Approximating a finite element model by neural network prediction for facility optimization in groundwater engineering

Arndt, Olaf; Barth, Thomas; Freisleben, Bernd; Grauer, Manfred

doi:10.1016/j.ejor.2003.09.039

Cited by 43 publications

(17 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The initial thought of using the hydraulic head as an output parameter was due to this being a common practice (Arndt et al, 2005;Coppola et al, 2005b;Daliakopoulos et al, 2005;Lallahem et al, 2005;Nayak et al, 2006;Feng et al, 2008;Krishna et al, 2008). However, the use of previous day hydraulic head as an input parameter and hydraulic head as an output parameter raises some questions.…”

Section: The Adopted Methodologymentioning

confidence: 99%

“…Several ANN applications in groundwater and surface water hydrology have been recently published. In groundwater hydrology these include simulation of a numerical model in order to obtain results in less time with smaller computational effort (Arndt et al, 2005;Hani et al, 2006;Nikolos et al, 2008); estimation of aquifer parameters (hydraulic conductivity), using an inverse problem method where, using hydraulic head measurements, the aquifer parameters are calculated (Zio, 1997;Wosten et al, 2001;Garcia and Shigidi, 2006;Samani et al, 2007); forecasting spring outflow, combining a mathematical model that calculates input parameters of a neural network (Lallahem and Mania, 2003a); prediction of a flow field, which is still in initial level and combines a conventional numerical model with ANN in order to produce a map of the flow field (Benning et al, 2001); and prediction of contamination risk, based on conductance, precipitation, temperature, and pumping data (Kuo et al, 2004;Coppola et al, 2005a;Sahoo et al, 2006). In surface water hydrology the main implementation concerns catchment flow prediction for managing flood-risk or reservoir storage (Coulibaly et al, 2000;Aqil et al, 2007); rainfall runoff modeling, which can be either lumped or semi-distributed (Sajikumar and Thandaveswara, 1999;Lallahem and Mania, 2003b;Chen and Adams, 2006); and time series modeling, which in association with fuzzy logic has been applied for river flow modeling (Nayak et al, 2004).…”

Section: Anns In Hydrologymentioning

confidence: 99%

See 1 more Smart Citation

Optimal selection of artificial neural network parameters for the prediction of a karstic aquifer's response

Trichakis

Nikolos

Karatzas

2009

Hydrological Processes

View full text Add to dashboard Cite

Abstract:The simulation of karstic aquifers is difficult using traditional groundwater numerical simulators, as the exact knowledge of the hydraulic characteristics of the physical system in small scale is rarely available and the numerical simulators produce results of limited reliability. In the present work, artificial neural networks (ANNs) are utilized to predict the response of a karstic aquifer, using the hydraulic head change per time step rather than the hydraulic head itself as output parameter of the network. As it will be demonstrated, in the first case a better approximation of the physical system's response is achieved as the change of the hydraulic head is more naturally connected to the input parameters of the network, which model the aquatic equilibrium of the system. The correlation of rainfall and hydraulic head change per time step was initially used to determine the time lag of the rainfall input data, which represents the time needed by the rainfall to percolate and reach the water table. In a second step, a differential evolution (DE) algorithm is utilized for the optimal selection of rainfall time lag as well as ANN's architecture and training parameters. Although a time consuming procedure, the improvement obtained suggests that the empirical determination of the ANN parameters and structure is not always sufficient and an optimization procedure, which minimizes the training and evaluation errors of the ANN, may provide substantially better simulation results. The optimized networks were finally used for midterm predictions (30 to 90 days ahead) of the hydraulic head, showing the ability of the ANN with hydraulic head change as output parameter to provide predictions with high accuracy at the end of the considered time period.

show abstract

Section: The Adopted Methodologymentioning

confidence: 99%

Section: Anns In Hydrologymentioning

confidence: 99%

Optimal selection of artificial neural network parameters for the prediction of a karstic aquifer's response

Trichakis

Nikolos

Karatzas

2009

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…ANN is an effective modeling tool that provides a nonlinear mapping capability that can approximate multiple inputs into multi-output relationships via a data learning process (Cherian, Smith, & Midha, 2000). Recently, ANN has attracted considerable attention in the areas of solving functional approximation (Arndt, Barth, Freisleben, & Grauer, 2005), adaptive sensor processing (Gulbag & Temurtas, 2007), prediction applications (Kanmani, Uthariaraj, Sankaranarayanan, & Thambidurai, 2007), and process controls (Pacella & Semeraro, 2007). The back-propagation network (BPN) is a popular supervised technique that adjusts randomized weights during the data learning phase based on the steepest gradient descent method along the error surface (Rumelhart, Hinton, & Williams, 1986).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Modeling and optimization of stencil printing operations: A comparison study

Tsai

2008

Computers & Industrial Engineering

View full text Add to dashboard Cite

“…In the recent studies, there is a significant attempt to use ANN(s) with FE simulations especially to reduce computational time where extensive number of FE simulations required. Arndt et al [14] was implemented a FEM-ANN approach to an optimization problem from groundwater engineering. The proposed approach simply uses the FE results in training and testing of the developed ANN, and the trained ANN is used for further predictions to perform optimization loop.…”

Section: Introductionmentioning

confidence: 99%

Determination of penetration depth at high velocity impact using finite element method and artificial neural network tools

2015

View full text Add to dashboard Cite

Determination of ballistic performance of an armor solution is a complicated task and evolved significantly with the application of finite element methods (FEM) in this research field. The traditional armor design studies performed with FEM requires sophisticated procedures and intensive computational effort, therefore simpler and accurate numerical approaches are always worthwhile to decrease armor development time. This study aims to apply a hybrid method using FEM simulation and artificial neural network (ANN) analysis to approximate ballistic limit thickness for armor steels. To achieve this objective, a predictive model based on the artificial neural networks is developed to determine ballistic resistance of high hardness armor steels against 7.62 mm armor piercing ammunition. In this methodology, the FEM simulations are used to create training cases for Multilayer Perceptron (MLP) three layer networks. In order to validate FE simulation methodology, ballistic shot tests on 20 mm thickness target were performed according to standard Stanag 4569. Afterwards, the successfully trained ANN(s) is used to predict the ballistic limit thickness of 500 HB high hardness steel armor. Results show that even with limited number of data, FEM-ANN approach can be used to predict ballistic penetration depth with adequate accuracy.

show abstract

Approximating a finite element model by neural network prediction for facility optimization in groundwater engineering

Cited by 43 publications

References 2 publications

Optimal selection of artificial neural network parameters for the prediction of a karstic aquifer's response

Optimal selection of artificial neural network parameters for the prediction of a karstic aquifer's response

Modeling and optimization of stencil printing operations: A comparison study

Determination of penetration depth at high velocity impact using finite element method and artificial neural network tools

Contact Info

Product

Resources

About