摘要
为减少测试成本和缩短设计周期,基于机器学习方法对树脂基复合材料模量的预报方法进行了研究.采用一种全新预测方法——神经网络联合遗传算法(GA-ANN),将T800/环氧复合材料的强度、泊松比和失效应变作为反向传播(BP)神经网络的3个输入变量,在遗传算法(GA)中得出最优阈值和权重,并将所得数值赋给对应的网络参数,更新BP神经网络以更高的准确率预测树脂基复合材料的模量;同等条件下,用Adam算法进行预测.对比这两种方法,结果充分证明了GA-ANN的可行性.
In order to reduce the cost of testing and shorten the design cycle,this paper studies the prediction method of the modulus of resin matrix composites based on the machine learning method.Using a new prediction method—the neural network in combination with the genetic algorithm(GA-ANN),the strength,the Poisson’s ratio,and the failure strain of the T800/epoxy composite material are used as three input variables of the back propagation(BP)neural network.Then,the optimal threshold and weight are obtained in the genetic algorithm(GA),which are assigned tOthe corresponding network parameters,and the BP neural network is updated for higher accuracy tOpredict the modulus of resin matrix composites.Under the same conditions,the Adam algorithm is used tOpredict.A comparison of these twOmethods fully proves the feasibility of the GA-ANN algorithm.
作者
王卓鑫
赵海涛
谢月涵
任翰韬
袁明清
张博明
陈吉安
WANG Zhuoxin;ZHAO Haitao;XIE Yuehan;REN Hantao;YUAN Mingqing;ZHANG Boming;CHEN Ji’an(School of Aeronautics and Astronautics,Shanghai JiaOTong University,Shanghai 200240,China;Composites Centre,Commercial Aircraft Corporation of China,Ltd.,Shanghai 201210,China;School of Materials Science and Engineering,Beihang University,Beijing 100191,China)
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2022年第10期1341-1348,共8页
Journal of Shanghai Jiaotong University
关键词
机器学习
反向传播神经网络
遗传算法
复合材料模量
Adam算法
machine learning
back propagation(BP)neural network
genetic algorithm
composite material modulus
Adam algorithm
