Artificial Intelligence-Optimized Predictive Safety and Sustainability in Industry 4.0 Smart Factories

Charles Chikwendu Okpala¹, Paul Chika Okpala² and Udu Chukwudi Emeka³

¹ Professor, Industrial/Production Engineering Department, Nnamdi Azikiwe University, Awka, Nigeria.

² Lecturer, Mechanical Engineering Department, Madonna University, Akpugo, Nigeria.

³ Researcher, Industrial/Production Engineering Department, Nnamdi Azikiwe University, Awka, Nigeria.  

Abstract

Industry 4.0 smart factories generate unprecedented volumes of real-time operational data, yet safety management and carbon performance optimization remain largely fragmented and reactive. This study introduces and empirically validates a novel AI-driven framework termed Low-Carbon Risk Intelligence (LCRI), which integrates digital twins, probabilistic safety modeling, human workload analytics, and carbon-aware reinforcement learning within a unified decision architecture. Using a 24-month longitudinal dataset that comprises of 18.2 million multimodal records from a highly automated automotive component manufacturing facility, the framework was deployed to co-optimize accident probability, carbon intensity per production unit, and human workload strain. Post-implementation results demonstrate statistically significant improvements, including a 36.5% reduction in recordable incidents, a 42.1% decrease in near-miss events, a 26.4% increase in mean time between failures, and an 18.6% reduction in carbon intensity (kg CO₂/unit). Energy waste declined by 31.0%, peak load events by 39.5%, and workload strain indices by 23.2%, with no observable trade-offs between safety and sustainability outcomes (p < 0.01). A multi-objective reinforcement learning agent embedded within a dynamic digital twin environment enabled real-time adjustment of maintenance scheduling, load balancing, and shift allocation, which validated the proposed Safety–Carbon Coupling Hypothesis. The findings demonstrated that predictive safety systems, when augmented with carbon intelligence and human-centered modeling, can generate measurable environmental and social sustainability gains. Through the operationalization of sustainability variables directly within AI optimization logic, this research advances Industry 4.0 scholarship towards an integrated paradigm of resilient, low-carbon, and human-centric smart manufacturing.     

Keywords: Industry 4.0, Digital twin, Predictive safety, Carbon intelligence, Human factors, Reinforcement learning, Sustainable manufacturing

