摘要
针对传统统计模型中温度和水压因子交叉影响、效应量不易分离的问题,提出了一种基于IABC-FCMRVM算法的拱坝变形预测模型。首先采用基于改进的人工蜂群(IABC)的模糊C-均值聚类算法(FCM)对变形数据进行分类,然后分别对分类后的数据建立分段的相关向量机模型(RVM),最后以某高拱坝变形数据对该模型进行了检验,并与统计模型和未聚类的RVM模型预测结果对比分析,结果表明,IABC-FCM-RVM模型具有更好的预测精度。
An IABC-FCM-RVM based prediction model of arch dam deformation is proposed to solve the problem of separating the effects of traditional statistical models,which is caused by the cross-influence of the effects of temperature and water pressure.First of all,fuzzy C-means clustering(FCM)based on improved artificial bee colony(IABC)algorithm is adopted for the classification of deformation data.Then,the segmented prediction models based on related vector machine(RVM)are established for the classified data respectively.Finally,the models are tested with the deformation data of a high arch dam,and the results are compared with those of the statistical model and the un-clustered RVM model.Through the case analysis,the accuracy of the IABC-FCM-RVM based prediction model for arch dam deformation is proved to be higher than those of other models.
作者
胡雨菡
包腾飞
朱征
龚健
HU Yuhan;BAO Tengfei;ZHU Zheng;GONG Jian(College of Water-conservancy and Hydropower,Hohai University,Nanjing 210098,China;State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering,Hohai University,Nanjing 210098,China;College of Hydraulic&Environmental Engineering,Three Gorges University,Yichang 443002,China)
出处
《武汉大学学报（工学版）》
CAS
CSCD
北大核心
2020年第12期1055-1064,共10页
Engineering Journal of Wuhan University
基金
国家重点研发计划项目(编号:2018YFC1508603、2016YFC0401601)
国家自然科学基金资助项目(编号:51579086、51739003)。
关键词
模糊C均值聚类
改进的人工蜂群算法
相关向量机
拱坝变形预测
fuzzy C-means clustering(FCM)
improved artificial bee colony(IABC)algorithm
related vector machine(RVM)
prediction model for arch dam deformation
