Dr. Nan DENG
Dr. Nan DENG
Embedded Files
Assistant Professor | Supervisor of Master's Candidates
School of Mechanical Engineering & Automation
Harbin Institute of Technology (Shenzhen)
Room 0911 of Block G, University Town, Xili, 518055, Shenzhen, China
dengnan@hit.edu.cn | nan.deng@ensta-paris.fr
Homepage: http://faculty.hitsz.edu.cn/dengnan
I received my Ph.D. in Fluid Mechanics from Institut Polytechnique de Paris (IP Paris) in January 2022. Immediately after, I joined the chair “AI and Aerodynamics” led by National Talent Prof. Dr. Bernd Rainer Noack as a postdoctoral fellow at Harbin Institute of Technology (Shenzhen), China.
I target an academic career focusing on automated reduced-order modeling (surrogate models) for digital twins, using flow data, machine learning, and first principles. The models will be employed for understanding, optimization, estimation, and control. The starting point is mean-field modeling, sparse identification, Galerkin force modeling, and cluster-based network modeling, which have been successfully applied to the benchmark configuration, “Fluidic Pinball.”
We tap the great potential of ROM synergizing machine learning techniques and first principles to meet the control and optimization requirements in complex industrial environments, addressing challenges of multi-scale and multi-frequency tasks.
Research interests:
Reduced-order modeling of complex systems using machine learning and first principles
Dimensionality reduction, feature extraction, and nonlinear modeling
Fluid dynamics, flow instabilities, and bifurcation theory
Join us!
We are looking for candidates in flow dynamics, nonlinear dynamics, CFD, machine learning, data science, and flow control. We also
Master students in Power Engineering and Engineering Thermophysics (General or CSC Program @ HIT Shenzhen)
PhD students in Power Engineering and Engineering Thermophysics (General or CSC Program @ HIT Shenzhen)
Postdoctoral researchers
The comprehensive annual income of post-doctoral fellows is no less than 300,000 RMB (Shenzhen Post-doctoral fellows' bonus included) before tax for the first two years.
[Qualifications may include the following:
- Ph.D. in Mechanics, Mathematics, Computer Science, or related area. Experience with dynamical modeling, data analysis, and AI is highly desirable.
- Doctoral degree obtained within 3 years, and under the age of 35. This condition can guarantee a tax-free bonus from the Shenzhen Municipal government in the amount of 180,000 RMB per year for two years.
- A proven track record in the form of publications in international English language journals, and the ability to communicate in written and spoken English]
2024. 01 - Now Assistant Professor @ Harbin Institute of Technology (Shenzhen), China.
Supervisor of Master Program in Major "Power Engineering and Engineering Thermophysics".
2022. 01 - 2024.01 Postdoctoral Fellow @ Harbin Institute of Technology (Shenzhen), China.
Supervisor: National Talent Prof. Dr. Bernd Rainer Noack.
2018. 10 - 2021.10 Doctoral studies in Fluid Mechanics @ ENSTA-Paris, Institut Polytechnique de Paris, France
Thesis: Deep mean-field modeling for successive bifurcations exemplified for the fluidic pinball
Supervisors: Prof. Dr. Luc Rémi Pastur and Prof. Dr. Bernd Rainer Noack.
Lab1: UME/DFA, IMSIA - Institut des Sciences de la Mécanique et Applications Industrielles, ENSTA-Paris IP Paris.
Lab2: AERO, LISN - Laboratoire Interdisciplinaire des Sciences du Numérique, CNRS.
2016. 09 - 2018.09 Master studies in Fluid Mechanics @ University of Paris-Saclay, France
Master of Science: Fluid Dynamics and Energetics
Lab: AERO, LISN - Laboratoire Interdisciplinaire des Sciences du Numérique, CNRS.
2015. 09 - 2016.08 Bachelor studies in Physics @ University of Paris-Sud, France
Bachelor of Science: Physics and Applications
2012. 09 - 2015.08 Bachelor studies in Engineering @ Huazhong University of Science and Technology, China
Bachelor of Engineering: Optoelectronic Information Engineering
Reduced-order modelling and system identification can help us figure out the elementary degrees of freedom and the underlying mechanisms from the high-dimensional and nonlinear dynamics of fluid flow. Machine learning has brought new opportunities to these two processes and is revolutionising traditional methods. We focus on building a general framework to obtain a sparse human-interpretable model from complex high-dimensional data using machine learning and first principles.
Google Sites
Report abuse