AI-ASSISTED PPE COMPLIANCE MONITORING IN MANUFACTURING: A FRAMEWORK FOR PERFORMANCE EVALUATION AND OCCUPATIONAL SAFETY INTERVENTION

Joseph Olufemi Fasinu

doi:10.5281/zenodo.24032071

Abstract

Background: Visual artificial intelligence (AI) can support the recognition of selected personal protective equipment (PPE), but its value for occupational safety depends on whether the system evaluates applicable task requirements, detects observable noncompliance, and enables a suitable response. Objective: This article develops a decision-centered framework for specifying, evaluating, and implementing AI-assisted PPE compliance monitoring in manufacturing. Methods: An integrative synthesis combines occupational safety requirements, peer-reviewed industrial and construction PPE-detection studies, object-detection evaluation methods, human– automation research, and implementation principles. Framework: Six coordinated functions are proposed: (1) task- and hazard-specific rule definition; (2) monitoring coverage and assessability; (3) worker–PPE association and violation-event construction; (4) independent performance assessment; (5) human verification and corrective intervention; and (6) governance and iterative reassessment. The framework distinguishes object-level recognition from event-level detection and operational performance, including false-alert workload, detection latency, coverage, and corrective-action follow-through. Application: Four illustrated workflows and three implementation tables translate these functions into measurable evidence requirements and decision points, using eye-protection monitoring as an example. Conclusion: The framework provides an operational specification for manufacturers to evaluate AI-assisted PPE monitoring as part of established occupational safety systems, with human accountability for compliance judgments and interventions

Keywords

occupational safety; personal protective equipment; eye and face protection; computer vision; artificial intelligence; manufacturing; compliance monitoring; safety intervention 1.

