论文部分内容阅读
针对爆破振动效应评价中诸多因素不确定性问题,应用支持向量机理论并结合工程实际,提出基于支持向量机理论的岩体爆破振动效应预测方法.以三峡工程坝区现场爆破试验的实测资料为依据,采用支持向量机回归方法,分别进行爆破振动速度预测及爆破损伤深度和损伤半径预测;考虑爆破震动信号的幅值强度特性、频谱特性、持时特性和时-能密度曲线特性,选用震动峰值速度、震动主频、震动持时和时-能密度曲线下的面积作为评价指标,以11组工程岩体爆破实测数据作为学习样本进行训练,建立岩体爆破振动损伤效应预测的支持向量机分类模型,并对8组待判样本进行判别.研究结果表明:建立的支持向量机分类与回归模型对岩体爆破效应预测效果良好,评估结果与实际结果吻合,为岩体爆破效应评估提供了一种新思路.
According to the uncertainties of many factors in blasting vibration effect evaluation, the support vector machine theory and engineering practice are used to predict the blasting vibration effect of rock mass based on SVM theory. The measured data of blasting test in dam site of the Three Gorges Project are According to the method, the prediction of blasting vibration velocity and prediction of blast damage depth and damage radius were carried out by using support vector machine regression method respectively. Considering the characteristics of amplitude strength, frequency spectrum, time-holding property and time-energy density of blasting vibration signal, Peak velocity, frequency of vibration, time-duration of vibration and area under time-energy density curve were used as evaluation indexes. 11 groups of engineering rock blasting measured data were used as training samples to establish a support vector machine for blasting vibration damage effect prediction of rock mass Classification model and discriminate the 8 groups of samples to be judged.The results show that the proposed SVM classification and regression model is effective in predicting the blasting effect of rock masses and the evaluation results are in good agreement with the actual results, A new idea.