高级检索
无机材料学报

无机材料学报 ›› 2026, Vol. 41 ›› Issue (7): 1001-1010.DOI: 10.15541/jim20260017 CSTR: 32189.14.10.15541/jim20260017

• 数据论文 • 上一篇    下一篇

基于机器学习的高温BSPT基压电陶瓷双重性能协同增强

左致平1,2(), 郭春1,2, 周志勇1()   

  1. 1 中国科学院 上海硅酸盐研究所, 关键陶瓷材料全国重点实验室, 上海 201899
    2 中国科学院大学 材料科学与光电工程中心, 北京 100049
  • 收稿日期:2026-01-12 修回日期:2026-02-27 出版日期:2026-07-20 网络出版日期:2026-03-02
  • 通讯作者: 周志勇, 研究员. E-mail: zyzhou@mail.sic.ac.cn
  • 作者简介:左致平(2001-), 男, 博士研究生. E-mail: zuozhiping23@mails.ucas.ac.cn

Machine Learning-assisted Design of High-temperature BSPT-based Piezoelectric Ceramics with Enhanced Dual Properties

ZUO Zhiping1,2(), GUO Chun1,2, ZHOU Zhiyong1()   

  1. 1 State Key Laboratory of High Performance Ceramics, Shanghai Institute of Ceramics, Chinese Academy of Sciences, Shanghai 201899, China
    2 Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2026-01-12 Revised:2026-02-27 Published:2026-07-20 Online:2026-03-02
  • Contact: ZHOU Zhiyong, professor. E-mail: zyzhou@mail.sic.ac.cn
  • About author:ZUO Zhiping (2001-), male, PhD candidate. E-mail: zuozhiping23@mails.ucas.ac.cn
  • Supported by:
    Strategic Priority Research Program of the Chinese Academy of Sciences(XDA0380302)

RichHTML

10

PDF (PC)

374

摘要：

BiScO3-PbTiO3 (BSPT)基压电陶瓷因其高居里温度(TC)以及高压电系数(d33), 成为350 ℃以上高温压电应用领域的重要候选材料。然而, 传统试错法难以在广泛的成分空间范围内实现高温压电陶瓷的快速设计。本研究基于小样本数据集构建了机器学习模型, 并结合实验先验知识, 加速了兼具高d33和高TC的BSPT基压电陶瓷的设计。利用该模型, 设计并制备了Ga-W离子对共掺杂的0.36BiScO3-0.64PbTi1-x(Ga2/3W2/3)xO3 (BSPTGW1000x)压电陶瓷。结果表明, 该掺杂策略明显调控了BSPT基压电陶瓷的晶格畸变和畴结构, 从而提升了压电性能。其中, BSPTGW10 (x=0.010)陶瓷表现出最好的综合性能(d33=525 pC/N, TC=423 ℃), 与模型预测性能接近; 且在365 ℃以下, d33变化率保持在±15%以内, 表现出优异的热稳定性。本研究不仅为快速发现同时具备高压电性能和高居里温度的BSPT基压电陶瓷提供了有效途径, 而且获得了一种适用于高温应用有前景的压电陶瓷材料。本文数据集可通过 https://www.doi.org/10.57760/sciencedb.27980访问获取。

关键词: 机器学习, 钪酸铋钛酸铅, 高温压电陶瓷, 数据驱动设计, 离子对掺杂

Abstract:

BiScO3-PbTiO3 (BSPT)-based piezoelectric ceramics have emerged as one of the most promising candidates for high-temperature piezoelectric applications above 350 ℃ due to their high Curie temperature (TC) and large piezoelectric coefficient (d33). However, the conventional trial-and-error approach is inefficient for the rapid design of high-temperature piezoelectric ceramics across a wide compositional space. In this work, we developed a machine learning model trained on a small dataset and integrated it with experimental knowledge to accelerate the design of BSPT-based ceramics with simultaneously large d33 and high TC. Guided by the trained model, we designed Ga-W ion-pair co-doped 0.36BiScO3-0.64PbTi1-x(Ga2/3W1/3)xO3 (BSPTGW1000x) ceramics. The results demonstrated that this doping strategy significantly modified the lattice distortion and domain structures of BSPT-based ceramics, leading to enhanced piezoelectric performance. Among the compositions, BSPTGW10 (x=0.010) exhibited the best overall properties (d33=525 pC/N, TC=423 ℃), which were in close agreement with the predicted values. Moreover, its piezoelectric coefficient variation remained within ±15% up to 365 ℃, indicating excellent thermal stability. This study not only provides an effective approach for the rapid discovery of BSPT-based ceramics with dual high-performance characteristics, but also yields a promising piezoelectric ceramic material suitable for high-temperature applications. The datasets in this article are listed in Science Data Bank at https://www.doi.org/10.57760/sciencedb.27980.

Key words: machine learning, BiScO3-PbTiO3, high-temperature piezoelectric ceramic, data-driven design, ion- pair co-doping

中图分类号: