Solar cell defect detection method based on convolutional neural network multi-feature fusion

A convolutional neural network, multi-feature fusion technology, applied in neural learning methods, biological neural network models, neural architectures, etc., to achieve high confidence values, improve accuracy, and reduce error rates.

Active Publication Date: 2020-10-13
TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies of the existing technology and solve the technical problem of network adaptability to various types of defects on the surface of solar panels, the present invention provides a solar cell defect detection method based on convolutional neural network multi-feature fusion

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 cell defect detection method based on convolutional neural network multi-feature fusion
  • Solar cell defect detection method based on convolutional neural network multi-feature fusion
  • Solar cell defect detection method based on convolutional neural network multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention. Unless otherwise specified, the examples are all in accordance with conventional experimental conditions. In addition, for those skilled in the art, on the premise of not departing from the spirit and scope of the present invention, various modifications or improvements to the material components and dosage in these embodiments all belong to the protection scope of the present invention.

[0036] Such as figure 1 The shown solar panel defect detection method based on convolutional neural network multi-feature fusion includes the following steps:

[0037] S1. Input a solar panel surface image of any size;

[0038] S2. A convolutional block for feature extraction is composed of a convolutional layer, an activation function, and a pooling layer. Five convolutional blocks are set in sequence in the order of image processing, and the featur...

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 cell defect detection method based on convolutional neural network multi-feature fusion. The invention belongs to the technical field of solar cell surface defect detection, solving the technical problem of adaptability of a network to various defect types on the surface of a solar cell panel. The solar cell defect detection method introduces the idea of cross-layerconnection on the basis of a Faster R-CNN convolutional neural network structure, so as to learn shallow layer information while learning deep layer characteristic information, thus reducing the error rate effectively, extracts the target candidate box in a multi-scale mode, and selects the proper box as the candidate box through fusion in a certain proportion, so that the omission ratio is reduced to a certain degree, and the multi-scale feature fusion layer is additionally arranged so that the method can be effectively suitable for detecting the surface defects of the solar cell panel. Aiming at the long, narrow and fine characteristics of the surface defects of the solar cell panel, various aspect ratios and scales are used, so that the solar cell panel is more suitable for defect types, and the accuracy of a prediction box can be improved, and the target detection accuracy and defect position detection can be effectively improved, and a higher confidence coefficient value is achieved.

Description

technical field [0001] The invention belongs to the technical field of solar cell surface defect detection, and in particular relates to a solar cell panel defect detection method based on convolutional neural network multi-feature fusion. Background technique [0002] In recent years, human activities have become more and more dependent on energy, and the environmental problems caused by the excessive use and massive consumption of non-renewable energy such as petroleum have intensified. Solar photovoltaic power generation technology is a typical representative of new energy technology. The wide application of this technology can well alleviate the current energy problems. Therefore, the exploitation and effective utilization of solar energy has become an important development trend in the future. Solar energy comes from sunlight, which is a green energy that is safe, reliable, clean, free from geographical restrictions, does not require fuel consumption, and has high energ...

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): G06T7/00G06N3/04G06N3/08G01N21/88
CPCG06T7/0004G06N3/08G01N21/8851G06T2207/10004G06T2207/20081G06T2207/20104G06T2207/20221G06T2207/30108G01N2021/8854G01N2021/8887G06N3/045Y02E10/50
Inventor 上官宏宁爱平郝雅雯张雄王安红彭司春侯婷
Owner TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
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