基于改进PSO-ELM算法的混凝土坝变形非线性监控模型  

Nonlinear Monitoring Model of Concrete Dam Deformation Based on Improved PSO-ELM Algorithm

作　　者：张海龙[1] 范振东 

机构地区：[1]西京学院土木工程学院,陕西西安710123 [2]国家能源局大坝安全监察中心,浙江杭州311122

出　　处：《水电能源科学》2018年第1期82-84,199,共4页Water Resources and Power

基　　金：陕西省教育厅科学研究项目(15JK2171);全国工程专业学位研究生教育2016~2017年度研究课题(2016-ZX-437)

摘　　要：针对混凝土坝变形模型高度非线性问题,将极限学习机(ELM)用于混凝土坝变形监控模型的构建中,由于极限学习机的精度受输入权值和隐含层阈值的影响,引入改进的粒子群算法(PSO)进行最优求解,从而建立基于改进PSO-ELM算法的混凝土坝变形非线性监控模型。实例应用结果表明,该模型不仅可行、有效,且具有较强的学习能力和泛化能力。To solving the highly nonlinear problem of concrete dam deformation model, extreme learning machine （ELM） was used to establish monitoring model of concrete dam deformation. However, the accuracy of the ELM model was affected by the input weight and threshold of the hidden layer. Therefore, improved particle swarm optimization was used to solve the model. Thus, nonlinear monitoring model of concrete dam deformation based improved PSO-ELM was established. The example application shows that the model is not only feasible and effective, but also has strong learning and generalization ability.

关 键 词：混凝土坝变形 非线性监控模型 极限学习机 粒子群算法 

分 类 号：TV698.1[水利工程—水利水电工程]