DOI: 10.11799/ce202512004
Research on a multi-dimensional status monitoring and real-time risk early warning system for underground mine workers
ZHANG Xuejun
YANG Guowei
HAO Bonan
Abstract：To address the complexity and high-risk nature of the underground coal mine working environment,as well as difficulties and limited methods in monitoring the health of underground personnel,a multi-dimensional status monitoring and real-time risk early warning system is proposed based on smart wristbands,portable monitors,and intelligent information-capable miner's lamps.The system collects underground workers'real-time physiological parameters such as heart rate,body temperature,blood oxygen saturation,etc.,and environmental parameters such as methane and carbon monoxide concentrations.Data is uploaded to a surface server via the mine Internet of Things to build a unified monitoring platform.An innovative fatigue assessment model based on a back propagation neural network is established for data processing.By analyzing the correlation between physiological parameters and sweat pH,miners'fatigue levels was accurately estimated.Furthermore,by integrating a Conditional Score-based Diffusion Model for Imputation(CSDI),the system can fuse multi-dimensional data including physiological status,environment,and personnel location to achieve dynamic risk early warning and proactive health diagnosis.Test results show that the system has a fatigue assessment error within 0.05 and an early warning accuracy rate above 95％,significantly improving the safety and health management level of mine personnel.
Keywords：health monitoringenvironmental monitoringfatigue assessmentneural networkrisk early warning
Publication Date：2025-12-20
Online Publishing Date：2026-01-29(First online date of this platform, not the publication date of the document)
Pages：7( 25-31 )