基于小波包熵和数据融合的煤与瓦斯突出预警

Study on Early-warning of Coal and Gas Outburst Based on Wavelet Packet Entropy and Data Fusion

在深入分析煤与瓦斯突出前的瓦斯浓度变化基础上,提出了基于小波包熵和数据融合的煤与瓦斯突出预警方法。利用基于均值的分批估计融合方法对瓦斯浓度多传感器数据进行处理,以获取煤与瓦斯突出预警所需更为准确、可靠的数据;利用瓦斯浓度变化的小波包熵特征,量化瓦斯浓度变化的无序程度;利用基于小波包熵特征的煤与瓦斯突出预警模型,进行煤与瓦斯突出的实时预警;利用基于重构信号能量的小波包分解层数确定方法,对瓦斯浓度变化的小波包熵特征提取所需的小波包分解层数进行科学确定。通过实例验证表明,煤与瓦斯突出前瓦斯浓度发生忽大忽小的无序变化时,所提方法可以有效探测工作面的煤与瓦斯突出危险性。

By analyzing gas concentration change before coal and gas outburst,an early-warning method based on wavelet packet entropy and data fusion was proposed.The data fusion method based on the arithmetic mean and batch estimation is used to deal with the collected multi-sensor gas data so as to improve the precision and reliability of these data.The wavelet packet entropy feature is used to quantize the disordered degree of gas concentration change.An early-warning model for coal and gas outburst based on the wavelet packet entropy feature is used to carry out real-time early-warning.A selection method of the wavelet packet decomposition level based on restructure signal energy was given to scientifically obtain the wavelet packet decomposition level.The proposed method was validated using practical measured time-series data.The simulation example shows that the proposed method can monitor the risk for coal and gas outburst in the working face when the gas concentration change is abnormal before coal and gas outburst.