Hewenxuan Li
Assistant Professor
Rochester Institute of Technology
Rochester, NY, USA
I am glad you are here! I am an Assistant Professor at Rochester Institute of Technology. My research interests center on data-centric modeling, intelligent perception, control, and health-aware design of aerospace, mechanical, and biological systems, structural health monitoring.
Read More ▼
I received my Ph.D. in Mechanical Engineering and Applied Mechanics from the University of Rhode Island in 2022. I worked in the Nonlinear Dynamics Laboratory, focusing on developing data-driven modal analysis and damage tracking/prediction algorithms for mechanical systems. After graduation, I joined the Laboratory for Intelligent Systems and Controls as a postdoctoral associate at Cornell University, developing digital twin models for hawkmoths perception and control; meanwhile, developing deep generative models for underwater localization and mapping. I am a recipient of the Best Paper Award of ASME IDETC/CIE 2019.
My current research interests mainly focus on unsupervised data-driven modeling and control of nonlinear systems; intelligent health monitoring and prognosis algorithms; anomaly-aware system design and control; and intelligent sensing, perception, and control for biomimicry flights. I am hiring highly-motivated PhD students to join my research journey.
Research Interests
Biomimicry Modeling and Control
Developing data-driven approaches for modeling, monitoring, and control of nonlinear systems. This includes dynamic modeling, perception, and control of biomimicry and underwater systems, as well as physics-based data-driven models for system behavior prediction.
Structural Health Monitoring
Focusing on damage monitoring, prognosis, and anti-damage design for nonlinear systems. This includes fatigue damage estimation under variable amplitude loading, data-driven damage identification and tracking frameworks, and full-field modal analysis methods for structural analysis and damage detection.
AI/ML for System Resilience
Applying deep learning and machine learning techniques for design, monitoring, and control of mechanical systems. This includes developing deep generative models, neural networks for material constitutive relations, and simultaneous classification, localization, and mapping algorithms.
Selected Publications
Variable-scale spectral feature gram (VSFgram): A convergence property-driven autonomous periodic transients extraction approach
IEEE Transactions on Instrumentation and Measurement, 2025
* indicates equal contribution or corresponding author
News
I am looking for highly-motivated PhD students to join my research group at Rochester Institute of Technology, starting from Fall 2026.
Openings
PhD Student Position ▼
I am currently hiring a PhD student to join my research group at Rochester Institute of Technology. The successful candidate will work on exciting research projects in data-centric modeling, intelligent perception and control, structural health monitoring, and system health-aware design.
Interested candidates should:
- Have a strong background in mechanical engineering, aerospace engineering, or related fields
- Demonstrate interest in data-driven methods, machine learning, and/or system dynamics
- Possess excellent analytical and problem-solving skills
- Highly self-motivated to conduct high-quality research
If you are interested in this position, please email me at hewenxuanli [at] hotmail [dot] com with your CV, transcripts, and a brief statement of research interests.
Contact
Email: hewenxuanli [at] hotmail [dot] com