Learning Chebyshev neural network-based spacecraft attitude tracking control ensuring finite-time prescribed performance

Aerospace Science and Technology, Год журнала: 2024, Номер 148, С. 109085 - 109085

Опубликована: Март 25, 2024

Язык: Английский

---

Dynamic Event-Triggered Prescribed-time Optimized Backstepping Attitude Consensus Tracking Control for Multiple Spacecrafts

Aerospace Science and Technology, Год журнала: 2025, Номер unknown, С. 110050 - 110050

Опубликована: Фев. 1, 2025

Язык: Английский

---

Distributed predefined-time robust adaptive control design for attitude consensus of multiple spacecraft

Advances in Space Research, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

Язык: Английский

---

Near-asteroid spacecraft formation control with prescribed-performance: a dynamic event-triggered reinforcement learning control approach

Aerospace Science and Technology, Год журнала: 2025, Номер unknown, С. 110138 - 110138

Опубликована: Март 1, 2025

Язык: Английский

---

Event-triggered predefined-time sliding mode control for consensus tracking of multiagent systems with actuator saturation and faults

International Journal of Dynamics and Control, Год журнала: 2025, Номер 13(5)

Опубликована: Апрель 21, 2025

Язык: Английский

---

Dynamic event‐triggered orbit coordination for spacecraft formation via a self‐learning sliding mode control approach

International Journal of Robust and Nonlinear Control, Год журнала: 2024, Номер 34(9), С. 5754 - 5773

Опубликована: Март 1, 2024

Summary This article investigates the issue of orbit coordination control for a class multi‐spacecraft formation systems in presence limited communication and external disturbance. To solve limitation sources, dynamic event trigger (DET) mechanism is developed to reduce frequency between follower spacecrafts. Subsequently, we explore robust DET mechanism‐based distributed self‐learning sliding mode design, which variable learning intensity‐based iterative algorithm designed approximate compensate space perturbation. approach can guarantee an triggering sequence without Zeno phenomenon accurate configuration simultaneously. Compared with traditional event‐triggered other state‐of‐the‐art approaches, scheme achieves higher accuracy meanwhile requires less resource. Finally, series numerical simulations demonstrate feasibility superiority triggered method.

Язык: Английский

---

Self-learning for translational control of elliptical orbit spacecraft formations

Aircraft Engineering and Aerospace Technology, Год журнала: 2024, Номер unknown

Опубликована: Июль 25, 2024

Purpose This paper aims to investigate the relative translational control for multiple spacecraft formation flying. proposes an engineering-friendly, structurally simple, fast and model-free algorithm. Design/methodology/approach a tanh-type self-learning (SLC) approach with variable learning intensity (VLI) guarantee global convergence of tracking error. algorithm utilizes controller's previous information in addition current system state avoids complicating structure. Findings The proposed is can obtain law without accurate modeling dynamics. tanh function tune magnitude reduce saturation behavior when error large. Practical implications model-free, robust perturbations such as disturbances uncertainties, has simple structure that very conducive engineering applications. Originality/value verified performance presence by simulation achieved high steady-state accuracy response speed over comparisons.

Язык: Английский

---

Optimization of Structures and Composite Materials: A Brief Review

Eng—Advances in Engineering, Год журнала: 2024, Номер 5(4), С. 3192 - 3211

Опубликована: Дек. 2, 2024

Neural networks (NNs) have revolutionized various fields, including aeronautics where it is applied in computational fluid dynamics, finite element analysis, load prediction, and structural optimization. Particularly optimization, neural deep are extensively employed to enhance the efficiency of genetic algorithms because, with this tool, possible speed up analysis process, which will also optimization process. The main objective paper present how can help process optimizing geometries composition composite structures (dimension, topology, volume fractions, reinforcement architecture, matrix/reinforcement composition, etc.) compared traditional methods. This article stands out by showcasing not only studies related but those field mechanics, emphasizing that underlying principles shared applicable both domains. use NNs as a surrogate model has been demonstrated be great tool for process; some shown accurate their predictions, an MSE 1×10−5 MAE 0.007%. It observed its helps reduce time, such 47.5 times faster than full aeroelastic model.

Язык: Английский

---

Dynamic event-triggered attitude synchronization of multi-spacecraft formation via a learning Chebyshev neural network control approach

Aircraft Engineering and Aerospace Technology, Год журнала: 2024, Номер unknown

Опубликована: Дек. 10, 2024

Purpose This paper aims to investigate the attitude synchronization issue of multi-spacecraft formation flying systems under limited communication resources. Design/methodology/approach The authors propose a distributed learning Chebyshev neural network controller (LCNNC) combining dynamic event-triggered (DET) mechanism and CNN model achieve accurate constraints. Findings proposed method can significantly reduce internal frequency improve accuracy. Practical implications requires low resources, has high control accuracy is thus suitable for engineering applications. Originality/value A novel DET mechanism-based LCNNC

Язык: Английский

---

Velocity-Free Prescribed-Time Orbit Containment Control for Satellite Clusters under Actuator Saturation

Advances in Space Research, Год журнала: 2024, Номер unknown

Опубликована: Дек. 1, 2024

Язык: Английский

---