Deep learning-based reentry prediction correction fault-tolerant guidance method for hypersonic aircraft

Abstract

The invention discloses a deep learning-based reentry prediction correction fault-tolerant guidance method for a hypersonic aircraft, and belongs to the technical field of aircraft navigation guidanceand control. The method comprises the following steps of firstly, balancing the rudder deflection of an aircraft under a fault condition, selecting an attack angle profile within a feasible attack angle range, and simultaneously obtaining the lift and drag coefficients of the aircraft; then, enabling the attack angle profile to be substituted into a reentry process constraint equation to obtain areentry corridor meeting the requirements, and enabling the reentry corridor to be converted into a roll angle amplitude constraint; estimating the change amount delta CL and delta CD between the lift and drag resistance coefficient of the aircraft relative to the lift and drag coefficients of the normal aircraft, and combining the reentry terminal constraint equation to obtain an inclination angle amplitude; utilizing the inclination angle reversal logic based on the course angle error corridor to obtain an inclination angle symbol; and finally, calculating the inclination angle profile by using the inclination angle amplitude and the inclination angle symbol, and combining the attack angle profile to obtain the guidance command meeting the requirement after the fault. The method is highin guidance precision, good in algorithm instantaneity and capable of meeting the requirement of fault-tolerant guidance.

Description

technical field [0001] The invention relates to a hypersonic vehicle reentry prediction correction fault-tolerant guidance method based on deep learning, and belongs to the technical field of aircraft navigation guidance and control. Background technique [0002] A hypersonic vehicle is a multi-constraint and multivariable system with strong nonlinearity, strong coupling, fast time-varying and strong uncertainty. The complex re-entry environment, strict process constraints, high-precision requirements for terminal landing and attitude tracking, and due to Actuating mechanism failures easily caused by harsh environments have brought unprecedented challenges to the research of guidance and control of aircraft. Research on fault-tolerant guidance and control is of great significance for improving the fault tolerance of hypersonic vehicles, improving and enhancing the safety and stability of hypersonic vehicles. Significance. [0003] In the case of less serious faults, the fau...

AI Technical Summary

Problems solved by technology

Judging from the existing literature, the current fault-tolerant guidance algorithm mainly has the following two problems: ①The coding is complex, a large number of trajectories need to be generated and stored offline, and the storage space of the onboard computer is relatively high. The fault-tolerant guidance method; ② Algorithm real-time problems, such as the pseudo-spectral method based on the estimation of aerodynamic parameters under faults

Images