Robust/Optimal Temperature Profile Control of a Re-Entry Vehicle Using Neural Networks
An approximate dynamic programming(ADP) based neurocontroller for the reentry temperature profile control of a space shuttle-type vehicle is synthesized in this study. Dynamics of heat transfer in a cooling fin for a vehicle re-entering the earth's atmosphere is represented by a nonlinear model, which accounts for conduction, convection and radiation at high temperatures. A one-dimensional distributed parameter model of the system is obtained from basic thermal physics principles. “Snap-shot” solutions of the dynamics are generated with a simple dynamic inversion based feedback controller. Empirical basis functions are designed using the “Proper Orthogonal Decomposition” technique(POD) and the snap-shot solutions. A low-order lumped parameter system to represent the infinite-dimensional system is obtained by carrying out a Galerkin projection. An ADP based suboptimal neurocontroller with a dual heuristic programming(DHP) formulation is obtained with a single-network- adaptive-critic(SNAC) controller for this approximate nonlinear model. Feedback control in the original domain can be obtained with the same POD basis functions. Further contribution of this paper includes the development of a robust controller to account for unmodeled dynamics and parametric uncertainties inherent in such a complex problem. An online neural network is developed for this purpose. A weight update rule that guarantees boundedness of the weights and relaxes the need for persistence of excitation (PE) condition is presented. Simulation studies show that in a fairly extensive but compact domain, any desired temperature profile can be achieved starting from any initial temperature profile and the controller is robust to different types of uncertainties. Since, the ADP and neural network based controllers are of fairly general structure, they appear to have the potential to be controller synthesis tools for nonlinear distributed parameter systems.
V. Yadav et al., "Robust/Optimal Temperature Profile Control of a Re-Entry Vehicle Using Neural Networks," Collection of Technical Papers - 2006 Atmospheric Flight Mechanics Conference, American Institute of Aeronautics and Astronautics (AIAA), Jan 2006.
The definitive version is available at https://doi.org/10.2514/6.2006-6141
Collection of Technical Papers - 2006 Atmospheric Flight Mechanics Conference (2006, Keystone, CO)
Mechanical and Aerospace Engineering
Article - Conference proceedings
© 2006 American Institute of Aeronautics and Astronautics (AIAA), All rights reserved.