Space debris identification and capture method and system based on brain-like neural network

Abstract

The invention discloses a space debris identification and capture method and system based on a brain-like neural network. The method comprises the following steps: acquiring image information of spacedebris; constructing a main body network, and optimizing the main body network into a target identification network; introducing an environment entropy calculation network to describe the distribution complexity of the space debris; introducing a network entropy calculation network to describe the network complexity of the target identification network; obtaining an entropy balance driving factoraccording to the network complexity and the distribution complexity of the space debris; under the guidance of a game theory framework, adaptively adjusting the network structure of the target identification network by using an entropy balance driving factor; and establishing an information closed loop between the space debris and the space-based detector, and outputting the relative position ofthe space-based detector and the space debris in real time until the space debris is captured. The method has the characteristics of low power consumption, strong generalization ability and high identification precision.

Description

technical field [0001] The present invention relates to the technical field of space debris identification, and more specifically relates to a method and system for identifying and capturing space debris based on a brain-like neural network. Background technique [0002] At present, machine learning and brain-like computing methods are usually used to detect space debris. Space debris detection is to detect space debris from the background, so as to facilitate the development of follow-up work. Traditional machine learning has a large demand for data, which relies on a huge amount of training and requires a huge amount of sample data (hundreds of megabytes, gigabytes or even megabytes of data) to complete the training; and the learning and training process requires accurate feedback , for many problems in the real world, such as aerospace or robotics, there is no good feedback, and there is no way to conduct a large number of simulation experiments to generate a large number...

AI Technical Summary

Problems solved by technology

Traditional machine learning has a large demand for data, which relies on a huge amount of training and requires a huge amount of sample data (hundreds of megabytes, gigabytes or even megabytes of data) to complete the training; and the learning and training process requires accurate feedback , for many problems in the real world, such as aerospace or robotics, there is no good feedback, and there is no way to conduct a large number of simulation experiments to generate a large number of samples for training, or the cost of generating samples is too high, making the application of machine learning become difficult. Very difficult

At the same time, the traditional machine learning model has poor generalization ability and high energy consumption; when the system encounters a new situation and obtains a new sample, it often needs to start from 0 on the already trained model on the data set containing the new sample. training, otherwise the trained model cannot be applied to new samples; a standard computer needs to consume 250 watts of energy to recognize only 1000 different objects

[0003] Traditional brain-inspired computing has insufficient analysis of the brain's functional structure, and the research tools for the brain cannot be both detailed and holistic, and it is impossible to perform global imaging of the brain at high spatio-temporal resolution

At the same time, it is difficult to abstract brain function into a mathematical model. The brain map is highly complex and dynamically changing. The functional division of brain neurons differs significantly under different spatial scales and spatial distributions. The algorithm for cataloging space debris is very complicated and must calculation, and cannot meet the real-time requirements

Images