Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Deformation Prediction Model of Concrete Arch Dam Based on Improved Particle Swarm Optimization Algorithm
The concrete arch dam is a high hyper-static structure. Its deformation acted by forces is very complicated, and the early-warning for dam safety is very difficult because of the effect of structure, restraint, environment and loading condition etc. The Particle Swarm Optimization (PSO) has been applied in the dam safety monitoring, where it was widely used to solve the problems of inversing parameters, optimizing functions and optimizing components etc by searching optimization. But when it is applied to high dimension solution space, the precocious phenomenon will occur with the convergence rate slowly. In order to overcome the shortcomings, the PSO is improved in this paper. According to the changing of influence fitness of each particle, an improved PSO (IPSO) is presented by adjusting the acceleration factors by adapting and combining. In the meantime, by merging the crossover and mutation operators of genetic algorithm (GA) with PSO, the population diversity of searching optimization solution is improved when calculating. The IPSO is used to set up the deformation prediction model of a concrete arch dam. It is shown that the IPSO can avoid the precocious phenomenon and effectively improve the convergence rate of PSO. Furthermore, compared with the least square regression (LSM), the precision of deformation forecasting model of concrete arch dam based on IPSO is higher and the calculation results can be more corresponding with the practice operating condition of the dam.
Deformation Prediction Model of Concrete Arch Dam Based on Improved Particle Swarm Optimization Algorithm
The concrete arch dam is a high hyper-static structure. Its deformation acted by forces is very complicated, and the early-warning for dam safety is very difficult because of the effect of structure, restraint, environment and loading condition etc. The Particle Swarm Optimization (PSO) has been applied in the dam safety monitoring, where it was widely used to solve the problems of inversing parameters, optimizing functions and optimizing components etc by searching optimization. But when it is applied to high dimension solution space, the precocious phenomenon will occur with the convergence rate slowly. In order to overcome the shortcomings, the PSO is improved in this paper. According to the changing of influence fitness of each particle, an improved PSO (IPSO) is presented by adjusting the acceleration factors by adapting and combining. In the meantime, by merging the crossover and mutation operators of genetic algorithm (GA) with PSO, the population diversity of searching optimization solution is improved when calculating. The IPSO is used to set up the deformation prediction model of a concrete arch dam. It is shown that the IPSO can avoid the precocious phenomenon and effectively improve the convergence rate of PSO. Furthermore, compared with the least square regression (LSM), the precision of deformation forecasting model of concrete arch dam based on IPSO is higher and the calculation results can be more corresponding with the practice operating condition of the dam.
Deformation Prediction Model of Concrete Arch Dam Based on Improved Particle Swarm Optimization Algorithm
Zhen-zhong, Shen (Autor:in) / Xiao-ning, Mei (Autor:in) / Wei, Wang (Autor:in) / Li-qun, Xu (Autor:in)
12th Biennial International Conference on Engineering, Construction, and Operations in Challenging Environments; and Fourth NASA/ARO/ASCE Workshop on Granular Materials in Lunar and Martian Exploration ; 2010 ; Honolulu, Hawaii, United States
Earth and Space 2010 ; 443-451
11.03.2010
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
| British Library Conference Proceedings | 2010
Optimal Reservoir Operation Based on Improved Particle Swarm Optimization Algorithm
| British Library Conference Proceedings | 2012