Research on coal mine longwall face gas state analysis and safety warning strategy based on multi-sensor forecasting...

Area of Science:

• Mining Engineering
• Intelligent Computing
• Safety Science

Background:

• Coal mining presents significant safety hazards, particularly gas risks.
• Traditional safety inspection methods require enhancement with advanced technologies.

Purpose of the Study:

• To develop a predictive model for assessing gas risk in coal mines using multi-source data.
• To devise an integrated risk warning and response strategy based on predictive confidence and data correlations.

Main Methods:

• Utilized intelligent computing for a multi-source data-based predictive model.
• Examined temporal and spatial correlations of gas dispersion patterns.
• Integrated safety thresholds and a four-level early warning system with predictive confidence.

Main Results:

• The predictive model demonstrated validity and correlation using multi-source monitoring data.
• Successfully tested and verified the model in Polish and Chinese coal mines.
• Developed a risk warning mechanism applicable to safety and regulatory management.

Conclusions:

• The proposed model effectively assesses gas risk and informs countermeasures in coal mines.
• Multi-source data and temporal-spatial correlations are crucial for accurate gas risk prediction.
• The risk warning mechanism enhances coal mine safety and regulatory oversight.