基于MIC-BBO-SVM的大坝渗流预测模型  

Prediction model of dam seepage based on MIC-BBO-SVM

作　　者：刘泽 章光[1] 李伟林 胡少华[1,2] LIU Ze;ZHANG Guang;LI Weilin;HU Shaohua(School of Safety Science and Emergency Management,Wuhan University of Technology,Wuhan Hubei 430070,China;National Research Center for Dam Safety Engineering Technology,Wuhan Hubei 430010,China)

机构地区：[1]武汉理工大学安全科学与应急管理学院,湖北武汉430070 [2]国家大坝安全工程技术研究中心,湖北武汉430010

出　　处：《中国安全生产科学技术》2020年第11期12-18,共7页Journal of Safety Science and Technology

基　　金：国家大坝安全工程技术研究中心开放基金项目(CX2019B014);国家自然科学基金项目(51979208);国家“十三五”重点研发计划重点专项项目(2017YFC0804600)。

摘　　要：为监控大坝运行过程中的异常状态,准确预测大坝渗流量的变化趋势,采用最大信息系数(MIC)量化渗流量与影响因子之间的相关性大小并从中选取主导因子作为输入变量,通过引入生物地理学优化算法(BBO)并以K折交叉验证意义下的平均均方根误差为损失函数来优化支持向量机(SVM)作为预测模型,以某水电站工程的拦河大坝为例进行模型验证。结果表明:MIC-BBO-SVM模型的拟合优度、均方根误差、平均绝对误差和平均绝对百分比误差分别为0.9575,0.1550 m^3/h,0.1356 m^3/h,11.51%,预测性能明显优于逐步回归模型、SVM模型和MIC-SVM模型,可为大坝渗流安全监测提供参考与借鉴。In order to monitor the abnormal state during the operation process of dam,and accurately predict the change trend of dam seepage flow,the maximal information coefficient(MIC)was used to quantify the correlation between seepage flow and influencing factors,and the dominant factor was selected from them as the input variable.The biogeography-based optimization algorithm(BBO)was introduced and the average root mean square error in the sense of K-fold cross validation was taken as the loss function to optimize the support vector machine(SVM)as a prediction model,then the dam of a hydropower station project was taken as an example for the model verification.The results showed that the goodness of fit,root mean square error,average absolute error and average absolute percentage error of the MIC-BBO-SVM model were 0.9575,0.1550 m^3/h,0.1356 m^3/h,and 11.51%,respectively.Its prediction performance was better than those of the stepwise regression model,SVM model and MIC-SVM model,which can provide reference for the safety monitoring of dam seepage.

关 键 词：安全监测 渗流量 因子优选 MIC-BBO-SVM 预测精度 

分 类 号：X959[环境科学与工程—安全科学]