Dual-Regime Hybrid Aerodynamic Modeling of Winged Blimps With Neural Mixing

Abstract

Winged blimps operate across distinct aerodynamic regimes that cannot be adequately captured by a single model. At high speeds and small angles of attack, their dynamics exhibit strong coupling between lift and attitude, resembling fixed-wing aircraft behavior. At low speeds or large angles of attack, viscous effects and flow separation dominate, leading to drag-driven and damping-dominated dynamics. Accurately representing transitions between these regimes remains a fundamental challenge. This paper presents a hybrid aerodynamic modeling framework that integrates a fixed-wing Aerodynamic Coupling Model (ACM) and a Generalized Drag Model (GDM) using a learned neural network mixer with explicit physics-based regularization. The mixer enables smooth transitions between regimes while retaining explicit, physics-based aerodynamic representation. Model parameters are identified through a structured three-phase pipeline tailored for hybrid aerodynamic modeling. The proposed approach is validated on the RGBlimp platform through a large-scale experimental campaign comprising 1,320 real-world flight trajectories across 330 thruster and moving mass configurations, spanning a wide range of speeds and angles of attack. Experimental results demonstrate that the proposed hybrid model consistently outperforms single-model and predefined-mixer baselines, establishing a practical and robust aerodynamic modeling solution for winged blimps.

Figures (10)

• Figure 1: Overview of the ACM--GDM hybrid aerodynamic model for winged blimps. Using RGBlimp as an example, the Aerodynamic Coupling Model (ACM) captures lift-drag coupling and angle-dependent moments in the high-speed, small-angle-of-attack flight regime, while the Generalized Drag Model (GDM) represents drag-dominated, viscous effects in the low-speed, large-angle-of-attack operating regime. A neural-network mixer provides a smooth, physically regularized transition between the two regimes. The resulting hybrid model reproduces the dominant aerodynamic behaviors of winged blimps across their full operating envelopes, offering a unified and interpretable modeling framework.
• Figure 2: Illustration of the RGBlimp prototype and schematic representation of its ACM and GDM dynamic models. (a) RGBlimp prototype illustrating the winged envelope and suspended gondola with two thrusters. (b) Side-view diagram demonstrating the mass distribution. (c) Schematic of ACM, capturing lift--drag interactions and angle-dependent moments. (d) Schematic of GDM, representing drag-dominated, viscous effects.
• Figure 3: Three-phase identification pipeline of the ACM–GDM hybrid model. The flight envelope is partitioned by $\alpha_1$, $\alpha_2$, $V_1$, $V_2$ into ACM, GDM, and transition regions. Phase 1 sets the mixing coefficient $\lambda=0$ and uses ACM region data to identify ACM parameters $\boldsymbol{\varphi }_{\text{ACM}}^{*}$. Phase 2 sets $\lambda=1$ and uses GDM region data to identify GDM parameters $\boldsymbol{\varphi }_{\text{GDM}}^{*}$, yielding the complete set of physical parameters $\boldsymbol{\varphi }^*$. Phase 3 fixes $\boldsymbol{\varphi } = \boldsymbol{\varphi }^*$ and trains the neural network $\lambda =\lambda \left( \alpha,V ;\boldsymbol{\xi } \right)$ on transition-region data to obtain the network parameters $\boldsymbol{\xi^*}$. The procedure produces the identified physical parameters $\boldsymbol{\varphi }^*$ and the learned transition parameters $\boldsymbol{\xi^*}$.
• Figure 4: Snapshots of RGBlimp flight experiments illustrating a variety of trajectories, angles of attack, and speeds. (a) Straight upward flight with input $\left (F_l,F_r,\Delta\bar{r}_x \right) = (4.59\,\text{gf},4.59\,\text{gf},-5\,\text{cm})$. (b) Straight downward flight with input $\left (F_l,F_r,\Delta\bar{r}_x \right) = (1.13\,\text{gf},1.13\,\text{gf},0\,\text{cm})$. (c) Spiral upward flight with input $\left (F_l,F_r,\Delta\bar{r}_x \right) = (7.57\,\text{gf},3.24\,\text{gf},0\,\text{cm})$. (d) Spiral downward flight with input $\left (F_l,F_r,\Delta\bar{r}_x \right) = (3.24\,\text{gf},2.06\,\text{gf},0\,\text{cm})$. Each snapshot includes an inset showing the time traces of $\alpha$ and $V$, along with their instantaneous values at the displayed frame.
• Figure 5: Steady-state flight data fitted using ordinary least squares to identify the model switching points $\alpha^*$ and $V^*$. (a) Fitted surface of the sideslip coefficient $C_S$ as a function of angle of attack $\alpha$ and sideslip angle $\beta$ in the ACM region. (b) Fitted surface of the lift coefficient $C_L$ as a function of $\alpha$ and $\beta$ in the ACM region. (c) Fitted relation of the yaw drag moment $D_{\psi}$ versus yaw rate $r$ in the GDM region.