CN114499409A - Photovoltaic module hot spot fault diagnosis method - Google Patents
Photovoltaic module hot spot fault diagnosis method Download PDFInfo
- Publication number
- CN114499409A CN114499409A CN202210171455.4A CN202210171455A CN114499409A CN 114499409 A CN114499409 A CN 114499409A CN 202210171455 A CN202210171455 A CN 202210171455A CN 114499409 A CN114499409 A CN 114499409A
- Authority
- CN
- China
- Prior art keywords
- hot spot
- current
- fault
- photovoltaic
- voltage
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003745 diagnosis Methods 0.000 title claims abstract description 42
- 230000006870 function Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000001931 thermography Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 abstract 1
- 239000013598 vector Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 239000002585 base Substances 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000003127 knee Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000003637 basic solution Substances 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005401 electroluminescence Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
- H02S50/10—Testing of PV devices, e.g. of PV modules or single PV cells
-
- 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
Landscapes
- Photovoltaic Devices (AREA)
- Testing Of Individual Semiconductor Devices (AREA)
Abstract
The invention provides a hot spot fault diagnosis method for a photovoltaic module, which comprises the following steps: the method comprises the following steps of detecting current and voltage time sequence operation data of a photovoltaic array direct current end in data by using an intelligent photovoltaic platform used by a photovoltaic operation enterprise, carrying out filtering processing, correcting an average value method to obtain a normal time sequence, carrying out standardization processing, and selecting 6 of the current and voltage time sequence: 00-19: and in the time period of 00, calculating skewness, eliminating sequences with poor symmetry to obtain sequences to be diagnosed, fitting current and voltage time sequences to obtain Gauss functions and Sigmoid functions, and extracting four fault characteristic quantities. And diagnosing whether the hot spot fault exists in the photovoltaic module and evaluating the fault degree through the established fuzzy reasoning system. According to the method, complex instruments such as a thermal imaging unmanned aerial vehicle and the like are not needed, the operation and maintenance cost of the photovoltaic power station is saved, the hot spot fault diagnosis and the degree evaluation can be realized only by current and voltage time sequence data of the existing photovoltaic intelligent platform, and the online monitoring and diagnosis are realized.
Description
The technical field is as follows:
the invention belongs to the technical field of fault diagnosis in distributed photovoltaic power stations, and particularly relates to a hot spot fault diagnosis method for a photovoltaic module.
Background art:
with the long-term operation of photovoltaic power stations, various fault problems of photovoltaic components are increasingly highlighted. The hot spot problem is the most common, the influence is the most serious, and the service life of the photovoltaic module is greatly shortened. In general, there are many reasons for forming hot spots, such as mismatch between components, internal defects, and the like, which may cause local heating of the photovoltaic components, hot spot failure, and power loss. The essence of the method is that the output characteristic of the component is changed, and then the power generation efficiency is reduced from normal power generation, the power generation efficiency is deteriorated into a load, and the power generation is evolved into a hot spot process.
The existing fault diagnosis method for the hot spot fault mainly utilizes the image characteristics of the photovoltaic module and a fault diagnosis method based on I-V characteristics or time series output characteristics. The method based on the image characteristics comprises a thermal imaging technology and an electroluminescence technology, the faults are diagnosed by utilizing the obvious image characteristic difference characteristics of the photovoltaic modules in normal and fault states, and the method is dependent on a detection instrument with high precision, has high cost and is not suitable for large-scale photovoltaic power stations. The I-V characteristic method carries out fault diagnosis through the I-V characteristic curve characteristics of the component, but the hot spot fault and other faults have an evolution relation, so that the curve characteristics have coupling performance, the hot spot fault cannot be accurately diagnosed, and the normal work of the component can be influenced because the power output needs to be continuously adjusted in a direct current output state when the I-V characteristic is acquired.
Therefore, a photovoltaic module hot spot fault diagnosis method is needed. And carrying out fault diagnosis under the condition of not interfering the normal operation of the power station. The method based on the current and voltage time series output characteristics can directly utilize photovoltaic array time series operation data collected by the field sensor nodes, analyze sequence characteristics, diagnose hot spot faults and estimate fault degrees, is suitable for large photovoltaic power stations, and has important significance for timely eliminating the hot spot faults, realizing online monitoring and diagnosis of the hot spot faults of the components and improving the power generation efficiency of the power stations.
The invention content is as follows:
the invention aims to provide a hot spot fault diagnosis method for a photovoltaic module.
