Speaker
Description
Abstract. The rapid advancement of industry 4.0 technologies has catalyzed the integration of smart digital twins into technical safety assessment and asset integrity assurance processes. These intelligent systems, powered by machine learning, IoT, and real-time analytics, offer unparalleled potential to enhance decision-making and reduce human cognitive fatigue. This paper presents a framework for categorizing the degree of autonomation in smart digital twins, focusing on their role in mitigating human error and optimizing operational safety. We define automation as the interplay between automation and human oversight, and we classify its levels based on task complexity, decision-making capabilities, and human intervention requirements. Case studies in industrial sectors, such as oil and gas, demonstrate the efficacy of the proposed framework. The findings highlight that appropriately calibrated levels of automation not only enhance the accuracy of safety assessments but also promote performance target traceability and sustainable asset management by minimizing operator workload and improving cognitive resilience. This research provides a pathway for implementing smart digital twins to achieve safer, more efficient, and resilient industrial systems.
