Search

Your search keyword '"An, Qingxian"' showing total 3 results
Start Over Author "An, Qingxian" Publisher american society of civil engineers
3 results on '"An, Qingxian"'

1. Robust Active Fault-Tolerant Configuration Control for Spacecraft Formation via Learning RBFNN Approaches.

Author

Shu, Rui, Jia, Qingxian, Wu, Yunhua, Liao, He, and Zhang, Chengxi

Subjects
*FAULT-tolerant control systems, *MACHINE learning, *FORMATION flying, *RADIAL basis functions, *ARTIFICIAL satellite attitude control systems
Abstract

This paper studies the issue of learning radial basis function neural network (RBFNN)-based robust reconfigurable fault-tolerant configuration control for spacecraft formation flying (SFF) systems subject to thruster faults and space perturbations. To robustly reconstruct thruster faults, a novel learning RBFNN estimator is innovatively explored, in which the P-type iterative learning algorithm is utilized to online update the weight matrix of the RBFNN model and the H∞ control technique is adopted to attenuate the effect of space perturbations. Further, a learning RBFNN output-feedback fault-tolerant control (FTC) method is developed for spacecraft formation configuration maintenance with high accuracy, and the learning RBFNN algorithm is used to update and compensate the synthesized perturbation. Finally, a numerical example is simulated to verify the presented learning RBFNN-based spacecraft formation FTC approach is feasible and superior. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

2. Recurrent-Functional-Link-Network-Based Predictive Control Hypersonic Vehicles with Dynamical Uncertainties

Author

Changsheng Jiang, Yanli Du, Qingxian Wu, and Lu Cheng

Subjects
Lyapunov stability, Engineering, Model predictive control, Recurrent neural network, Artificial neural network, Control theory, business.industry, Approximation error, Robustness (computer science), Adaptive system, Control engineering, business, Residual
Abstract

This paper presents a novel adaptive predictive control methodology for air-breathing hypersonic vehicles (AHVs) in the presence of dynamical thrust and parameter uncertainties. The method combines the nonlinear generalized predictive control (NGPC) with a new recurrent-functional-link- network (RFLN) adaptive law proposed here. The RFLN is a simple recurrent neural network without hidden layers, so it is suitable for the approximation of dynamical uncertainties during the hypersonic flight. The RFLN weights are online tuned by the derived adaptive laws based on Lyapunov stability theorem for the first time. The learning process does not need any offline training phase. Additionally, a robust controller whose gain can be adaptively adjusted is designed to recover the residual of the approximation error. Finally, simulation results show better performance of the controller for the AHV attitude tracking than the method compared, moreover, the robustness to dynamical parameters variations and the disturbance rejection are successfully accomplished.

Published
2010

Catalog

Books, media, physical & digital resources
See catalog results