| 基于改进PSO-ELM算法的混凝土坝变形非线性监控模型 |
| |
| 引用本文： | 张海龙,范振东.基于改进PSO-ELM算法的混凝土坝变形非线性监控模型[J].水电能源科学,2018,36(1):82-84. |
| |
| 作者姓名： | 张海龙 范振东 |
| |
| 作者单位： | 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 |
| |
| 基金项目： | 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。
|
| 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 |
Nonlinear Monitoring Model of Concrete Dam Deformation Based on Improved PSO-ELM Algorithm |
| |
| Abstract: | 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. |
| |
| Keywords: | concrete dam deformation nonlinear monitoring model extreme learning machine particle swarm optimization |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《水电能源科学》浏览原始摘要信息 |
|
点击此处可从《水电能源科学》下载全文 |
