Generative AI for Unified Bill of Materials: Connecting Engineering, Manufacturing, Service and Sales

Article Sidebar

PDF
Published: 2026-02-03
DOI: https://doi.org/10.15662/IJRPETM.2026.0901005
Keywords:
Generative AI, Bill of Materials (BOM), Data automation, Lifecycle management, Machine learning, Systems integration, Product development efficiency

Main Article Content

Krishna Baride
Coventry University, UK

Abstract

In general, production products are usually based on numerous Bills of Materials (BOMs) such as engineering BOMs to design, manufacturing BOMs to produce, service BOMs to service, and sales/customer BOMs to configure. Although these BOMs are optimized according to various life cycle phases, their segregation is likely to cause fragmentation of data management, which causes version discrepancies, manual redundancy, and data quality problems. These issues are a great impediment to efficient product development and after sales.


 


This paper provides a framework of Generative AI-based unified Bill of Materials (BOM) management to overcome these constraints. Using Generative AI and machine-learning algorithms, the suggested framework is able to automatically extract the BOM data in unstructured sources and harmonize several perspectives of BOM into a single representation. As an example, an AI-based system can decipher engineering drawings and technical documentation in the format of PDFs to create structured BOMs, which saves a ton of manual work and saves time on processing.


 


The suggested strategy will allow a smooth process of co-ordinating the engineering, manufacturing, service, and sales processes, which will enhance cross-functional coordination and real-time decision-making. The paper explains the ways in which Generative AI implementation in BOM management improves the accuracy of data, shortens the time of product development, and minimizes operational losses. Additionally, it outlines the opportunities of the suggested framework to enhance the integration of the enterprise systems and competitiveness of the organization according to the changing demands of the market.

Article Details

Issue

Vol. 9 No. 1 (2026): International Journal of Research Publications in Engineering, Technology and Management

Section

Articles

How to Cite

Generative AI for Unified Bill of Materials: Connecting Engineering, Manufacturing, Service and Sales. (2026). International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 9(1), 30-43. https://doi.org/10.15662/IJRPETM.2026.0901005

References

1. A. Alqahtani, S. Banitaan, and S. Banitaan, "A systematic literature review of software risk management for global software development," in 2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), 2017, pp. 1310–1317. [Online]. Available: https://doi.org/10.1109/AICCSA.2017.71.

2. I. Barclay, A. Preece, I. Taylor, S. Krishnakumar Radha, and J. Nabrzyski, "Providing assurance and scrutability on shared data and machine learning models with verifiable credentials," Concurrency and Computation: Practice and Experience, vol. 35, no. 18, e6997, 2023.

3. I. Barclay, A. Preece, I. Taylor, and D. Verma, "Towards traceability in data ecosystems using a bill of materials model," arXiv preprint arXiv:1904.04253, 2019.

4. C. Benedetti, F. Cofano, et al., "The Impact of SBOM Generators on Vulnerability Assessment in Python: A Comparison and a Novel Approach," in International Conference on Software Engineering and Security, Springer, 2024, pp. 1–12. [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-031-95764-2_19.

5. K. Bennet, G. Krishnan Rajbahadur, A. Suriyawongkul, and K. Stewart, "Implementing AI Bill of Materials (AI BOM) with SPDX 3.0," The Linux Foundation, 2024. [Online]. Available: https://doi.org/10.70828/RNED4427.

6. K. Blind and M. Böhm, "The Relationship Between Open Source Software and Standard Setting," Technical Report JRC116106, European Commission, 2019. [Online]. Available: https://publications.jrc.ec.europa.eu/repository/handle/JRC116106.

7. Center for Devices and Radiological Health, "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions," 2025.

8. European Commission, "The relationship between open source software and standard setting," Publications Office, LU, 2019. [Online]. Available: https://doi.org/10.2760/163594.

9. Coalition for Secure AI, "SAIF Risk Assessment: A new tool to help secure AI systems across industry," 2024. [Online]. Available: https://www.coalitionforsecureai.org/googlesaif-risk-assessment/.

10. SPDX contributors, "SPDX Meeting Notes," 2024. [Online]. Available: https://github.com/spdx/meetings/tree/main/ai.

11. S. Coughlan, "OpenChain Work Groups– New and Improved Structure," OpenChain Project, 2022. [Online]. Available: https://openchainproject.org/news/2022/10/12/wg-structure.

12. Cybersecurity and Infrastructure Security Agency (CISA), "2025 Minimum Elements for a Software Bill of Materials (SBOM) Public Comment Draft," 2025. [Online]. Available: https://www.cisa.gov/resources-tools/resources/2025-minimumelements-software-bill-materials-sbom.

