of FMEA Efforts Using Action Priority
Barsalou, M. A. (2022) · Management and Production Engineering Review · doi:10.24425/mper.2022.142395 · Cited by 6
REFS-A Risk Evaluation Framework on Supply Chain
Mihálcz, I., & Kosztyán, Z. T. (2024) · Mathematics · doi:10.3390/math12060841 · Cited by 4
Ma, X., & Gu, M. (2025) · Machines · doi:10.3390/machines13030242 · Cited by 4
Risk Assessment Using the PFDA-FMEA Integrated Method
Čička, M., Turisová, R., & Čičková, D. (2022) · Quality Innovation Prosperity · doi:10.12776/qip.v26i3.1772 · Cited by 3
Nechita, R.-M., Stochioiu, F.-P.-G., & Grecu, I. (2025) · Preprints.org · doi:10.20944/preprints202507.0187.v1 · Cited by 3
Ratajszczak, K., Oancea, A.-V., Misztal, A., Ionescu, N., Ionescu, L. M., & Wencek, A. (2025) · Applied Sciences · doi:10.3390/app152413199 · Cited by 3
Self-citationRisk Prioritization in the Laser Cutting Process Using the FMEA Method Compared to the TOPSIS Method
Rachieru, N. (2024) · RECENT - REzultatele CErcetărilor Noastre Tehnice · doi:10.31926/recent.2024.73.122 · Cited by 2
Ramard, M., Laniel, R., Miroir, M., et al. (2025) · Journal of Manufacturing and Materials Processing · doi:10.3390/jmmp9030091 · Cited by 2
Addressing Uncertainty in Digital Risk Evaluation Using a Fuzzy-FMEA MethodologyPreprint
Naciri, L., Merzouk, S., Gallab, M., Nardo, M. D., & Soulhi, A. (2025) · Research Square · doi:10.21203/rs.3.rs-6423322/v1 · Cited by 2
Integrating Industry 4.0 Technologies into 8D Methodologies: A Case Study in the Automotive Industry
Oancea, A.-V., Ionescu, N., Rontescu, C., Ionescu, L.-M., Misztal, A., Bogatu, A.-M., Cicic, D.-T., & Pirvu, V. (2025) · Applied Sciences · doi:10.3390/app152011262 · Cited by 1
Self-citationSmart Machine Vision System to Improve Decision-Maker on the Assembly Line
Silva, C. A. D. S., & Paladini, E. P. (2024) · doi:10.20944/preprints202412.0617.v1
Drzewiecka-Dahlke, M. (2024) · EUROPEAN RESEARCH STUDIES JOURNAL · doi:10.35808/ersj/3719
Research works printed but not linked: 4
- Barsalou, M. (2020, January 21–22). DFMEAs with the New AIAG/VDA FMEA Handbook. Proceedings of the 4th ICQEM Conference, Braga, Portugal.
- Anackovski, 2021, Action priority in new FMEA as factor for resources management in risk reduction, Int. J. Sci. Eng. Res., 12, 921
- 2018, Sensitivity analysis of FMEA as possible ranking method in risk prioritization, UPB Sci. Bull. Ser. D, 80, 55
- Pietreanu, 2018, Qualitative and Quantitative Assessment of Risks Associated to HELIOS HP 03-2 Unmanned Aerial Vehicle Developed by NASA, UPB Sci. Bull. Ser. D, 80, 39
Cited by
Jeluš, A., Breznická, A., Kohutiar, M., Krbaťa, M., Eckert, M., Mikuš, P., Kakošová, L., & Fekiač, J. J. (2026) · Processes · doi:10.3390/pr14121976
Metadata
- Authors
- Oancea, A.-V., Ionescu, L.-M., Rontescu, C., Ionescu, N., Misztal, A., Bogatu, A.-M., Știrbu, C., Cicic, D.-T., & Stanciu, E.-M.
- Affiliations
- Universitatea Națională de Știință și Tehnologie Politehnica București (RO)
- Faculty of Electronics, Communications and Computers, Pitești University Centre, National University of Science and Technology Politehnica Bucharest, 313 Spl. Independenței, 060042 Bucharest, Romania
- Doctoral School, Faculty of Industrial Engineering and Robotic, National University of Science and Technology Politehnica Bucharest, 313 Spl. Independenței, 060042 Bucharest, Romania
- Poznań University of Technology (PL)
- Transilvania University of Brașov (RO)
- ORCID
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2026-03-09
- Volume
- 16
- Issue
- 5
- Pages
- 2591
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W7134242580
- Semantic Scholar
- 035f8af46e7f90ff6801c6322c56af655a009227
- Cited by
- 1
- References
- 20
- Citations by year
- 2026: 1
- FWCI
- 5.98
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Social Sciences › Business, Management and Accounting › Strategy and Management › Management Systems and Quality Improvement
- Social Sciences › Business, Management and Accounting › Strategy and Management › Management and Optimization Techniques
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Reliability and Maintenance Optimization
- Keywords
- failure mode and effects analysis, action priorities, risk priority number, risk-based decision making, corrective action prioritization, Industry 4.0, large language models, artificial intelligence in engineering, IoT monitoring, real-time data acquisition, quality management systems, production process optimization, digital transformation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.