Journal ArticleDOI
A new soft computing approach for studying the wire coating dynamics with Oldroyd 8-constant fluid
TLDR
A novel soft computing paradigm is designed to analyze the governing mathematical model of wire coating by defining weighted Legendre polynomials based on Legendre neural networks (LeNN) to establish the worth of the designed scheme for variants of the wire coating process.Abstract:
In this paper, a mathematical model for wire coating in the presence of pressure type die along with the bath of Oldroyd 8-constant fluid is presented. The model is governed by a partial differential equation, transformed into a nonlinear ordinary differential equation in dimensionless form through similarity transformations. We have designed a novel soft computing paradigm to analyze the governing mathematical model of wire coating by defining weighted Legendre polynomials based on Legendre neural networks (LeNN). Training of design neurons in the network is carried out globally by using the whale optimization algorithm (WOA) hybrid with the Nelder–Mead (NM) algorithm for rapid local convergence. Designed scheme (LeNN-WOA-NM algorithm) is applied to study the effect of variations in dilating constant (α), pressure gradient (Ω), and pseudoplastic constant β on velocity profile w(r) of fluid. To validate the proposed technique's efficiency, solutions and absolute errors are compared with the particle swarm optimization algorithm. Graphical and statistical performance of fitness value, absolute errors, and performance measures in terms of minimum, mean, median, and standard deviations further establishes the worth of the designed scheme for variants of the wire coating process.read more
Citations
More filters
Journal ArticleDOI
Application of Euler Neural Networks with Soft Computing Paradigm to Solve Nonlinear Problems Arising in Heat Transfer.
Naveed Ahmad Khan,Osamah Ibrahim Khalaf,Carlos Andrés Tavera Romero,Muhammad Sulaiman,Maharani Abu Bakar +4 more
TL;DR: In this article, a novel application of neurocomputing technique is presented for solving nonlinear heat transfer and natural convection porous fin problems arising in almost all areas of engineering and technology, especially in mechanical engineering.
Journal ArticleDOI
Application of Intelligent Paradigm through Neural Networks for Numerical Solution of Multiorder Fractional Differential Equations
TL;DR: The approximate solutions by the BLM-NN algorithm are compared with analytical solutions and performance based on mean square error (MSE), error histogram (EH), regression, and curve fitting further validates the accuracy, robustness, and efficiency of the proposed algorithm.
Journal ArticleDOI
DRLinFluids---An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM
TL;DR: In this article , an open-source python platform for applications of Deep Reinforcement Learning (DRL) in fluid mechanics is proposed, where an agent maximizes a cumulative reward by learning a feedback policy by acting in an environment and the cumulative reward would correspond to the cost function, the agent to the actuator, the environment to the measured signals, and the learned policy to the feedback law.
Journal ArticleDOI
Theoretical Analysis on Absorption of Carbon Dioxide (CO2) into Solutions of Phenyl Glycidyl Ether (PGE) Using Nonlinear Autoregressive Exogenous Neural Networks
TL;DR: In this article, the authors analyzed the mass transfer model with chemical reactions during the absorption of carbon dioxide (CO2) into phenyl glycidyl ether (PGE) solution.
Journal ArticleDOI
Thermal Analysis of Conductive-Convective-Radiative Heat Exchangers With Temperature Dependent Thermal Conductivity
TL;DR: In this paper, an intelligent soft computing paradigm named as the LeNN-WOA-NM algorithm is designed to analyze the mathematical model for the temperature field of convective-conductive-radiative fin with thermal conductivity depending on temperature.
References
More filters
Journal ArticleDOI
The Whale Optimization Algorithm
Seyedali Mirjalili,Andrew Lewis +1 more
TL;DR: Optimization results prove that the WOA algorithm is very competitive compared to the state-of-art meta-heuristic algorithms as well as conventional methods.
Journal ArticleDOI
A new constitutive equation derived from network theory
Nhan Phan Thien,Roger I. Tanner +1 more
TL;DR: In this paper, a constitutive equation is derived from a Lodge-Yamamoto type of network theory for polymeric fluids, where the network junctions are not assumed to move strictly as points of the continuum but allowed a certain "effective slip".
Journal ArticleDOI
Non-Newtonian effects in steady motion of some idealized elastico-viscous liquids
Abstract: Normal-stress effects and the variation of apparent viscosity with rate of shear in simple types of steady flow of certain idealized elastico-viscous liquids are discussed. The liquids are those whose behaviour at sufficiently small variable shear stresses can be characterized by three constants (a coefficient of viscosity, a relaxation time and a retardation time) and whose invariant differential equations of state for general motion (involving eight independent physical constants) are linear in the stresses and include terms of no higher degree than the second in the stresses and velocity gradients together. The normal stresses which, in addition to shear stresses, are present in such a liquid in a state of simple shearing flow, or in flow in a circular pipe, or between rotating cylinders, are investigated; and the conditions under which the Weissenberg climbing effect will occur, in a positive or negative sense, are examined. In many liquids of this class, steady rectilinear flow under a uniform pressure gradient is not always possible in a straight pipe of arbitrary section, nor is steady flow in horizontal circles in a region bounded by arbitrary surfaces of revolution in relative rotation about common vertical axis. The behaviour of these idealized liquids when sheared in a narrow gap between a rotating wide-angled cone and a flat plate is compared with the observations of Roberts (1952, 1953) on some real elastico-viscous liquids. Certain liquids of this class, characterized by six independent constants satisfying certain inequalities, exhibit rheological behaviour which is, at least qualitatively, similar to the behaviour of many real elastico-viscous liquids in the following respects: the behaviour at small variable shear stresses, the variation of apparent viscosity with rate of steady shearing, the climbing effect up a vertical rod rotated in the liquid, and a distribution of normal stresses equivalent to an extra tension along the streamlines (with an isotropic state of stress in the plane normal to the streamlines) which is present in all the simple types of steady shearing flow investigated. These liquids can flow steadily in straight lines through a straight pipe of any section.
Journal ArticleDOI
A model for viscoelastic fluid behavior which allows non-affine deformation
TL;DR: In this paper, a continuum theory of viscoelasticity is developed which allows non-affine deformation, defined in an appropriate manner, and applied to simple shear flows, the scalar parameter being determined to match certain experimental data.
Journal ArticleDOI
A hybrid simplex search and particle swarm optimization for unconstrained optimization
Shu-Kai S. Fan,Erwie Zahara +1 more
TL;DR: The hybrid NM-PSO algorithm based on the Nelder–Mead (NM) simplex search method and particle swarm optimization (PSO) for unconstrained optimization is proposed to demonstrate how the standard particle swarm optimizers can be improved by incorporating a hybridization strategy.