CN109842372A - A kind of photovoltaic module fault detection method and system - Google Patents
A kind of photovoltaic module fault detection method and system Download PDFInfo
- Publication number
- CN109842372A CN109842372A CN201711217190.2A CN201711217190A CN109842372A CN 109842372 A CN109842372 A CN 109842372A CN 201711217190 A CN201711217190 A CN 201711217190A CN 109842372 A CN109842372 A CN 109842372A
- Authority
- CN
- China
- Prior art keywords
- sample
- fault detection
- photovoltaic module
- power point
- maximum power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Abstract
The present invention provides a kind of photovoltaic module fault detection method and systems, comprising: by the fault detection function constructed in advance, the residual error and historical data sample for comparing photovoltaic module sample to be tested concentrate whether the difference of sample average is more than the threshold value for allowing to occur error；If being more than, photovoltaic module breaks down；Otherwise photovoltaic module normal operation；Wherein, the sample standard deviation that historical data sample is concentrated includes the historical data under operating normally, and historical data includes short circuit current, open-circuit voltage, maximum power point electric current and maximum power point voltage；Fault detection function is built by being fitted the relational expression of maximum power point voltage and history short circuit current, history open-circuit voltage and history maximum power point.This method and system can realize the fault detection of photovoltaic module by electric current and voltage change, under a small amount of sample conditions, have higher diagnostic reliability compared with Artificial Neural Network.
Description
Technical field
The invention belongs to field of new energy generation, and in particular to a kind of photovoltaic module fault detection method and system.
Background technique
Luminous energy is directly become direct current energy by photovoltaic module, is one of core component of photovoltaic generating system.Theoretical glazing
The service life about 20-25 of component is lied prostrate, but photovoltaic module is influenced, unavoidably for a long time in outside work by use environment
All kinds of failures such as aging, damage can occur for ground.These failures gently then influence the generating efficiency of system, heavy then to cause fire etc. great
Disaster.Therefore timely fault detection is carried out to photovoltaic module, has for the stable and high effective operation of photovoltaic generating system important
Meaning.
Mainly there are FUSION WITH MULTISENSOR DETECTION method, tim e- domain detection method and infrared figure for the method for diagnosing faults of photovoltaic module at present
As analytic approach etc., but mostly in theoretical or simulation stage, while needing to add a large amount of additional sensors and camera etc. and setting
It is standby, higher cost.Therefore, the method analyzed based on artificial intelligence and I-V curve is gradually paid attention to.And it is limited by artificial neuron
For network using empirical risk minimization as the theory of algorithm of Optimality Criteria basis, such method requires large sample in learning process
Amount, while being also easily trapped into Local Minimum problem.When learning to a small amount of photovoltaic module data, the algorithm performance is unstable
It is fixed, need to carry out reliability of the multiple operation to ensure result.
Summary of the invention
To overcome above-mentioned the deficiencies in the prior art, the present invention proposes a kind of photovoltaic module fault detection method and system.
Realize solution used by above-mentioned purpose are as follows:
A kind of photovoltaic module fault detection method, thes improvement is that:
By the fault detection function constructed in advance, compare the residual error and historical data sample collection of photovoltaic module sample to be tested
Whether the difference of middle sample average is more than the threshold value for allowing to occur error；
If being more than, photovoltaic module breaks down；Otherwise photovoltaic module normal operation；
The sample standard deviation that the historical data sample is concentrated includes the historical data under operating normally, and the historical data includes
Short circuit current, open-circuit voltage, maximum power point electric current and maximum power point voltage；The fault detection function passes through described in fitting
The relational expression of maximum power point voltage and history short circuit current, history open-circuit voltage and history maximum power point is built.
First optimal technical scheme provided by the invention, it is improved in that the fault detection function passes through fitting
The relational expression of the history maximum power point voltage and history short circuit current, history open-circuit voltage and history maximum power point carries out
Building, comprising:
By the historical data under operating normally, multi-group data sample is formed；
The corresponding residual values of every group of data sample are calculated according to the relational expression；
The threshold value for allowing that error occurs is calculated according to the residual values；
Fault detection function is generated according to the threshold value.
