Introduction Nanofiber orientation in suspensions determines the performance of nanoparticle suspensions which have potential applications in intelligent control.Material and method Na2Ti3O7 nanofibers were prepared w...Introduction Nanofiber orientation in suspensions determines the performance of nanoparticle suspensions which have potential applications in intelligent control.Material and method Na2Ti3O7 nanofibers were prepared with a hydrothermal method.The orientation degree of Na2Ti3O7 nanofibers in silicone oil has been studied by in situ small-angle X-ray scattering technique.Thünemann–Ruland method was used to extract the distribution widths of Na2Ti3O7 nanofibers in the suspensions.Conclution An empirical formula has been proposed to describe the dependence of nanofiber orientation degree on the external electric-field strength(E)and the nanofiber concentration(C).The results demonstrate that the response of nanofiber orientation to the electric field can be divided into exponential and linear stages before and after the inflection point of electric-field strength(Ec0.09 kV/mm).Low concentration of suspension is more sensitive to the external electric field.The increase in nanofiber concentration will decrease the response sensitivity of nanofiber orientation degree to the change of E.The critical concentration of Na2Ti3O7 nanofibers in the suspension is about 5 wt%.This study is expected to give new clue for the structurally responsive mechanism of anisotropic nanoparticles in suspensions to electric-field strength and particle concentration.展开更多
Polymer composites with one-dimensional(1D)oriented fillers,recognized for their high thermal conductivity(TC),are extensively utilized in cooling electronic components.However,the prediction of the TC of composites w...Polymer composites with one-dimensional(1D)oriented fillers,recognized for their high thermal conductivity(TC),are extensively utilized in cooling electronic components.However,the prediction of the TC of composites with 1D oriented fillers poses a challenge due to the significant impact of filler orientation on composite TC.In this paper,we use a strategy that combines deep learning and ensemble learning to efficiently and quickly predict the TC of composites with 1D oriented fillers.First,as a control,we used convolutional neural network(CNN)model to predict the TC of 1D carbon fiber-epoxy composite,and the R-squared(R^(2))on the test set reached 0.924.However,for composites consist of different matrices and fillers,the CNN model needs to be retrained,which greatly wastes computing resources.Therefore,we define a descriptor‘Orientation degree(O_(d))’to quantitatively describe the spatial distribution of the 1D fillers.CNN model was used to predict this structural parameter,the accuracy R^(2)can reach 0.950 on the test set.Using O_(d)as a feature,random forest regression(RFR)was used to predict the TC,and the accuracy R^(2)reached 0.954 on the test set,which was higher than that of CNN control group.We further successfully extended this strategy to composites consist of different 1D fillers and matrices,and only one CNN model and one RFR model needed to be trained to achieve fast and accurate TC prediction.This strategy provides valuable insights and guidance for machine learning-based material property prediction.展开更多
基金the Ministry of Science and Technology of China(Grant No.2017YFA0403000)the National Natural Science Foundation of China(Grant No.11405199).
文摘Introduction Nanofiber orientation in suspensions determines the performance of nanoparticle suspensions which have potential applications in intelligent control.Material and method Na2Ti3O7 nanofibers were prepared with a hydrothermal method.The orientation degree of Na2Ti3O7 nanofibers in silicone oil has been studied by in situ small-angle X-ray scattering technique.Thünemann–Ruland method was used to extract the distribution widths of Na2Ti3O7 nanofibers in the suspensions.Conclution An empirical formula has been proposed to describe the dependence of nanofiber orientation degree on the external electric-field strength(E)and the nanofiber concentration(C).The results demonstrate that the response of nanofiber orientation to the electric field can be divided into exponential and linear stages before and after the inflection point of electric-field strength(Ec0.09 kV/mm).Low concentration of suspension is more sensitive to the external electric field.The increase in nanofiber concentration will decrease the response sensitivity of nanofiber orientation degree to the change of E.The critical concentration of Na2Ti3O7 nanofibers in the suspension is about 5 wt%.This study is expected to give new clue for the structurally responsive mechanism of anisotropic nanoparticles in suspensions to electric-field strength and particle concentration.
基金supported by the Natural Science Foundation of Shandong Province(Grant Nos.ZR2022QA092,ZR2022MA011,ZR2023QE223)the Excellent Young Scientists Fund(Overseas)of Shandong Province(Grant No.2022HWYQ-091)the Taishan Scholars Program of Shandong Province.
文摘Polymer composites with one-dimensional(1D)oriented fillers,recognized for their high thermal conductivity(TC),are extensively utilized in cooling electronic components.However,the prediction of the TC of composites with 1D oriented fillers poses a challenge due to the significant impact of filler orientation on composite TC.In this paper,we use a strategy that combines deep learning and ensemble learning to efficiently and quickly predict the TC of composites with 1D oriented fillers.First,as a control,we used convolutional neural network(CNN)model to predict the TC of 1D carbon fiber-epoxy composite,and the R-squared(R^(2))on the test set reached 0.924.However,for composites consist of different matrices and fillers,the CNN model needs to be retrained,which greatly wastes computing resources.Therefore,we define a descriptor‘Orientation degree(O_(d))’to quantitatively describe the spatial distribution of the 1D fillers.CNN model was used to predict this structural parameter,the accuracy R^(2)can reach 0.950 on the test set.Using O_(d)as a feature,random forest regression(RFR)was used to predict the TC,and the accuracy R^(2)reached 0.954 on the test set,which was higher than that of CNN control group.We further successfully extended this strategy to composites consist of different 1D fillers and matrices,and only one CNN model and one RFR model needed to be trained to achieve fast and accurate TC prediction.This strategy provides valuable insights and guidance for machine learning-based material property prediction.
