Citation :

Suyash Kamble, Dadarao Raut, Dattaji Shinde, Pratik Gaikwad, "Artificial Intelligence Integration in the Eight Disciplines (8D) Problem-Solving Methodology: AI-Enhanced Problem Classification at D1 with Complete Manual Execution of D2–D8 — A Manufacturing Case Study," International Journal of Mechanical Engineering, vol. 13, no. 5, pp. 116-128, 2026. Crossref, https://doi.org/10.14445/23488360/IJME-V13I5P108

Abstract

The Eight Disciplines (8D) is a structured approach to problem-solving that is used in process and manufacturing quality management. Despite the popularity of the methodology, it remains that problem description and classification (D1) continues to be a bottleneck in its implementation, taking an outsized share of manual labor compared to analytical yield. This paper details a full-fledged end-to-end 8D implementation of a pulley fettling defect occurring in a small to medium casting and manufacturing firm at Kolhapur(Maharashtra, India). Only automated D1 (Problem Classification) with a dedicated AI system, while leveraging traditional manual methods for disciplines D2 through D8 to maintain the team-based and human-centric nature of the 8D framework. The AI method is performed through a classification algorithm powered by a Large Language Model (LLM) with rigorously defined composite confidence metric ψ=α·ψssm+β·ψstruct + γ·ψcons with empirically optimised weights (α = 0.45, β = 0.35, γ = 0.20). The performance of the AI system for the D1 classification demonstrates good accuracy, with a corresponding sensitivity (accuracy) of 89.7%, departmental recall of 92.1%, precision of 87.3%, F1-score equal to 0.895 and mean confidence score of ~0.847; Time taken for D1 phase was decreased from four working days (manual baseline) to 30 minutes resulting in a time saving of 99.0%. The latter manual 8D disciplines (D2–D8) are ideally bounded, including setting up the cross-functional team, taking interim containment actions, performing an Ishikawa fishbone root cause analysis, planning and implementing corrective actions as well as preventive measures in place, and recognizing the team. Quantitatively, these outcomes show that the AI-enabled D1 provided a clearer, more specific, and well-formed problem definition for which downstream manual work can be both higher quality and require less time to complete. In total, the 8D cycle time itself improved from a prior state average gap of 63 days to 41 days — about a modest improvement of 34.9 percent directly attributable to AI at D1 level improvements alone. Based on the findings, process performance outcomes validate that the corrective actions are effective: (i) fettling cycle time was reduced by 74 per cent, monthly production capacity was increased by 58.8 per cent, operator fatigue improved by 73 per cent, and (ii) there have been no incidents of operator injuries. This paper creates the groundwork for a five-paper series on discipline-specific concepts for integrating AI-8D.

Keywords

Artificial Intelligence, Eight Disciplines (8d), Industry 5.0, Large Language Model, Quality Management Problem Classification.

References

1. Khalid Mahmood, “Solving Manufacturing Problems with 8D Methodology: A Case Study of Leakage Current in a Production Company,” Journal of Electrical Electronics Engineering, pp. 1-18, 2023.
   [Google Scholar] [Publisher Link]
2. Anand Bewoor, Sagar Sapkal, and Pratiksha Dhaygude, “Mappng Lean Six Sigma with 8D Problem-Solving Methodology to Improve Productivity and Safety,” Proceedings of ICIME- 2021, 2021.
   [Google Scholar]
3. Rajeev Rathi, “Investigation and Implementation of 8D Methodology in a Manufacturing System,” Materials Today: Proceedings, vol. 50, pp. 743-750, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Mithun Sharma, Shilpi Sharma, and Sanjeev Sahni, “Structured Problem Solving: Combined Approach Using 8D and Six Sigma,” Engineering Management in Production and Services, vol. 12, no. 1, pp. 57-69, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Arturo Realyvásquez-Vargas et al., “Improving a Manufacturing Process Using the 8Ds Method. A Case Study in a Manufacturing Company,” Applied Sciences, vol. 10, no. 7, pp. 1-26, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Hsiang-Ru Chen, and Bor-Wen Cheng, “A Case Study in Solving Customer Complaints Based on the 8Ds Method and Kano Model,” Journal of the Chinese Institute of Industrial Engineers, vol. 27, no. 10, pp. 339-350, 2010.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Sevilay Uslu Divanoğlu, and Ülge Taş, “Application of 8D Methodology: An Approach to Reduce Failures in the Automotive Industry,” Engineering Failure Analysis, vol. 134, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Cristina – Florena Banica, and Nadia Belu, “Application of 8D Methodology — An Effective Problem-Solving Tool in the Automotive Industry,” Scientific Bulletin, pp. 1-7, 2019.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Lalit Kumar Biban, and Deepak Dhounchak, “Relevance of 8D Methodology,” Journal of Emerging Technologies and Innovative Research, pp. 415-419, 2017.
   [Google Scholar] [Publisher Link]
10. Joaquín Ordieres-Meré, Miguel Gutierrez, and Javier Villalba-Díez, “Toward the Industry 5.0 Paradigm: Increasing Value Creation through the Robust Integration of Humans and Machines,” Computers in Industry, vol. 150, pp. 1-15, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
11. João Barata, and Ina Kayser, “Industry 5.0 — Past, Present, and Near Future,” Procedia Computer Science, vol. 219, pp. 778-788, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Evgeniy Bryndin, “Formation and Management of Industry 5.0 by Systems with Artificial Intelligence,” American Journal of Mechanical and Industrial Engineering, vol. 5, no. 2, pp. 24-30, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Morteza Ghobakhloo et al., “Behind the Definition of Industry 5.0: A Systematic Review of Technologies, Principles, Components, and Values,” Journal of Industrial and Production Engineering, vol. 40, no. 6, pp. 432-447, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Gregoris Mentzas et al., “Human-Centered Artificial Intelligence in Industry 5.0,” Frontiers in Artificial Intelligence, vol. 7, pp. 1-4, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Barbara Martini, Denise Bellisario, and Paola Coletti, “Human-Centered and Sustainable Artificial Intelligence in Industry 5.0,” Sustainability, vol. 16, no. 13, pp. 1-17, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Konstantinos Papageorgiou et al., “A Systematic Review on Machine Learning Methods for Root Cause Analysis towards Zero-Defect Manufacturing,” Frontiers in Manufacturing Technology, vol. 2, pp. 1-16, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Nikhil Bharadwaj Ramashastri, “Rise of AI-Powered Root Cause Analysis: Revolutionizing Problem Solving in Modern Systems,” International Journal of Computer Engineering and Technology, vol. 15, no. 4, pp. 158-167, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Srecko Joksimovic et al., “Opportunities of Artificial Intelligence for Supporting Complex Problem-Solving: Findings from a Scoping Review,” Computers and Education: Artificial Intelligence, vol. 4, pp. 1-12, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Joanna Cyganiuk et al., “Solving Selected Quality Management Problems with the D4 Discipline Algorithm of the G8D Method,” System Safety: Human - Technical Facility - Environment, vol. 1, no. 1, pp. 996-1003, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Seyedehshelernaz Azimi, and Claus Pahl, “Root Cause Analysis and Remediation for Quality and Value Improvement in Machine Learning Driven Information Models,” International Conference on Enterprise Information Systems, vol. 1, pp. 656-665, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Dominik Pietsch et al., “Root Cause Analysis in Industrial Manufacturing: A Scoping Review,” Journal of Manufacturing and Materials Processing, vol. 8, no. 6, pp. 1-19, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]