BP神经网络在台阶爆破参数优化中的应用

Application of BP neural networks to bench blasting parameter optimization

在遵义县新材料工业园区平场工程土石方开挖中,为了达到良好的爆破效果,需对爆破参数进行优化研究。首先根据目前所采用的生产设备和爆破器材确定了中深孔台阶爆破所需优化的参数,利用BP神经网络以岩石性质参数、爆破现场条件以及爆破效果要求作为BP神经网络的输入层,以需优化的爆破参数作为BP神经网络的输出层,然后以25组经典数据分析了模型参数的选取并进行了神经网络训练验证了网络的有效性,最后将现场参数输入神经网络得到了满足生产要求的爆破参数,达到了良好的爆破效果。

In the formation works excavation of Zunyi new materials industrial park, in order to achieve good blasting effects, the blasting parameters need to be optimized. First, based on the production and blasting equipments, determine the parameters which are needed to be optimized in medium-length hole blasting, use rock properties, blasting field condition and requirement of blast- ing effects as the input layer, and the blasting parameters which are needed to be optimized as the output layer; then, analyze the selection of model parameters based on 25 typical data, make a neural network training to verify the effectiveness of the network; finally, input the parameters to the BP neural network to obtain the blasting parameters which satisfy the production requirement, and make a good blasting effects.