Yujun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yujun Li has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
Zhiyong Zhao
11 shared publications- Jianjun Jiang
School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, China
9 shared publications Junbiao Wang
9 shared publicationsHongshuai Wang
7 shared publicationsJunzhen Chen
School of Mechanical Engineering Northwestern Polytechnical University Xi'an People's Republic of China
7 shared publicationsChenyang Xie
6 shared publications
Latest Publications
- 22 October 2026
- Published by Wiley in Polymer Composites
Real‐Time Spatiotemporal Prediction of Flow‐Front Evolution in Vacuum‐Assisted Resin Infusion via ConvLSTM
Real‐time flow‐front tracking in vacuum‐assisted resin infusion (VARI) is critical for mitigating composite manufacturing defects. However, traditional numerical solvers suffer from prohibitive computational latency. This study presents a deep learning‐based spatiotemporal framework for faster‐than‐real‐time flow‐front prediction. Training datasets are generated via a parallelized control‐volume finite element method (CVFEM) integrated with Karhunen‐Loève (KL) expansions to capture stochastic preform permeability fields. A Convolutional Long Short‐Term Memory (ConvLSTM) network is developed to autoregressively predict two‐dimensional transient fluid advancement while strictly preserving spatial topologies. To evaluate industrial deployment, an in situ visual‐predictive closed loop is established by deploying a YOLOv11‐seg instance segmentation model on real manufacturing video feeds. Results demonstrate that the integrated network executes a 10‐step future spatiotemporal rollout within single‐digit millisecond computational latency, maintaining an Intersection over Union (IoU) of 95.33% at Step 10 on physical experimental data. This paradigm provides a robust data‐driven strategy for proactive quality control and online digital‐twin implementations in liquid composite molding.
- 22 October 2026
- Published by Wiley in Polymer Composites
Real‐Time Spatiotemporal Prediction of Flow‐Front Evolution in Vacuum‐Assisted Resin Infusion via ConvLSTM
Real‐time flow‐front tracking in vacuum‐assisted resin infusion (VARI) is critical for mitigating composite manufacturing defects. However, traditional numerical solvers suffer from prohibitive computational latency. This study presents a deep learning‐based spatiotemporal framework for faster‐than‐real‐time flow‐front prediction. Training datasets are generated via a parallelized control‐volume finite element method (CVFEM) integrated with Karhunen‐Loève (KL) expansions to capture stochastic preform permeability fields. A Convolutional Long Short‐Term Memory (ConvLSTM) network is developed to autoregressively predict two‐dimensional transient fluid advancement while strictly preserving spatial topologies. To evaluate industrial deployment, an in situ visual‐predictive closed loop is established by deploying a YOLOv11‐seg instance segmentation model on real manufacturing video feeds. Results demonstrate that the integrated network executes a 10‐step future spatiotemporal rollout within single‐digit millisecond computational latency, maintaining an Intersection over Union (IoU) of 95.33% at Step 10 on physical experimental data. This paradigm provides a robust data‐driven strategy for proactive quality control and online digital‐twin implementations in liquid composite molding.
- 1 October 2026
- Published by Elsevier in International Journal of Mechanical Sciences
- Vol. 330
Inverse identification of composite cure-induced deformation parameters
- 1 October 2026
- Published by Elsevier in International Journal of Mechanical Sciences
- Vol. 330
Inverse identification of composite cure-induced deformation parameters
- 25 July 2026
- Published by Elsevier in Composites Communications
- Vol. 66
Defect classification and residual tensile strength-based quality assessment of dry carbon fiber preforms
- 25 July 2026
- Published by Elsevier in Composites Communications
- Vol. 66
Defect classification and residual tensile strength-based quality assessment of dry carbon fiber preforms
- Open Access
- 8 June 2026
- Published by Elsevier in SSRN Electronic Journal
Inverse identification of composite cure-induced deformation parameters
Accurate prediction of cure-induced deformation in carbon fiber reinforced polymers is essential for the precision manufacturing of aerospace components. To reduce the difficulty of characterizing resin properties in the rubbery state and the heavy reliance on traditional experiments, this study proposes a hybrid inversion framework combining least squares optimization and Bayesian optimization to identify the equivalent properties of unidirectional composites efficiently. An improved micromechanical model is developed by introducing the thickness fraction of interlaminar resin-rich layers, enabling the distinction between transverse and through-thickness properties. Morris global sensitivity analysis shows that the through-thickness coefficients of chemical shrinkage and thermal expansion dominate the spring-back of L-shaped parts, whereas the transverse thermal expansion coefficient mainly controls flat laminate warpage. Accordingly, carbon fiber anisotropic properties are first identified using least-squares optimization, and resin-related process-equivalent properties are subsequently calibrated by Bayesian optimization using measured spring-back angles and warpage curvatures. The inverted parameters outperform directly measured values, limiting the maximum prediction errors to within 6% for flat laminates, 15% for L-shaped parts, and 12% for complex-curvature T-stringers. The proposed framework provides a mechanically interpretable and experimentally efficient route for parameter identification and deformation prediction in composite curing.
- 8 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessInverse identification of composite cure-induced deformation parameters
Accurate prediction of cure-induced deformation in carbon fiber reinforced polymers is essential for the precision manufacturing of aerospace components. To reduce the difficulty of characterizing resin properties in the rubbery state and the heavy reliance on traditional experiments, this study proposes a hybrid inversion framework combining least squares optimization and Bayesian optimization to identify the equivalent properties of unidirectional composites efficiently. An improved micromechanical model is developed by introducing the thickness fraction of interlaminar resin-rich layers, enabling the distinction between transverse and through-thickness properties. Morris global sensitivity analysis shows that the through-thickness coefficients of chemical shrinkage and thermal expansion dominate the spring-back of L-shaped parts, whereas the transverse thermal expansion coefficient mainly controls flat laminate warpage. Accordingly, carbon fiber anisotropic properties are first identified using least-squares optimization, and resin-related process-equivalent properties are subsequently calibrated by Bayesian optimization using measured spring-back angles and warpage curvatures. The inverted parameters outperform directly measured values, limiting the maximum prediction errors to within 6% for flat laminates, 15% for L-shaped parts, and 12% for complex-curvature T-stringers. The proposed framework provides a mechanically interpretable and experimentally efficient route for parameter identification and deformation prediction in composite curing.
- 19 May 2026
- Published by Elsevier in Composite Structures
- Vol. 390
Inverse identification of a two-stage eigenstrain model using macroscopic spring-back and warpage
- 19 May 2026
- Published by Elsevier in Composite Structures
- Vol. 390
Inverse identification of a two-stage eigenstrain model using macroscopic spring-back and warpage
- 15 December 2025
- Published by Elsevier in Composites Part A: Applied Science and Manufacturing
- Vol. 202
Modeling the impact of interlayer shifting on the local permeability of textile preforms
- 15 December 2025
- Published by Elsevier in Composites Part A: Applied Science and Manufacturing
- Vol. 202
Modeling the impact of interlayer shifting on the local permeability of textile preforms
- 21 July 2025
- Published by Elsevier in Composites Part B: Engineering
- Vol. 306
Enhanced energy dissipation in CFRP through strategically integrated nacreous and Bouligand microstructures
- 21 July 2025
- Published by Elsevier in Composites Part B: Engineering
- Vol. 306
Enhanced energy dissipation in CFRP through strategically integrated nacreous and Bouligand microstructures