References

1. Ajaefobi, J.O. and Okpala, C.C. (2026) ‘Six Sigma in the era of Industry 4.0: A bibliometric and benchmarking review’, International Journal of Engineering Research and Development, 22(3), pp. 71–84. https://www.ijerd.com/paper/vol22-issue3/22037184.pdf
2. Carayon, P., Schoofs Hundt, A., Karsh, B.-T., et al. (2015) ‘Work system design for patient safety: The SEIPS model’, Quality and Safety in Health Care, 15(Suppl. 1), pp. i50–i58.
3. Chukwumuanya, E.O., Okpala, C.C. and Udu, C.E. (2025) ‘Carbon accounting at the shop-floor: The integration of real-time energy monitoring, process modeling and LCA for net-zero targets’, Jurnal Teknik Indonesia, 4(1), pp. 28–41. https://jurnal.seaninstitute.or.id/index.php/juti/article/view/728
4. Chukwunedum, O.C., Okpala, C.C. and Udu, C.E. (2026) ‘A data-driven integration of total productive maintenance and Industry 4.0 technologies: A machine learning framework for predictive OEE optimization’, International Journal of Engineering Research and Development, 22(3), pp. 85–95. https://www.ijerd.com/paper/vol22-issue3/22038595.pdf
5. Deswal, S. and Deswal, A. (2017) A Basic Course in Environmental Studies. 3^rd ed. New Delhi: Dhanpat Rai & Co. (P) Ltd.
6. Deswal, S. and Deswal, P. (2025) ‘Sustainability: Greenhouse Gas Protocol and global GHG emissions’ status and trends’, International Journal of Multidisciplinary Research and Growth Evaluation, 6(1), pp. 2051-2063. https://doi.org/10.54660/.IJMRGE.2025.6.1.2051-2063
7. Egwuagu, O.M., Okpala, C.C. and Udu, C.E. (2026) ‘Circular Economy and Net-Zero Manufacturing: A Data-Driven Multidisciplinary Framework for Sustainable Industrial Transformation’, International Journal of Technology, Health and Sustainability, 2(2), pp. 540-550. https://ijths.com/wp-content/uploads/IJTHS-0202021.pdf 
8. Ezeanyim, O.C., Okpala, C.C. and Udu, C.E. (2026) ‘Artificial intelligence-enabled lean six sigma: A multi-industry longitudinal analysis of operational performance and sustainable digital transformation’, International Journal of Technology, Health and Sustainability, 2(2), pp. 428-439. https://ijths.com/wp-content/uploads/IJTHS-0202001.pdf
9. Fuller, A., Fan, Z., Day, C., et al. (2020) ‘Digital twin: Enabling technologies, challenges and open research, IEEE Access, 8, pp. 108952–108971.
10. Geissdoerfer, M., Savaget, P., Bocken, N.M.P., et al. (2017) ‘The circular economy: A new sustainability paradigm?’, Journal of Cleaner Production, 143, pp. 757–768.
11. Gutowski, T.G., Dahmus, J.B. and Thiriez, A. (2009) ‘Electrical energy requirements for manufacturing processes’, Energy, 34(9), pp. 1285–1290.
12. Herrmann, C., Schmidt, C., Kurle, D., et al. (2014) ‘Sustainability in manufacturing and factories of the future’, International Journal of Precision Engineering and Manufacturing–Green Technology, 1(4), pp. 283–292.
13. Hollnagel, E. (2014) Safety-I and Safety-II: The past and future of safety management. Ashgate.
14. IEA (2022) Industry sector emissions and energy use 2022 report. International Energy Agency.
15. Igbokwe, N.C., Nwamekwe, C.O. and Okpala, C.C. (2026) ‘Manufacturing waste reduction through data-driven process optimization: Evidence from smart production systems’, International Journal of Technology, Health and Sustainability, 2(1), pp. 165-174. https://ijths.com/wp-content/uploads/IJTHS-020167.pdf
16. Igbokwe, N.C., Okpala, C.C. and Nwamekwe, C.O. (2024b) ‘The implementation of Internet of Things in the manufacturing industry: An appraisal’, International Journal of Engineering Research and Development, 20(7), pp. 510–516. https://www.ijerd.com/paper/vol20-issue7/2007510516.pdf
17. Igbokwe, N.C., Okpala, C.C. and Nwankwo, C.O. (2024a) ‘Industry 4.0 implementation: A paradigm shift in manufacturing’, Journal of Inventive Engineering and Technology, 6(1), pp. 20–26. https://jiengtech.com/index.php/INDEX/article/view/113/135
18. Kusiak, A. (2018) ‘Smart manufacturing’, International Journal of Production Research, 56(1–2), pp. 508–517.
19. Lee, J., Bagheri, B. and Kao, H.-A. (2015) ‘A cyber-physical systems architecture for Industry 4.0-based manufacturing systems’, Manufacturing Letters, 3, pp. 18–23.
20. Mgbemena, C.E., Onuoha, D.O., Okpala, C.C., et al. (2020) ‘Design and development of a proximity warning system for improved safety on the manufacturing shop floor’, Journal of King Saud University – Engineering Sciences, 34(5), pp. 339-343.  https://doi.org/10.1016/j.jksues.2020.11.004  
21. Nguyen, T.X., Luu, Q. M., Do, M.H., et al., (2026) ‘Analysis of CO₂ emissions and energy efficiency potential of data centers in Vietnam’, International Journal of Technology, Health and Sustainability, 2(2), pp. 421-427. https://ijths.com/wp-content/uploads/IJTHS-0202003.pdf
