摘要
以落石的水平运动距离、弹跳高度和运动能量3个运动特征参数为目标,引入正交试验法对其影响因素进行了敏感性分析及其较不利因素水平组合研究。然后选取影响落石运动特征参数的5个因素为影响因子建立数据样本集,引入支持向量机方法建立落石预测系统对岩质边坡落石运动特征参数进行了预测。最后结合工程实例对预测系统进行了验证。本文研究结果表明:正交试验方法可以确定影响落石运动特征参数的主次因素及较不利因素水平组合;基于支持向量机(Support Vector Machine,SVM)的预测系统不需要进行Rockfall软件的建模计算过程,就可以估算出岩质边坡落石的运动特征参数,方便快捷。
Taking the rockfall movement characteristic parameters including horizontal movement distance,bounce height and motion energy as the research objects,the orthogonal experimental method is introduced to study the sensitivity and unfavorable level combination of the influencing factors.Then,5 factors affecting the rockfall movement characteristic parameters are selected to establish the data specimen set,and the rockfall prediction system is established by support vector machine method to predict the characteristic parameters of rockfall movement on rock slope.Finally,the prediction system is verified by an engineering example.The result shows that（1） the orthogonal test method can determine the primary and secondary influencing factors of rockfall movement characteristic parameters and the unfavorable level combination;（2） the prediction system based on SVM can easily estimate the characteristic parameters of rockfall movement without modeling and computing with Rockfall software.
出处
《公路交通科技》
CAS
CSCD
北大核心
2017年第3期20-25,共6页
Journal of Highway and Transportation Research and Development
基金
国家自然科学基金项目(41301015)
河北省教育厅重点项目(ZD2015073
ZD2016038)
关键词
道路工程
落石
正交试验
影响因素
支持向量机
参数预测
road engineering
rockfall
orthogonal test
influencing factor
support vector machine
parameter prediction
