Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Modeling uncertainty analysis in flow and solute transport model using Adaptive Neuro Fuzzy Inference System and particle swarm optimization
Abstract Groundwater flow and contaminant transport simulations require the determination of various hydro geological parameters such as transmissivity, aquifer thickness, seepage velocity, dispersibility etc. Due to the complex behavior of Groundwater flow and contaminant transport simulations, reliable measurement of the parameters involved is often not possible while performing groundwater system simulations. Hence a methodology is developed in this study wherein a neural-fuzzy model based on an Adaptive Neuro Fuzzy Inference System (ANFIS) is integrated with the particle swarm optimization to estimate the uncertainties in output parameters due to imprecision in input parameters. The Particle Swarm Optimization (PSO) technique is used to find a global optimal solution to a groundwater flow and contaminant transport problem. This is achieved by incorporating the Adaptive Neuro Fuzzy Inference System (ANFIS) to evaluate the objective function within the PSO framework. Later, the ANFIS-PSO algorithm is applied to four problems taking a) a single imprecise parameter for radial flow to a well, b) two imprecise parameters for one dimensional solute transport in steady uniform flow, c) three imprecise parameters for a two-dimensional heterogeneous steady flow problem and finally d) four imprecise parameters for the problem of two-dimensional solute transport. The results show that with the ANFIS-PSO algorithm, the computational burden is reduced considerably when compared to the commonly used vertex method.
Modeling uncertainty analysis in flow and solute transport model using Adaptive Neuro Fuzzy Inference System and particle swarm optimization
Abstract Groundwater flow and contaminant transport simulations require the determination of various hydro geological parameters such as transmissivity, aquifer thickness, seepage velocity, dispersibility etc. Due to the complex behavior of Groundwater flow and contaminant transport simulations, reliable measurement of the parameters involved is often not possible while performing groundwater system simulations. Hence a methodology is developed in this study wherein a neural-fuzzy model based on an Adaptive Neuro Fuzzy Inference System (ANFIS) is integrated with the particle swarm optimization to estimate the uncertainties in output parameters due to imprecision in input parameters. The Particle Swarm Optimization (PSO) technique is used to find a global optimal solution to a groundwater flow and contaminant transport problem. This is achieved by incorporating the Adaptive Neuro Fuzzy Inference System (ANFIS) to evaluate the objective function within the PSO framework. Later, the ANFIS-PSO algorithm is applied to four problems taking a) a single imprecise parameter for radial flow to a well, b) two imprecise parameters for one dimensional solute transport in steady uniform flow, c) three imprecise parameters for a two-dimensional heterogeneous steady flow problem and finally d) four imprecise parameters for the problem of two-dimensional solute transport. The results show that with the ANFIS-PSO algorithm, the computational burden is reduced considerably when compared to the commonly used vertex method.
Modeling uncertainty analysis in flow and solute transport model using Adaptive Neuro Fuzzy Inference System and particle swarm optimization
Ch, Sudheer (Autor:in) / Mathur, Shashi (Autor:in)
KSCE Journal of Civil Engineering ; 14 ; 941-951
28.10.2010
11 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Modeling water table depth using adaptive Neuro-Fuzzy Inference System
| Taylor & Francis Verlag | 2019
Regional Analysis of Flow Duration Curves Using Adaptive Neuro-Fuzzy Inference System
| British Library Online Contents | 2015
Development of Transport Mode Choice Model by Using Adaptive Neuro-Fuzzy Inference System
| British Library Conference Proceedings | 2006