Prediction of spontaneous combustion in the coal stockpile based on an improved metabolic grey model

Abstract

Abstract Spontaneous combustion of coal can lead to serious environmental pollution, safety hazards and huge economic losses. Hazard prevention and environmental protection requires effective monitoring network and efficient prediction methods. To acquire the real-time data of coal parameters we designed multi-layered Zig-bee based wireless sensor network. The shape of the coal pile is formed by the industrial laser scanner followed by the formation of 3D temperature point cloud field via Kriging interpolation. Afterwards, an integrated evaluation indicator Heat Loss Capacity (HLC) is proposed, which synthesizes various factors inducing spontaneous combustion. The real-time and high accurate HLC prediction is realized by using metabolic method to update the raw sequence of the GM(1,1) grey prediction model in cycle with the latest acquired sensor data. Finally, a hybrid model ABC-MGM(1,1) combining the ABC optimization algorithm with the metabolic GM(1,1) model is proposed. Experiment shows that the ABC-MGM(1,1) model has better performance in parameter optimization as well as HLC prediction, especially for short-term prediction. The proposed method has been utilized to predict spontaneous combustion of the stockpiled coal in Xutang power plant of China. The timely parameter acquisition by 25 Zig-bee nodes and effective prediction by the proposed model shows great practicability in safety and hazard prevention.