Second optimal technical scheme provided by the invention, it is improved in that the history by under operating normally
Data form multi-group data sample, comprising:
Short circuit current I under the conditions of acquiring different illumination conditions and temperature respectively, when photovoltaic module operates normallySC, open circuit
Voltage UOC, maximum power point electric current ImWith maximum power point voltage Um, every group of data vector [ISC,UOC,Im,Um] indicate.
Third optimal technical scheme provided by the invention, it is improved in that the fitting maximum power point electricity
It presses and includes: with the relational expression of history short circuit current, history open-circuit voltage and history maximum power point
I is fitted using Least square support vector regression methodSC、UOC、ImAnd UmBetween relational expression:
Um'=f (ISC,UOC,Im) (1)
Wherein, Um' it is UmFunction prediction value.
4th optimal technical scheme provided by the invention, it is improved in that described calculate every group of number according to relational expression
Include: according to the corresponding residual values of sample
The corresponding residual values of data as described in calculating following formula
G (i)=Um’(i)-Um(i)=f (ISC(i),UOC(i),Im(i))-Um(i) (2)
The corresponding residual values g (i) of data described in each group is successively calculated, data set is obtained
Wherein g (i) indicates the corresponding residual values of i-th group of data, and i=1,2 ..., k are the serial number of data group, and k is data
The number of group, Um' the function prediction value of (i) for i-th group of data, UmIt (i) is the actual value of this group of data.
5th optimal technical scheme provided by the invention, it is improved in that described calculated according to the residual values is permitted
Perhaps the threshold value of generation error includes:
As following formula calculates the threshold epsilon for allowing that error occurs:
Wherein μ isThe average value of middle element, σ areStandard deviation.
6th optimal technical scheme provided by the invention, it is improved in that described generate failure according to the threshold value
Detection function includes:
As following formula generates fault detection function:
F (g)=sgn (| g (i) |-ε-μ) (5)
Wherein sgn () is the number of taking function.
7th optimal technical scheme provided by the invention, it is improved in that the failure by constructing in advance is examined
Function is surveyed, the residual error and historical data sample for comparing photovoltaic module sample to be tested concentrate whether the difference of sample average is more than threshold value,
Include:
Photovoltaic module sample to be tested { I will be acquiredSC,UOC,Im,Um}testIt substitutes into formula (1), obtains maximum power point voltage
Function prediction value Um’test；According to formula (2), residual values g is calculatedtest；Use gtestReplace the g in fault detection function f (g)
(i), judge whether photovoltaic module breaks down according to f (g) output valve；When | gtestWhen |≤μ+ε, f (g)≤0, then according to failure
Detection function output valve determines photovoltaic module normal operation；When | gtest| when > μ+ε, f (g)=1, then according to fault detection function
Output valve determines that photovoltaic module breaks down；
Wherein, { ISC,UOC,Im,Um}testIn ISC、UOC、ImAnd UmSuccessively respectively indicate the short of the photovoltaic module to be measured
Road electric current, open-circuit voltage, maximum power point electric current and maximum power point voltage.
A kind of photovoltaic module fault detection system, it is improved in that including comparison module and judgment module；
The comparison module is used to compare the residual error of photovoltaic module sample to be tested by the fault detection function constructed in advance
And historical data sample concentrates whether the difference of sample average is more than the threshold value for allowing to occur error；
If the judgment module is for being more than to judge that photovoltaic module breaks down；Otherwise judge photovoltaic module operation just
Often；
The sample standard deviation that the historical data sample is concentrated includes the historical data under operating normally, and the historical data includes
Short circuit current, open-circuit voltage, maximum power point electric current and maximum power point voltage；The fault detection function passes through described in fitting
The relational expression of maximum power point voltage and history short circuit current, history open-circuit voltage and history maximum power point is built.
8th optimal technical scheme provided by the invention, it is improved in that further include: fault detection function constructs mould
Block；
The fault detection function building module includes: that sample forms subelement, residual computations subelement, threshold calculations
Unit and function generate subelement；
The sample forms subelement and is used to form multi-group data sample by the historical data under operating normally；
The residual computations subelement is used to calculate the corresponding residual values of every group of data sample according to the relational expression；
The threshold calculations subelement is used to calculate the threshold value for allowing that error occurs according to the residual values；
The function generates subelement and is used to generate fault detection function according to the threshold value.
Compared with the immediate prior art, the device have the advantages that as follows:
1. the present invention can realize the fault detection of photovoltaic module by electric current and voltage change.
