The intelligent detection technology driven by X-ray images and deep learning represents the forefront of advanced techniques and development trends in flaw detection and automated evaluation of light alloy castings.H...The intelligent detection technology driven by X-ray images and deep learning represents the forefront of advanced techniques and development trends in flaw detection and automated evaluation of light alloy castings.However,the efficacy of deep learning models hinges upon a substantial abundance of flaw samples.The existing research on X-ray image augmentation for flaw detection suffers from shortcomings such as poor diversity of flaw samples and low reliability of quality evaluation.To this end,a novel approach was put forward,which involves the creation of the Interpolation-Deep Convolutional Generative Adversarial Network(I-DCGAN)for flaw detection image generation and a comprehensive evaluation algorithm named TOPSIS-IFP.I-DCGAN enables the generation of high-resolution,diverse simulated images with multiple appearances,achieving an improvement in sample diversity and quality while maintaining a relatively lower computational complexity.TOPSIS-IFP facilitates multi-dimensional quality evaluation,including aspects such as diversity,authenticity,image distribution difference,and image distortion degree.The results indicate that the X-ray radiographic images of magnesium and aluminum alloy castings achieve optimal performance when trained up to the 800th and 600th epochs,respectively.The TOPSIS-IFP value reaches 78.7%and 73.8%similarity to the ideal solution,respectively.Compared to single index evaluation,the TOPSIS-IFP algorithm achieves higher-quality simulated images at the optimal training epoch.This approach successfully mitigates the issue of unreliable quality associated with single index evaluation.The image generation and comprehensive quality evaluation method developed in this paper provides a novel approach for image augmentation in flaw recognition,holding significant importance for enhancing the robustness of subsequent flaw recognition networks.展开更多
Polymer density-functional theories(PDFTs)have distinct advantages in the study of polyelectrolyte(PE)systems over experiments and molecular simulations.Here we give an introductory review of some PDFTs recently devel...Polymer density-functional theories(PDFTs)have distinct advantages in the study of polyelectrolyte(PE)systems over experiments and molecular simulations.Here we give an introductory review of some PDFTs recently developed for PE systems.We start with a general formalism of PDFTs and its relation to the widely used polymer self-consistent field theory(SCFT),then explain the various correlations that are neglected in SCFT but can be accounted for in PDFTs,including those due to the excluded-volume interaction and chain connectivity of uncharged polymers,the electrostatic correlations of small ions,and the chain correlations in PEs.We also list some applications of PDFTs for PE systems,and finally give some perspectives on future work.We hope that our review can attract more researchers to apply and further develop PDFTs as a promising class of theoretical and computational tools.展开更多
A new lattice model is designed to be suitable for simulating low-molecular-weight block copolymer(BCP)melts currently used in experiments to achieve sub-10 nm domain sizes(i.e.,having an invariant degree of polymeriz...A new lattice model is designed to be suitable for simulating low-molecular-weight block copolymer(BCP)melts currently used in experiments to achieve sub-10 nm domain sizes(i.e.,having an invariant degree of polymerization between 10^(2) and 10^(3)).It gives an isothermal compressibility comparable to real polymers such as polystyrene and poly(methyl methacrylate),high Monte Carlo simulation efficiency,and the fluctuation effects important for the low-molecular-weight BCPs.With its high lattice coordination number,the model can also be readily used for branched chains such as star BCPs.展开更多
基金funded by the National Key R&D Program of China(2020YFB1710100)the National Natural Science Foundation of China(Nos.52275337,52090042,51905188).
文摘The intelligent detection technology driven by X-ray images and deep learning represents the forefront of advanced techniques and development trends in flaw detection and automated evaluation of light alloy castings.However,the efficacy of deep learning models hinges upon a substantial abundance of flaw samples.The existing research on X-ray image augmentation for flaw detection suffers from shortcomings such as poor diversity of flaw samples and low reliability of quality evaluation.To this end,a novel approach was put forward,which involves the creation of the Interpolation-Deep Convolutional Generative Adversarial Network(I-DCGAN)for flaw detection image generation and a comprehensive evaluation algorithm named TOPSIS-IFP.I-DCGAN enables the generation of high-resolution,diverse simulated images with multiple appearances,achieving an improvement in sample diversity and quality while maintaining a relatively lower computational complexity.TOPSIS-IFP facilitates multi-dimensional quality evaluation,including aspects such as diversity,authenticity,image distribution difference,and image distortion degree.The results indicate that the X-ray radiographic images of magnesium and aluminum alloy castings achieve optimal performance when trained up to the 800th and 600th epochs,respectively.The TOPSIS-IFP value reaches 78.7%and 73.8%similarity to the ideal solution,respectively.Compared to single index evaluation,the TOPSIS-IFP algorithm achieves higher-quality simulated images at the optimal training epoch.This approach successfully mitigates the issue of unreliable quality associated with single index evaluation.The image generation and comprehensive quality evaluation method developed in this paper provides a novel approach for image augmentation in flaw recognition,holding significant importance for enhancing the robustness of subsequent flaw recognition networks.
基金support for this work provided by the National Natural Science Foundation of China(Nos.22173051 and 21829301).
文摘Polymer density-functional theories(PDFTs)have distinct advantages in the study of polyelectrolyte(PE)systems over experiments and molecular simulations.Here we give an introductory review of some PDFTs recently developed for PE systems.We start with a general formalism of PDFTs and its relation to the widely used polymer self-consistent field theory(SCFT),then explain the various correlations that are neglected in SCFT but can be accounted for in PDFTs,including those due to the excluded-volume interaction and chain connectivity of uncharged polymers,the electrostatic correlations of small ions,and the chain correlations in PEs.We also list some applications of PDFTs for PE systems,and finally give some perspectives on future work.We hope that our review can attract more researchers to apply and further develop PDFTs as a promising class of theoretical and computational tools.
基金the National Natural Science Foundation of China(No.21829301)the 111 Project(No.B16027).
文摘A new lattice model is designed to be suitable for simulating low-molecular-weight block copolymer(BCP)melts currently used in experiments to achieve sub-10 nm domain sizes(i.e.,having an invariant degree of polymerization between 10^(2) and 10^(3)).It gives an isothermal compressibility comparable to real polymers such as polystyrene and poly(methyl methacrylate),high Monte Carlo simulation efficiency,and the fluctuation effects important for the low-molecular-weight BCPs.With its high lattice coordination number,the model can also be readily used for branched chains such as star BCPs.
