共 45 条
A general active-learning method for surrogate-based structural reliability analysis
被引:5
作者:
Zha, Congyi
[1
]
Sun, Zhili
[1
]
Wang, Jian
[1
]
Pan, Chenrong
[2
]
Liu, Zhendong
[1
]
Dong, Pengfei
[1
]
机构:
[1] Northeastern Univ, Sch Mech Engn & Automat, Wenhua Rd, Shenyang 110819, Liaoning, Peoples R China
[2] Anhui Xinhua Univ, Dept Gen Educ, 555 Wangjiang West Rd, Hefei 230088, Anhui, Peoples R China
基金:
中国国家自然科学基金;
关键词:
active-learning method;
reliability analysis;
structural reliability;
surrogate model;
RESPONSE-SURFACE METHOD;
RADIAL BASIS FUNCTION;
DESIGN OPTIMIZATION;
EFFICIENT;
STRATEGY;
MODEL;
D O I:
10.12989/sem.2022.83.2.167
中图分类号:
TU [建筑科学];
学科分类号:
0813 ;
摘要:
Surrogate models aim to approximate the performance function with an active-learning design of experiments (DoE) to obtain a sufficiently accurate prediction of the performance function???s sign for an inexpensive computational demand in reliability analysis. Nevertheless, many existing active-learning methods are limited to the Kriging model, while the uncertainties of the Kriging itself affect the reliability analysis results. Moreover, the existing general active-learning methods may not achieve a fully satisfactory balance between accuracy and efficiency. Therefore, a novel active-learning method GLM-CM is constructed to yield the issues, which conciliates several merits of existing methods. To demonstrate the performance of the proposed method, four examples, concerning both mathematical and engineering problems, were selected. By benchmarking obtained results with literature findings, various surrogate models combined with the proposed method not only provide an accurate reliability evaluation while highly alleviating the computational burden, but also provides a satisfactory balance between accuracy and efficiency compared to the other reliability methods.
引用
收藏
页码:167 / 178
页数:12
相关论文