Photovoltaic array fault diagnosis method based on statistical modeling

A technique for photovoltaic arrays, statistical modeling

Pending Publication Date: 2022-03-18
CHINA THREE GORGES CORPORATION +1
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the technical problems that the matching degree of the existing diagnosis method is low, and there is often a large gap between the parameter model and the actual physical model, the present invention provides a photovoltaic array fault diagnosis method based on statistical modeling. The output data is subjected to non-parametric statistical fitting to establish a probability distribution model, so as to solve the problem of inaccurate output model under uncertain conditions, and apply it to fault diagnosis

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 array fault diagnosis method based on statistical modeling
  • Photovoltaic array fault diagnosis method based on statistical modeling
  • Photovoltaic array fault diagnosis method based on statistical modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 As shown, the present invention provides a photovoltaic array fault diagnosis method based on statistical modeling. First, collect historical operating data and historical environmental data of photovoltaic power plants, clean the historical data, and establish state indicators; then establish the probability of the three state indicators Density distribution model; then obtain the upper and lower bounds of the state index under a certain confidence level, and calculate the threshold value of the electrical parameter in real-time operation; finally compare the actual operating current, voltage, power data with the threshold value, and perform fault diagnosis combined with the diagnosis process.

[0065] The data in this example comes from a photovoltaic power station with an installed capacity of 40MW. Each array is composed of 16 branches connected in parallel, and each branch is composed of 16 components connected in series. The system collects data ev...

Embodiment 2

[0079] This embodiment provides a photovoltaic array fault diagnosis method. The difference from Embodiment 1 is that the probability density estimation process does not use the non-parametric kernel density estimation method, but uses three common parameter estimation methods, namely the normal distribution, logistic distribution, t-distribution.

[0080] Also adopt the data in the power station described in embodiment 1 to carry out model training, use the parameter estimation method to obtain the probability density curve of the state index, set the confidence level to 95%, and use the four kinds of fault data obtained in embodiment 1 to detect, Table 2 shows the results of these three estimation methods.

[0081]

[0082]

[0083] Table 2. Diagnosis results obtained by parameter estimation method

[0084] Table 2 shows that no matter what kind of fault, the sample recognition rate of voltage is higher than 97%, which increases the diagnosis rate to a certain extent....

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 method for analyzing and diagnosing a photovoltaic array fault based on statistical modeling, which comprises the following steps of: firstly, establishing state indexes of current, voltage and power from the perspective of statistics, and secondly, establishing a probability density distribution model of the state indexes by using a kernel density estimation method, then, confidence is set, a confidence interval is obtained, the threshold range of real-time operation data is determined, and finally, the real-time state is judged through a fault diagnosis process. Starting from the outdoor operation data of the array, the problem that the photovoltaic output model is inaccurate under the uncertain condition can be effectively solved, and the proposed fault diagnosis method can flexibly adjust the threshold interval according to the human needs, and has great field engineering application value.

Description

technical field [0001] The invention belongs to the technical field of photovoltaic power generation, and in particular relates to a photovoltaic array fault diagnosis method based on a statistical modeling algorithm. Background technique [0002] In recent years, as climate change has brought warning signs to human beings, governments of various countries have been thinking about how to save energy and reduce emissions. Despite the economic slowdown caused by COVID-19, the world added more than 126GW of PV installations in 2020, an increase of 21.8% over 2019. At present, most manufacturers guarantee that the life of photovoltaic modules is at least 20 years under the condition that the maximum loss does not exceed 20% of the rated power. However, photovoltaic power plants are often installed in harsh environments such as mountains and deserts, and are exposed to the open air all year round, resulting in performance degradation and frequent failures. Therefore, maintenance...

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): G06F16/215G06F30/20G06Q50/06
CPCG06F30/20G06F16/215G06Q50/06Y04S10/50
Inventor 苏营朱红路邹祖冰潘晶娜吴海飞孙爽张险峰汤维贵孙长平
Owner CHINA THREE GORGES CORPORATION
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