基于组合赋权的遗传算法优化BP神经网络岩爆预测研究

Forecast Research on the Rockburst Tendency with the BP Neural Network Optimized by Genetic Algorithm Based on the Combination Weight

针对岩爆倾向性预测的复杂问题,选取隧洞应力系数、脆性系数及围岩冲击倾向指数为评价指标,利用组合赋权法确定指标的权重,结合遗传算法和BP神经网络,建立了基于组合赋权的遗传算法优化BP神经网络的预测模型。利用岩爆实例数据对建立的模型进行测试,测试结果具有良好的准确度,验证了该模型的可行性及有效性。

According to the complex system problem of rockburst intensity prediction,the stress coefficient,brittleness coefficient and surrounding rock impact tendency index of tunnel are selected as the evaluation index. The weight of the indexs above is determined by the combination weighting method. Rock burst prediction model of BP Neural Network and Genetic Algorithm based on combination weighting method has been established. The established model above is tested by rockburst instance data,and the test results have good accuracy,which verifies the feasibility and effectiveness of the model.