Radar threat assessment method based on hierarchical indexes

A technology of third-level indicators and second-level indicators, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of lack of applicability and reliability in threat value assessment

Active Publication Date: 2021-08-20
HARBIN ENG UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the construction of existing hierarchical indicators needs to rely on expert experienc...

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
  • Radar threat assessment method based on hierarchical indexes
  • Radar threat assessment method based on hierarchical indexes
  • Radar threat assessment method based on hierarchical indexes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] The present invention uses GAT to establish the relationship between the first-level index and the third-level index in the hierarchical index, and combines the AP algorithm and DNN to design the hierarchical index relationship that represents the relationship between the first-level index, the second-level index and the third-level index, and realizes radar detection. Threat assessment. as attached figure 1 Shown is a schematic flow chart of the new threat assessment method based on hierarchical indicators of the present invention; as attached figure 2 As shown, it is a schematic diagram of the GAT training process of the threat assessment method in Embodiment 1 of the present invention.

[0107] Step 1: Use each sensor data and corresponding threat value to construct a data set, train GAT, and obtain the attention coefficient between the first-level indicators and the third-level indicators in the hierarchical indicators.

[0108] Step 1.1: Obtain all sensor data a...

Embodiment 2

[0196] Figure 7 An exemplary list of information directly or indirectly detectable by sensors, including pulse repetition frequency, flight speed, distance, flight altitude, angle, temperature, air attack pattern and instantaneous bandwidth; Figure 8 It is the table of mean absolute error and root mean square error after 800 experiments.

[0197]In the second embodiment of the present invention, by collecting sensors, 200 signals are collected, 120 signals are used as training sets, 60 signals are used as test sets, and the experiment is repeated 800 times, and the method in the first embodiment of the present invention is used to solve the problem , first use the training set to construct the indicator set, and then use the test set to calculate the final threat value, wherein the mean absolute error is 2.19, and the root mean square error is 7.23, which shows that the method provided by the present invention has high reliability. The present invention relates to the field...

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 belongs to the technical field of radar threat assessment, and particularly relates to a radar threat assessment method based on hierarchical indexes. According to the method, the relationship between the first-level index and the third-level index in the hierarchical indexes is established by using the GAT, and the hierarchical index relationship representing the relationship between the first-level index, the second-level index and the third-level index is designed in combination with the AP algorithm and the DNN, so that threat assessment of the radar is realized. According to the method, the attention mechanism is combined, and the similarity theory is fused to design the weight distribution method, so that the construction of the hierarchical index relationship is more objective; meanwhile, a brand-new hierarchical index relationship associated with actual sensor data is designed by utilizing a graph attention network and a deep neural network, so that the robustness and adaptability of the threat assessment method are improved, the reliability of the method is improved, and the risk of threat assessment is reduced. Therefore, accurate evaluation of the threat value can still be achieved under the condition that the received information is not comprehensive.

Description

technical field [0001] The invention belongs to the technical field of radar threat assessment, and in particular relates to a radar threat assessment method based on hierarchical indicators. Background technique [0002] The existing radar threat assessment method directly assigns the hierarchical index relationship by experts, and after obtaining the sensor data, reasoning layer by layer, and finally calculates the threat value. However, since this method needs to determine the model structure and parameters based on historical experience and expert knowledge, it needs relatively comprehensive prior information. When the received information is incomplete, the existing method will not be applicable, and the accuracy of threat assessment will be poor. . [0003] In the "Air Combat Dynamic Situation Estimation Method Based on Improved Evidence Network" published in "Acta Aeronautics Sinica" (2020,21(02):91-96), Wang Yu et al. designed a threat level assessment method, which...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/048G06N3/045G06F18/22G06F18/23213G06F18/214
Inventor 高敬鹏毛新蕊吴若无许雄胡欣瑜项建弘綦俊炜王上月
Owner HARBIN ENG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap