煤与瓦斯突出预测的SOFM模型及应用

煤与瓦斯突出是煤矿生产活动中常见的一种动力灾害之一,其危险性等级评价是煤矿安全生产的必要前提和保证。文章综合考虑煤与瓦斯突出发生的地应力、瓦斯和煤的物理力学性质等条件,选取地质破坏程度、瓦斯压力、瓦斯放散初速度、煤的坚固性系数以及开采深度作为煤与瓦斯突出危险性预测的评价指标。基于此,文章借签一种自组织特征映射(SOFM)神经网络,建立煤与瓦斯突出危险性预测的SOFM神经网络模型,将SOFM神经网络模型应用于国内26个典型矿井的煤与瓦斯突出危险性预测。研究表明,SOFM神经网络模型预测效果较好,其正判率为92.31%。说明该模型可为小样本、多指标的煤与瓦斯突出预测提供一种新的思路。

SOFM neural network model for prediction of coal and gas outburst and its application

Coal and gas outburst is one of the most common dynamic disasters in coal mine production activities, and its hazard rating is the prerequisite and guarantee of coal mine safety production. Article comprehensively consider the stress of coal and gas outburst occurred, the physical and mechanical properties of gas and coal, geological damage, gas pressure, gas radiation initial velocity and the consistence coefficient of coal and mining depth as the danger of coal and gas outburst prediction index. Based on this, this article borrow sign a self-organizing feature map (SOFM) neural network, establish risk prediction of coal and gas outburst of SOFM neural network model of SOFM neural network model was applied to 26 domestic typical risk prediction of coal and gas outburst mine. The research shows that SOFM neural network model has good prediction effect, and its misjudgment rate is 92.31%. The model can provide a new way for the prediction of coal and gas outburst of small sample and multi-index.