Reconstruction of nanoparticle size distribution in laser-shocked matter from small-angle X-ray scattering via neural networks  

作　　者：Z.He J.Lütgert M.G.Stevenson B.Heuser D.Ranjan C.Qu D.Kraus 

机构地区：[1]Helmholtz-Zentrum Dresden-Rossendorf,Dresden,Germany [2]Institut für Physik,Universität Rostock,Rostock,Germany [3]Shanghai Institute of Laser Plasma,CAEP,Shanghai,China

出　　处：《High Power Laser Science and Engineering》2024年第4期72-78,共7页高功率激光科学与工程（英文版）

基　　金：supported by the Helmholtz Association under VH-NG-1141 and ERC-RA-0041.Z.H.acknowledges;support from the National Natural Science Foundation of China under Grant No.12304033;the financial support from China Scholarship Council。

摘　　要：Small-angle X-ray scattering(SAXS)has been widely used as a microstructure characterization technology.In this work,a fully connected dense forward network is applied to inversely retrieve the mean particle size and particle distribution from SAXS data of samples dynamically compressed with high-power lasers and probed with X-ray free electron lasers.The trained network allows automatic acquisition of microstructure information,performing well in predictions on single-species nanoparticles on the theoretical model and in situ experimental data.We evaluate our network by comparing it with other methods,revealing its reliability and efficiency in dynamic experiments,which is of great value for in situ characterization of materials under high-power laser-driven dynamic compression.

关 键 词：in situ X-ray diagnostics machine learning shock-compressed matter small-angle X-ray scattering 

分 类 号：TB383.1[一般工业技术—材料科学与工程] TP183[自动化与计算机技术—控制理论与控制工程] O434.19[自动化与计算机技术—控制科学与工程]