The Search for BaTiO3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning. Yuan, R., Xue, D., Xue, D., Zhou, Y., Ding, X., Sun, J., & Lookman, T. 66(2):394–401. Number: 2 Conference Name: IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency ControlPaper doi abstract bibtex 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.
@article{yuan_search_2019,
title = {The Search for {BaTiO}3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning},
volume = {66},
issn = {1525-8955},
url = {https://ieeexplore.ieee.org/abstract/document/8581483},
doi = {10.1109/TUFFC.2018.2888800},
abstract = {We employ a data-driven approach to search for {BaTiO}3-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.},
pages = {394--401},
number = {2},
journaltitle = {{IEEE} Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},
author = {Yuan, Ruihao and Xue, Deqing and Xue, Dezhen and Zhou, Yumei and Ding, Xiangdong and Sun, Jun and Lookman, Turab},
urldate = {2023-11-03},
date = {2019-02},
note = {Number: 2
Conference Name: {IEEE} Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},
}
Downloads: 0
{"_id":"guYE9fskexxsj5o5a","bibbaseid":"yuan-xue-xue-zhou-ding-sun-lookman-thesearchforbatio3basedpiezoelectricswithlargepiezoelectriccoefficientusingmachinelearning","author_short":["Yuan, R.","Xue, D.","Xue, D.","Zhou, Y.","Ding, X.","Sun, J.","Lookman, T."],"bibdata":{"bibtype":"article","type":"article","title":"The Search for BaTiO3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning","volume":"66","issn":"1525-8955","url":"https://ieeexplore.ieee.org/abstract/document/8581483","doi":"10.1109/TUFFC.2018.2888800","abstract":"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.","pages":"394–401","number":"2","journaltitle":"IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control","author":[{"propositions":[],"lastnames":["Yuan"],"firstnames":["Ruihao"],"suffixes":[]},{"propositions":[],"lastnames":["Xue"],"firstnames":["Deqing"],"suffixes":[]},{"propositions":[],"lastnames":["Xue"],"firstnames":["Dezhen"],"suffixes":[]},{"propositions":[],"lastnames":["Zhou"],"firstnames":["Yumei"],"suffixes":[]},{"propositions":[],"lastnames":["Ding"],"firstnames":["Xiangdong"],"suffixes":[]},{"propositions":[],"lastnames":["Sun"],"firstnames":["Jun"],"suffixes":[]},{"propositions":[],"lastnames":["Lookman"],"firstnames":["Turab"],"suffixes":[]}],"urldate":"2023-11-03","date":"2019-02","note":"Number: 2 Conference Name: IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control","bibtex":"@article{yuan_search_2019,\n\ttitle = {The Search for {BaTiO}3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning},\n\tvolume = {66},\n\tissn = {1525-8955},\n\turl = {https://ieeexplore.ieee.org/abstract/document/8581483},\n\tdoi = {10.1109/TUFFC.2018.2888800},\n\tabstract = {We employ a data-driven approach to search for {BaTiO}3-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.},\n\tpages = {394--401},\n\tnumber = {2},\n\tjournaltitle = {{IEEE} Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},\n\tauthor = {Yuan, Ruihao and Xue, Deqing and Xue, Dezhen and Zhou, Yumei and Ding, Xiangdong and Sun, Jun and Lookman, Turab},\n\turldate = {2023-11-03},\n\tdate = {2019-02},\n\tnote = {Number: 2\nConference Name: {IEEE} Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},\n}\n\n","author_short":["Yuan, R.","Xue, D.","Xue, D.","Zhou, Y.","Ding, X.","Sun, J.","Lookman, T."],"key":"yuan_search_2019","id":"yuan_search_2019","bibbaseid":"yuan-xue-xue-zhou-ding-sun-lookman-thesearchforbatio3basedpiezoelectricswithlargepiezoelectriccoefficientusingmachinelearning","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/abstract/document/8581483"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/L6oHYoy8a5nTT8bpW","dataSources":["DwbKXqN9YyN8gkNab","Z9u3GzKyzYSLc7khn"],"keywords":[],"search_terms":["search","batio3","based","piezoelectrics","large","piezoelectric","coefficient","using","machine","learning","yuan","xue","xue","zhou","ding","sun","lookman"],"title":"The Search for BaTiO3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning","year":null}