Constraint-Based Wing Planform Sizing of a Fixed-Wing UAV Using an AVL–ANN Surrogate and Artificial Bee Colony Optimization

This project looks at how to size the wing of a fixed‑wing unmanned aerial vehicle (UAV) using a constraint‑based optimization process. The design is described by two main geometric variables: span (b) and chord (c). First, the method screens possible designs with a series of physical limits: – stall limit and stall speed – wing loading – power demand for a fixed‑mass model, a cruise speed of 50 km/h, and motor power limits Designs that pass these checks are then run through Athena Vortex Lattice (AVL), a Vortex Lattice Method (VLM) solver. AVL provides the lift‑to‑drag ratio (L/D) and the directional‑stability derivative (Cₙβ) at the required lift condition.

To avoid the heavy computational cost of repeatedly running AVL during optimization, a feed‑forward Artificial Neural Network (ANN) is trained as a surrogate model. The ANN maps the geometric inputs [b, c, aspect ratio (AR), wing area (S)] directly to the performance outputs [L/D, Cₙβ]. Finally, an Artificial Bee Colony (ABC) metaheuristic algorithm searches for the best design by maximizing a multi‑objective index built from the ANN predictions. The whole framework gives students a clear path to explore machine‑learning tools in computational aerodynamics and early‑stage aircraft design.

Message: Hi FE, I need help with “Constraint-Based Wing Planform Sizing of a Fixed-Wing UAV Using an AVL–ANN Surrogate and Artificial Bee Colony Optimization” in “Aerospace Engineering”