13. Cybersecurity and Infrastructure Security Agency (CISA), "Software Bill of Materials (SBOM) Sharing and Use: A Guide for Organizations," Technical Report, U.S. Department of Homeland Security, 2023. [Online]. Available: https://www.cisa.gov/resources-tools/sbom-sharing-and-use-guide.

14. DMSC (n.d.) Overview of the Quality Information Framework (QIF) Standard. Digital Metrology Standards Consortium. Available at: https://qifstandards.org/ (accessed 24 January 2026).

15. Garcia, C.I., DiBattista, M.A., Letelier, T.A., Halloran, H.D. and Camelio, J.A. (2024) 'Framework for LLM applications in manufacturing', Manufacturing Letters, 41(Supplement), pp. 253–263. https://doi.org/10.1016/j.mfglet.2024.09.030.

16. Helu, M., Hedberg Jr., T. and Barnard Feeney, A. (2017) 'Reference architecture to integrate heterogeneous manufacturing systems for the digital thread', CIRP Journal of Manufacturing Science and Technology, 19, pp. 191–195.

17. ISO (2020) ISO 10303-242:2020 Industrial automation systems and integration – Product data representation and exchange – Part 242: Application protocol: Managed model-based 3D engineering. International Organization for Standardization. Available at: https://www.iso.org/standard/66654.html (accessed 24 January 2026).

18. ISO (2020) ISO 23952:2020 Automation systems and integration – Quality information framework (QIF) – An integrated model for manufacturing quality information. International Organization for Standardization. Available at: https://www.iso.org/standard/77461.html (accessed 24 January 2026).

19. ISA (n.d.) ISA-95 Standard: Enterprise-Control System Integration. International Society of Automation. Available at: https://www.isa.org/standards-and-publications/isa-standards/isa-95-standard (accessed 24 January 2026).

20. Kasper, N., Pfenning, M. and Eigner, M. (2024) 'The digital thread for system lifecycle management with a native graph database in a polyglot architecture', Proceedings of the Design Society, International Design Conference – DESIGN 2024. https://doi.org/10.1017/pds.2024.210.

21. Kwon, S., Kim, J., Hedberg Jr., T. and Fischer, L. (2020) 'Enriching standards-based digital thread by fusing as-designed and as-inspected data using knowledge graphs based on ontology', Advanced Engineering Informatics, 45, 101102. https://doi.org/10.1016/j.aei.2020.101102.

22. Listl, F.G., Fischer, J., Sohr, A., Dittler, D., Jazdi, N. and Weyrich, M. (2023) 'Utilizing ISA-95 in an Industrial Knowledge Graph for Material Flow Simulation – Semantic Model Extensions and Efficient Data Integration', Procedia CIRP, 123, pp. 241–246. https://doi.org/10.1016/j.procir.2023.09.214.

23. NIST (n.d.) NIST STEP to OWL Translator (STP2OWL). National Institute of Standards and Technology. Available at: https://github.com/usnistgov/stp2owl (accessed 24 January 2026).

24. Prostep iViP Association (2023) 'Bill of Materials (BOM): semantics and practice – Fact Sheet'. prostep ivip Association. Available at: https://www.prostep.org/mediathek/fact-sheets/iso-10303-242 (accessed 24 January 2026).

25. Standfield, B., Holterman, E. and Waddell, R. (2024) Spatial and Temporal Data Alignment from Disparate Sources for Feature Association. NIST Grant/Contract Report (NIST GCR) 24-050. https://doi.org/10.6028/NIST.GCR.24-050.

26. Wan, Y., Liu, Y., Chen, Z., Chen, C., Li, X., Hu, F. and Packianather, M. (2024) 'Making knowledge graphs work for smart manufacturing: Research topics, applications and prospects', Journal of Manufacturing Systems, 76, pp. 103–132. https://doi.org/10.1016/j.jmsy.2024.07.009.

27. Wang, Y., Ren, W., Zhang, C. and Zhao, X. (2022) 'Bill of material consistency reconstruction method for complex products driven by digital twin', International Journal of Advanced Manufacturing Technology, 120, pp. 185–202. https://doi.org/10.1007/s00170-021-08603-0.

28. Wang, Y., Wang, Y., Ren, W. and Jiang, Z. (2024) 'Knowledge driven multiview bill of material reconfiguration for complex products in the digital twin workshop', International Journal of Advanced Manufacturing Technology. https://doi.org/10.1007/s00170-023-12885-x.

29. Zhao, X., Wei, S., Ren, S., Cai, W. and Zhang, Y. (2024) 'Integrating MBD with BOM for consistent data transformation during lifecycle synergetic decision-making of complex products', Advanced Engineering Informatics, 61, 102491. https://doi.org/10.1016/j.aei.2024.102491.