PhD, Nuclear Engineering and Science, Rensselaer Polytechnic Institute, 2025
Through the deep integration of artificial intelligence and physics-based models, my research targets prediction, control, and multiphysics coupled-system simulation for fusion energy devices, advanced fission reactor systems, and cryogenic propellant storage systems for deep-space exploration, aiming to build efficient and interpretable intelligent solutions:
1. Neural network based tokamak plasma disruption prediction and mitigation
2. General neural operator frameworks for PDE solver acceleration
3. Physics-constrained multiphysics surrogate models with uncertainty quantification
4. Multiscale coupling simulation and real-time data assimilation for cryogenic storage systems in deep-space exploration missions
[1] Q. Cheng, M. H. Sahadath, H. Yang, S. Pan, and W. Ji, MD-PNOP: Equation-Recast Neural Operators for Minimal-Data Extrapolation and PDE Solver Acceleration, Journal of Computational Physics, 557, 114844 (2026).
[2] Q. Cheng, H. Yang, and W. Ji, An Adaptive Real-Time Forecasting Framework for Cryogenic Fluid Management in Space Systems, Aerospace Science and Technology, 173, 11851 (2026).
[3] Q. Cheng, M. H. Sahadath, H. Yang, S. Pan, and W. Ji, Surrogate Modeling of Heat Trans-
fer under Fluctuation Conditions using Fourier Basis-Deep Operator Network with Uncertainty Quantification, Progress in Nuclear Energy, 188, 105895 (2025).
[4] Q. Cheng, H. Yang, S. Shi, and W. Ji, A Data-Driven Based Concurrent Coupling Approach
for Cryogenic Propellant Tank Long-term Pressure Control Predictions, Cryogenics, 149, 104098 (2025).
[5] Q. Cheng, C. Clauser, E.d.D. Zapata-Cornejo, N. Ferraro, C. Rea, A Cross Machine and Parametric Neural Operator Surrogate Model for MHD Simulations, IAEA Workshop on Digital Engineering for Fusion Energy Research, Cambridge, MA, Dec. 9–12 (2025).
[6] Q. Cheng, C. Rea, C. Clauser, N. Ferraro, and R. Sweeney, Accelerating High-Fidelity Parametric Thermal Quench Simulations via Neural Operator Preconditioning for Disruption Mitigation in Tokamaks, Proc. 67th APS-DPP, Long Beach, CA, Nov. 17–21 (2025).