Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A simulation and verification system for intersatellite laser interference frequency planning based on time series reinforcement learning

A technology of frequency planning and laser interference, which is applied in the field of inter-satellite laser interference frequency planning simulation verification system to achieve the effect of reducing risks

Active Publication Date: 2022-02-22
NAT SPACE SCI CENT CAS
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the defects of the existing frequency planning scheme and verify the reliability of the frequency planning scheme, and propose a time-sequence reinforcement learning intersatellite laser interference frequency planning simulation verification system

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
  • A simulation and verification system for intersatellite laser interference frequency planning based on time series reinforcement learning
  • A simulation and verification system for intersatellite laser interference frequency planning based on time series reinforcement learning
  • A simulation and verification system for intersatellite laser interference frequency planning based on time series reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0105] Such as figure 1 As shown, Embodiment 1 of the present invention proposes a system for formulating a time series retrospective reinforcement learning model for frequency planning schemes, the system includes six optical platforms A1, A2, A3, A5, A4, A6. The angle between optical tables A1 and A2 is 60 degrees for a group of adjacent optical tables, the angle between A3 and A4 is 60 degrees for a group of adjacent optical tables, the angle between A5 and A6 is 60 degrees for a group of adjacent optical tables optical table. A1 and A6 are a group of relative optical tables, A2 and A3 are a group of relative optical tables, A4 and A5 are a group of relative optical tables.

[0106] Each optical platform includes tunable lasers, multiple beam splitters, multiple one-way glasses, multiple four-quadrant photodetectors, multiple beam couplers, and a Doppler frequency shift interference generator. The optical platforms A1, A2, A3, A5, A4, and A6 have the same structure and a...

Embodiment 2

[0122] Such as Figure 5 As shown, Embodiment 2 of the present invention proposes a method for simulation and verification of intersatellite laser interference frequency planning based on time-series reinforcement learning, which is implemented based on the system of Embodiment 1. Specific methods include:

[0123] Calculate the Doppler frequency shift at a specified moment according to the orbit data, and store it in the Doppler frequency shift interference information memory of the storage component;

[0124] Input the Doppler frequency shift at a specified moment into the decision model that has been established and trained, and obtain the laser frequency to be emitted at each moment of each laser interference optical platform, form a frequency planning scheme including each moment and store it in the reinforcement learning of the storage component policy memory;

[0125] Input the frequency planning scheme into the laser transmitter of each laser interferometry optical p...

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 intersatellite laser interference frequency planning simulation and verification system for time series intensive learning. The system includes: a laser interference optical platform group, a storage component, and a display terminal; wherein, the laser interference optical platform group includes six laser interference devices with the same structure. The optical platform, every two platforms is a pair, adjusts the frequency and phase of the laser in real time according to the frequency planning scheme, and shifts the frequency of the incident laser according to the Doppler interference frequency information to simulate the satellite in space due to Doppler The interference caused by the phenomenon; the storage component is used to store the pre-established and trained decision-making model, the frequency planning scheme determined by the decision-making model, corresponding to the Doppler interference frequency information at each moment of the experiment, and stored in the experiment. The selected frequency planning scheme; the decision-making model is trained by time-series retrospective reinforcement learning method; the display terminal is used to display Doppler interference frequency information and laser beat frequency information in real time.

Description

technical field [0001] The invention relates to the field of optical laser interferometry and the field of computer reinforcement learning technology, and in particular to a time sequence reinforcement learning simulation verification system for intersatellite laser interference frequency planning simulation. Background technique [0002] Reinforcement learning is a new direction in the field of machine learning. Its purpose is to learn through the actions chosen by the machine independently and the punishment of environmental feedback. In the process of "seeking advantages and avoiding disadvantages" step by step, the "intelligent body" controlled by the program gradually understands the environment and makes the optimal strategy selection through continuous trial and error. The algorithm needs to set the environment of the agent in advance and the reward after the agent chooses an action. Its ultimate goal is to enable the agent to have the ability to analyze the environm...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/27G06N20/00
CPCG06F30/27G06N20/00
Inventor 张佳锋马晓珊杨震彭晓东唐文林强丽娥张玉珠高辰赵梦园
Owner NAT SPACE SCI CENT CAS
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
Eureka Blog
Learn More
PatSnap group products