运用GA-BP神经网络对爆破振动速度预测

Prediction of Blasting Vibration Velocity using GA-BP Neural Network

为了更好的预测爆破振动速度,运用遗传算法(GA)对BP神经网络的权值与阈值进行优化,构建GA-BP神经网络预测模型。结合华润小径湾实际爆破工程监测数据,确定以最大单段药量、爆心距以及测点至爆心的高程差作为输入参数,对爆破振动速度进行预测,并与BP神经网络模型的预测结果进行对比。结果表明:GA-BP神经网络模型预测结果的平均相对误差为5.80%,明显小于BP神经网络模型预测的平均误差14.19%。相比之下,GA-BP神经网络模型的预测精度更高,稳定性更好,可为多因素影响下类似工程爆破振动速度预测提供借鉴经验。

The genetic algorithm(GA)is used to optimize the weight and threshold of BP neural network,and the GA-BP neural network prediction model is constructed to predict the blasting vibration velocity precisely.In the actual blasting engineering of China Resources Xiaojingwan,monitoring data,including the maximum single-dose amount,the blasting distance and the elevation difference from the measuring point to the blasting heart,is taken as input parameters.The blasting vibration velocity predicted by the GA-BP neural network model is compared with the one soluted by the BP neural network.The results show that the average relative error of the GA-BP neural network model is 5.80%,which is significantly smaller than that(14.19%)predicted by the BP neural network model.As a result,the GA-BP neural network model presents higher prediction accuracy and better stability,which can provide reference experience for similar engineering blasting vibration velocity prediction under the influence of multiple factors.