中国物理B ›› 2024, Vol. 33 ›› Issue (8): 87701-087701.doi: 10.1088/1674-1056/ad51f3

所属专题： Featured Column — DATA PAPER

• • 上一篇    下一篇

Physics-embedded machine learning search for Sm-doped PMN-PT piezoelectric ceramics with high performance

Rui Xin(辛睿)1, Yaqi Wang(王亚祺)1, Ze Fang(房泽)1, Fengji Zheng(郑凤基)1, Wen Gao(高雯)1, Dashi Fu(付大石)1, Guoqing Shi(史国庆)1, Jian-Yi Liu(刘建一)1,2,†, and Yongcheng Zhang(张永成)1,‡   

  1. 1 College of Physics, Center for Marine Observation and Communications, National Demonstration Center for Experimental Applied Physics Education, Qingdao University, Qingdao 266071, China;
    2 Centre for Theoretical and Computational Physics, College of Physics, Qingdao University, Qingdao 266071, China
  • 收稿日期:2024-02-03 修回日期:2024-05-23 出版日期:2024-08-15 发布日期:2024-07-15
  • 通讯作者: Jian-Yi Liu, Yongcheng Zhang E-mail:jianyi_liu@qdu.edu.cn;qdzhyc@qdu.edu.cn
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 52272116 and 12002400), the Natural Science Foundation of Shandong Province (Grant No. ZR2021ME096), and the Youth Innovation Team Project of Shandong Provincial Education Department (Grant No. 2019KJJ012).

Physics-embedded machine learning search for Sm-doped PMN-PT piezoelectric ceramics with high performance

Rui Xin(辛睿)1, Yaqi Wang(王亚祺)1, Ze Fang(房泽)1, Fengji Zheng(郑凤基)1, Wen Gao(高雯)1, Dashi Fu(付大石)1, Guoqing Shi(史国庆)1, Jian-Yi Liu(刘建一)1,2,†, and Yongcheng Zhang(张永成)1,‡   

  1. 1 College of Physics, Center for Marine Observation and Communications, National Demonstration Center for Experimental Applied Physics Education, Qingdao University, Qingdao 266071, China;
    2 Centre for Theoretical and Computational Physics, College of Physics, Qingdao University, Qingdao 266071, China
  • Received:2024-02-03 Revised:2024-05-23 Online:2024-08-15 Published:2024-07-15
  • Contact: Jian-Yi Liu, Yongcheng Zhang E-mail:jianyi_liu@qdu.edu.cn;qdzhyc@qdu.edu.cn
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 52272116 and 12002400), the Natural Science Foundation of Shandong Province (Grant No. ZR2021ME096), and the Youth Innovation Team Project of Shandong Provincial Education Department (Grant No. 2019KJJ012).

RichHTML

1

PDF (PC)

45

赞

摘要： Pb(Mg$_{1/3}$Nb$_{2/3}$)O$_{3}$-PbTiO$_{3}$ (PMN-PT) piezoelectric ceramics have excellent piezoelectric properties and are used in a wide range of applications. Adjusting the solid solution ratios of PMN/PT and different concentrations of elemental doping are the main methods to modulate their piezoelectric coefficients. The combination of these controllable conditions leads to an exponential increase of possible compositions in ceramics, which makes it not easy to extend the sample data by additional experimental or theoretical calculations. In this paper, a physics-embedded machine learning method is proposed to overcome the difficulties in obtaining piezoelectric coefficients and Curie temperatures of Sm-doped PMN-PT ceramics with different components. In contrast to all-data-driven model, physics-embedded machine learning is able to learn nonlinear variation rules based on small datasets through potential correlation between ferroelectric properties. Based on the model outputs, the positions of morphotropic phase boundary (MPB) with different Sm doping amounts are explored. We also find the components with the best piezoelectric property and comprehensive performance. Moreover, we set up a database according to the obtained results, through which we can quickly find the optimal components of Sm-doped PMN-PT ceramics according to our specific needs.

关键词: Pb(Mg$_{1/3}$Nb$_{2/3}$)O$_{3}$-PbTiO$_{3}$ (PMN-PT) ceramic, physics-embedded machine learning, piezoelectric coefficient, Curie temperature

Abstract: Pb(Mg$_{1/3}$Nb$_{2/3}$)O$_{3}$-PbTiO$_{3}$ (PMN-PT) piezoelectric ceramics have excellent piezoelectric properties and are used in a wide range of applications. Adjusting the solid solution ratios of PMN/PT and different concentrations of elemental doping are the main methods to modulate their piezoelectric coefficients. The combination of these controllable conditions leads to an exponential increase of possible compositions in ceramics, which makes it not easy to extend the sample data by additional experimental or theoretical calculations. In this paper, a physics-embedded machine learning method is proposed to overcome the difficulties in obtaining piezoelectric coefficients and Curie temperatures of Sm-doped PMN-PT ceramics with different components. In contrast to all-data-driven model, physics-embedded machine learning is able to learn nonlinear variation rules based on small datasets through potential correlation between ferroelectric properties. Based on the model outputs, the positions of morphotropic phase boundary (MPB) with different Sm doping amounts are explored. We also find the components with the best piezoelectric property and comprehensive performance. Moreover, we set up a database according to the obtained results, through which we can quickly find the optimal components of Sm-doped PMN-PT ceramics according to our specific needs.

Key words: Pb(Mg$_{1/3}$Nb$_{2/3}$)O$_{3}$-PbTiO$_{3}$ (PMN-PT) ceramic, physics-embedded machine learning, piezoelectric coefficient, Curie temperature

中图分类号:  (Dielectric, piezoelectric, ferroelectric, and antiferroelectric materials)

  • 77.84.-s
77.84.Cg (PZT ceramics and other titanates) 77.90.+k (Other topics in dielectrics, piezoelectrics, and ferroelectrics and their properties) 77.80.Jk (Relaxor ferroelectrics)