Xiangyun Long
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiangyun Long has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Chao Jiang
8 shared publicationsWei Xiong
4 shared publications- Chao Jiang
State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, College of Mechanical and Vehicle Engineering, Hunan University, Changsha, China
2 shared publications Jinkang Liu
College of Mechanical and Vehicle Engineering, Hunan University, Changsha City, People’s Republic of China
2 shared publicationsJinwu Li
2 shared publicationsStéphane P.A. Bordas
2 shared publications
Latest Publications
- 12 September 2026
- Published by Elsevier in Computers & Structures
- Vol. 332
The deep operator finite element method: A discrete variational neural operator for elasticity under variable loading
- 12 September 2026
- Published by Elsevier in Computers & Structures
- Vol. 332
The deep operator finite element method: A discrete variational neural operator for elasticity under variable loading
- Open Access
- 1 July 2026
- Published by KEAI Publishing in Chinese Journal of Mechanical Engineering
Multi-Scale Displacement Network: A Deep Learning Framework for Automatic Displacement Field Measurement
- 1 July 2026
- Published by KEAI Publishing in Chinese Journal of Mechanical Engineering
Open AccessMulti-Scale Displacement Network: A Deep Learning Framework for Automatic Displacement Field Measurement
- 17 March 2026
- Published by Springer Nature in Structural and Multidisciplinary Optimization
- Vol. 69 (4) , 81
A deep convolutional framework for unpaired multi-fidelity fusion through structured panel encoding
- 17 March 2026
- Published by Springer Nature in Structural and Multidisciplinary Optimization
- Vol. 69 (4) , 81
A deep convolutional framework for unpaired multi-fidelity fusion through structured panel encoding
- Top Cited Papers
- 28 February 2026
- Published by Elsevier in Engineering Fracture Mechanics
- Vol. 337
Physics-informed neural networks for inverse length scale identification and forward phase-field fracture modeling
- 28 February 2026
- Published by Elsevier in Engineering Fracture Mechanics
- Vol. 337
Top Cited PapersPhysics-informed neural networks for inverse length scale identification and forward phase-field fracture modeling
- Open Access
- 9 February 2026
- Published by Elsevier in SSRN Electronic Journal
The Deep Operator Finite Element Method: A Stable and Efficient Neural Operator for Elasticity Problems with Variable Loading
Learning solution operators for parametric partial differential equations is crucial for many-query engineering tasks. However, existing neural operators, especially physics-informed variants, are often plagued by training instability and efficiency. To address this challenge, this paper introduces a novel deep operator finite element method (DOFEM) for stable training and real-time prediction of elasticity problems with variable loading. The DOFEM uniquely integrates the DeepONet architecture with a variational energy functional constructed directly from the finite element stiffness matrix. This design allows its physics-informed loss function to circumvent high-order derivative computations and numerical integration errors, ensuring exceptional training stability. Numerical examples demonstrate that the DOFEM significantly outperforms the energy-based Physics-Informed DeepONet in both stability and accuracy, remaining robust in three-dimensional problems where the latter fails to converge. Furthermore, the model exhibits strong generalization to unseen loads and provides smoother, physically regularized solutions for singular loads compared to the standard finite element method. DOFEM thus presents an efficient and reliable paradigm for the rapid analysis of complex engineering systems under diverse operating conditions.
- 9 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessThe Deep Operator Finite Element Method: A Stable and Efficient Neural Operator for Elasticity Problems with Variable Loading
Learning solution operators for parametric partial differential equations is crucial for many-query engineering tasks. However, existing neural operators, especially physics-informed variants, are often plagued by training instability and efficiency. To address this challenge, this paper introduces a novel deep operator finite element method (DOFEM) for stable training and real-time prediction of elasticity problems with variable loading. The DOFEM uniquely integrates the DeepONet architecture with a variational energy functional constructed directly from the finite element stiffness matrix. This design allows its physics-informed loss function to circumvent high-order derivative computations and numerical integration errors, ensuring exceptional training stability. Numerical examples demonstrate that the DOFEM significantly outperforms the energy-based Physics-Informed DeepONet in both stability and accuracy, remaining robust in three-dimensional problems where the latter fails to converge. Furthermore, the model exhibits strong generalization to unseen loads and provides smoother, physically regularized solutions for singular loads compared to the standard finite element method. DOFEM thus presents an efficient and reliable paradigm for the rapid analysis of complex engineering systems under diverse operating conditions.
- 16 October 2025
- Published by Elsevier in Engineering Failure Analysis
- Vol. 183
A multiaxial fatigue life prediction framework for additively manufactured K418B nickel-based superalloy used in turbine blisks
- 16 October 2025
- Published by Elsevier in Engineering Failure Analysis
- Vol. 183
A multiaxial fatigue life prediction framework for additively manufactured K418B nickel-based superalloy used in turbine blisks
- Top Cited Papers
- 24 December 2024
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 436
The deep finite element method: A deep learning framework integrating the physics-informed neural networks with the finite element method
- 24 December 2024
- Published by Elsevier in Computer Methods in Applied Mechanics and Engineering
- Vol. 436
Top Cited PapersThe deep finite element method: A deep learning framework integrating the physics-informed neural networks with the finite element method
- 23 October 2024
- Published by Elsevier in International Journal of Fatigue
- Vol. 190
MT-CrackNet:A multi-task deep learning framework for automatic in-situ fatigue micro-crack detection and quantification
- 23 October 2024
- Published by Elsevier in International Journal of Fatigue
- Vol. 190
MT-CrackNet:A multi-task deep learning framework for automatic in-situ fatigue micro-crack detection and quantification
- 5 June 2024
- Published by Elsevier in Composite Structures
- Vol. 342, 118260
Energy absorption characteristics of modular assembly structures under quasi-static compression load
- 5 June 2024
- Published by Elsevier in Composite Structures
- Vol. 342, 118260
Energy absorption characteristics of modular assembly structures under quasi-static compression load
- 15 September 2023
- Published by Morressier GmbH
An intelligent crack damage assessment method by integrating information and physics
- 15 September 2023
- Published by Morressier GmbH
An intelligent crack damage assessment method by integrating information and physics