2. having higher diagnostic reliability compared with Artificial Neural Network under a small amount of sample conditions.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of photovoltaic module fault detection method provided by the invention；
Fig. 2 is a kind of schematic illustration of photovoltaic module fault detection method provided by the invention；
Fig. 3 is sample residual distribution schematic diagram in a kind of photovoltaic module fault detection method provided by the invention.
Specific embodiment
The present invention fits each parameter of photovoltaic module at runtime by Least square support vector regression LS-SVR method
The functional relation of satisfaction calculates the ideal output of photovoltaic module under prescribed conditions by function, passes through the ideal output of comparison
And reality output, judge whether photovoltaic module breaks down.A specific embodiment of the invention is done into one with reference to the accompanying drawing
The detailed description of step.
A kind of flow diagram of photovoltaic module fault detection method provided by the invention is as shown in Figure 1, comprising:
By the fault detection function constructed in advance, compare the residual error and historical data sample collection of photovoltaic module sample to be tested
Whether the difference of middle sample average is more than the threshold value for allowing to occur error；
If being more than, photovoltaic module breaks down；Otherwise photovoltaic module normal operation；
Wherein, the sample standard deviation that historical data sample is concentrated includes the historical data under operating normally, and historical data includes short
Road electric current, open-circuit voltage, maximum power point electric current and maximum power point voltage；Fault detection function passes through fitting maximum power point
The relational expression of voltage and history short circuit current, history open-circuit voltage and history maximum power point is built.
The schematic illustration of photovoltaic module fault detection method provided by the invention a kind of is as shown in Fig. 2, solid line portion in Fig. 2
Divide the building process of representing fault detection function, dotted portion representative diagnoses sample to be tested using fault detection function
Process.
This method specifically includes:
1, the short circuit current I under the conditions of acquiring different illumination conditions and temperature respectively, when photovoltaic module failure-free operationSC、
Open-circuit voltage UOC, maximum power point electric current ImWith maximum power point voltage Um, every group of sample vector [ISC,UOC,Im,Um] table
Show.
2, I is fitted using LS-SVR methodSC、UOC、ImAnd UmBetween relational expression:
Um'=f (ISC,UOC,Im) (1)
Wherein, Um' it is UmFunction prediction value.When Function Approximation Algorithm is had excellent performance, sample under non-failure conditions,
Function prediction value Um' usually surround UmActual sample value small range up and down fluctuate.LS-SVR specific method is the prior art, this
Invention does not elaborate.
3, the corresponding residual values g (i) of each group sample is calculated, data set is obtained
G (i)=Um’(i)-Um(i)=f (ISC(i),UOC(i),Im(i))-Um(i) (2)
Wherein i=1,2 ..., k, are the serial number of sample group, and k is the number of sample group, Um' (i) be i-th group of sample letter
Number output valve, UmIt (i) is the actual value of this group of sample.
4, it sets element in G and meets normal distribution N (μ, σ2), using 3Sigma principle in traditional statistics, providing allows to send out
The calculation method of the threshold epsilon of raw error:
Wherein μ isThe average value of middle element, σ areStandard deviation；According to 3Sigma principle, when
When sample normal distribution, when measured value is greater than 3 σ at a distance from mean value, it can determine that the tested sample is abnormal.Therefore data setMiddle element should be distributed as shown in figure 3, the residual error of normal sample and sample average should be without departing from threshold epsilon.
5, fault detection function is generated:
F (g)=sgn (| g (i) |-ε-μ) (5)
The present invention provides shown in fault detection function such as formula (5), and wherein sgn () is the number of taking function.
6, sample to be tested is tested:
Given sample to be tested { ISC,UOC,Im,Um}test, by { ISC,UOC,Im,}testSubstitution formula formula (1), acquires Um’test,
Then residual error g is calculated according to formula (2)test；Use gtestThe g (i) in fault detection function f (g) is replaced, according to detection function
Output valve judges whether photovoltaic module breaks down, when | gtestWhen |≤μ+ε, f≤0, fault detection function determines the photovoltaic
Assembly operating is normal；When | g | when > μ+ε, f=1, fault detection function determines component failure.Wherein, { ISC,UOC,Im,
Um}testIn ISC、UOC、ImAnd UmSuccessively respectively indicate short circuit current, the open-circuit voltage, maximum power of the photovoltaic module to be measured
Point electric current and maximum power point voltage.
