Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Photovoltaic cell panel inspection method based on deep learning

A photovoltaic panel and deep learning technology, applied in the field of power inspection and image processing, can solve the problems of unable to inspect the area of ​​photovoltaic panels, unable to provide guarantee for the stable operation of photovoltaic substations, and unable to obtain the real status of equipment in time, etc., to achieve Effects of suppressing background interference, solving inspections, and improving robustness and accuracy

Pending Publication Date: 2022-02-08
HUANENG NANJING JINLING POWER GENERATION
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problems in the prior art that when the photovoltaic cell panel is inspected, it is impossible to accurately and quickly inspect the target photovoltaic cell panel area, and it is impossible to obtain the real state of the equipment in time, and to find the faulty area and complete the maintenance task, so that it is impossible to provide guarantee for the stable operation of the entire photovoltaic substation, and a photovoltaic panel inspection method based on deep learning is proposed

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 cell panel inspection method based on deep learning
  • Photovoltaic cell panel inspection method based on deep learning
  • Photovoltaic cell panel inspection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046]The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

[0047] refer to Figure 1-3 , a photovoltaic panel inspection method based on deep learning, the steps are as follows:

[0048] Step 1: Prepare the network input data, use the drone to carry the imaging device to collect the image data set of the photovoltaic panel, including different damage types: damage, crack, cover, etc., all the image sizes are adjusted to eight 256pixel×256pixel, and then pass Labelme software labels the collected images with true value and outputs the labeled data set and the corresponding true value map;

[0049] Step 2: Enhance the data set by rotating, mirroring, scaling, and adjusting brightness to enrich the type and quantity of the data...

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 cell panel inspection method based on deep learning, and relates to the field of electric power inspection and image processing, and the method comprises the following steps: preparing network input data, and collecting an image data set of a photovoltaic cell panel through employing an imaging device carried by an unmanned plane; enhancing and expanding a training set and a test set through operations such as overturning, rotating, mirroring and brightness adjustment, and increasing the diversity of data; according to the invention, a detection algorithm of a photovoltaic cell panel defect area is designed through an improved Unet segmentation model, a network structure of an original Unet model is improved according to characteristics of image acquisition of an unmanned aerial vehicle and requirements of small area detection, a double-attention feature fusion module is introduced, proper network parameters such as an activation function are set, the feature extraction of tiny defects such as cracks is realized, background interference is inhibited, the robustness and accuracy of the network are improved, the problem of photovoltaic cell panel inspection can be effectively solved, and a guarantee is provided for the stable operation of a photovoltaic transformer substation.

Description

technical field [0001] The invention relates to the technical fields of electric power inspection and image processing, in particular to a method for inspection of photovoltaic panels based on deep learning. Background technique [0002] With the further aggravation of energy crisis and environmental pollution, people are gradually seeking new green energy to replace traditional fossil energy. As a renewable energy source, solar energy has the advantages of easy access, sustainable utilization, and environmental protection. At the same time, the photovoltaic industry and technology are also constantly progressing and developing, and various places have gradually begun to build photovoltaic power stations to utilize solar energy. There are a large number of solar panels distributed in these power stations, and each panel is one of the most important components in solar power generation. Its conversion rate and service life are important factors that determine whether the sol...

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): G06Q10/00G06Q50/06G06N3/04G06N3/08
CPCG06Q10/20G06Q50/06G06N3/08G06N3/048G06N3/045
Inventor 黄禹铭李永胜潘虹
Owner HUANENG NANJING JINLING POWER GENERATION
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
Eureka Blog
Learn More
PatSnap group products