Attitude Control of a Two-CubeSat Virtual Telescope in Highly Elliptical Orbits

Pirayesh, Reza; Naseri, Asal; Stochaj, Steven; Shah, Neerav; Krizmanic, John F.

doi:10.2514/6.2018-0866

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 5 provides the mission with the lowest E. In the scientific phase, sliding mode controller (SMC) provides the mission with E=0.0066 J/hr while maintaining the desired e [4], [16], [17]. In the formation stabilization phase, E is negligible [4], [15], [16] compared to the other two phases as it is in the order of e − 5 J. Since For each orbit a 10-hour formation is maintained in the the scientific phase, E is roughly 0.066 J for the science observation phase.…”

Section: E Machine Learning Results Comparisonmentioning

confidence: 99%

“…Formation has been studied as leader-follower approach, behavior-based method, potential field approach, and generalized coordinates [14]. In VTXO, leader-follower approach is taken [12], [15], [16] where the leader holds the lens, known as the optics spacecraft (OS), and the follower holds the X-ray camera, known as the imaging spacecraft (IS).…”

Section: Introductionmentioning

confidence: 99%

“…VTXO uses a lightweight Phased Fresnel Lens (PFL) to obtain near diffraction-limited angular resolution in the X-ray band [4], [10], [12], [15]- [18]. PFL provides the VTXO mission with nearly 55 milli-arcsecond (mas) (FWHM) imaging resolution of astrophysical sources in the X-ray band for a 1 km focal length.…”

Section: Introductionmentioning

confidence: 99%

“…Trajectory optimization is used to determine the optimal phases, the optimal orbits, and the optimal controllers for the GNC [6], [10]- [12]. For the VTXO, 3 phases are assigned to the ACS, and each phase is designed to optimize the performance of the VTXO mission by increasing the accuracy and reducing the energy consumption [4], [15]- [18], [22]. The benefits of assigning phases to the mission are…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Designing Monte Carlo Simulation and an Optimal Machine Learning to Optimize and Model Space Missions

Pirayeshshirazinezhad

Biedron

et al. 2022

IEEE Access

View full text Add to dashboard Cite

This paper investigates applying artificial intelligence (AI) algorithms to attitude control system of satellites to optimally tune the controller using high performance computing. This methodology is applied to the Virtual Telescope for X-ray Observation mission, which is a precise formation of two separate spacecraft observing multiple objects in the space in the X-ray domain. The mission is divided into phases based on the instrumentation and the mission goal. To reach an stable precise formation robust to stochastic slew and slew rate (i.e., Euler angles and angular velocities) in a minimal constrained time T , consumed energy of the attitude control system, denoted as E, and root-mean-square state error of attitude control system, denoted as e, are minimized. Monte-Carlo simulation is used for the sensitivity analysis of optimization and designing a controller. Deep neural networks (DNN), Gaussian processes (GP), and support vector regression (SVR) learn this optimization as a surrogate model, while their hyperparameters are optimized in a novel approach. THETA supercomputer at Argonne Leadership Computing Facility (ALCF) is used for optimizing the hyperparameters of DNN. The surrogate model meets the requirements of the mission, and it shows a better performance over the optimization and Monte-Carlo. The optimal DNN can satisfy the mission requirements e and T while reducing E for 90% compared to the other given methods.

show abstract

Section: E Machine Learning Results Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%