An integrated interpretable control effectiveness learning and nonlinear control allocation methodology for overactuated aircrafts

2026-06-11

AI Summary

This work addresses the limitations of conventional linear control allocation in highly nonlinear flight regimes—namely, degraded accuracy due to model mismatch, high computational cost of high-fidelity models, and poor interpretability of black-box data-driven approaches—by proposing an interpretable control effectiveness learning framework based on Sparse Identification of Nonlinear Dynamics (SINDy). The method identifies an explicit, physics-constrained analytical model directly from flight data, enabling efficient solution of nonlinear control allocation through analytically computable derivatives. An online adaptive mechanism, driven by residual monitoring, facilitates graceful reconfiguration in response to actuator faults and changing operating conditions. High-maneuverability flight tests on a high-fidelity overactuated aircraft benchmark demonstrate that the proposed approach achieves control accuracy comparable to full nonlinear onboard models while substantially reducing computational overhead.

Abstract

Nonlinear dynamics and the strong couplings that arise between multiple effectors undermine the assumptions behind conventional, linear control allocation techniques. When flight enters regimes where nonlinear effects dominate, linear allocators exhibit reduced accuracy due to increased model mismatch, which subsequently degrades performance and robustness of the flight control system. High fidelity onboard models and black box data driven approaches can recover accuracy across the flight envelope, but respectively impose computational burdens prohibitive for real time allocation and sacrifice the interpretability required for verification and fault diagnosis. This paper addresses these limitations by learning an explicit, physics constrained analytical model of the control effectiveness mapping from representative flight data using Sparse Identification of Nonlinear Dynamics. The resulting mapping is compact, interpretable, and admits analytical derivatives, enabling efficient computation within nonlinear solvers that additionally incorporate actuator dynamics, without requiring an onboard model. An online adaptation mechanism monitors prediction residuals and refreshes the model when significant plant changes are detected, providing graceful reconfiguration under actuator failures and varying operating conditions. The methodology is evaluated on a high fidelity nonlinear benchmark aircraft across a range of aggressive maneuvers, achieving accuracy comparable to a full nonlinear onboard model while substantially reducing computational cost relative to established baselines.

Problem

• nonlinear control allocation
• control effectiveness
• overactuated aircraft
• model interpretability
• flight envelope

Innovation

• Sparse Identification of Nonlinear Dynamics
• interpretable control effectiveness
• nonlinear control allocation
• online adaptation
• overactuated aircraft