Unlock instant, AI-driven research and patent intelligence for your innovation.

Convolutional neural network based inspection of blade-defects of a wind turbine

A technology of wind turbines, blades, applied in the field of computer program products, which can solve the problem of not being cost-effective, etc., to achieve the effect of cost-effectiveness, less time, and high accuracy

Pending Publication Date: 2021-03-16
SIEMENS GAMESA RENEWABLE ENERGY GMBH & CO KG +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a result, this analysis is not cost-effective

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
  • Convolutional neural network based inspection of blade-defects of a wind turbine
  • Convolutional neural network based inspection of blade-defects of a wind turbine
  • Convolutional neural network based inspection of blade-defects of a wind turbine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] To avoid time-consuming and cost-effective manual determination of blade defects of wind turbines, a method for automatic blade defect classification and localization in images is described below.

[0033] The method uses a supervised machine learning model that utilizes a fully convolutional neural network (CNN). Two steps of CNN for leaf detection and localization (corresponding to finding leaf contours) and background removal, so that leaf contours remain as the only image information in so-called modified images, and with contoured leaves and background removed Classification and localization of leaf defects in images. The steps of blade defect classification and localization can be done on a pixel level, which leads to a high accuracy of the determined blade defects.

[0034]In order to be able to perform a CNN, it is necessary to train it with suitable training data. For this purpose, multiple images are manually annotated with predefined object categories for t...

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

A computer-implemented method for determination of blade defects is automatically carried out by a computing system (CS). In step S1), an image (01) of a wind turbine containing at least a part of oneor more blades of the wind turbine is received by an interface (IF) of the computer system (CS). The image has a given original number of pixels in height and width. A step S2) basically consists oftwo consecutive steps S2a) and S2b) which are executed by a processing unit (PU)of the computer system (CS). In step S2a), the image (01) is analyzed to determine an outline of the blades in the image. In step S2b) a modified image (AI) is created from the analyzed image (01) containing image information of the blades only. Finally, step S3) consists of analyzing, by the processing unit (PU), themodified image (AI) to determine a blade defect (BD) and / or a blade defect type (BDT) of the blades. As a result, the blade defects (BD) and / or blade defect types (BDT) are output by the processing unit (PU).

Description

technical field [0001] The present invention relates to a method and system and a computer program product for computer-implemented determination of blade defects of a wind turbine. In particular, the invention relates to visual inspection of blades of wind turbines. Background technique [0002] During periods of use, damage to the rotor blades (short: blades) of a wind turbine, such as corrosion, can occur. To find such blade defects, numerous high-resolution images are taken, for example by drones. So far, classification and localization of blade defects in these images has been done manually by an annotator who visually analyzes the images one by one. Annotators identify and mark the location of defects in the image. The information so collected is stored in a database. [0003] The main disadvantage of manually inspecting multiple images is that detection accuracy is sometimes poor. In addition, the time required for visual inspection is very long. This can take u...

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): G06T7/00F03D17/00F03D80/50
CPCF05B2260/80F03D17/00F03D80/50G06T7/0004G06T2207/20084G06T2207/30164Y02E10/72
Inventor M·巴赫-安德森P·杜德菲尔德S·亚先科
Owner SIEMENS GAMESA RENEWABLE ENERGY GMBH & CO KG
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com