Spraying feature extraction method and device based on neural network, and storage medium

A technology of feature extraction and neural network, applied in biological neural network models, neural architecture, image data processing, etc., can solve the problems of no unified method, no convenient tools, etc., and achieve the effect of accurate extraction, strong applicability, and close integration

Pending Publication Date: 2020-11-10
TONGJI UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Now for the extraction of spray features, there is no unified method and no convenient tool

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
  • Spraying feature extraction method and device based on neural network, and storage medium
  • Spraying feature extraction method and device based on neural network, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0039] A neural network-based spray feature extraction method of the present invention, its flow chart is as follows figure 1 Two steps are shown. The first step is to train the model. First obtain the spray image and the corresponding working condition information. In this example, the size of the spray image is 400*400, the image is a grayscale image, that is, the number of channels of the image is 1, and the working condition information is the pressure and temperature of the spray.

[0040] A new image matrix is ​​formed by compounding the spray image and the spray working condition information, and the compound method adopts image interpolation and expansion methods. In this example, the column is used as the insertion object. Combine pressure and temperature into one sequence. In this example, the pressure is 2 digits, and the temperature is 3 digits. Put the pressure in the front and the temperature in the back, and the combination is 5 digits. Since the size of th...

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 spraying feature extraction method and device based on a neural network, and a storage medium. The method comprises the steps of 1, training a convolutional neural network,2, reading a model, and inputting a spray image. The method specifically comprises the steps of: 1, acquiring a spray image, forming a new composite matrix by combining working condition information and the spray image, acquiring a spray feature label, and inputting the new image matrix and the label into a neural network to obtain a structure weight under a specific neural network; and 2, readingthe model in the step 1 to obtain a spray image, compounding the spray image and the working condition information into a new image matrix, and inputting the new composite spray image into the modelto obtain spray characteristics. The invention creatively provides the method for compounding the spray image and the working condition information into the new image matrix, the method well highlights the influence of the spray working condition on the spray, the feature extraction result is more closely related to the working condition, the credibility is high, and the error is small.

Description

technical field [0001] The invention relates to the field of spray and computer technology, in particular to a neural network-based spray feature extraction method, device and storage medium. Background technique [0002] Aerosolology has become an international research field. Because of its wide range of applications, it can be applied to spray combustion, cleaning sensors, cleaning glass, from rocket spray, car spray to spray in home life, the application of spray is far beyond people's imagination. Therefore, it is extremely important to study spray characteristics, which include spray area, spray penetration distance, spray cone angle, etc. [0003] Now for the extraction of spray features, there is no uniform method and no convenient tool. And rely on high-precision tools such as high-speed cameras, Malvern particle size observers, etc. So how to extract spray features conveniently and quickly is a big problem at present. Today's computer vision technology is boomi...

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): G06K9/46G06K9/62G06N3/04G06T3/40G06T7/00G06T7/60G06T7/62
CPCG06T3/4007G06T7/62G06T7/60G06T7/0004G06T2207/20081G06T2207/20084G06V10/40G06V10/56G06N3/045G06F18/214
Inventor 马玉霖张博文李治龙邓俊
Owner TONGJI 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