From Reactive Compliance to Predictive SHE Management: Evaluating AI–IIoT Continuous Monitoring for Workplace Health and Environmental Performance

Abstract

The integration of Artificial Intelligence (AI) with the Industrial Internet of Things (IIoT) is creating new opportunities to shift Safety, Health, and Environmental (SHE) management from reactive compliance practices toward continuous, predictive, and prevention-oriented risk management. This study presents a secondary-research synthesis and techno-economic assessment of AI–IIoT-enabled continuous monitoring systems designed to strengthen workplace health protection and environmental performance across industrial operations. Drawing on a structured review of relevant literature, standards and regulatory frameworks, and comparative cost–benefit modelling, the study examines integrated architectures combining fixed continuous emission monitoring systems, wearable worker-sensing technologies, edge-to-cloud data processing, and explainable machine-learning applications for hazard identification, risk prediction, and decision support. The assessment considers key performance dimensions including potential reductions in hazardous exposure, workplace incidents, and incident-related lost workdays, alongside capital expenditure, operating costs, payback period, and net present value under alternative implementation scenarios. The synthesis indicates that appropriately calibrated AI–IIoT configurations, when embedded within ISO 45001 and ISO 14001 management processes and supported by explainable and human-supervised AI, can enhance the timeliness of hazard detection, strengthen occupational health interventions, and generate potentially favourable techno-economic outcomes in medium- and large-scale industrial facilities. However, the effectiveness and economic viability of these systems remain dependent on sensor accuracy and reliability, interoperability of digital platforms, workforce capability, data governance, and an enabling regulatory environment.