Xin Liu
Research Subjects
Xin Liu has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
Wenbin Yu
Purdue University
18 shared publicationsFederico Gasco
5 shared publicationsFei Tao
5 shared publicationsBangde Liu
University of Texas at Arlington
4 shared publicationsSu Tian
AnalySwift LLC
4 shared publications- Wenbin Yu
Purdue University West Lafayette
4 shared publications
Latest Publications
- 1 November 2026
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 64 (11) , 6729-6738
Structural Analysis of Tow-Steered Composites Using Transfer Learning
Tow-steered composites offer enhanced structural performance by enabling the design of curvilinear fiber paths, making them highly attractive for aerospace applications. However, their widespread adoption is hindered by the high computational cost of exploring the large design space using traditional finite element analysis (FEA). While efficient surrogate models, such as neural network (NN) models, provide a promising alternative, training them typically requires extensive high-fidelity FEA data, which remain computationally intensive. To address this challenge, we propose a transfer learning (TL) framework that leverages sufficient low-fidelity data from coarse-mesh models and a limited set of high-fidelity data from fine-mesh models to train an NN model. Three case studies of tow-steered composite structures with different numbers of design variables are performed. The results show that TL can achieve accuracy comparable to that of conventional NN models trained using high-fidelity data while substantially reducing computational costs. Additionally, key factors affecting TL are systematically investigated, including the quality of low-fidelity data, the mixed ratio of the low- to high-fidelity data, and the architecture of the TL model. The results provide valuable insights and practical guidelines for applying TL to develop efficient NN models for structural analysis.
- 1 November 2026
- Published by American Institute of Aeronautics and Astronautics (AIAA) in AIAA Journal
- Vol. 64 (11) , 6729-6738
Structural Analysis of Tow-Steered Composites Using Transfer Learning
Tow-steered composites offer enhanced structural performance by enabling the design of curvilinear fiber paths, making them highly attractive for aerospace applications. However, their widespread adoption is hindered by the high computational cost of exploring the large design space using traditional finite element analysis (FEA). While efficient surrogate models, such as neural network (NN) models, provide a promising alternative, training them typically requires extensive high-fidelity FEA data, which remain computationally intensive. To address this challenge, we propose a transfer learning (TL) framework that leverages sufficient low-fidelity data from coarse-mesh models and a limited set of high-fidelity data from fine-mesh models to train an NN model. Three case studies of tow-steered composite structures with different numbers of design variables are performed. The results show that TL can achieve accuracy comparable to that of conventional NN models trained using high-fidelity data while substantially reducing computational costs. Additionally, key factors affecting TL are systematically investigated, including the quality of low-fidelity data, the mixed ratio of the low- to high-fidelity data, and the architecture of the TL model. The results provide valuable insights and practical guidelines for applying TL to develop efficient NN models for structural analysis.
- 17 September 2026
- Published by Elsevier in Thin-Walled Structures
- Vol. 232
A modularized neural network model for multiscale plate analysis of composite sandwich structures with metamaterial cores
- 17 September 2026
- Published by Elsevier in Thin-Walled Structures
- Vol. 232
A modularized neural network model for multiscale plate analysis of composite sandwich structures with metamaterial cores
- 13 September 2025
- Published by Elsevier in Composite Structures
- Vol. 373
Neural network-assisted design optimization with adaptive sampling for tow-steered composite structures
- 13 September 2025
- Published by Elsevier in Composite Structures
- Vol. 373
Neural network-assisted design optimization with adaptive sampling for tow-steered composite structures
- 5 August 2025
- Published by Elsevier in Advances in Engineering Software
- Vol. 209
Design tool for tow-steered composite laminates in Abaqus and MSC.Patran/Nastran
- 5 August 2025
- Published by Elsevier in Advances in Engineering Software
- Vol. 209
Design tool for tow-steered composite laminates in Abaqus and MSC.Patran/Nastran
- 14 January 2025
- Published by Elsevier in Composite Structures
- Vol. 355
Design and analysis of reinforced I-beam body-centered cubic lattices for enhanced energy absorption
- 14 January 2025
- Published by Elsevier in Composite Structures
- Vol. 355
Design and analysis of reinforced I-beam body-centered cubic lattices for enhanced energy absorption
- 28 April 2023
- Published by Elsevier in Mechanics of Materials
- Vol. 182
Improving stiffness and strength of body-centered cubic lattices with an I-shape beam cross-section
- 28 April 2023
- Published by Elsevier in Mechanics of Materials
- Vol. 182
Improving stiffness and strength of body-centered cubic lattices with an I-shape beam cross-section
- 10 May 2022
- Published by Elsevier in Composites Part B: Engineering
- Vol. 239
Discover failure criteria of composites from experimental data by sparse regression
- 10 May 2022
- Published by Elsevier in Composites Part B: Engineering
- Vol. 239
Discover failure criteria of composites from experimental data by sparse regression