支持向量机在岩爆预测中的应用

Application of the Support Vector Machine in Prediction of Rock Burst

岩爆是高地应力地下工程中的地质灾害之一,其影响因素存在极其复杂的非线性关系。选取岩石抗压强度、抗拉强度、弹性能量指数和洞壁最大切向应力作为岩爆预测的特征向量,建立岩爆预测的支持向量机模型,对岩爆的发生及其烈度进行预测。预测结果与实际情况及其他方法相吻合,表明支持向量机在岩爆预测中的可行性和有效性。

Rock-burst is one of the main geological hazards during rocky tunnel construction in high crustal stress zone, and its influencing factors have an extremely complex nonlinear relationship. The compression strength, tensile strength, elastic energy index of rock and maximum tangential stress of cavern wall are chosen as characteristic vector of predicting rock-burst, and the prediction model of rock-burst based on support vector machines is established to predict the rock burst and intensity. The consistent prediction of rock-burst occurrence and intensity with the actual situation and with those by other methods showed that it is feasible and valid to use the support vector machines model for predicting rock-burst.