IoT-Bayes fusion: Advancing real-time environmental safety risk monitoring in underground mining and construction

Effectively managing environmental hazards in underground mining and construction sites is a formidable challenge for project managers and site engineers. These complex underground systems are characterized by inadequate ventilation, hazardous gases, and elevated levels of heat and humidity. However, conventional approaches to underground risk management often rely on static and oversimplified methodologies, which limit the ability to accurately predict and control these multifaceted hazards. This research aims to develop an innovative real-time safety risk monitoring system tailored to underground environments. The proposed system facilitates dynamic and remote monitoring, analysis, and control of safety risks within underground workspaces. The methodology integrates data streams from Internet of Things (IoT) sensors to perceptively capture the underground environment, combined with the application of Bayesian networks (BNs) as a robust probabilistic risk modeling engine. To demonstrate the practicality of the proposed system, two proof-of-concept examples using real datasets collected from underground coal mines in Poland and China are presented. The demonstration effectively showcases the system's applicability and potential benefits. Upon implementation, the proposed system will enable real-time and remote monitoring of underground ecosystems, significantly enhancing the safety and reliability of underground operations.