References

1) Occupational Safety and Health Administration. 29 CFR §1910.132: General requirements—personal
protective equipment. Washington, DC: US Department of Labor. https://www.osha.gov/lawsregs/regulations/standardnumber/1910/1910.132
2) Occupational Safety and Health Administration. 29 CFR §1910.133: Eye and face protection.
Washington, DC: US Department of Labor. https://www.osha.gov/lawsregs/regulations/standardnumber/1910/1910.133
3) Occupational Safety and Health Administration. Recommended Practices for Safety and Health
Programs. OSHA 3885. Washington, DC: US Department of Labor; 2016.
https://www.osha.gov/sites/default/files/publications/OSHA3885.pdf
4) International Organization for Standardization. ISO 45001:2018: Occupational health and safety
management systems—Requirements with guidance for use. Geneva: ISO; 2018.
https://www.iso.org/standard/63787.html
5) International Labour Organization. A safe and healthy working environment is a fundamental principle
and right at work. Geneva: ILO; 2022. https://www.ilo.org/publications/safe-and-healthy-workingenvironment-fundamental-principle-and-right-work
6) Balakreshnan B, Richards G, Nanda G, Mao H, Athinarayanan R, Zaccaria J. PPE compliance detection
using artificial intelligence in learning factories. Procedia Manufacturing. 2020;45:277–282.
doi:10.1016/j.promfg.2020.04.017.
7) Vukicevic AM, Djapan M, Isailovic V, Milasinovic D, Savkovic M, Milosevic P. Generic compliance
of industrial PPE by using deep learning techniques. Safety Science. 2022;148:105646.
doi:10.1016/j.ssci.2021.105646.
8) Isailovic V, Peulic A, Djapan M, Savkovic M, Vukicevic AM. The compliance of head-mounted
industrial PPE by using deep learning object detectors. Scientific Reports. 2022;12:16347.
doi:10.1038/s41598-022-20282-9.
9) Park MW, Elsafty N, Zhu Z. Hardhat-wearing detection for enhancing on-site safety of construction
workers. Journal of Construction Engineering and Management. 2015;141(9):04015024.
doi:10.1061/(ASCE)CO.1943-7862.0000974.
10) Fang W, Ding L, Luo H, Love PED. Falls from heights: A computer vision-based approach for safety
harness detection. Automation in Construction. 2018;91:53–61. doi:10.1016/j.autcon.2018.02.018.
11) Nath ND, Behzadan AH, Paal SG. Deep learning for site safety: Real-time detection of personal
protective equipment. Automation in Construction. 2020;112:103085.
doi:10.1016/j.autcon.2020.103085.
12) Delhi VSK, Sankarlal R, Thomas A. Detection of personal protective equipment (PPE) compliance on
construction site using computer vision based deep learning techniques. Frontiers in Built Environment.
2020;6:136. doi:10.3389/fbuil.2020.00136.
13) Cheng JCP, Wong PKY, Luo H, Wang M, Leung PH. Vision-based monitoring of site safety compliance
based on worker re-identification and personal protective equipment classification. Automation in
Construction. 2022;139:104312. doi:10.1016/j.autcon.2022.104312.
14) Occupational Safety and Health Administration. Using Leading Indicators to Improve Safety and Health
Outcomes. OSHA 3970. Washington, DC: US Department of Labor; 2019.
https://www.osha.gov/sites/default/files/publications/OSHA_Leading_Indicators.pdf
15) Torraco RJ. Writing integrative literature reviews: Guidelines and examples. Human Resource
Development Review. 2005;4(3):356–367. doi:10.1177/1534484305278283.
16) Barro-Torres S, Fernández-Caramés TM, Pérez-Iglesias HJ, Escudero CJ. Real-time personal protective
equipment monitoring system. Computer Communications. 2012;36(1):42–50.
doi:10.1016/j.comcom.2012.01.005.
17) Podgórski D, Majchrzycka K, Dąbrowska A, Gralewicz G, Okrasa M. Towards a conceptual framework
of OSH risk management in smart working environments based on smart PPE, ambient intelligence and
the Internet of Things technologies. International Journal of Occupational Safety and Ergonomics.
2017;23(1):1–20. doi:10.1080/10803548.2016.1214431.
18) Okpala I, Nnaji C, Awolusi I, Akanmu A. Developing a success model for assessing the impact of
wearable sensing devices in the construction industry. Journal of Construction Engineering and
Management. 2021;147(7):04021060. doi:10.1061/(ASCE)CO.1943-7862.0002064.
19) Arabshahi M, Wang D, Sun J, Rahnamayiezekavat P, Tang W, Wang Y, Wang X. Review on sensing
technology adoption in the construction industry. Sensors. 2021;21(24):8307. doi:10.3390/s21248307.
20) Padilla R, Passos WL, Dias TLB, Netto SL, da Silva EAB. A comparative analysis of object detection
metrics with a companion open-source toolkit. Electronics. 2021;10(3):279.
doi:10.3390/electronics10030279.
21) Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating
binary classifiers on imbalanced datasets. PLoS ONE. 2015;10(3):e0118432.
doi:10.1371/journal.pone.0118432.
22) Tabassi E. Artificial Intelligence Risk Management Framework (AI RMF 1.0). NIST AI 100-1.
Gaithersburg, MD: National Institute of Standards and Technology; 2023. doi:10.6028/NIST.AI.100-1.
23) Cohen J. A coefficient of agreement for nominal scales. Educational and Psychological Measurement.
1960;20(1):37–46. doi:10.1177/001316446002000104.
24) Parasuraman R, Riley V. Humans and automation: Use, misuse, disuse, abuse. Human Factors.
1997;39(2):230–253. doi:10.1518/001872097778543886.
25) Lee JD, See KA. Trust in automation: Designing for appropriate reliance. Human Factors.
2004;46(1):50–80. doi:10.1518/hfes.46.1.50_30392.
26) Parasuraman R, Sheridan TB, Wickens CD. A model for types and levels of human interaction with
automation. IEEE Transactions on Systems, Man, and Cybernetics—Part A: Systems and Humans.
2000;30(3):286–297. doi:10.1109/3468.844354.
27) Davis FD. Perceived usefulness, perceived ease of use, and user acceptance of information technology.
MIS Quarterly. 1989;13(3):319–340. doi:10.2307/249008.
28) Venkatesh V, Morris MG, Davis GB, Davis FD. User acceptance of information technology: Toward a
unified view. MIS Quarterly. 2003;27(3):425–478. doi:10.2307/30036540.
29) European Agency for Safety and Health at Work. Smart Digital Monitoring Systems for Occupational
Safety and Health: Uses and Challenges. Luxembourg: Publications Office of the European Union; 2022.
doi:10.2802/25469.
30) European Parliament and Council of the European Union. Regulation (EU) 2016/679 of 27 April 2016
(General Data Protection Regulation). Official Journal of the European Union. 2016;L119:1–88.
https://eur-lex.europa.eu/eli/reg/2016/679/oj
31) Health and Safety Executive. Personal Protective Equipment at Work: The Personal Protective
Equipment at Work Regulations 1992 (as amended): Guidance on Regulations. 4th ed. L25. London:
HSE; 2022. https://www.hse.gov.uk/pubns/books/l25.htm
32) Proctor E, Silmere H, Raghavan R, Hovmand P, Aarons G, Bunger A, Griffey R, Hensley M. Outcomes
for implementation research: Conceptual distinctions, measurement challenges, and research agenda.
Administration and Policy in Mental Health and Mental Health Services Research. 2011;38(2):65–76.
doi:10.1007/s10488-010-0319-7.
33) Glasgow RE, Vogt TM, Boles SM. Evaluating the public health impact of health promotion
interventions: The RE-AIM framework. American Journal of Public Health. 1999;89(9):1322–1327.
doi:10.2105/AJPH.89.9.1322.
34) National Safety Council. OSHA reveals Top 10 safety violations at NSC Safety Congress & Expo.
September 20, 2022. https://www.nsc.org/newsroom/osha-reveals-top-10-safety-violations-for-fiscal-y