Evaluation of time series artificial intelligence models for real-time/near-real-time methane prediction in coal mines

Atmospheric monitoring systems are critical in underground coal mine ventilation where methane explosion hazards can develop. The number and location of sensors are important for ventilation monitoring. Atmospheric monitoring system sensors should be installed near the most critical locations like the shearer cutting drum and along the longwall face. Sensors can provide information for a limited area, and their readings may have delays caused by sensor response time, gas diffusion rate, and temperature. Computational fluid dynamics modeling can provide relatively accurate predictions regarding the location of possible explosive gas concentrations. However, it requires significant computational resources and time, which is not conducive to real-time decision-making. This paper evaluates artificial intelligence systems for predicting near-real-time explosion hazards. The prediction performance of 10 time series algorithms is compared by using seven datasets and assessed by classification accuracy. Accurate real-time/near-real-time methane predictions are possible with two algorithms: HIVE-COTE and RISE. Initial results demonstrate that near-real-time decision-making for explosive hazard warning systems is accurate and robust, and artificial intelligence modeling of explosion hazards enhances mine safety.