Intelligent task reconstruction method for a carrier rocket in an ascending stage under a thrust drop fault

A launch vehicle and thrust technology, applied in the directions of instruments, adaptive control, control/regulation systems, etc., can solve problems such as flight mission failure, thrust drop, and difficulty in completing tasks, and achieve the effect of saving online computing time.

Pending Publication Date: 2021-10-08
DALIAN UNIV OF TECH
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology helps train people who have lost their ability to communicate signals over long distances more efficiently through neural networks trained on data from previous sessions or simulations. It suggests selecting the best path for future tasks based upon its failure mode - which makes it easier than trying hard to find specific goals during trial runs. Additionally, this approach allows for adaptation between different types of recovery tracks and flight paths depending on how well they were achieved at each stage. Overall, these technical improvements make better communication capabilities even when faced challenging situations such as reconstructed disabilities caused due to neurology problems.

Problems solved by technology

The technical problem addressed in this patented text relates how to improve the efficiency at recovering failed engines during space exploration tasks by optimizing their recovery path based on real-time constraints such as fuel usage and environmental factors like altitude.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent task reconstruction method for a carrier rocket in an ascending stage under a thrust drop fault
  • Intelligent task reconstruction method for a carrier rocket in an ascending stage under a thrust drop fault
  • Intelligent task reconstruction method for a carrier rocket in an ascending stage under a thrust drop fault

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] Taking the entire secondary flight phase of the launch vehicle as the research object, the parameters come from the literature Z.Song, C.Wang, Q.Gong, Joint dynamic optimization of the target orbit and flight trajectory of a launch vehicle based on state-triggered indices, ActaAstronaut. , 174(2020) 82-93. The collocation points used in the adaptive pseudospectral method are the zeros of the orthogonal Legendre polynomials. The fault occurrence time of the data set is 0~378s, the step size is 0.5s; the thrust drop size is 12%~30%, the step size is 0.1%. In the data set, 90% of the data is randomly selected as the training set, and the remaining 10% of the data is used as the test set. The diffusion factor of radial basis neural network training is 0.5, and the number of neurons in the final trained hidden layer is 100.

[0080] figure 2 The online calculation time comparison of RBFNN-ACM and CVX-ACM in solving Problem 1 is shown. Compared with CVX-ACM, with the RBFN...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent task reconstruction method for a carrier rocket in an ascending stage under a thrust drop fault. The method comprises the following steps: acquiring an optimal rescue orbit and a corresponding flight path by adopting a self-adaptive point collocation method; extracting an optimal track from the flight tracks corresponding to the optimal rescue track, performing interpolation on the optimal track according to discrete flight time nodes, and generating a fault state-optimal track data set; performing normalization processing on the data set by adopting a maximum-minimum method, selecting a radial basis function neural network data center through an orthogonal least square method, and establishing a relation from a fault state to an optimal trajectory; migrating the radial basis function neural network to actual flight of the rocket, wherein the radial basis function neural network decides an approximate optimal trajectory online; and utilizing the decided approximate optimal trajectory as an initial guess value, and carrying out online solving by adopting a self-adaptive pseudo-spectral method to obtain an optimal rescue trajectory and a flight trajectory. According to the method, the rescue track and the corresponding flight path can be optimized on line at the same time, and the calculation time is saved.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products