Sharma, “Intelligent parameters optimization for laser cutting of highly reflective and thermally conductive materials using artificial neural network,” Mater. X Chen Z Yi Y Zhou P Guo SG Farkoush H Niroumandi 2021 Artificial neural network modeling and optimization of the solid oxide fuel cell parameters using grey wolf optimizer Energy 3459 KH Park SO Jun SM Baek MH Cho KJ Yee DH Lee 2013 Reduced-order model with an artificial neural network for aerostructural design optimization J Aircr 50 4 1106 1116 M Papadrakakis ND Lagaros Y Tsompanakis 1998 Structural optimization using evolution strategies and neural networks Comput Methods Appl Mech Eng 156 1 309 333 (97)00215-6 ![]() NV Nguyen J-W Lee M Tyan S Kim 2015 Repetitively enhanced neural networks method for complex engineering design optimisation problems Aeronaut J 119 1220 1253 1270 GG Wang S Shan 2006 Review of metamodeling techniques in support of engineering design optimization J Mech Des 129 4 370 380 Chichester, England Hoboken, N.J: Wiley, 2005.ĪIJ Forrester AJ Keane 2009 Recent advances in surrogate-based optimization Prog Aerosp Sci 45 1–3 50 79 įorrester A, Sobester A, Keane A (2008) Engineering design via surrogate modelling: a practical guide. Keane A, Nair P Computational approaches for aerospace design: the pursuit of excellence, 1 edition. The second one shows whether the IDNN can generate existing airfoils by a set of target parameters. The first case study shows how accurate the network can generate an airfoil with arbitrary input parameters. The accuracy of the Airfoil-IDNN was demonstrated using two case studies. During the database enhancement loop the validation mean squared error has reduced to 57.37%, and totally to 96.48% after the final hyperparameter selection. The Airfoil-IDNN generates a NACA 4-series airfoil that corresponds to target aerodynamic parameters given as an input. A construction of Airfoil inverse design neural network is demonstrated in this paper. After the training database is generated the final hyperparameter selection is performed. Then database enhancement loop refines the training database by iteratively adding new samples to initial database based on results of validation. ![]() ![]() The initial hyperparameter selection defines the configuration of IDNN that increases the accuracy of inverse design and reduces the network training time. The algorithm generates an inverse design deep neural network (IDNN) by performing a two-stage hyperparameter selection and iteratively enhancing training database. A deep-learning based rapid engineering design (DL-RED) algorithm is developed and presented for solving engineering inverse design problems.
0 Comments
Leave a Reply. |