22. Nwamekwe, C.O. and Okpala, C.C. (2025) ‘Circular economy strategies in industrial engineering: From theory to practice’, International Journal of Multidisciplinary Research and Growth Evaluation, 6(1), pp. 1773–1782. https://www.allmultidisciplinaryjournal.com/uploads/archives/20250212103754_MGE-2025-1-288.1.pdf
23. Nwamekwe, C.O., Ewuzie, N.V., Igbokwe, N.C., et al. (2026) ‘Evaluating the performances of various machine learning models for accurate production forecasting in the textile industry’, International Journal of Technology, Health and Sustainability, 2(1), pp. 138-148. https://ijths.com/wp-content/uploads/IJTHS-020163.pdf 
24. Ogbodo, I.F., Okpala, C.C. and Egwuagu, O.M. (2026) ‘From lean waste to measurable sustainability: Data-driven optimization in smart manufacturing’, International Journal of Technology, Health and Sustainability, 2(2), pp. 523-532. https://ijths.com/wp-content/uploads/IJTHS-0202020.pdf 
25. Okpala, C.C. (2026) ‘Human-centered design of jigs and fixtures: A data-driven approach to productivity, safety, and manufacturing sustainability’, International Journal of Technology, Health and Sustainability, 2(1), pp. 291-299. https://ijths.com/wp-content/uploads/IJTHS-020185.pdf 
26. Okpala, C.C., Egwuatu-Elem, I.C. and Nwamekwe, C.O. (2025d) ‘Integrating artificial intelligence and time-series forecasting for smart textile production: Trends, challenges, and opportunities in the Industry 4.0 era’, International Journal of Society Reviews, 3(2), pp. 461–477. https://injoqast.net/index.php/INJOSER/article/view/641
27. Okpala, C.C., Udu, C.E. and Chukwumuanya, E.O. (2025b) ‘Lean 4.0: The enhancement of lean practices with smart technologies’, International Journal of Engineering and Modern Technology, 11(6), pp. 160–173. https://doi.org/10.56201/ijemt.vol.11.no6.2025.pg160.173
28. Okpala, C.C., Udu, C.E. and Ejichukwu, E.O. (2025c) ‘The need for ergonomics and safety in automated manufacturing environments’, International Journal of Multidisciplinary Research and Growth Evaluation, 6(3), pp. 300-307. https://www.allmultidisciplinaryjournal.com/uploads/archives/20250508172255_MGE-2025-3-046.1.pdf
29. Okpala, C.C., Udu, C.E. and Nwankwo, C.O. (2025a) ‘Digital twin applications for predicting and controlling vibrations in manufacturing systems’, World Journal of Advanced Research and Reviews, 25(1), pp. 764–772. https://doi.org/10.30574/wjarr.2025.25.1.3821
30. Okpala, S.C. and Okpala, C.C. (2025) ‘Human digital twins: A paradigm shift in personalized healthcare and predictive medicine’, International Journal of Medical Evaluation and Physical Report, 9(6), pp. 12–26. https://doi.org/10.56201/ijmepr.v9.no6.2025.pg12.26
31. Ono, C.G., Okeagu, F.N. and Chukwunedum, O.C. (2026) ‘Life cycle assessment frameworks for sustainability in digitally managed factories’, International Journal of Technology, Health and Sustainability, 2(1), pp. 253-267. https://ijths.com/wp-content/uploads/IJTHS-020183.pdf
32. Reason, J. (1997) Managing the risks of organizational accidents. Ashgate.
33. Sutton, R.S. and Barto, A.G. (2018) Reinforcement learning: An introduction. 2^nd ed. MIT Press.
34. Tao, F., Qi, Q., Liu, A., et al. (2018) ‘Data-driven smart manufacturing’, Journal of Manufacturing Systems, 48, pp. 157–169.
35. Tao, F., Zhang, M., Liu, Y., et al. (2019) Digital twin driven smart manufacturing. Academic Press.
36. Udu, C.E. and Okpala, C.C. (2025) ‘Enhancement of shop floor safety with ISO 45001: Challenges and best practices’, International Journal of Engineering Research and Development, 21(1), pp. 75-85. https://ijerd.com/paper/vol21-issue1/21017585.pdf
37. Udu, C.E. and Okpala, C.C. (2026) ‘Artificial Intelligence-Enabled Resilient Scheduling: A Systematic Review and Research Roadmap for Digital Twin and Machine Learning in Disruption-Aware Operations’, International Journal of Technology, Health and Sustainability, 2(2), pp. 486-497. https://ijths.com/wp-content/uploads/IJTHS-0202014.pdf
38. Udu, C.E., Uche, C.J. and Okpala, C.C. (2025d) ‘Digital twins in wastewater treatment plants: A real-time optimization framework’, International Journal of Engineering and Modern Technology, 11(7), pp. 91–106. https://doi.org/10.56201/ijemt.vol.11.no7.2025.pg91.106
39. Wofuru-Nyenke, O.K. (2026) ‘Multi-Criteria Decision Analysis for Optimal Production Schedule Choice’, International Journal of Technology, Health and Sustainability, 2(2), pp. 533-539. https://ijths.com/wp-content/uploads/IJTHS-0202022.pdf
40. Zhou, Z., Xie, S. and Chen, D. (2019) ‘Fundamentals of digital twin and its application in manufacturing’, IEEE Access, 7, pp. 108952–108971.
41. Zio, E. (2018) ‘The future of risk assessment’, Reliability Engineering and System Safety, 177, pp. 176–190.