Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Common Aircraft Surface Material Recognition Method Based on Neural Network

A technology of neural network and identification method, which is applied in the field of identification of surface materials of aircraft commonly used in aerospace, can solve problems such as classification and identification difficulties, and achieve fast and accurate data processing, fast data processing speed, and simple analysis

Active Publication Date: 2019-08-23
BEIJING INST OF SPACECRAFT SYST ENG
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the difficulties in the classification and identification of commonly used aircraft surface materials, the present invention provides an effective identification method suitable for commonly used aircraft surface materials. Classification

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
  • Common Aircraft Surface Material Recognition Method Based on Neural Network
  • Common Aircraft Surface Material Recognition Method Based on Neural Network
  • Common Aircraft Surface Material Recognition Method Based on Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to illustrate the technical solution of the present invention more clearly, the present invention will be further described through specific examples below, but these examples are only for illustration, rather than limitation of the present invention.

[0044] parameter Figure 1 to Figure 3 , a neural network-based method for commonly used aircraft surface material identification, comprising the following steps:

[0045] Step 1: Use a near-infrared spectrometer to collect a large number of diffuse reflectance infrared spectra of various commonly used aircraft surface materials, and establish a basic database; the commonly used aircraft surface materials include: aluminum plates, steel plates, carbon fiber plates, monocrystalline silicon wafers, solar panels, etc.;

[0046] Step 2: preprocessing the spectrum collected in step 1,

[0047] 2.1) Remove background noise:

[0048]Utilize the near-infrared spectrometer to measure the infrared spectrum data of the a...

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 relates to a method for identifying common aircraft surface materials based on neural networks. The method comprises the following steps: step 1, collecting a large number of diffuse reflection infrared spectra of multiple common aircraft surface materials; step 2, pretreating the collected spectra; step 3, detecting the materials according to a traditional material detection method,and calibrating the infrared spectra of the corresponding materials to establish an infrared spectrum data and material matching model; step 4, classifying the infrared spectra of a database; and step 5, performing format conversion on the spectrum data, and performing deep learning and training on the database by utilizing a neural network to establish a neural network model. The neural networkis divided into an input layer and a competition layer, each neuron of the network competition layer acquires a response opportunity to an input mode through competition, and finally, only one neuronbecomes a winner. The method can analyze samples in an external field without sample preparation, and the average identification accuracy reaches 85% or more.

Description

technical field [0001] The invention belongs to the field of material identification, and in particular relates to a neural network-based identification method for the surface material of commonly used aerospace vehicles. Background technique [0002] Aircraft materials have a wide range and are divided into airframe materials (including structural materials and non-structural materials), engine materials and coatings, the most important of which are airframe structural materials and engine materials. Non-structural materials include: transparent materials, cabin facilities and decoration materials, accessories and piping materials for hydraulic, air-conditioning and other systems, radome and electromagnetic materials, tire materials, etc. The amount of non-structural materials is small but there are many varieties, including: glass, plastic, textiles, rubber, aluminum alloy, magnesium alloy, copper alloy and stainless steel. [0003] The first airplanes to fly people into ...

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): G01N21/3563G01N21/359
Inventor 贺东雷李怀峰
Owner BEIJING INST OF SPACECRAFT SYST ENG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products