Based on the same inventive concept, the present invention also provides a kind of photovoltaic module fault detections into system, since these set
The standby principle for solving technical problem is similar to photovoltaic module fault detection method, and overlaps will not be repeated.
The system includes: comparison module and judgment module；
Wherein, comparison module is used to compare the residual of photovoltaic module sample to be tested by the fault detection function constructed in advance
Difference and historical data sample concentrate whether the difference of sample average is more than the threshold value for allowing to occur error；
If fault detection module is for being more than to judge that photovoltaic module breaks down；Otherwise judge photovoltaic module operation just
Often；
Wherein, the sample standard deviation that historical data sample is concentrated includes the historical data under operating normally, and historical data includes short
Road electric current, open-circuit voltage, maximum power point electric current and maximum power point voltage；Fault detection function passes through fitting maximum power point
The relational expression of voltage and history short circuit current, history open-circuit voltage and history maximum power point is built.
Wherein, system further include: fault detection function constructs module；
Fault detection function building module includes: that sample forms subelement, residual computations subelement, threshold calculations subelement
Subelement is generated with function；
Sample forms subelement and is used to form multi-group data sample by the historical data under operating normally；
Residual computations subelement is used to calculate the corresponding residual values of every group of data sample according to relational expression；
Threshold calculations subelement is used to calculate the threshold value for allowing that error occurs according to residual values；
Function generates subelement and is used to generate fault detection function according to the threshold value.
Finally it should be noted that: above embodiments are merely to illustrate the technical solution of the application rather than to its protection scopes
Limitation, although the application is described in detail referring to above-described embodiment, those of ordinary skill in the art should
Understand: those skilled in the art read the specific embodiment of application can still be carried out after the application various changes, modification or
Person's equivalent replacement, but these changes, modification or equivalent replacement, are applying within pending claims.
Claims (10)
1. a kind of photovoltaic module fault detection method, it is characterised in that:
By the fault detection function constructed in advance, the residual error and historical data sample for comparing photovoltaic module sample to be tested concentrate sample
Whether the difference of this mean value is more than the threshold value for allowing to occur error；
If being more than, photovoltaic module breaks down；Otherwise photovoltaic module normal operation；
The sample standard deviation that the historical data sample is concentrated includes the historical data under operating normally, and the historical data includes short circuit
Electric current, open-circuit voltage, maximum power point electric current and maximum power point voltage；The fault detection function is by being fitted the maximum
The relational expression of power point voltage and history short circuit current, history open-circuit voltage and history maximum power point is built.
2. the method as described in claim 1, it is characterised in that: the fault detection function is by being fitted the history maximum work
Rate point voltage and the relational expression of history short circuit current, history open-circuit voltage and history maximum power point are constructed, comprising:
By the historical data under operating normally, multi-group data sample is formed；
The corresponding residual values of every group of data sample are calculated according to the relational expression；
The threshold value for allowing that error occurs is calculated according to the residual values；
Fault detection function is generated according to the threshold value.
3. method according to claim 2, which is characterized in that the historical data by under operating normally forms multiple groups
Data sample, comprising:
Short circuit current I under the conditions of acquiring different illumination conditions and temperature respectively, when photovoltaic module operates normallySC, open-circuit voltage
UOC, maximum power point electric current ImWith maximum power point voltage Um, every group of data vector [ISC,UOC,Im,Um] indicate.
4. method as claimed in claim 3, which is characterized in that the fitting maximum power point voltage and history short circuit electricity
Stream, history open-circuit voltage and history maximum power point relational expression include:
I is fitted using Least square support vector regression methodSC、UOC、ImAnd UmBetween relational expression:
Um'=f (ISC,UOC,Im) (1)
Wherein, Um' it is UmFunction prediction value.
5. method as claimed in claim 4, which is characterized in that described corresponding residual according to relational expression every group of data sample of calculating
Difference includes:
The corresponding residual values of data as described in calculating following formula
G (i)=Um’(i)-Um(i)=f (ISC(i),UOC(i),Im(i))-Um(i) (2)
The corresponding residual values g (i) of data described in each group is successively calculated, data set is obtained
Wherein g (i) indicates the corresponding residual values of i-th group of data, and i=1,2 ..., k are the serial number of data group, and k is data group
Number, Um' the function prediction value of (i) for i-th group of data, UmIt (i) is the actual value of this group of data.
