Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | 125207 |
| Seitenumfang | 14 |
| Fachzeitschrift | Expert systems with applications |
| Jahrgang | 258 |
| Frühes Online-Datum | 25 Aug. 2024 |
| Publikationsstatus | Elektronisch veröffentlicht (E-Pub) - 25 Aug. 2024 |
Abstract
Reliability analysis is crucial for quantitatively evaluating structural safety amidst uncertainties, laying the foundation for reliability-based design optimization aimed at augmenting structural reliability and reducing economic expenditures, thereby offering substantial engineering benefits. However, performing reliability analysis on intricate structures, especially those requiring time-intensive finite element models, presents a formidable challenge. This study develops an innovative physics-informed neural network classification (PINNC) model to tackle this issue. In the PINNC model, the loss associated with the structural output state (i.e., safety or failed state) is defined as classification loss. Additionally, the structural output value (i.e., actual structural response) is treated as critical physical information, with its associated loss termed as physical loss. To facilitate a separate calculation of physical loss and classification loss, a parametric sigmoid activation function is used, establishing a link between the structural output value and the structural output state. The total loss is calculated as a weighted sum of both physical and classification losses. Unlike conventional neural network classification models that solely focus on classification loss, the PINNC model integrates both physical and classification losses, markedly improving the model's efficacy in structural reliability analysis. Moreover, an adaptive framework is developed to incrementally include samples proximal to the limit state surface as new training data, thereby reinforcing the PINNC model's computational precision. The effectiveness of the proposed PINNC framework in overcoming reliability analysis challenges is demonstrated through various applications.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Artificial intelligence
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Expert systems with applications, Jahrgang 258, 125207, 15.12.2024.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Physics-informed neural network classification framework for reliability analysis
AU - Shi, Yan
AU - Beer, Michael
N1 - Publisher Copyright: © 2024 The Author(s)
PY - 2024/8/25
Y1 - 2024/8/25
N2 - Reliability analysis is crucial for quantitatively evaluating structural safety amidst uncertainties, laying the foundation for reliability-based design optimization aimed at augmenting structural reliability and reducing economic expenditures, thereby offering substantial engineering benefits. However, performing reliability analysis on intricate structures, especially those requiring time-intensive finite element models, presents a formidable challenge. This study develops an innovative physics-informed neural network classification (PINNC) model to tackle this issue. In the PINNC model, the loss associated with the structural output state (i.e., safety or failed state) is defined as classification loss. Additionally, the structural output value (i.e., actual structural response) is treated as critical physical information, with its associated loss termed as physical loss. To facilitate a separate calculation of physical loss and classification loss, a parametric sigmoid activation function is used, establishing a link between the structural output value and the structural output state. The total loss is calculated as a weighted sum of both physical and classification losses. Unlike conventional neural network classification models that solely focus on classification loss, the PINNC model integrates both physical and classification losses, markedly improving the model's efficacy in structural reliability analysis. Moreover, an adaptive framework is developed to incrementally include samples proximal to the limit state surface as new training data, thereby reinforcing the PINNC model's computational precision. The effectiveness of the proposed PINNC framework in overcoming reliability analysis challenges is demonstrated through various applications.
AB - Reliability analysis is crucial for quantitatively evaluating structural safety amidst uncertainties, laying the foundation for reliability-based design optimization aimed at augmenting structural reliability and reducing economic expenditures, thereby offering substantial engineering benefits. However, performing reliability analysis on intricate structures, especially those requiring time-intensive finite element models, presents a formidable challenge. This study develops an innovative physics-informed neural network classification (PINNC) model to tackle this issue. In the PINNC model, the loss associated with the structural output state (i.e., safety or failed state) is defined as classification loss. Additionally, the structural output value (i.e., actual structural response) is treated as critical physical information, with its associated loss termed as physical loss. To facilitate a separate calculation of physical loss and classification loss, a parametric sigmoid activation function is used, establishing a link between the structural output value and the structural output state. The total loss is calculated as a weighted sum of both physical and classification losses. Unlike conventional neural network classification models that solely focus on classification loss, the PINNC model integrates both physical and classification losses, markedly improving the model's efficacy in structural reliability analysis. Moreover, an adaptive framework is developed to incrementally include samples proximal to the limit state surface as new training data, thereby reinforcing the PINNC model's computational precision. The effectiveness of the proposed PINNC framework in overcoming reliability analysis challenges is demonstrated through various applications.
KW - Adaptive framework
KW - Classification model
KW - Physics-informed neural network
KW - Reliability analysis
KW - Weighted loss function
UR - http://www.scopus.com/inward/record.url?scp=85202213751&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2024.125207
DO - 10.1016/j.eswa.2024.125207
M3 - Article
AN - SCOPUS:85202213751
VL - 258
JO - Expert systems with applications
JF - Expert systems with applications
SN - 0957-4174
M1 - 125207
ER -