摘要
为了将隧道工程环境影响控制在区域环境所能承载的范围之内,考虑适应性、可操作性和推广性等原则,提出基于环境承载力构建隧道工程环境影响评价指标体系。支持向量回归机(Support vector Regression, SVR)与传统评价方法相比减少了指标体系赋权过程,能避免人为因素或指标数据的干扰,提高评价体系的通用性。利用SVR建立的隧道工程环境影响评价模型,并结合交叉验证法对SVR模型参数进行优化选择,解决SVR模型在参数选择上的盲目性。以兰渝铁路全线中段的西秦岭隧道为例进行模型运算。结果表明该方法符合实际,适应性及可操作性强,能够为隧址区生态环境的修复工作提供科学依据。
In order to control the environmental impact of tunnel engineering within the bearing range of the regional environment, considering the principles of adaptability, operability and extensibility, an environmental impact assessment index system based on the environmental carrying capacity of tunnel engineering was proposed. Compared with traditional evaluation methods, Support vector Regression(SVR) reduces the empowerment process of the index system. It can avoid the interference of human factors or index data, and improve the universality of the evaluation system. Therefore, a tunnel engineering environmental impact assessment model was established by using SVR. The parameters of the SVR model were optimized by combining the crossvalidation method, which solved the blindness of the SVR model in parameter selection. Finally, the model calculation is carried out by taking the Xiqinling tunnel in the middle section of the Lanzhou-Chongqing railway as an example. The results show that this method is practical, adaptable and operable, and can provide scientific basis for the restoration of ecological environment in tunneling site.
作者
万炳彤
鲍学英
李爱春
WAN Bingtong;BAO Xueying;LI Aichun(School of Civil Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《铁道科学与工程学报》
CAS
CSCD
北大核心
2020年第1期258-265,共8页
Journal of Railway Science and Engineering
基金
国家自然科学基金资助项目(51768034)
关键词
隧道施工
环境承载力
支持向量回归机(SVR)
交叉验证法
tunnel construction
environmental carrying capacity
support vector regression machine (SVR)
cross validation
