2篇
您的检索式：作者名="Danpeng Cheng"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Degradation mechanism analysis of LiNi_(0.5)Co_(0.2)Mn_(0.3)O_(2) single crystal cathode materials through machine learning显示文摘LiNi_(0.5)Co_(0.2)Mn_(0.3)O_(2)(NCM523)has become one of the most popular cathode materials for current lithium-ion batteries due to its high-energy density and cost performance.However,the rapid capacity fading of NCM severely hinders its development and applications.Here,the single crystal NCM523 materials under different degradation states are characterized using scanning transmission electron microscopy(STEM).Then we developed a neural network model with a two-sequential attention block to recognize the crystal structure and locate defects in STEM images.The number of point defects in NCM523 is observed to experience a trend of increasing first and then decreasing in the degradation process.The space between the transition metal columns shrinks obviously,inducing dramatic capacity decay.This analysis sheds light on the defect evolution and chemical transformation correlated with layered material degradation.It also provides interesting hints for researchers to regenerate the electrochemical capacity and design better battery materials with longer life. | Wuxin Sha Yaqing Guo Danpeng Cheng Qigao Han Ping Lou Minyuan Guan Shun Tang Xinfang Zhang Songfeng Lu Shijie Cheng Yuan-Cheng Cao | 2022 | npj Computational Materials2022，，1： | 1 |
| 2 | AtomGAN:unsupervised deep learning for fast and accurate defect detection of 2D materials at the atomic scale显示文摘The extraction of atomic-level material features from electron microscope images is crucial for studying structure-property relationships and discovering new materials.However,traditional electron microscope analyses rely on time-consuming and complex human operations;thus,they are only applicable to images with a small number of atoms.In addition,the analysis results vary due to observers’individual deviations.Although efforts to introduce automated methods have been performed previously,many of these methods lack sufficient labeled data or require various conditions in the detection process that can only be applied to the target material.Thus,in this study,we developed AtomGAN,which is a robust,unsupervised learning method,that segments defects in classical 2D material systems and the heterostructures of MoS_(2)/WS_(2)automatically.To solve the data scarcity problem,the proposed model is trained on unpaired simulated data that contain point and line defects for MoS_(2)/WS_(2).The proposed AtomGAN was evaluated on both simulated and real electron microscope images.The results demonstrate that the segmented point defects and line defects are presented perfectly in the resulting figures,with a measurement precision of 96.9%.In addition,the cycled structure of AtomGAN can quickly generate a large number of simulated electron microscope images. | Danpeng CHENG Wuxin SHA Zuo XU Shide LI Zhigao YIN Yuling LANG Shun TANG Yuan-Cheng CAO | 2023 | Science China(Information Sciences)2023，66，6： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员