Navigation, Guidance, Control and Dynamics Commons^™

Deep-Learning Based Multiple-Model Bayesian Architecture For Spacecraft Fault Estimation, Rocio Jado Puente

Doctoral Dissertations and Master's Theses

This thesis presents recent findings regarding the performance of an intelligent architecture designed for spacecraft fault estimation. The approach incorporates a collection of systematically organized autoencoders within a Bayesian framework, enabling early detection and classification of various spacecraft faults such as reaction-wheel damage, sensor faults, and power system degradation.

To assess the effectiveness of this architecture, a range of performance metrics is employed. Through extensive numerical simulations and in-lab experimental testing utilizing a dedicated spacecraft testbed, the capabilities and accuracy of the proposed intelligent architecture are analyzed. These evaluations provide valuable insights into the architecture's ability to detect and classify …

Six-Degree-Of-Freedom Optimal Feedback Control Of Pinpoint Landing Using Deep Neural Networks, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua

Student Works

Machine learning regression techniques have shown success at feedback control to perform near-optimal pinpoint landings for low fidelity formulations (e.g. 3 degree-of-freedom). Trajectories from these low-fidelity landing formulations have been used in imitation learning techniques to train deep neural network policies to replicate these optimal landings in closed loop. This study details the development of a near-optimal, neural network feedback controller for a 6 degree-of-freedom pinpoint landing system. To model disturbances, the problem is cast as either a multi-phase optimal control problem or a triple single-phase optimal control problem to generate examples of optimal control through the presence of disturbances. …

Stability Of Deep Neural Networks For Feedback-Optimal Pinpoint Landings, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua

Student Works

The ability to certify systems driven by neural networks is crucial for future rollouts of machine learning technologies in aerospace applications. In this study, the neural networks are used to represent a fuel-optimal feedback controller for two different 3-degree-of-freedom pinpoint landing problems. It is shown that the standard sum-ofsquares Lyapunov candidate is too restrictive to assess the stability of systems with fuel-optimal control profiles. Instead, a parametric Lyapunov candidate (i.e. a neural network) can be trained to sufficiently evaluate the closed-loop stability of fuel-optimal control profiles. Then, a stability-constrained imitation learning method is applied, which simultaneously trains a neural network …

Rigid Body Constrained Motion Optimization And Control On Lie Groups And Their Tangent Bundles, Brennan S. Mccann

Doctoral Dissertations and Master's Theses

Rigid body motion requires formulations where rotational and translational motion are accounted for appropriately. Two Lie groups, the special orthogonal group SO(3) and the space of quaternions H, are commonly used to represent attitude. When considering rigid body pose, that is spacecraft position and attitude, the special Euclidean group SE(3) and the space of dual quaternions DH are frequently utilized. All these groups are Lie groups and Riemannian manifolds, and these identifications have profound implications for dynamics and controls. The trajectory optimization and optimal control problem on Riemannian manifolds presents significant opportunities for theoretical development. Riemannian optimization is an attractive …

An Online Adaptive Machine Learning Framework For Autonomous Fault Detection, Nolan Coulter

Doctoral Dissertations and Master's Theses

The increasing complexity and autonomy of modern systems, particularly in the aerospace industry, demand robust and adaptive fault detection and health management solutions. The development of a data-driven fault detection system that can adapt to varying conditions and system changes is critical to the performance, safety, and reliability of these systems. This dissertation presents a novel fault detection approach based on the integration of the artificial immune system (AIS) paradigm and Online Support Vector Machines (OSVM). Together, these algorithms create the Artificial Immune System augemented Online Support Vector Machine (AISOSVM).

The AISOSVM framework combines the strengths of the AIS and …

Nonlinear Dynamics Analysis And Control Of Space Vehicles With Flexible Structures, Marco Fagetti

Doctoral Dissertations and Master's Theses

Space vehicles that implement hardware such as antennas, solar panels, and other extended appendages necessary for their respective missions must consider the nonlinear rotational and vibrational dynamics of these flexible structures. Formulation and analysis of these flexible structures must account for the rigid-flexible coupling present in the system dynamics for stability analysis and control design. The system model is represented by a flexible appendage attached to a central rigid body, where the flexible appendage is modeled as a cantilevered Euler-Bernoulli beam. Discretization techniques, such as the assumed modes method and the finite element method, are used to model the coupled …

Solar Sailing Adaptive Control Using Integral Concurrent Learning For Solar Flux Estimation, Luis Enrique Mendoza Zambrano, Riccardo Bevilacqua

Student Works

In the interest of exploiting natural forces for propellant-less spacecraft missions, this investigation proposes an adaptive control strategy to account for unknown parameters in the dynamic modeling of a reflectivity-controlled solar sail spacecraft. A Lyapunov-based control law along with integral concurrent learning is suggested to accomplish and prove global exponential tracking of the estimated parameters and states of interest, without satisfying the common persistence of excitation condition, which in most nonlinear systems cannot be guaranteed a priori. This involves estimating the solar flux or irradiance from the Sun to account for uncertainty and variation over time in this value. To …

Dual Quaternion Relative Dynamics For Gravity Recovery Missions, Ryan Kinzie, Riccardo Bevilacqua, Seo Dongeun

Student Works

A dual quaternion modeling approach is compared to traditional modeling methods for formation flying spacecraft utilized for gravity recovery missions. A modeling method that has traditionally been used for gravity recovery missions is presented which models the motion of two formation flying spacecraft and a test mass. This is followed by the dual quaternion-based formulation for the equations of motion of the twelve degree-of-freedom coupled relative dynamics of formation flying spacecraft and a test mass. Lastly, utilizing data products from the Gravity Recovery and Climate Experiment Follow-On mission, a comparison of these two modeling methods is presented which proves the …