Computing an Adaptive Mesh in Fluid Problems Using Neural Network and Genetic Algorithm With Adaptive Relaxation

Abstract

A method based on neural network with Back-Propagation Algorithm (BPA) and Adaptive Smoothing Errors (ASE), and a Genetic Algorithm (GA) employing a new concept named Adaptive Relaxation (GAAR) is presented in this paper to construct learning system that can find an Adaptive Mesh points (AM) in fluid problems. AM based on reallocation scheme is implemented on different types of two steps channels by using a three layer neural network with GA. Results of numerical experiments using Finite Element Method (FEM) are discussed. Such discussion is intended to validate the process and to demonstrate the performance of the proposed learning system on three types of two steps channels. It appears that training is fast enough and accurate due to the optimal values of weights by using a few numbers of patterns. Results confirm that the presented neural network with the proposed GA consistently finds better solutions than the conventional neural network.

An intelligent computing technique for fluid flow problems using hybrid adaptive neural network and genetic algorithm

“…The adaptive mesh points based on reallocation schemes on the symmetrical backward-facing steps channels are enforced effi- ciently [1,2]. However, in this work, 120 elements are placed in the flow region and it is enough to get high accuracy of the numerical simulation model using FEM/MAIL (see Fig.…”

“…However, in this work, 120 elements are placed in the flow region and it is enough to get high accuracy of the numerical simulation model using FEM/MAIL (see Fig. 7a) [1,2].…”

“…This paper implements simultaneously three stages by using FEM with MAIL in Eqs. (1) and (2). These equations are used to select effectively a number of patterns presented by function for different flow velocity to build learning system as shown in Fig.…”

“…Dividing the original domain of analysis into a set of finite elements is not easy, especially for channels with irregular boundaries, or sudden expansion of their diameters [2] (see Fig. 1).…”

“…It is also very expensive with respect to the storage if mesh points refinement is used [1,2]. Navier-Stokes equations (NSE) are one good example.…”