Neural network-based sliding mode variable structure control for Mars entry

Abstract

To deliver a Mars entry vehicle through the Martian atmosphere to the prescribed parachute deployment point, active Mars entry guidance and control is essential. This article addresses the problem of Mars atmospheric entry control by a neural network-based sliding mode variable structure control (NNSMVSC) to reduce the effect of the bounded uncertainties on the atmospheric density and aerodynamic coefficients. First, NNSMVSC is designed to robustly track the prescribed nominal trajectory under high uncertainties and to effectively reduce the downrange error. Then, the heading alignment logic is adopted in the lateral plane to reduce the cross-range error. Finally, the validity of the control algorithm proposed in this article is demonstrated by computer simulation analysis.

RBF neural network based second-order sliding mode guidance for Mars entry under uncertainties

“…Entry vehicles are commanded to fly at a constant trim angle of attack, and the controlled guidance of the vehicle is achieved only through modulating the bank angle with a reaction control system (RCS). The three degree-of-freedom (DOF) dynamic equations of Mars entry vehicle, defined with respect to the Mars centered Mars-fixed coordinate system are given by [20][21][22] …”

“…In order to circumvent the above-mentioned problem, neural network is utilized to online approximate the bounded uncertainty during Mars atmospheric entry and combined with sliding mode variable structure control (SMVSC). Simulation results show that the neural network-based sliding mode variable structure control (NNSMVSC) algorithm can effectively alleviate the impact of undesired uncertainties and improve the guidance accuracy to a greater extent [21].…”

“…Motivated by the works reported in [21] and [22], we propose and design the RBF neural network based second-order sliding mode guidance (RNNSOSMG) algorithm for Mars Atmospheric Entry. Firstly, the second-order sliding mode guidance (SOSMG) law is adopted to robustly track the reference trajectory under large uncertainties.…”

“…Recently, the sliding control methodology has been considered as an elementary approach to robust control, and a perfect performance can be, in principle, achieved in the presence of parameter inaccuracy [17][18][19]. In order to suppress the adverse impact of uncertainties in atmospheric density and then improve entry guidance accuracy, standard sliding mode variable structure control (SMVSC) and multiple sliding surface guidance (MSSG) were respectively adopted to design the Mars entry guidance law [20][21][22]. Both theoretical analysis and simulation results show that the higher-order sliding mode (HOSM) has the desired property of practically eliminating the dangerous chattering often featuring the standard (first-order) sliding mode [17,22].…”

Tuning of Pulse-Width Pulse-Frequency Modulator using PSO: An Engineering Approach to Spacecraft Attitude Controller Design

“…Hu and co-workers have examined several control methods such as variable structure and fault tolerant controller for flexible spacecraft implemented by PWPF [6,7,29,30]. Li and Peng in [32], used a combination of neural networkbased sliding mode controller with PWPF for Mars entry Tuning of Pulse-Width Pulse-Frequency Modulator using PSO: An Engineering Approach...…”