The Search for BaTiO3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning

The Search for BaTiO3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning
复制标题

利用机器学习寻找具有大压电系数的 BaTiO3 基压电材料

DOI:
10.1109/tuffc.2018.2888800
复制
发表时间:
2019-02
期刊:
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
影响因子:
--
通讯作者:
Lookman Turab
Lookman Turab
中科院分区:
其他
文献类型:
--
作者:
Yuan Ruihao;Xue Deqing;Xue Dezhen;Zhou Yumei;Ding Xiangdong;Sun Jun;Lookman Turab

文献摘要

参考文献

被引文献

相似文献

我们采用数据驱动的方法来寻找具有大压电系数d33的钛酸钡基压电体。我们的方法使用代理模型来预测具有不确定性的d33,然后是选择下一个最佳化合物进行合成的设计步骤。我们比较了几种组合的选择的模型和设计选择策略的训练数据,从我们以前进行的许多实验,我们选择了最好的两个表演者指导新的实验。这种自适应设计策略迭代五次,在每次迭代中,基于两种不同的设计选择标准合成四种新化合物。在这项工作中发现的最好的新化合物是(Ba0.85Ca0.15)(Ti0.91Zr0.09)O3,其d33为362 pC/N,而在训练数据中最好的化合物BCT-0.5BZT的d33为~610 pC/N。我们从这项研究中得出的结论是,尽管我们的模型很好地描述了大多数可用的d33数据,但BCT-0.5BZT的特别大的值难以与任何替代模型拟合,并强调需要将基于物理的方法与本研究中使用的纯数据驱动方法相结合。
We employ a data-driven approach to search for BaTiO3-based piezoelectrics with large piezoelectric coefficient d33. Our approach uses a surrogate model to make predictions of d33 with uncertainties, followed by a design step that selects the next optimal compound to synthesize. We compare several combinations of choices of the model and design selection strategies on the training data assembled from many experiments that we have previously performed, and we choose the best two performers for guiding new experiments. This adaptive design strategy is iterated five times and in each iteration, four new compounds are synthesized based on the two different design selection criteria. The best new compound found in this work is (Ba0.85Ca0.15)(Ti0.91Zr0.09)O3 with a d33 of 362 pC/N, compared to the best compound BCT-0.5BZT in the training data with a d33 of ~610 pC/N. Our conclusion from this study is that although our model describes well most of the available d33 data, the especially large value for BCT-0.5BZT is difficult to fit with any surrogate model and emphasizes the need to combine a physics-based approach with a pure data-driven approach used in this study.
DOI: 10.1126/sciadv.1602241
发表时间: 2017-04
期刊: Science advances
影响因子: 13.6
作者:
Sanvito S;Oses C;Xue J;Tiwari A;Zic M;Archer T;Tozman P;Venkatesan M;Coey M;Curtarolo S
通讯作者: Curtarolo S
DOI: 10.1023/a:1009926623551
发表时间: 1998-12-01
影响因子: 1.7
作者:
Tressler, JF;Alkoy, S;Newnham, RE
通讯作者: Newnham, RE
DOI: 10.1038/srep19660
发表时间: 2016-01-21
期刊: Scientific reports
影响因子: 4.6
作者:
Balachandran PV;Xue D;Theiler J;Hogden J;Lookman T
通讯作者: Lookman T
使用贝叶斯学习加速搜索具有垂直同形相边界的 BaTiO3 基压电材料
DOI: 10.1073/pnas.1607412113
发表时间: 2016-11
影响因子: 11.1
作者:
Xue Dezhen;Balach;ran Prasanna V.;Yuan Ruihao;Hu Tao;Qian Xiaoning;Dougherty Edward R.;Lookman Turab
通讯作者: Lookman Turab
DOI: 10.1063/1.4812323
发表时间: 2013-07-01
期刊: APL MATERIALS
影响因子: 6.1
作者:
Jain, Anubhav;Shyue Ping Ong;Persson, Kristin A.
通讯作者: Persson, Kristin A.