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

Solar screen defect detection method based on double-flow CNN model

A technology of defect detection and solar energy, applied in the field of defect detection, can solve the problems of research shortage and high missed rate of defect detection

Pending Publication Date: 2021-09-07
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the shortage of machine vision research on solar screens and the high failure rate of traditional machine vision detection technology for defect detection, the present invention proposes a defect detection method based on deep learning

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
  • Solar screen defect detection method based on double-flow CNN model
  • Solar screen defect detection method based on double-flow CNN model
  • Solar screen defect detection method based on double-flow CNN model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] See attached Figure 1~2 , a solar screen defect detection method based on a dual-stream CNN deep convolutional neural network model, which detects defects on a solar screen with a detection area of ​​156mm×156mm, including the following steps:

[0032] Step 1. Initialize the system, adjust the light source, and adjust the camera to the starting position of shooting, and take pictures of the screen detection area in turn, and the camera collects images with a resolution of 8192×8192 each time.

[0033] Step 2. Segment the image collected by the camera in step 1, and divide the original image into several image blocks with a resolution of 224×224.

[0034] Step 3. Gaussian filtering is used to process the segmented image blocks to remove noise in the image and generate a defect training image data set.

[0035] Further, the specific operation of the Gaussian filter in the step 3 is: scan each pixel in the image block with a user-specified template, and use the weighted ...

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 solar screen defect detection method based on a double-flow CNN deep convolutional neural network model, and the method achieves the detection of solar screen defects through the steps of original image collection, image block segmentation, Gaussian filtering processing and training image data set generation, double-flow CNN model training and fine adjustment, feature extraction and defect detection. According to the method, the double-flow CNN deep convolutional neural network model is combined with machine vision defect detection, so that the accuracy and the working efficiency of solar screen defect detection are improved, the defect omission ratio is reduced, the production quality of the solar screen and a battery is ensured, and the production cost is reduced.

Description

technical field [0001] The invention belongs to the field of defect detection, and in particular relates to a method for detecting defects of a solar screen based on a deep convolutional neural network. Background technique [0002] In recent years, solar energy, as a clean and non-polluting renewable energy with huge reserves, has been widely used in industrial and agricultural production and daily life. Solar photovoltaic power generation refers to the power generation method that directly converts light energy into electrical energy without going through a thermal process. Photovoltaic power generation is one of the main ways to realize solar power generation, and solar cells are a key component of the photovoltaic power generation system. The mass production of solar cells mostly uses solar screens as molds, and its quality is an important factor affecting the photoelectric conversion efficiency and life of solar cells. [0003] At present, the defect detection of solar...

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
IPC IPC(8): G06T7/00G06T7/12G06T7/70G06T5/00G06N3/08G06N3/04
CPCG06T7/70G06T7/0004G06T7/12G06N3/084G06N3/045G06T5/70
Inventor 雷宇唐昆彭琳和金庆松龚湘东张明军毛聪胡永乐
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY