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

Blower blade fault intelligent identification method based on deep learning

A deep learning and fan blade technology, applied in character and pattern recognition, computer components, image data processing, etc., can solve the problems of blade leading edge grinding, blade surface gel coat wear, and lightning protection index reduction, etc., to achieve reduction Small misjudgments and missed judgments, improve work efficiency, and reduce the effect of working procedures

Active Publication Date: 2018-08-17
NANJING ILUVATAR COREX TECH CO LTD (DBA ILUVATAR COREX INC NANJING)
View PDF11 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the blade is running at high speed, it will inevitably rub and collide with the dust and particles in the air, which will cause the leading edge of the blade to be ground, and the leading edge will be bonded and cracked, etc.
In addition, as the operating life of the fan increases, blisters and cracks will appear after the rubber coat on the surface of the blade wears and falls off.
On the one hand, trachoma will increase blade resistance and affect power generation; on the other hand, if it becomes through-cavity trachoma, there will be water accumulation, which will reduce the lightning protection index and make it vulnerable to lightning damage

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
  • Blower blade fault intelligent identification method based on deep learning
  • Blower blade fault intelligent identification method based on deep learning
  • Blower blade fault intelligent identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0053] refer to figure 1 As shown, in view of the defects of the prior art, the present invention provides a technology for automatically analyzing wind turbine video (for example, it may be taken by a drone). Due to the complexity of the fan background in some fan videos, it cannot be solved well with traditional image processing methods. Therefore, deep learning is used as the main technical route.

[0054] A kind of fan blade fault identification method based on deep learning of the present invention comprises the following steps:

[0055] S10, constructing a deep learning network model by using the marked fan video fault frames;

[0056] S20, divide the video of the fan to be detected into frames, and identify the picture of the fault frame;

[0057] S30, the compressed fault frame picture is input to the target detection network to obta...

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 belongs to the application of deep leaning in the technical field of computer vision, and discloses a blower blade fault intelligent identification method based on deep learning. Fault identification and location can be automatically performed on the blower video photographed by the unmanned aerial vehicle so that the labor cost can be saved and the working efficiency can be enhancedfor the work personnel. The method concretely comprises the following steps that: a deep learning network model is constructed by using the marked blower video frame; frame capture is performed on the blower video to be detected so as to identify the fault frame image; and the compressed fault frame image is inputted to the target detection network, and the fault area sample is acquired and further inputted to the deep learning regression network model so as to calculate the area of the blower blade fault area.

Description

technical field [0001] The invention belongs to the application of deep learning in the technical field of computer vision, and relates to an intelligent identification method for fan blade faults based on deep learning. Background technique [0002] Wind energy is a clean renewable resource with large reserves and wide distribution. Wind power is of great significance for alleviating energy supply, improving energy structure, and protecting the environment. In recent years, wind turbines have been widely installed and used in our country. Since wind turbines are usually located in the wild with harsh environmental conditions and are prone to failures, the operation and maintenance team of the power station needs to conduct regular inspections of wind turbines to ensure reliable operation of wind turbines and improve equipment availability. However, generators are mostly located in remote areas, and the arrangement is scattered. Manual inspection not only has problems such...

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): G06K9/00G06K9/62G06T7/62
CPCG06T7/62G06T2207/10016G06T2207/30232G06V20/49G06V20/52G06F18/23213G06F18/214G06F18/24
Inventor 李晶晶戴川吕艳洁郑欣胡大鹏陈班
Owner NANJING ILUVATAR COREX TECH CO LTD (DBA ILUVATAR COREX INC NANJING)
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