A Neural Envelope Method for Rapid Gradient-based Optimum Takeoff Trajectory Design
Organizations: Missouri University of Science and Technology, Rolla, MO 65409, USA
Abstract
Urban air mobility arises to mitigate ground traffic congestion. Multidisciplinary analysis and optimization (MDAO) has been introduced to reduce the energy consumption, thereby expanding aircraft performance. Surrogate-based MDAO lowers the cost of optimization, but multimodality disrupts global optimum search for both simulation-based and surrogate-based optimizations. Convex envelopes convert multimodal spaces into unimodal spaces, permitting efficient convex optimization; however, convexifying a design space may produce infeasible "optimal" designs due to complex design constraints. To address these challenges, this work proposes the coupling of a physics-constrained generative adversarial networks (physicsGAN) and neural envelope to transform original, constrained, non-convex optimizations into unconstrained, convex optimizations. Specifically, the physicsGAN discovers a feasible design space where all design candidates inherently satisfy all constraints, by penalizing surrogate-predicted constraint violations during training. Moreover, the neural envelope constructs a neural network-based convex envelope for the transformed objective function within the physicsGAN-discovered feasible space. Note that the neural envelope only needs to deal with objective function since constraints are inherently satisfied in the feasible space. The neural envelope is demonstrated on takeoff trajectory optimizations of the Airbus A3 Vahana eVTOL aircraft. Results show that neural envelopes achieve a 99.91% mean accuracy within a flight-condition space compared with reference convex envelopes. Neural-envelope-enabled optimizations achieve 99.84% accuracy on the global optimum design, costing only 0.04 seconds on average. The neural envelope accelerates the trajectory optimization by 53 and 162 times on average compared to the physicsGAN-enabled gradient-based and global optimizations, respectively.
Figures & tables
| Function/Variable | Description | Quantity | |
|---|---|---|---|
| minimize | E | Electrical energy | |
| with respect to | x , , or z | B-spline control points, twinGAN variables, or physicsGAN variables | 40, 3, or 3 |
| Total takeoff time | 1, 1, or N/A | ||
| Total design variables | 41 , 4 , or 3 | ||
| subject to | g | Acceleration constraint | 1 |
| Total constraint functions | 1 |
| Model | Latent Variables | Coverage Percentage | Power Fitting Accuracy | Wing Angle Fitting Accuracy |
|---|---|---|---|---|
| physicsGAN | 2 | 99.20% | 99.51% | 99.61% |
| Model | Envelope MAPRA | Global Minimum Energy MAPRA | Global Minimum Location NRMSE |
| Neural Envelope | 99.91% | 99.84% | 0.018567 |
| Model | DE Duration (s) | SLSQP Duration (s) | L-BFGS-B Duration (s) |
|---|---|---|---|
| physicsGAN | 6.321 | 0.177 | 0.103 |
| Neural Envelope | 2.815 | 0.071 | 0.039 |
Trajectory Optimization
Trajectory optimization computes motion or control sequences that minimize costs while satisfying system dynamics, safety limits, and task constraints.
See all 223 papers