Estimation of an improved surrogate model in uncertainty quantification by neural networks

被引：0
作者：
Benedict Götz
Sebastian Kersting
Michael Kohler
机构：
[1] Technische Universität Darmstadt,Fachgebiet Systemzuverlässigkeit, Adaptronik und Maschinenakustik SAM
[2] Technische Universität Darmstadt,Fachbereich Mathematik
来源：
Annals of the Institute of Statistical Mathematics | 2021年 / 73卷
关键词：
Curse of dimensionality; Density estimation; Imperfect models; error; Neural networks; Surrogate models; Uncertainty quantification;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Quantification of uncertainty of a technical system is often based on a surrogate model of a corresponding simulation model. In any application, the simulation model will not describe the reality perfectly, and consequently the surrogate model will be imperfect. In this article, we combine observed data from the technical system with simulated data from the imperfect simulation model in order to estimate an improved surrogate model consisting of multilayer feedforward neural networks, and we show that under suitable assumptions, this estimate is able to circumvent the curse of dimensionality. Based on this improved surrogate model, we show a rate of the convergence result for density estimates. The finite sample size performance of the estimates is illustrated by applying them to simulated data. The practical usefulness of the newly proposed estimates is demonstrated by using them to predict the uncertainty of a lateral vibration attenuation system with piezo-elastic supports.
引用
收藏
页码：249 / 281
页数：32
相关论文
共 50 条
[21]   Uncertainty Quantification for Neutron Shield Using Convolutional Neural Networks [J].
Zamora, J. C. ;
Bollen, G. ;
Ginter, T. ;
Chowdhury, R. Pal .
NUCLEAR TECHNOLOGY, 2025,
[22]   Surrogate neural network model for sensitivity analysis and uncertainty quantification of the mechanical behavior in the optical lens-barrel assembly [J].
Shahane, Shantanu ;
Guleryuz, Erman ;
Abueidda, Diab W. ;
Lee, Allen ;
Liu, Joe ;
Yu, Xin ;
Chiu, Raymond ;
Koric, Seid ;
Aluru, Narayana R. ;
Ferreira, Placid M. .
COMPUTERS & STRUCTURES, 2022, 270
[23]   Robust deep neural network surrogate models with uncertainty quantification via adversarial training [J].
Zhang, Lixiang ;
Li, Jia .
STATISTICAL ANALYSIS AND DATA MINING, 2023, 16 (03) :295-304
[24]   Neural SDE-Based Epistemic Uncertainty Quantification in Deep Neural Networks [J].
Tharzeen, Aabila ;
Dahale, Shweta ;
Natarajan, Balasubramaniam .
ENGINEERING APPLICATIONS OF NEURAL NETWORKS, EANN 2024, 2024, 2141 :247-258
[25]   Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification [J].
Zhu, Yinhao ;
Zabaras, Nicholas .
JOURNAL OF COMPUTATIONAL PHYSICS, 2018, 366 :415-447
[26]   Uncertainty Quantification of a Flapping Airfoil with a Stochastic Velocity Deviation Based on a Surrogate Model [J].
Zhao, Liangyu ;
Zhang, Xiaqing .
ADVANCED MANUFACTURING SYSTEMS, PTS 1-3, 2011, 201-203 :1209-+
[27]   FAST AND FLEXIBLE UNCERTAINTY QUANTIFICATION THROUGH A DATA-DRIVEN SURROGATE MODEL [J].
Dietrich, Felix ;
Kuenzner, Florian ;
Neckel, Tobias ;
Koester, Gerta ;
Bungartz, Hans-Joachim .
INTERNATIONAL JOURNAL FOR UNCERTAINTY QUANTIFICATION, 2018, 8 (02) :175-192
[28]   Framework for Robust Optimization Combining Surrogate Model, Memetic Algorithm, and Uncertainty Quantification [J].
Palar, Pramudita Satria ;
Dwianto, Yohanes Bimo ;
Zuhal, Lavi Rizki ;
Tsuchiya, Takeshi .
ADVANCES IN SWARM INTELLIGENCE, ICSI 2016, PT I, 2016, 9712 :48-55
[29]   Filtering and improved Uncertainty Quantification in the dynamic estimation of effective reproduction numbers [J].
Capistran, Marcos A. ;
Capella, Antonio ;
Christen, J. Andres .
EPIDEMICS, 2022, 40
[30]   Integrating Dropout and Kullback-Leibler Regularization in Bayesian Neural Networks for improved uncertainty estimation in Regression [J].
Devadas, Raghavendra M. ;
Hiremani, Vani .
METHODSX, 2024, 12
12345