Optimisation of convolutional neural network architecture using genetic algorithm for the prediction of adhesively bonded joint strength

被引：0
作者：
Edore G. Arhore
Mehdi Yasaee
Iman Dayyani
机构：
[1] School of Aerospace,
[2] Transport and Manufacturing,undefined
来源：
Structural and Multidisciplinary Optimization | 2022年 / 65卷
关键词：
Adhesive joints; Convolutional neural network; Genetic algorithm; Composite adherend; Lightweight design;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The classical method of optimising structures for strength is computationally expensive due to the requirement of performing complex non-linear finite element analysis (FEA). This study aims to optimise an artificial neural network (ANN) architecture to perform the task of predicting the strength of adhesively bonded joints in place of non-linear FEA. A manual multi-objective optimisation was performed to find a suitable ANN architecture design space. Then a genetic algorithm optimisation of the reduced design space was conducted to find an optimum ANN architecture. The generated optimum ANN architecture predicts efficiently the strength of adhesively bonded joints to a high degree of accuracy in comparison with the legacy method using FEA with a 93% savings in computational cost.
引用
收藏
相关论文
共 103 条
[1]  
Alqahtani H(2021)Classification of fatigue crack damage in polycrystalline alloy structures using convolutional neural networks Eng Fail Anal 119 278-287
[2]  
Bharadwaj S(2019)Convolutional neural networks based potholes detection using thermal imaging J King Saud Univ Comput Inf Sci 226–227 305-317
[3]  
Ray A(2021)Comparison of GA and topology optimization of adherend for adhesively bonded metal composite joints Int J Solids Struct 275 354-377
[4]  
Arhore EG(2020)Granger causality detection in high-dimensional systems using feedforward neural networks Int J Forecast 23 448-465
[5]  
Yasaee M(2018)A review on neural networks with random weights Neurocomputing 79 69-74
[6]  
Dayyani I(2019)Deep neural networks as scientific models Trends Cogn Sci 31 2137-2152
[7]  
Calvo-Pardo H(2020)Automatic speaker recognition from speech signals using self organizing feature map and hybrid neural network Microprocess Microsyst 142 121-129
[8]  
Mancini T(2020)Dynamic model of a lithium-ion cell using an artificial feedforward neural network with dynamical signal preprocessing J Energy Storage 77 103-109
[9]  
Olmo J(2022)CNN architecture optimization using bio-inspired algorithms for breast cancer detection in infrared images Comput Biol Med 477 482-494
[10]  
Cao W(2018)Recent advances in convolutional neural networks Pattern Recognit 120 434-451
12345678910