The invention discloses a method for estimating low-thrust intersection burnup by using a neural network. The method comprises the following steps: firstly, obtaining a training data set in which initial and target orbits, intersection duration and burnup are in one-to-one correspondence; secondly, two neural networks are built, one neural network is used for building an agent model for the realizability of the small-thrust intersection trajectory, and the other neural network is used for building an agent model for small-thrust intersection burnup calculation; the method comprises the following steps: training a neural network by using sampling data, taking any input initial orbit and target orbit as input layer data, firstly substituting the input layer data into a first neural network to obtain output layer data, namely the feasibility of low-thrust intersection, and if the orbit transfer is feasible, continuously substituting the input layer data into a second neural network to obtain output data, namely the feasibility of low-thrust intersection. The increment is the increment of the low-thrust rendezvous speed. According to the method, the problems of large calculation amount, low convergence performance and low approximation precision of a low-thrust trajectory optimization method in the prior art are solved.

    本发明公开了一种使用神经网络估计小推力交会燃耗量的方法,首先获得初始和目标轨道、交会时长与燃耗量一一对应的训练数据集;然后搭建两个神经网络,其中一个用以建立小推力交会轨迹的可实现性的代理模型,另一个用以建立小推力交会燃耗量计算的代理模型;利用采样数据对神经网络进行训练,最后根据输入的任意初始轨道和目标轨道,作为输入层数据,首先代入第一个神经网络获得输出层数据,即为小推力交会的可行性,若该轨道转移可行,则继续代入第二个神经网络获得输出数据,即为小推力交会速度增量。本发明解决了现有技术中存在的小推力轨迹优化方法计算量大、收敛性能低且近似精度低的问题。


    Access

    Download


    Export, share and cite



    Title :

    Method for estimating low-thrust intersection fuel consumption by using neural network


    Additional title:

    使用神经网络估计小推力交会燃耗量的方法


    Contributors:
    HUANG ANYI (author) / LI HENGNIAN (author) / SHEN HONGXIN (author) / KUAI ZHENGZHONG (author) / SHENG CHAO (author) / LI ZHAO (author) / GUO YANCHEN (author)

    Publication date :

    2023-06-13


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B64G Raumfahrt , COSMONAUTICS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Fuel Consumption Intersection Control Performance Index

    Stevanovic, Aleksandar / Shayeb, Suhaib Al / Patra, Satya S. | Transportation Research Record | 2021


    SYSTEM FOR ESTIMATING CAMBER THRUST, METHOD FOR ESTIMATING CAMBER THRUST, AND VEHICLE

    MIKI MASAYUKI | European Patent Office | 2017

    Free access

    SYSTEM FOR ESTIMATING CAMBER THRUST, METHOD FOR ESTIMATING CAMBER THRUST, AND VEHICLE

    MIKI MASAYUKI | European Patent Office | 2015

    Free access

    Scramjet: Minimum Thrust-Specific Fuel Consumption with Material Limit

    Roux, J. A. / Shakya, N. / Choi, J. | AIAA | 2013


    Estimating thrust horse-power

    Willis, J.G. | Engineering Index Backfile | 1938