摘要
根据实验测得环氧树脂不同体积浓度浸泡液下的碳纳米管/环氧树脂复合薄膜的力学性能的实验数据,应用基于粒子群算法(PSO)寻优的支持向量回归(SVR)方法,建立了不同实验参数对复合薄膜力学性能影响的预测模型。留一交叉法(LOOCV)结果表明环氧树脂体积分数与复合薄膜力学性能之间关系复杂,呈现高度的非线性。表征力学性能的拉伸强度σb(MPa)、延伸率δ(%)和弹性模量E(GPa)的平均绝对百分误差分别为3.96%,3.14%和2.62%,相关系数(R2)分别高达0.991,0.990和0.997。该方法不仅准确预测了双壁碳纳米管与环氧树脂复合薄膜的力学性能,而且为实验工作者研究实验参数与力学性能之间关系提供了理论指导。
The support vector regression(SVR)combined with particle swarm optimization(PSO)for its parameter optimization was employed to construct mathematical model for prediction of the mechanical properties of the carbon nanotubes/epoxy composites according to an experimental dataset on the mechanical properties under different process parameters.The leave-one-out cross validation(LOOCV)test result by SVR support supports that the generalization ability of SVR model is high enough.The relationship between the response and process parameters is highly nonlinear and quite complicated.The mean absolute percentage error for tensile strength,elongation and elastic modulus are 3.96%,3.14%and 2.62%,the correlation coefficient(R)is as high as 0.991,0.990 and 0.997 respectively of SVR-LOOCV model.This study suggests that the SVR model can be used to accurately foresee the mechanical properties of carbon nanotubes/epoxy composites,and can be used to optimize designing or controlling the experimental process for experimental researchers.
作者
程文德
张家伟
CHENG Wende;ZHANG Jiawei(School of Mathematics and Physics,Chongqing University of Science and Technology,Chongqing 401331,China)
出处
《大学物理实验》
2021年第4期7-10,共4页
Physical Experiment of College
基金
重庆市科委基金(cstc2018jcyjAX0713)
重庆市教委基金(KJQN202001541)
重庆科技学院重点项目培育基金(CK2016Z03)。
关键词
碳纳米管
环氧树脂
力学性能
支持向量回归
预测
carbon nanotube/epoxy composites
mechanical properties
support vector regression
prediction
