Accelerating degradation model for photovoltaic component constructed on basis of deep learning method and forecasting method for service life of photovoltaic component

A photovoltaic module and accelerated degradation technology, applied in the direction of neural learning methods, biological neural network models, informatics, etc., can solve the problems of many stress factors and difficulties in the performance degradation of photovoltaic modules, and the difficulty of clarifying the functional relationship

Active Publication Date: 2017-03-15
GUANGDONG TESTING INST OF PROD QUALITY SUPERVISION
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Traditional acceleration models are mostly built using empirical data statistics and physical analysis, such as Arrhenius model (temperature stress), Eyring model (temperature stress), inverse power law model (electrical stress), etc., while photovoltaic module performance degradation stress factors are more (temperature T , humidity H, light radiation Ra, etc.), the application time is short, and the structure is relatively complex (integration of semiconductor electronics, polymer materials,

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
  • Accelerating degradation model for photovoltaic component constructed on basis of deep learning method and forecasting method for service life of photovoltaic component
  • Accelerating degradation model for photovoltaic component constructed on basis of deep learning method and forecasting method for service life of photovoltaic component
  • Accelerating degradation model for photovoltaic component constructed on basis of deep learning method and forecasting method for service life of photovoltaic component

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] The accelerated degradation model of photovoltaic modules based on the deep learning method and the life prediction method of photovoltaic modules provided in this embodiment include the following steps:

[0042] (1) Acquisition of initial data: Select photovoltaic modules, set and establish accelerated degradation model with different accelerated stress level combinations S i(i=1,2,3….n, representing different accelerated stress combinations), S i including temperature T i , Humidity H i and light radiation Ra i , conduct accelerated degradation experiments to obtain the output power P of photovoltaic modules under accelerated degradation conditions di , according to the output power P di Obtain the pseudo-failure life, and obtain the pseudo-failure life distribution quantile function Q according to the pseudo-failure life i (p), the different accelerated stress conditions S i , Pseudo-failure life distribution quantile function Q i (p) as initial data;

[0043...

Embodiment 2

[0059] The accelerated degradation model of photovoltaic modules based on the deep learning method and the life prediction method of photovoltaic modules provided in this embodiment include the following steps:

[0060] (1) Acquisition of initial data: Select photovoltaic modules, set and establish accelerated degradation model with different accelerated stress level combinations S i , S i including temperature T i , Humidity H i and light radiation Ra i , conduct accelerated degradation experiments, obtain the output power of photovoltaic modules under accelerated degradation conditions, and obtain the pseudo-failure life distribution quantile function Q according to the output power i (p), the different accelerated stress conditions S i , Pseudo-failure life distribution quantile function Q i (p) as initial data;

[0061] The specific process is as follows:

[0062] 1.1. Accelerated degradation test

[0063] The accelerated degradation test system used to obtain perf...

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 an accelerating degradation model for a photovoltaic component constructed on the basis of a deep learning method and a forecasting method for the service life of the photovoltaic component. The method comprises the following steps: constructing a DNN (Deep Neural Network) through an RBM (Restricted Boltzmann Machine); taking different acceleration stress conditions (Ti, Hi and Rai) and a corresponding false failure service life distribution quantile function Qi(p) as input vectors; training RBM and DNN by utilizing a CD quick learning algorithm; searching for an optimal model parameter set theta*; and constructing the accelerating degradation model for the photovoltaic component, thereby forecasting the expected service life of the photovoltaic component under a normal stress condition.

Description

technical field [0001] The present invention relates to the life prediction of photovoltaic components, specifically, a photovoltaic component accelerated degradation model and a photovoltaic component life prediction method constructed based on a deep learning method. Background technique [0002] Traditional acceleration models are mostly built using empirical data statistics and physical analysis, such as Arrhenius model (temperature stress), Eyring model (temperature stress), inverse power law model (electrical stress), etc., while photovoltaic module performance degradation stress factors are more (temperature T , humidity H, light radiation Ra, etc.), the application time is short, and the structure is relatively complex (integration of semiconductor electronics, polymer materials, electrical design, etc.), the failure mechanism of various stresses is inconsistent, and the relationship between accelerated stress and product life is directly established Some definite fu...

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): G06F19/00G06N3/08
CPCG06N3/082G06N3/088G16Z99/00Y04S10/50
Inventor 余荣斌刘桂雄徐欢
Owner GUANGDONG TESTING INST OF PROD QUALITY SUPERVISION
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