Development of AI-based ergonomics risk assessment tools for harmonization of industrial work systems

• Author / Creator

  Govindan, Aswin Ramaswamy

• Manufacturing industry workers face significant ergonomic risks due to poorly designed work
  systems. Consequently, it is crucial to periodically assess work systems to identify areas for
  improvement. However, the assessment process is often disregarded due to the absence of userfriendly ergonomics risk assessment tools. The primary objective of this study is to address this
  issue by leveraging artificial intelligence to develop convenient ergonomics risk assessment tools
  for occupational injury management. The study identified four significant challenges that hamper
  the effectiveness of ergonomics risk assessment: (1) a lack of versatile physical-ergonomic tools;
  (2) the fragmented nature of existing ergonomic tools that fails to provide an integrated assessment
  of work systems; (3) the challenge of developing an interpretable data analytics framework for risk
  diagnosis; and (4) the inability to develop human-centered ML-powered ergonomics risk
  assessment tools. To address these challenges, the study pursued four objectives. First, a versatile
  physical-ergonomics risk assessment tool is developed using the Pattern Search optimization
  algorithm to simplify tool selection for improving work systems. Second, a fuzzy logic-based
  Decision Support System is developed to provide an integrated assessment of the ergonomic
  performance of work systems by blending physical, environmental, and sensory risk factors. Third,
  an effective and interpretable machine learning-based data analytics framework is developed for
  diagnosing safety and ergonomics risk factors in work systems. Finally, a literature review is
  conducted to uncover the many design challenges that hinder the development of human-centered
  ML-powered ergonomics risk assessment tools. Overall, this study aims to demonstrate the
  effectiveness of AI as a valuable technology for developing convenient ergonomics risk
  assessment tools that aid health and safety specialists in mitigating ergonomic risks by facilitating
  the harmonization of industrial work systems

• Subjects / Keywords

  • Ergonomics
  • Risk Assessment
  • Artificial Intelligence
  • Occupational injury management
  • Machine Learning

• Graduation date

  Fall 2023

• Type of Item

  Thesis

• Degree

  Doctor of Philosophy

• DOI

  https://doi.org/10.7939/r3-k4rf-r873

• License

  This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.