文献类型：期刊文献

英文题名：A machine learning method for buckling design of internally pressurized torispherical heads considering geometric imperfection

作者：Liu, Fang[1,2];Yang, Jie[3];Weng, Shuo[1];Xuan, Fu-Zhen[2];Gong, Jian-Guo[2]

机构：[1]Univ Shanghai Sci & Technol, Sch Mech Engn, Shanghai 200093, Peoples R China;[2]East China Univ Sci & Technol, Sch Mech & Power Engn, Key Lab Pressure Syst & Safety, Shanghai 200237, Peoples R China;[3]Univ Shanghai Sci & Technol, Sch Energy & Power Engn, Shanghai 200093, Peoples R China

年份：2023

卷号：189

外文期刊名：THIN-WALLED STRUCTURES

收录：;EI(收录号：20232514271882);WOS:【SCI-EXPANDED(收录号:WOS:001028852200001)】；

基金：The authors gratefully acknowledge the supports from the National Natural Science Foundation of China (52175139), University of Shanghai for Science and Technology, China and East China University of Science and Technology during the course of this work.

语种：英文

外文关键词：Machine learning; Buckling design; Torispherical heads; Geometric imperfection; Primary features

摘要：A machine learning (ML) method is proposed for buckling design of internally pressurized torispherical heads, and geometric imperfection (GI) generated in the fabrication process is considered in the prediction of buckling pressure. Firstly, principal component analysis (PCA) is used to extract the primary features. Then, four fabrication methods are transformed from categorical variables into numerical features which could be considered as GI feature in ML models. Finally, random forest (RF) and support vector machines (SVM) are applied to predict buckling pressure of torispherical heads with different input features. Results demonstrate that the ML models have better predictive performance than traditional method. For RF and SVM, the models with primary and GI features predict the most accurate buckling pressure and SVM with a design factor of 1.25 is recommended in buckling design of torispherical heads.