Transfer-Learning-Based Virtual Process Optimization for LiPON

WU Jun-jun; WANG Tao; WANG Ying-kai; WANG Xing-hui

doi:10.12263/DZXB.20211241

您当前的位置：

首页 >

文章列表页 >

Transfer-Learning-Based Virtual Process Optimization for LiPON

PAPERS | 更新时间：2025-12-08

- Transfer-Learning-Based Virtual Process Optimization for LiPON
- ACTA ELECTRONICA SINICA Vol. 51, Issue 3, Pages: 687-693(2023)
- 作者机构：
  
  1.福州大学物理与信息工程学院，福建福州 350000
  2.福州大学微纳器件与太阳能电池研究所，福建福州 350000
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(83417013);Natural Science Foundation of Fujian Province(2019J06008;2018J01535)
- DOI：10.12263/DZXB.20211241
  CLC： TM912;TP181
- Received：08 September 2021，
  
  Revised：2021-12-10，
  
  Published：25 March 2023
- 稿件说明：
移动端阅览
吴军君,王涛,王英楷等.基于迁移学习的LiPON制备工艺模拟优化[J].电子学报,2023,51(03):687-693.

WU Jun-jun,WANG Tao,WANG Ying-kai,et al.Transfer-Learning-Based Virtual Process Optimization for LiPON[J].ACTA ELECTRONICA SINICA,2023,51(03):687-693.
吴军君,王涛,王英楷等.基于迁移学习的LiPON制备工艺模拟优化[J].电子学报,2023,51(03):687-693. DOI： 10.12263/DZXB.20211241.

WU Jun-jun,WANG Tao,WANG Ying-kai,et al.Transfer-Learning-Based Virtual Process Optimization for LiPON[J].ACTA ELECTRONICA SINICA,2023,51(03):687-693. DOI： 10.12263/DZXB.20211241.

摘要

不同工艺参数对磁控溅射制备固态电解质薄膜LiPON的物理化学特性有巨大影响，使用机器学习对过程建模，能加强内部原理理解，优化参数提升薄膜性能.迁移学习通过挖掘历史数据集中的信息，提升模型精确度与泛化能力，从而更好地找到良好的工艺参数.本文以文献中磁控溅射制备LiPON的数据集为例，探究靶基距离、溅射功率、溅射气压对LiPON薄膜的离子电导率的影响.对比普通机器学习，迁移学习模型在多项误差指标上提升30%以上.通过模型遍历参数空间，搜寻最佳工艺组合，预测LiPON薄膜的离子电导率为2.04 μS/cm，优于文献中的最优值，方差分析与实际样本证明了该方法具有可行性.

Abstract

Different process parameters have a huge impact on the physical and chemical properties of the LiPON thin films synthesized by magnetron sputtering. It has great significance to model the synthesis process for strengthening the understanding of internal principles and improving the properties of the thin films. Transfer learning can improve model accuracy and generalization ability by mining information in historical data sets

so as to better find good process parameters. This paper takes the datasets of LiPON synthesized by magnetron sputtering in literatures as examples to explore the influence of target-substrate distance

sputtering power

and sputtering pressure on the ion-conductivity of LiPON films. Comparing with ordinary machine learning

the transfer learning model improves by more than 30% in multiple error metrics. The built model recommended the optimal parameters combination after traversing parameters space

and the predicted ion-conductivity of LiPON film is 2.04 μS/cm

which is better than the maximum value in the literature. The mapped contour graph of process parameters and performance recommended for a process parameter range

and the performance of film is good and stable within the range. The analysis of variance and actual samples prove that the method is practical.

关键词

Keywords

references

MANI P D , SARAF S , SINGH V , et al . Ionic conductivity of bias sputtered lithium phosphorus oxy-nitride thin films [J]. Solid State Ionics , 2016 , 287 : 48 - 59 .

张勤 . USC-80U型乙烯裂解模型化炉与仿真优化 [D]. 北京 : 北京化工大学 , 2009 .

ZHANG Q . Modeling Simulation and Optimization of USC-80U Naphtha Pyrolysis Furnace [D]. Beijing : Beijing University of Chemical Technology , 2009 . (in Chinese)

BATES J B , DUDNEY N J , GRUZALSKI G R , et al . Electrical properties of amorphous lithium electrolyte thin films [J]. Solid State Ionics , 1992 , 53/54/55/56 : 647 - 654 .

BATES J B , DUDNEY N J , GRUZALSKI G R , et al . Fabrication and characterization of amorphous lithium electrolyte thin films and rechargeable thin-film batteries [J]. Journal of Power Sources , 1993 , 43 ( 1/2/3 ): 103 - 110 .

FLEUTOT B , PECQUENARD B , MARTINEZ H , et al . Investigation of the local structure of LiPON thin films to better understand the role of nitrogen on their performance [J]. Solid State Ionics , 2011 , 186 ( 1 ): 29 - 36 .

PARK H Y , NAM S C , LIM Y C , et al . Effects of sputtering pressure on the characteristics of lithium ion conductive lithium phosphorous oxynitride thin film [J]. Journal of Electroceramics , 2006 , 17 ( 2/3/4 ): 1023 - 1030 .

