Back to search

École de technologie supérieure

Developing hybrid intelligent methods to manage systemic risks in the integration of smart wearables in manufacturing

Abstract

dc:description

The increasing integration of smart wearables, such as smart glasses and smart gloves, into modern manufacturing systems promises benefits in worker guidance, ergonomics, and real time monitoring. However, these technologies also introduce new systemic risks that traditional risk management methods struggle to capture. Advanced systemic approaches such as STAMP–STPA, and FRAM more accurately capture the complexity of socio-technical systems; however, they remain predominantly qualitative. This dissertation develops and validates three hybrid methods that combine systemic risk models with Particle Swarm Optimization (PSO) to enhance quantitative assessment and mitigation. First, the STPA–PSO framework extends System-Theoretic Process Analysis by quantifying control actions and supporting semi-automated mitigation strategies. Second, the FRAM–PSO framework integrates the Functional Resonance Analysis Method with PSO to model performance variability and, for the first time, embeds sustainability dimensions— economic, environmental, and social—into systemic risk mitigation. Third, the STPA-BN– PSO framework applies Bayesian Networks optimized with PSO to capture probabilistic dependencies among control actions, hazards, and losses, enabling path-based systemic risk quantification and sensitivity analysis. These frameworks were applied to three case studies in sequential assembly, job-shop assembly, and disassembly, with a focus on the introduction and integration of multiple smart wearables. The results highlight three main findings: (1) the combined use of smart glasses and smart gloves creates new couplings and dependencies that reshape the risk landscape; (2) the three hybrid frameworks provide complementary strengths—with STPA–PSO suited to early design, FRAM–PSO to variability and sustainability evaluation, and STPA-BN–PSO to operational risk monitoring; and (3) embedding sustainability principles enables not only measurable reductions in systemic risk but also alignment with broader industrial and societal objectives. In summary, this research advances the state of risk assessment by hybridizing systemic models with metaheuristic optimization. This shows that qualitative and quantitative approaches can be meaningfully combined. The work extends existing systemic methods with new hybrid frameworks and demonstrates their applicability through case studies involving multiple wearables, and provides decision-makers with practical methods to achieve safer, more sustainable, and human-centered manufacturing. Through this contribution, the thesis advances the principles of Industry 5.0, emphasizing the complementary roles of humans and intelligent technologies in shaping resilient socio-technical systems of the future.

Degree

thesis:*
Name thesis:degree_name
Thèse de doctorat électronique
Level thesis:degree_level
phd
Grantor dc:publisher
École de technologie supérieure
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Karevan, Ali

Subjects

dc:subject × 1

Rights

Language dc:language
en

Identifiers

dc:identifier.*
Identifier
INSERT-YOUR-LIBRARY-ID-HERE3840

Chain of custody

source
Harvested from
ETS (Quebec)
Base URL
espace.etsmtl.ca/cgi/oai2
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Karevan, Ali. Developing hybrid intelligent methods to manage systemic risks in the integration of smart wearables in manufacturing. phd thesis, École de technologie supérieure, 2026.