基于BP网络理论的岩爆预测方法

Rock Burst Prediction Methods Based on BP Network Theory

选取影响岩爆的一些主要因素,如地应力大小、岩石抗压和抗拉强度、岩石弹性能量指数,采用人工神经网络理论,根据国内外一些岩石地下工程实例构造样本集,建立了一种新的岩爆预测模型。此模型可以直接应用于岩石地下工程,对岩爆的发生与否及烈度大小进行预测。实例表明,预测结果与实际情况符合得很好,说明了此模型的有效性。

According to the collected data from actual underground rock projects at home and broad, a new rock burst prediction model is established based on the neural network theory, in which some main control factors of rock burst are chosen as criteria indexes including in - situ stress, tensile strength of rock and the elastic energy index of rock. This model can be directly applied in underground rock projects to predict whether the rock burst will happen and how intensified the rock burst is. The instances indicate that the evaluated results agree well with the practical records,which shows the model is effective in prediction of rock burst.