📚 Scholarship & Publications
🔗 Google Scholar
Welcome to visit my Google Scholar profile by clicking here.
📄 Inverse Design of Mechanical Metamaterials Balancing Manufacturability and Compactness: A Case Study on Lattice Cells
Online: July 25, 2025
Journal: Extreme Mechanics Letters
This study addresses the challenge of balancing manufacturability and compactness in mechanical metamaterial design. We implemented a regressional and conditional generative adversarial network based multi-objective (RCGAN-MO) architecture that enables inverse design while dynamically optimizing trade-offs between competing performance metrics. The approach includes neural networks for generation and prediction, combined with a weighted multi-objective optimizer. Applied to lattice cell design, the method achieved high accuracy in targeting specific compressive elastic modulus values while allowing flexible adjustment of manufacturability and compactness priorities through 3D printed prototypes.
Citation:
Xue J., Bao H., Liu T., Wu L., Tian X., Li D. Inverse Design of Mechanical Metamaterials Balancing Manufacturability and Compactness: A Case Study on Lattice Cells. Extreme Mechanics Letters 2025. doi: 10.1016/j.cjmeam.2025.200061.
My Contribution:
Primary Researcher and Lead Author - Conducted all aspects of this research including algorithm development, experimental design, data analysis, and manuscript preparation.
📄 Machine Learning-Based Online Monitoring and Closed-Loop Controlling for 3D Printing of Continuous Fiber-Reinforced Composites
Published: March 18, 2025
Journal: Additive Manufacturing Frontiers
This study addresses the challenge of ensuring consistent mechanical performance in 3D-printed continuous fiber-reinforced composites by developing a process monitoring and closed-loop feedback control strategy. A neural network with 94.70% accuracy enabled real-time flow rate recognition and control, significantly improving surface quality and mechanical properties—up to 3–6× enhancement in tensile strength and elastic modulus. This strategy supports remote and unmanned printing in extreme environments.
Citation:
Chi X.†, Xue J.†, Jia L., et al. Machine Learning-Based Online Monitoring and Closed-Loop Controlling for 3D Printing of Continuous Fiber-Reinforced Composites. Additive Manufacturing Frontiers 2025; 4:200196. doi: 10.1016/j.amf.2025.200196. †Co-first authors.
My Contribution:
Hardware and Software Engineering, Literature Writing
📄 3D-Printed Metamaterials with Versatile Functionalities
Published: September 22, 2023
Journal: Additive Manufacturing Frontiers
This review explores how 3D printing enables the fabrication of complex, multifunctional metamaterials with novel properties across electromagnetic, thermal, acoustic, and mechanical domains. It highlights the interdependence between structure, function, and the manufacturing process, showcasing how additive manufacturing fuels innovation in metamaterial design.
Citation:
Wu L., Xue J., Tian X., et al. 3D-Printed Metamaterials with Versatile Functionalities. Additive Manufacturing Frontiers 2023; 2:100091. doi: 10.1016/j.cjmeam.2023.100091.
My Contribution:
Literature Search and Writing
📄 Mechanical Metamaterials for Handwritten Digits Recognition
Published: December 25, 2023
Journal: Advanced Science
This paper presents a non-electrical mechanical neural network based on bistable kirigami-inspired metamaterials. It functions reliably in low-temperature, electricity-free environments, performing handwritten digit recognition. This innovation demonstrates the potential for mechanically driven computing as a complement to traditional electronic systems.
Citation:
Wu L., Lu Y., Li P., Wang Y., Xue J., et al. Mechanical Metamaterials for Handwritten Digits Recognition. Advanced Science 2024; 11:2308137. doi: 10.1002/advs.202308137.
My Contribution:
Machine Learning Development
📄 Genetic Algorithm-Enabled Mechanical Metamaterials for Vibration Isolation with Different Payloads
Published: November 23, 2024
Journal: Journal of Materiomics
This study introduces machine learning to design quasi-zero stiffness metamaterials with adaptable payloads, manufactured using multi-material 3D printing. They effectively isolate low-frequency vibrations across varying payloads and application scenarios, opening new avenues for smart mechanical energy shielding.
Recommended citation:
Song X., Yan S., Wang Y., Zhang H., Xue J., et al. Genetic Algorithm-Enabled Mechanical Metamaterials for Vibration Isolation with Different Payloads. Journal of Materiomics 2025; 11:100944. doi: 10.1016/j.jmat.2024.100944.
My Contribution:
Hardware Development
Feel free to reach out for collaboration or full-text requests!