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

Fan blade defect intelligent detection method based on double-spectrum image

A technology for fan blades and intelligent detection, which is used in image enhancement, image analysis, image data processing, etc.

Pending Publication Date: 2020-09-22
航天图景(北京)科技有限公司
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention discloses an intelligent detection method for fan blade defects based on dual-spectral images. The present invention is based on the accumulation of a large number of blade damage defect data, and through big data technology, mining various types of damage in a large number of blade damage data The development law of defects, the construction of mathematical models, and finally combined with machine automatic learning technology to realize the prediction and evaluation of blade defects and health status

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
  • Fan blade defect intelligent detection method based on double-spectrum image
  • Fan blade defect intelligent detection method based on double-spectrum image
  • Fan blade defect intelligent detection method based on double-spectrum image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] This embodiment discloses as figure 1 A method for intelligent detection of fan blade defects based on bispectral images is shown, the method includes the following steps:

[0092] S1 marks the blade area of ​​the visible light image of the fan blade, and builds a deep learning image segmentation network model;

[0093] S2 segment the visible light image of the fan blade to be detected to realize the segmentation of the blade area;

[0094] S3 processes the infrared temperature data and synthesizes a high-contrast pseudo-color image of the temperature data;

[0095] S4 segmenting the infrared image by utilizing the corresponding relationship between the visible light image and the infrared image;

[0096] S5 randomly divides the segmented visible light image and infrared image into a test set and a training set;

[0097] S6 uses the marked fan blade defect image training set to extract the features of the visible light image and the infrared image through the CNN net...

Embodiment 2

[0172] In this example, refer to figure 2 As shown, aiming at the current situation of the industry, this embodiment provides a technology for automatically intelligently detecting defects of fan blades in a bispectral image. Due to the complex background of images collected by drones, traditional image processing methods are difficult to achieve good results. Therefore, this technology uses deep learning as the main technical route.

[0173] In this embodiment, the intelligent detection method for fan blade defects based on dual-spectrum images includes the following steps:

[0174] A: Construct a deep learning blade segmentation model using the labeled fan blade segmentation dataset

[0175] B: Segment the fan blade image to be segmented, and accurately segment the blade area

[0176] C: Carry out defect labeling on the segmented image, and use the network for feature extraction and feature fusion

[0177] D: Input the defect detection network to the image after feature ...

Embodiment 3

[0184]This embodiment is based on embodiment 2, and the training method to deep learning leaf segmentation model is:

[0185] The first step is to construct the image database by using the scientific ground image database establishment method to ensure the diversity, representativeness and comprehensiveness of the image sample database.

[0186] In the second step, professional data personnel mark the image and accurately mark the leaf area in the image. At the same time, in order to improve the generalization ability, the brightness, rotation, noise, cropping and other operations of the original visible light image and the mask image are simultaneously performed for data augmentation.

[0187] The third step is to build a target segmentation network and select a semantic segmentation network to achieve pixel-level semantic segmentation. The segmentation network consists of 11 convolutional layers and 3 pooling layers. Each convolutional layer is followed by a BN layer and 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 application of deep learning in the technical field of computer vision. The invention particularly relates to a fan blade defect intelligent detection method based on a double-spectrum image. According to the method, the image segmentation technology is utilized to realize segmentation of the blade area, background removal is realized, the identification efficiency and accuracy are improved, the infrared image and the visible light image are fused through the image processing technology, and then the deep learning technology is utilized to perform defect identificationon a large number of fan blade images. By accumulating a large amount of blade damage defect data and via techniques through big data, development rules of various damage defects in a large amount ofblade damage data are mined, a mathematical model is constructed, prediction and evaluation of the blade defects and the health state are finally achieved in combination with the machine automatic learning technology, the image processing technology and the double-light-source imaging technology are fused, the utilization rate of image information is effectively increased, and image feature information is obviously highlighted.

Description

technical field [0001] The invention relates to the application of deep learning in the technical field of computer vision, in particular to an intelligent detection method for fan blade defects based on bispectral images. Background technique [0002] With the emergence of the disadvantages of fossil energy, wind power and solar power have become the key renewable energy sources in my country. In recent years, with the country's increased support for wind power policies, the reduction of equipment and installation costs, and the maturing of supporting industries, a large number of wind power projects have been put into operation, and the wind power industry has achieved considerable development. At present, my country has become the largest country in the wind power industry in the world. With the release of a large number of wind turbines, the management of wind power operation and maintenance has increasingly attracted widespread attention in the industry. Due to the com...

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): G06T7/00G06T7/11G06T7/90G06K9/62
CPCG06T7/0002G06T7/11G06T7/90G06T2207/10048G06F18/2414G06F18/253
Inventor 刘金龙许素霞刘浪飞王永威
Owner 航天图景(北京)科技有限公司
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

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