Efficient Global Sensitivity Analysis of Model-Based Ultrasonic Nondestructive Testing Systems Using Machine Learning and Sobol’ Indices
Efficient Global Sensitivity Analysis of Model-Based Ultrasonic Nondestructive Testing Systems Using Machine Learning and Sobol’ Indices
复制标题
使用机器学习和 Sobol™ 指数对基于模型的超声无损检测系统进行高效的全局灵敏度分析
DOI:
10.1115/1.4051100
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Leifsson, Leifur
中科院分区:
文献类型:
--
作者:
Nagawkar, Jethro;Leifsson, Leifur
The objective of this work is to reduce the cost of performing model-based sensitivity analysis for ultrasonic nondestructive testing systems by replacing the accurate physics-based model with machine learning (ML) algorithms and quickly compute Sobol’ indices. The ML algorithms considered in this work are neural networks (NNs), convolutional NN (CNNs), and deep Gaussian processes (DGPs). The performance of these algorithms is measured by the root mean-squared error on a fixed number of testing points and by the number of high-fidelity samples required to reach a target accuracy. The algorithms are compared on three ultrasonic testing benchmark cases with three uncertainty parameters, namely, spherically void defect under a focused and a planar transducer and spherical-inclusion defect under a focused transducer. The results show that NNs required 35, 100, and 35 samples for the three cases, respectively. CNNs required 35, 100, and 56, respectively, while DGPs required 84, 84, and 56, respectively.
登录
查看更多内容
影响因子:
0.6
作者:
R. Miorelli;X. Artusi;A. B. Abdessalem;C. Reboud
通讯作者:
C. Reboud
DOI:
10.1007/bf03185104
发表时间:
2001
期刊:
KSME International Journal
影响因子:
--
作者:
Y. Nam
通讯作者:
Y. Nam
DOI:
10.1016/j.proeng.2014.11.059
发表时间:
2014
期刊:
Procedia Engineering
影响因子:
--
作者:
S. Subair;K. Balasubramaniam;P. Rajagopal;Anish Kumar;B. Rao;T. Jayakumar
通讯作者:
T. Jayakumar
影响因子:
0.6
作者:
K. Adamus;P. Lacki
通讯作者:
P. Lacki
影响因子:
2.1
作者:
S. Bilicz;E. Vázquez;S. Gyimóthy;J. Pávó;M. Lambert
通讯作者:
M. Lambert