论文部分内容阅读
岩爆是深部高地应力区地下岩体工程中的主要工程地质灾害之一,对其发生及烈度预测是一个复杂的不确定系统问题。结合投影寻踪算法、粒子群优化算法和逻辑斯谛曲线函数,并选取洞室最大切向应力与岩石单轴抗压强度的比值、脆性系数和弹性能量指数作为判别指标,建立了岩爆预测的粒子群优化投影寻踪模型。该模型一方面采用粒子群算法优化投影指标函数及逻辑斯谛曲线函数参数,确保了模型参数的准确性;另一方面利用逻辑斯谛曲线函数建立投影值与经验等级之间的非线性关系。模型的测试结果显示了良好的精度。将该模型应用到秦岭隧道和冬瓜山铜矿的岩爆预测中,预测结果与实际情况吻合较好,表明该模型在岩爆预测中的可行性和有效性。
Rockburst is one of the major engineering geological disasters in underground rock mass engineering in deep high stress area, and its occurrence and intensity prediction are complex and uncertain system problems. Combined with the projection pursuit algorithm, particle swarm optimization algorithm and Logistic curve function, the ratio of the maximum tangential stress in the cavern to the uniaxial compressive strength of rock, brittleness coefficient and elastic energy index were selected as the discriminant indexes to establish the rockburst prediction Particle Swarm Optimization Projection Pursuit Model. On the one hand, particle swarm optimization algorithm is used to optimize the projection index function and Logistic curve function parameters to ensure the accuracy of the model parameters; on the other hand, the nonlinear relationship between projection value and experience level is established by using Logistic curve function. The model test results show good accuracy. Applying the model to the rockburst prediction of Qinling tunnel and Dongguashan copper mine, the prediction results are in good agreement with the actual situation, indicating the feasibility and effectiveness of the model in rockburst prediction.