Dynamic Risk Assessment and Hazard Prediction in Complex Workplaces Using a Digital Twin Architecture
TL;DR
This paper assesses the value-add of AI in safety performance by deeply integrating advanced industrial safety engineering risk analysis methodologies, including Hazard Identification and Risk Assessment (HIRA), Fault Tree Analysis (FTA), and Failure Mode and Effects Analysis (FMEA).
Abstract
The rise of digital transformation (DT) across industries has catalyzed incremental progress through technological revolutions such as Artificial Intelligence (AI) and Digital Twins. This research explores the organizational digital transformation within complex workplaces—specifically construction sites and process plants—and evaluates how Digital Twins can enhance occupational health and safety (OSH). Current safety management procedures struggle to keep pace with dynamic industrial environments, leading to high accident rates. By digitizing physical environments and synchronizing real-time data from IoT sensors, cyber-physical systems, and historical logs, organizations can enable proactive risk assessment, hazard prediction, and effective safety training. This paper assesses the value-add of AI in safety performance by deeply integrating advanced industrial safety engineering risk analysis methodologies, including Hazard Identification and Risk Assessment (HIRA), Fault Tree Analysis (FTA), and Failure Mode and Effects Analysis (FMEA). The evolution of safety roles and shifting collaborative dynamics are examined in detail, ultimately providing a scalable framework for adopting predictive safety mechanisms up to the 2024-2025 technological horizon.