Application of neural network for computing heat performance in axisymmetric viscoelastic transport: Hybrid meta heuristic techniques

Abstract

Background and Objectives: Genetic algorithm and Interior point algorithms individually can have reliable and effective approaches to tackle physical flow problems. However, hybrid heuristic algorithms GA-IPA has been discovered an efficient and accurate solver than GA and IPA algorithms. Methodology: Mathematical development and governing equations under the channel boundaries is developed and explore with mechanism of thermal deposition. Moreover, Genetic Algorithm (GA) and Interior Point Algorithm (IPA) are explored in a hybrid arrangement for the weights optimization of ANN which optimized the performance of thermal deposition in axisymmetric viscoelastic transport phenomena. Additionally, we incorporate artificial neural networks (ANNs) architecture Schematic and workflow diagram for experimental explanation of proposed design scheme. Significances: A universal function approximation technique which is known as Artificial Neural Network (ANN) has been applied in the various field of practical importance. Among these fields are control systems, system identification, time series forecasting and decision support systems. For the purpose of ANN modeling, the weights optimization is required in a supervised manner to model the desired function. Conclusions: Artificial Neural Network is a stable and provide accurate and reliable solutions. For the validation purpose,we provide error graphs against number of runs. Keywords: Genetic algorithms, Interior point algorithms, Hybrid metaheuristic technique, Neural networks, Heat performance