水力发电2024，Vol.50Issue(6)：111-116,6.
基于APSO-Robust-ELM的大坝变形原始监测数据粗差识别方法
A Method for Identifying Gross Error in Raw Dam Deformation Monitoring Data Based on APSO-Robust-ELM
摘要
Abstract
Aiming at the universal of gross error in the raw monitoring data of dams,a gross error identification method combining robust estimation and extreme learning machine is proposed,and on this basis,an adaptive particle swarm algorithm is utilized to find the optimal number of nodes in the hidden layer of the neural network.Finally,a dam safety prediction model is utilized to validate the necessity and applicability of the proposed method.In a study case,the processing results of the APSO-Robust-ELM method are compared with those of the Robust-ELM method,Romanovsky criterion and Pauta criterion,and the results show that the APSO-Robust-ELM method is able to better identify gross error in the raw monitoring data,thus improving the management efficiency of the safe operation of dams.关键词
监测数据/大坝安全/粗差识别/人工智能/APSO-Robust-ELMKey words
monitoring data/dam safety/gross error identification/artificial intelligence/APSO-Robust-ELM分类
建筑与水利引用本文复制引用
杨兴富,刘得潭,杨进,刘少文,高睿颖,顾昊,王岩博..基于APSO-Robust-ELM的大坝变形原始监测数据粗差识别方法[J].水力发电,2024,50(6):111-116,6.基金项目
国家自然科学基金资助项目(51739003) （51739003）
中央高校基本科研业务费专项资金资助项目(B230201011) （B230201011）
江苏省水利科技项目(2022024) （2022024）