6. method as claimed in claim 5, which is characterized in that described to calculate the threshold for allowing that error occurs according to the residual values
Value includes:
As following formula calculates the threshold epsilon for allowing that error occurs:
Wherein μ isThe average value of middle element, σ areStandard deviation.
7. method as claimed in claim 6, which is characterized in that described to include: according to threshold value generation fault detection function
As following formula generates fault detection function:
F (g)=sgn (| g (i) |-ε-μ) (5)
Wherein sgn () is the number of taking function.
8. the method for claim 7, which is characterized in that the fault detection function by constructing in advance compares light
The residual error and historical data sample for lying prostrate component sample to be tested concentrate whether the difference of sample average is more than threshold value, comprising:
By the photovoltaic module sample to be tested { I of acquisitionSC,UOC,Im,Um}testIt substitutes into formula (1), obtains the letter of maximum power point voltage
Number predicted value Um’test；According to formula (2), residual values g is calculatedtest；
Use gtestReplace the g (i) in fault detection function f (g)；
When | gtestWhen |≤μ+ε, f (g)≤0 then determines photovoltaic module normal operation according to fault detection function-output；When |
gtest| when > μ+ε, f (g)=1 then determines that photovoltaic module breaks down according to fault detection function-output；
Wherein, { ISC,UOC,Im,Um}testIn ISC、UOC、ImAnd UmSuccessively respectively indicate the short circuit electricity of the photovoltaic module to be measured
Stream, open-circuit voltage, maximum power point electric current and maximum power point voltage.
9. a kind of photovoltaic module fault detection system, which is characterized in that including comparison module and judgment module；
The comparison module is used to compare by the fault detection function that constructs the residual error of photovoltaic module sample to be tested in advance and goes through
History data sample concentrates whether the difference of sample average is more than the threshold value for allowing to occur error；
If the judgment module is for being more than to judge that photovoltaic module breaks down；Otherwise judge photovoltaic module normal operation；
The sample standard deviation that the historical data sample is concentrated includes the historical data under operating normally, and the historical data includes short circuit
Electric current, open-circuit voltage, maximum power point electric current and maximum power point voltage；The fault detection function is by being fitted the maximum
The relational expression of power point voltage and history short circuit current, history open-circuit voltage and history maximum power point is built.
10. system as claimed in claim 9, which is characterized in that further include: fault detection function constructs module；
The fault detection function building module includes: that sample forms subelement, residual computations subelement, threshold calculations subelement
Subelement is generated with function；
The sample forms subelement and is used to form multi-group data sample by the historical data under operating normally；
The residual computations subelement is used to calculate the corresponding residual values of every group of data sample according to the relational expression；
The threshold calculations subelement is used to calculate the threshold value for allowing that error occurs according to the residual values；
The function generates subelement and is used to generate fault detection function according to the threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711217190.2A CN109842372A (en) | 2017-11-28 | 2017-11-28 | A kind of photovoltaic module fault detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711217190.2A CN109842372A (en) | 2017-11-28 | 2017-11-28 | A kind of photovoltaic module fault detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109842372A true CN109842372A (en) | 2019-06-04 |
Family
ID=66881074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711217190.2A Pending CN109842372A (en) | 2017-11-28 | 2017-11-28 | A kind of photovoltaic module fault detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109842372A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110244117A (en) * | 2019-07-01 | 2019-09-17 | 江苏康博光伏电力科技有限公司 | A kind of photovoltaic panel monitoring of working condition method of photovoltaic plant |
| CN110399926A (en) * | 2019-07-26 | 2019-11-01 | 广州辰创科技发展有限公司 | A kind of street lamp fault diagnostic method and device |
| CN110995153A (en) * | 2019-12-18 | 2020-04-10 | 国网电子商务有限公司 | Abnormal data detection method and device for photovoltaic power station and electronic equipment |
