West Virginia University
Improving the Health and Safety of Manufacturing Workers by Detecting and Addressing Personal Protective Equipment (PPE) Violations in Real-Time with the Use of Automated PPE Detection Technology
Abstract
dc:description.abstractThe Centers for Disease Control and Prevention (CDC) emphasized that Personal Protective Equipment (PPE) can significantly reduce the risk of occupational injuries and illnesses. However, improper use, failure to use, and other PPE-related violations can still result in injuries and fatalities. Eye and face protection violation has been one of the top 10 most frequently violated OSHA standards in fiscal years 2018, 2019, 2020, 2021 and 2022 consecutively. A common practice among safety professionals to ensure PPE compliance has been to physically inspect or monitor PPE usage among workers, which has been found to be unsustainable on a continuous real-time basis. While there have been efforts to investigate and recommend solutions to PPE non-compliance over the years, little effort has been made to the concept of continuous real-time PPE compliance monitoring among manufacturing workers. This dissertation focuses on the use of automated PPE compliance monitoring systems in a manufacturing setting. The traditional method of PPE compliance monitoring, relying on human observation and review of recorded videos, is prone to human errors and limitations. This study aims to investigate the effectiveness of an automated system used in detecting PPE violations in real-time, and to evaluate its scope and limitations under various normal working conditions. Three major hypotheses were proposed, including the impact of worker training or experience on PPE compliance, and a comparison between an automated PPE detection technology (driven by Artificial Intelligence) and video recording with human reviews. The objective of this study is to provide insights into the effectiveness of an automated PPE compliance monitoring system when compared to traditional PPE monitoring system which relies on human reviews of video recordings, and to inform the development of policies and systems to improve PPE compliance in real-time which can reduce injuries in the manufacturing industry. The findings of this study can contribute to the improvement of workplace safety and health in the manufacturing industry.
Degree
thesis:*- Name thesis:degree_name
- PhD
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Industrial and Managements Systems Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Fasinu, Joseph Olufemi
- Contributors dc:contributor
-
- Jeremy Gouzd
- David Wyrick
- Avishek Choudhury
- John Hando
- Ibukun Ogunade
- Omar Al-Shebeeb
Subjects
dc:subject × 16- Personal Protective Equipment (PPE)
- Artificial Intelligence (AI)
- Machine Learning (ML)
- Automated PPE Monitoring
- PPE Violations
- PPE Compliance
- Manufacturing Workers
- Workplace Injuries and Illnesses
- Video Monitoring
- Safety Professionals
- Environmental Health and Protection
- Industrial Engineering
- Operations Research, Systems Engineering and Industrial Engineering
- Other Engineering
- Other Operations Research, Systems Engineering and Industrial Engineering
- Risk Analysis
Identifiers
dc:identifier.*- Identifier
-
<p><a href="https://orcid.org/0009-0008-8165-4714">https://orcid.org/0009-0008-8165-4714</a></p>
https://researchrepository.wvu.edu/etd/12222