Data-driven approach to solve vertical drain under time-dependent loading

作     者：Trong NGHIA-NGUYEN Mamoru KIKUMOTO Samir KHATIR Salisa CHAIYAPUT HNGUYEN-XUAN Thanh CUONG-LE Trong NGHIA-NGUYEN;Mamoru KIKUMOTO;Samir KHATIR;Salisa CHAIYAPUT;H.NGUYEN-XUAN;Thanh CUONG-LE

作者机构：Department of Civil EngineeringYokohama National UniversityYokohama 240-8501Japan Faculty of Civil EngineeringHo Chi Minh City Open UniversityHo Chi Minh City 70000Vietnam Department of Electrical EnergyMetalsMechanical Constructions and SystemsFaculty of Engineering and ArchitectureGhent UniversityGhent 9000Belgium Department of Civil EngineeringSchool of EngineeringKing Mongkut’s Institute of Technology LadkrabangBangkok 10520Thailand CIRTECH InstituteHo Chi Minh City University of Technology(HUTECH)Ho Chi Minh City 708300Vietnam 

出 版 物：《Frontiers of Structural and Civil Engineering》 (结构与土木工程前沿（英文版）)

年 卷 期：2021年第15卷第3期

页      面：696-711页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 070101[理学-基础数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：support provided by Ho Chi Minh City Open University 

主　　题：vertical drain artificial neural network time-dependent loading deep learning network genetic algorithm particle swarm optimization 

摘      要：Currently,the vertical drain consolidation problem is solved by numerous analytical solutions,such as time-dependent solutions and linear or parabolic radial drainage in the smear zone,and no artificial intelligence(AI)approach has been ***,in this study,a new hybrid model based on deep neural networks(DNNs),particle swarm optimization(PSO),and genetic algorithms(GAs)is proposed to solve this *** DNN can effectively simulate any sophisticated equation,and the PSO and GA can optimize the selected DNN and improve the performance of the prediction *** the present study,analytical solutions to vertical drains in the literature are incorporated into the DNN–PSO and DNN–GA prediction models with three different radial drainage patterns in the smear zone under timedependent *** verification performed with analytical solutions and measurements from three full-scale embankment tests revealed promising applications of the proposed approach.