Constellation ground coverage performance comprehensive analysis method based on multi-layer perceptron network agent model

Abstract

The invention discloses a multi-layer perceptron network agent model-based constellation ground coverage performance comprehensive analysis method, which comprises the following steps of: determining constellation parameters and performance parameters of constellation ground coverage performance comprehensive analysis, and giving a value range of the constellation parameters; a plurality of training data are generated, and the training data comprise a group of constellation parameters and corresponding performance parameters; performing standardization processing on the training data; constructing a multi-layer perceptron neural network model, and training the multi-layer perceptron neural network model by using the standardized training data to fit a mapping relationship between constellation parameters and performance parameters; and utilizing the trained multilayer perceptron neural network model to predict and analyze the coverage performance of the constellation to the ground. The multi-layer perceptron neural network is utilized to construct the proxy model for constellation ground coverage performance analysis, comprehensive rapid analysis of constellation space coverage performance and time coverage performance can be achieved, the calculation amount is small, calculation time is short, and analysis precision is high.

Description

technical field [0001] The invention relates to the technical field of satellite constellation design optimization, in particular to a method for comprehensive analysis of constellation-to-ground coverage performance based on a multi-layer perceptron network agent model. Background technique [0002] Satellite constellation design is a design process that requires comprehensive weighing and optimization of various factors. Among them, the constellation coverage performance analysis is the core content of the constellation design. On the one hand, when designing the constellation, it is necessary to fully analyze the influence laws of multiple design parameters to provide a basis for the comprehensive trade-off of the design scheme. On the other hand, when designing the constellation, it is necessary to further optimize the solution on the basis of performance analysis. Since each adjustment of the optimization objective or design constraint corresponds to a complete analys...

AI Technical Summary

Problems solved by technology

[0005] Since the iterative optimization of the constellation design scheme requires multiple analysis and calculations of the constellation coverage performance, when the grid analysis-based constellation coverage performance analysis method is applied to the constellation optimization design, due to the simulation time, the number of constellation satellites, and the Influenced by multiple factors such as the number of factors, the optimization efficiency is low, and the optimization time is extremely long. With the increase of the scale of the constellation system, the calculation amount and calculation time increase exponentially.

Images