機械学習および量子化学計算を用いた気体材料の絶縁破壊電界・沸点予測の精度向上に関する一検討

カテゴリ: 論文誌(論文単位)

グループ名: 【A】基礎・材料・共通部門

発行日: 2017/07/01

タイトル(英語): Advanced Empirical Prediction of Electric Breakdown Field and Boiling Point of Gases using Machine Learning Techniques and Quantum Chemical Calculations

著者名: 佐藤　正寛（東京大学大学院 工学系研究科 電気系工学専攻），熊田　亜紀子（東京大学大学院 工学系研究科 電気系工学専攻），日高　邦彦（東京大学大学院 工学系研究科 電気系工学専攻）

著者名(英語): Masahiro Sato (School of Engineering, The University of Tokyo), Akiko Kumada (School of Engineering, The University of Tokyo), Kunihiko Hidaka (School of Engineering, The University of Tokyo)

キーワード: 絶縁破壊，代替ガス，SF6，機械学習，kernel ridge regression，量子化学計算　　electrical breakdown，alternative gas，SF6，machine learning，kernel ridge regression，quantum chemical calculation

要約(英語): This study demonstrates that the accuracy of empirical prediction of electric breakdown field of gases can be improved by adopting an appropriate machine learning approach. The performance of the machine learning models for predicting electrical breakdown strengths were evaluated by means of double cross validation technique. It is shown that the coefficient of determination between experimental and predicted electric breakdown strengths can be increased by roughly 30% and the standard deviation can be decreased by roughly 30% by adopting kernel ridge regression (KRR) method and by choosing the best number and combinations of predictors. Electric breakdown strengths and boiling points of (CF3)2CFCN and CF3C(O)CF(CF3)2 molecules that are recently proposed as alternative gases for SF6, are predicted by KRR method with the aid of quantum chemical calculations. Predicted electric breakdown strengths and boiling points were in good agreement with experimental findings; the prediction errors of breakdown strengths and boiling points were within 30 and 10%, respectively.

本誌: 電気学会論文誌A（基礎・材料・共通部門誌） Vol.137 No.7 （2017） 特集：平成28年基礎・材料・共通部門大会－テーマ付きセッション：ナノ磁性体の物性と機能性－

本誌掲載ページ: 422-427 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejfms/137/7/137_422/_article/-char/ja/