交叉隧道爆破振速回归分析及对比研究

Regression analysis and comparative study on blasting vibration velocity of crossing tunnel

为了系统研究隧道爆破振动响应特征及优化爆破振动速度的拟合过程,结合交叉隧道爆破工程实例,引入一种联合量纲分析及粒子群优化的回归分析方法。首先,利用量纲分析得到可以反映交叉隧道爆破振动衰减规律模型方程。然后,以模型方程为适应度函数进行粒子群优化,求得待定参数完成拟合。同时,通过现有其他爆破振速拟合模型处理数据,与本文分析得到的拟合效果进行对比。计算结果表明,本文引入的回归分析模型所得到的相关系数为0.9982,与现有拟合模型相比更接近于1;残差平方和为0.009,均小于其他拟合模型。以上分析结果证实证明本文引入的拟合模型预测精度最佳,可以为类似近接隧道爆破工程提供一定的借鉴。

In order to systematically study the response characteristics of tunnel blasting vibration and optimize the fitting process of blasting vibration velocity,combined with the cross-tunnel blasting engineering example,a regression analysis method of joint dimensional analysis and particle swarm optimization is introduced.First,the dimensional analysis is used to obtain a model equation that can reflect the attenuation law of cross-tunnel blasting vibration.Then,the model equation is used as the fitness function for particle swarm optimization,and the undetermined parameters are obtained to complete the fitting.In addition,the data is processed by other existing blasting vibration velocity fitting models and compared with the fitting results analyzed in this paper.The calculation results show that the correlation coefficient obtained by the regression analysis model introduced in this paper is 0.9982,which is closer to 1 compared with the existing fitting model;the residual sum of squares is 0.009,which is smaller than other fitting models.This proves that the prediction model in this paper has the best fitting effect and can provide a certain reference for similar adjacent tunnel blasting projects.