Photovoltaic power station unmanned aerial vehicle inspection method and system based on machine learning

A machine learning and unmanned aerial vehicle technology, applied in the field of unmanned aerial vehicles, can solve the problems of low efficiency and huge manpower investment, and achieve the effect of fast moving speed, reduced overall noise and fast speed

Pending Publication Date: 2020-08-11
GUIZHOU ELECTRIC POWER DESIGN INST
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing technology adopts the method of manual walking and visual inspection, which is inefficient, because in order to increase the sunlight receiving area of ​​photovoltaic power stations as much as possible, the area of ​​photovoltaic power stations is usually built very large, which requires investment Huge manpower can complete the inspection of all photovoltaic panels in the photovoltaic power station in time

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
  • Photovoltaic power station unmanned aerial vehicle inspection method and system based on machine learning
  • Photovoltaic power station unmanned aerial vehicle inspection method and system based on machine learning
  • Photovoltaic power station unmanned aerial vehicle inspection method and system based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Example 1: Reference figure 1 , a machine learning-based drone inspection method for photovoltaic power plants, including the following steps:

[0050] S02. Use a drone to take aerial photos of the photovoltaic power station area, and obtain aerial photos with and without debris on the surface of the photovoltaic panel, and then preprocess the aerial photos to obtain a training sample set;

[0051] S03, using a machine learning algorithm to generate a classification prediction model from the training samples;

[0052] S04. Classify the aerial pictures to be processed by using the classification prediction model;

[0053] S05. Judging whether the classification result of the aerial image to be processed meets the expectation, if it meets the expectation, enter step S07, otherwise enter step S06;

[0054] S06. Add the aerial pictures with incorrect classification results to the training sample set, and repeat steps S02 to S05;

[0055] S07. Outputting classification re...

Embodiment 2

[0083] Implementation Example 2: Reference figure 2 , a photovoltaic power plant UAV inspection system based on machine learning, including: an area division module, the area division module is used to divide the photovoltaic power plant area map into more than one area, each area is assigned a UAV , the area division module is a piece of computer code, which can divide the map into areas; the unmanned aerial vehicle is used to take aerial photos of the areas allocated by the area division module, and send the aerial pictures to the image preprocessing module, without The man-machine is connected with the data of the area division module, and the drone can sample the aerial photography drone produced by DJI and other companies; the picture preprocessing module, the picture preprocessing module receives the aerial pictures taken by the drone, and then converts the aerial pictures in the aerial pictures The photovoltaic panels are individually cut out to form a training sample ...

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 discloses a photovoltaic power station unmanned aerial vehicle inspection method based on machine learning, and the method comprises the following steps: S02, carrying out the aerial photography of a photovoltaic power station region through an unmanned aerial vehicle, obtaining an aerial photography pictures with impurities and without impurities on the upper surface of a photovoltaic panel through aerial photography, and preprocessing the aerial photography picture to obtain a training sample set; S03, generating a classification prediction model from the training sample by using a machine learning algorithm; S04, classifying aerial photography pictures to be processed by using the classification prediction model; S05, determining whether the classification result of the to-be-processed aerial photography pictures reaches the expectation or not, if so, entering the step S07, and otherwise, entering the step S06; S06, adding aerial photography pictures with wrong classification results into the training sample set, and repeating the steps S02 to S05; and S07, outputting a classification result. The problem of low inspection efficiency in the prior art is solved.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, in particular to a machine learning-based unmanned aerial vehicle inspection method and system for photovoltaic power plants. Background technique [0002] The photovoltaic panels of the photovoltaic power station are used to receive solar radiation and convert the solar radiation into electrical energy. Therefore, the photovoltaic panels of the photovoltaic power station are exposed. The exposed photovoltaic panels are often damaged by dust, leaves, bird droppings, branches and plastic bags. Falling on it blocks its sunlight and reduces the power generation efficiency of photovoltaic panels. In order to ensure that the efficiency of photovoltaic panels does not decrease, it is necessary to conduct regular inspections on the photovoltaic panels of the photovoltaic power station to find debris on the photovoltaic panels and facilitate timely cleaning. [0003] The existing techno...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/13G06V20/41G06V10/56G06F18/214
Inventor 李超李钟邹江张玉柱邓健罗婕莹李亚鹏王宏亮
Owner GUIZHOU ELECTRIC POWER DESIGN INST
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