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

Helicopter flight state identification method based on one-dimensional convolutional neural network

A technology of convolutional neural network and flight state, applied in biological neural network model, neural architecture, character and pattern recognition, etc., can solve the problem of poor recognition of flight state, insufficient use of parameter features, high requirements for pre-classification results, etc. question

Pending Publication Date: 2021-07-06
NANCHANG HANGKONG UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional neural network methods have high requirements for pre-classification results, and do not make full use of parameter features, resulting in poor flight status recognition results

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
  • Helicopter flight state identification method based on one-dimensional convolutional neural network
  • Helicopter flight state identification method based on one-dimensional convolutional neural network
  • Helicopter flight state identification method based on one-dimensional convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The experimental data of the method of the present invention are the flight parameters collected by 23 sensors during the actual flight of the helicopter, and are used to identify 35 flight states of the helicopter. Table 1 shows the 35 flight states of the helicopter to be recognized.

[0040] Table 1 Helicopter flight status

[0041]

[0042]

[0043] The present invention adopts such as figure 1 The workflow shown in the flowchart realizes the recognition of helicopter flight status based on one-dimensional convolutional neural network. The specific implementation steps are as follows:

[0044] 1. Remove the flight parameter data segment that deviates from the normal

[0045] The described removal of the data segment that deviates from the normal flight parameter is to use a visual method to find and remove the data segment that does not meet the corresponding state parameter value in the flight parameter. The specific implementation steps are as follows:

...

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 a helicopter flight state recognition method based on a one-dimensional convolutional neural network. The method comprises the following steps: (1) removing flight parameter data segments deviating from normal; (2) preprocessing flight parameters; (3) making a flight state label data set; (4) designing a one-dimensional convolutional neural network model for flight state recognition; (5) training and storing network model parameters; and (6) testing the data and obtaining the recognition accuracy of each state. The method has the advantages that all flight parameters are used as network input, the parameter features are fully utilized, the diversity of the network features is enhanced, and the recognition accuracy is improved; the flight state does not need to be pre-classified, so that a classification error caused by a pre-classification error is avoided, and the accuracy of flight state recognition is further improved; and the method has the advantages of high speed, high precision and good robustness, and can accurately identify the flight state of the helicopter.

Description

technical field [0001] The invention belongs to the field of helicopter flight state recognition technology research, and in particular relates to a helicopter flight state recognition method based on a one-dimensional convolutional neural network. Background technique [0002] Helicopter is a special aircraft widely used in military, transportation, rescue and other fields. Due to the complex application occasions of helicopters (need to be used in plateaus, deserts, extreme cold and other harsh climates), and the flight missions are changeable, the moving parts on the helicopter are subjected to high-cycle vibration fatigue, which is the main cause of damage to the moving parts. The reason, and the damage degree of these structural components is closely related to the flight state of the helicopter. Therefore, it is of great significance to correctly identify the flight state for the fault diagnosis and life prediction of helicopter maneuvering parts and life parts. [0...

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 Applications(China)
IPC IPC(8): G06F17/10G06K9/62G06N3/04
CPCG06F17/10G06N3/045G06F18/214G06F18/241
Inventor 熊邦书张睿婷欧巧凤李新民
Owner NANCHANG HANGKONG UNIVERSITY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com