PICHONAT T , LETHIEN C , TIERCELIN N , et al . Further studies on the lithium phosphorus oxynitride solid electrolyte [J]. Materials Chemistry and Physics , 2010 , 123 ( 1 ): 231 - 235 .

WANG B , CHAKOUMAKOS B C , SALES B C , et al . Synthesis, crystal structure, and ionic conductivity of a polycrystalline lithium phosphorus oxynitride with the γ-Li 3 PO 4 structure [J]. Journal of Solid State Chemistry , 1995 , 115 ( 2 ): 313 - 323 .

WANG B , KWAK B S , SALES B C , et al . Ionic conductivities and structure of lithium phosphorus oxynitride glasses [J]. Journal of Non-Crystalline Solids , 1995 , 183 ( 3 ): 297 - 306 .

WEI L F , XU X J , GURUDAYAL , et al . Machine learning optimization of p-type transparent conducting films [J]. Chemistry of Materials , 2019 , 31 ( 18 ): 7340 - 7350 .

BANKO L , LYSOGORSKIY Y , GROCHLA D , et al . Predicting structure zone diagrams for thin film synthesis by generative machine learning [J]. Communications Materials , 2020 , 1 ( 1 ): 1 - 10 .

HAN Y , TANG B J , WANG L , et al . Machine-learning-driven synthesis of carbon dots with enhanced quantum yields [J]. ACS Nano , 2020 , 14 ( 11 ): 14761 - 14768 .

周书恒 , 杜文莉 . 基于迁移学习的裂解炉产率建模 [J]. 化工学报 , 2014 , 65 ( 12 ): 4921 - 4928 .

ZHOU S H , DU W L . Modeling of ethylene cracking furnace yields based on transfer learning [J]. CIESC Journal , 2014 , 65 ( 12 ): 4921 - 4928 . (in Chinese)

KIM E , HUANG K , JEGELKA S , et al . Virtual screening of inorganic materials synthesis parameters with deep learning [J]. Npj Computational Materials , 2017 , 3 ( 1 ): 1120 - 1127 .

SUN B C , FENG J S , SAENKO K . Return of frustratingly easy domain adaptation [EB/OL]. ( 2015-11-17 ). https://arxiv.org/abs/1511.05547 https://arxiv.org/abs/1511.05547 .

LU J D , GAO F R . Process modeling based on process similarity [J]. Industrial & Engineering Chemistry Research , 2008 , 47 ( 6 ): 1967 - 1974 .

PEDREGOSA F , VAROQUAUX G , GRAMFORT A , et al . Scikit-learn: Machine learning in Python [J]. Journal of Machine Learning Research , 2011 , 12 : 2825 - 2830 .

LU J D , YAO K , GAO F R . Process similarity and developing new process models through migration [J]. AIChE Journal , 2009 , 55 ( 9 ): 2318 - 2328 .

PAN S J , YANG Q . A survey on transfer learning [J]. IEEE Transactions on Knowledge and Data Engineering , 2010 , 22 ( 10 ): 1345 - 1359 .

CAI J F , CANDÈS E J , SHEN Z W . A singular value thresholding algorithm for matrix completion [J]. SIAM Journal on Optimization , 2010 , 20 ( 4 ): 1956 - 1982 .

HAMON Y , DOUARD A , SABARY F , et al . Influence of sputtering conditions on ionic conductivity of LiPON thin films [J]. Solid State Ionics , 2006 , 177 ( 3/4 ): 257 - 261 .

李林 . LiPON固态电解质与全固态薄膜锂离子电池制备及特性研究 [D]. 兰州 : 兰州大学 , 2018 .

LI L . Study of Solid Electrolyte LiPON and all Solid-State Thin-Film Lithium-Ion Batteries' Fabrications and Characteristics [D]. Lanzhou : Lanzhou University , 2018 . (in Chinese)

LARSON M G . Analysis of variance [J]. Circulation , 2008 , 117 ( 1 ): 115 - 121 .

LIU S , SU Y , YIN H , et al . An infrastructure with user-centered presentation data model for integrated management of materials data and services [J]. Computational Materials , 2021 , 7 : 88 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Transfer Learning for Software Defect Prediction

A Detection Method for Android Repackaged Malware Based on Sensitive Component Function Call Graph

Locomotion Intention Prediction via Multi-Sensor Fusion and Transfer Learning for Lower Limb Exoskeletons

Hybrid Task Assignment for Crowd Sensing Based on Mobility Prediction

Related Author

WANG Xing-hui

CHENG Ming

WU Guo-qing

YUAN Meng-ting

DU Rui-ying

CHEN Jing

WU Cong

YAN Xi-yu

Related Institution

School of Computer, Wuhan University

State Key Lab of Software Engineering, Wuhan University

School of Computer Wuhan University Wuhan Hubei China

State Key Lab of Software Engineering Wuhan University Wuhan Hubei China

School of Computer and Information Engineering, Henan Normal University

⁰