Artificial Neural Networks (ANNs) comprise a powerful tool to approximate the complicated behavior and response of physical systems allowing considerable reduction in computation time during time-consuming optimization runs In this work, a Radial Basis Function Artificial Neural Network (RBFN) is combined with a Differential Evolution (DE) algorithm to solve a water resources management problem, using an optimization procedure The objective of the optimization scheme is to cover the daily water demand on the coastal aquifer east of the city of Heraklion, Crete, without reducing the subsurface water quality due to seawater intrusion The RBFN is utilized as an on-line surrogate model to approximate the behavior of the aquifer and to replace some of the costly evaluations of an accurate numerical simulation model which solves the subsurface water flow differential equations The RBFN is used as a local approximation model in such a way as to maintain the robustness of the DE algorithm The results of this procedure are compared to the corresponding results obtained by using the Simplex method and by using the DE procedure without the surrogate model As it is demonstrated, the use of the surrogate model accelerates the convergence of the DE optimization procedure and additionally provides a better solution at the same number of exact evaluations, compared to the original DE algorithm

An extended second-order macroscopic traffic flow model is presented that describes multi-lane traffic dynamics and also incorporates the effects of adaptive cruise control (ACC) or cooperative ACC (CACC). The extended model equations stem from a recently proposed multi-lane gas-kinetic traffic flow (GKT) model that can simulate lane changes due to vehicle interactions as well as spontaneous ones. The proposed extension that models the effects of ACC/CACC satisfies the time-gap principle of such systems on each lane and allows for consideration of mixed traffic comprising both manual and ACC/CACC vehicles. Numerical simulations are performed for a particular three-lane motorway stretch in the United Kingdom, where recurrent traffic congestion is observed during the morning peak hours, so as to compare the effects of ACC/CACC in the traffic flow conditions with those resulting from manual driving.

Freeform deformation (FFD) is a well established technique for 3D animation applications, used to deform two—or three-dimensional geometrical entities. Over the past few years, FFD technique has aroused growing interest in several scientific communities. In this work, an extensive bibliographic survey of the FFD technique is initially introduced, in order to explore its capabilities in shape parametrization. Moreover, FFD technique is compared to the classical parametrization technique using B-spline curves, in the context of the airfoil design optimization problem, by performing inverse airfoil design tests, with a differential evolution algorithm to serve as the optimizer. The criterion of the comparison between the two techniques is the achieved accuracy in the approximation of the reference pressure distribution. Experiments are presented, comparing FFD to B-spline techniques under the same flow conditions, for various numbers of design variables. Sensitivity analysis is applied for providing further insight into the differences in the performance of the two techniques.

In this work an algorithm using the finite-volume method is presented for the parallelized computation of radiative heat transfer for absorbing, emitting, and either isotropically or anisotropically scattering gray media. Attention is mainly toward the extension of the finite-volume methodology to hybrid unstructured meshes, using a node-centered median-dual approach, with highly stretched elements at the solid wall regions, and the evaluation of its effectiveness and accuracy in such girds. As the parallelized calculation and the utilization of hybrid meshes are not common, results of the present algorithm against benchmark problems are used to demonstrate their equal potential.