爆破参数智能设计的T-S模糊神经网络方法

针对地下矿山爆破参数设计的工作繁琐、任务量大等问题，建立基于T-S模糊神经网络的地下矿山爆破参数智能设计模型，实现爆破参数快速、智能设计。以某矿山地下矿中深孔爆破为研究对象，收集大量矿山现场实测数据，以抗压强度、抗拉强度、初始弹模、弹性模量、泊松比、黏聚力、内摩擦角、孔底距和排距为输入量，利用BP神经网络和T-S模糊神经网络，建立不同的地下矿山爆破参数预测模型，结果表明，T-S模糊神经网络具有更高的准确性以及更快的运行时间，能够更好地表达地下矿爆破参数与主控因素之间的非线性关系，网络预测值与目标值的均方误差达到1.375 9×10^-5，模型预测效果最佳，为矿山地下矿爆破参数设计提供了参考依据。

Intelligent Design of Blasting Parameters Based on T-S Fuzzy Neural Network

Aiming at the problems of complicated work and large amount of tasks in the design of blasting parameters of underground mines,an intelligent design model of blasting parameters of underground mines based on T-S fuzzy neural network is established to realize the rapid and intelligent design of blasting parameters.Taking the deep-hole blasting in underground mine of a mine as the research object,this paper collects a large number of field measured data of the mine,and takes the compressive strength,tensile strength,initial elastic modulus,elastic modulus,Poisson's ratio,cohesion,internal friction angle,hole bottom distance and row distance as input variables.Using BP neural network and T-S fuzzy neural network,different prediction models of blasting parameters of underground mine are established.The results show that the prediction model of blasting parameters of underground mine is different.T-S fuzzy neural network has higher accuracy and faster operation time.It can better express the non-linear relationship between blasting parameters and main control factors.The mean square error between the predicted value and the target value of the network reaches 1.375 9×10-5.The model has the best prediction effect.It provides a reference basis for the design of blasting parameters of underground mines.