| CN110991666A (en) * | 2019-11-25 | 2020-04-10 | 远景智能国际私人投资有限公司 | Fault detection method, model training method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106100579A (en) * | 2016-06-07 | 2016-11-09 | 国电南瑞南京控制系统有限公司 | A kind of photovoltaic plant method for diagnosing faults based on data analysis |
| CN106570593A (en) * | 2016-11-10 | 2017-04-19 | 甘肃省电力公司风电技术中心 | Photovoltaic power station output data repairing method based on weather information |
| CN106961249A (en) * | 2017-03-17 | 2017-07-18 | 广西大学 | A kind of diagnosing failure of photovoltaic array and method for early warning |
| CN107065829A (en) * | 2017-04-13 | 2017-08-18 | 西安西热电站信息技术有限公司 | A kind of photovoltaic module pollution diagnosis method supervised based on solar power generation under big data is excavated |
-
2017
- 2017-11-28 CN CN201711217190.2A patent/CN109842372A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106100579A (en) * | 2016-06-07 | 2016-11-09 | 国电南瑞南京控制系统有限公司 | A kind of photovoltaic plant method for diagnosing faults based on data analysis |
| CN106570593A (en) * | 2016-11-10 | 2017-04-19 | 甘肃省电力公司风电技术中心 | Photovoltaic power station output data repairing method based on weather information |
| CN106961249A (en) * | 2017-03-17 | 2017-07-18 | 广西大学 | A kind of diagnosing failure of photovoltaic array and method for early warning |
| CN107065829A (en) * | 2017-04-13 | 2017-08-18 | 西安西热电站信息技术有限公司 | A kind of photovoltaic module pollution diagnosis method supervised based on solar power generation under big data is excavated |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110244117A (en) * | 2019-07-01 | 2019-09-17 | 江苏康博光伏电力科技有限公司 | A kind of photovoltaic panel monitoring of working condition method of photovoltaic plant |
| CN110399926A (en) * | 2019-07-26 | 2019-11-01 | 广州辰创科技发展有限公司 | A kind of street lamp fault diagnostic method and device |
| CN110991666A (en) * | 2019-11-25 | 2020-04-10 | 远景智能国际私人投资有限公司 | Fault detection method, model training method, device, equipment and storage medium |
| CN110991666B (en) * | 2019-11-25 | 2023-09-15 | 远景智能国际私人投资有限公司 | Fault detection method, training device, training equipment and training equipment for model, and storage medium |
| CN110995153A (en) * | 2019-12-18 | 2020-04-10 | 国网电子商务有限公司 | Abnormal data detection method and device for photovoltaic power station and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2016202891B2 (en) | Automatic generation and analysis of solar cell IV curves | |
| CN109842372A (en) | A kind of photovoltaic module fault detection method and system | |
| US8744791B1 (en) | Automatic generation and analysis of solar cell IV curves | |
| CN108847686B (en) | Photovoltaic inverter fault prediction method | |
| KR20120138866A (en) | Trouble recognition apparatus for photovoltaic system and methord thereof | |
| KR20130106532A (en) | Fault diagnosis method of grid-connected photovoltaic system and apparatus thereof | |
| KR101297078B1 (en) | Photovoltaic monitoring device that can be default diagnosis each module and method of diagnosing Photovoltaic power generator | |
| KR20180072244A (en) | Fault diagnosis control system for solar generation system and control method thereof | |
| CN113169709A (en) | Solar power generation control system and method based on machine learning | |
| JP2022042469A (en) | Power generation prediction and efficiency diagnosis system for photovoltaic power generation facility using frbfnn model | |
| US20210408799A1 (en) | System and method for controlling photovoltaic balancing | |
| CN116308304A (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| CN110022130A (en) | A kind of photovoltaic array fault test set and method | |
| US20170054411A1 (en) | Solar device diagnosis method | |
| CN103077439A (en) | Detection system and detection method for electrical energy waste | |
| CN104767480A (en) | Convergence detecting method and system for convergence box and solar power station | |
| CN115689532A (en) | Power system fault analysis method and device | |
| CN104779914A (en) | Conflux detection method and system for conflux boxes and solar power station | |
| Onoshakpor et al. | Smart grid reliability computation-a solution to ageing infrastructure in power grid networks | |
| CN104796086A (en) | Convergence detection method and system for convergence box and solar power station | |
| KR20190064782A (en) | New regeneration energy monitoring system | |
| CN107909096A (en) | A kind of fault of converter early warning criterion implementation method based on two points of K mean clusters | |
| KR20180129399A (en) | Photovoltaic system | |
| CN106301213A (en) | Solar energy equipment diagnostic method | |
| CN112162164A (en) | Cable life prediction system based on neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190604 |