The invention is realized by adopting the following scheme, which comprises the following steps:
the method comprises the following steps: the method comprises the following steps of detecting current and voltage time sequence operation data of a direct current end of a photovoltaic array in the data by using an intelligent photovoltaic platform used in a production management system of a photovoltaic operation enterprise, neglecting low irradiance sequence data such as dark night, rainy days and the like in the operation data, and selecting 6 which is relatively sufficient in light intensity in the current and voltage time sequence in one day: 00-19: the time period of 00 hours, the sampling period was 5 minutes/time, and a total of 156 data points was a set of raw diagnostic data.
Step two: and filtering the original diagnostic data by adopting a moving average algorithm to eliminate noise fluctuation in a time sequence. Obtaining a normal sequence by adopting a mean value correcting method, and carrying out standardization processing to obtain a current and voltage time sequence mapped in a numerical value interval of [0,1 ];
step three: calculating the skewness S of the current and voltage time sequences obtained in the step two, and eliminating the current and voltage time sequences with poor symmetry and S less than or equal to 0.45 to obtain a time sequence to be diagnosed;
step four: fitting the voltage time series to a Sigmoid function V (t)i) And due to symmetry, the first half part 6 of the voltage time sequence is obtained in the selection step three: 00-12: fitting for 30 time periods to obtain V (t)i) A function. Fitting the current time series to Gauss function I (t)i) And utilizing the current time sequence obtained in the third step to fit and determine I (t)i) From I (t)i) Extracting a current peak value I for representing the peak value change of the current sequencehB, carrying out the following steps of; from V (t)i) Extracting V representing voltage peak value in stable stateh. Calculating a characteristic parameter of the hot spot degree: current and voltage fill factor ηIAnd ηVCharacterizing the reduction degree of the hot spot fault and the normal current and voltage;
step five: and constructing a fuzzy inference fault diagnosis model, and diagnosing whether hot spot faults occur to components in the photovoltaic array, wherein the fuzzy inference fault diagnosis model comprises the input of fuzzy subsets and the definition of domains of discourse, the definition of membership function and the establishment of a rule base. And finally, judging whether hot spots occur or not by outputting the language value, and realizing degree estimation by using an accurate value corresponding to the language value.
Description of the drawings:
FIG. 1 is a schematic diagram of a photovoltaic module hot spot fault diagnosis system according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of a photovoltaic module hot spot fault diagnosis method according to an exemplary embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a current time series at different skewness according to an exemplary embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a fuzzy inference system model architecture according to an exemplary embodiment of the present specification;
FIG. 5 is a schematic current and voltage time series diagram of a hot spot fault as described in an exemplary embodiment of the present description.
The specific implementation mode is as follows:
the invention provides a hot spot fault diagnosis method for a photovoltaic module, and further explanation is carried out to make the purpose, the technical scheme and the effect of the invention more clear. The specific examples described herein are intended to be illustrative only and are not intended to be limiting.
The present invention is further described with reference to the accompanying drawings, fig. 1 is a schematic diagram of a photovoltaic module hot spot fault diagnosis system according to an exemplary embodiment of the present specification, and fig. 2 is a flowchart of a photovoltaic module hot spot fault diagnosis method according to an exemplary embodiment of the present specification, which specifically includes the following steps:
the method comprises the following steps: because photovoltaic module begins the electricity generation under certain light intensity, all the other time quantum do not generate electricity, and the numerical value is zero all the time, so simplified the data, neglect low irradiance sequence data such as night, rainy day, select the light intensity in the day electric current and the voltage time series more sufficient 6: 00-19: the time period of 00 hours, the sampling period was 5 minutes/time, and a total of 156 data points was a set of raw diagnostic data.
Step two: and filtering the current and voltage time sequence running data of the direct current end of the photovoltaic array by adopting a moving average algorithm to eliminate noise fluctuation in the time sequence. Obtaining a normal sequence by adopting a mean value correcting method, and carrying out standardization processing to obtain a current and voltage time sequence mapped in a numerical value interval of [0,1 ];
the original data contains abnormal fluctuation of data caused by environmental mutation, unstable transmission of sensor equipment and the like, and the data can influence subsequent characteristic quantity calculation and seriously influence the diagnosis accuracy rate, so that the original data is firstly subjected to the sliding average algorithmThe initial data filtering algorithm mainly comprises the following processes: let a data set X with the number of elements N1In which one element is xiI ∈ {1,2, …, N }. Dividing the elements into n groups according to the sequence, and taking the average value of the groups as a new element xjAnd repeating the operation for N-N +1 times to obtain filtered data for subsequent processing.
The output characteristics of the photovoltaic array depend on environmental changes and array structures, time series numerical values under different environments or structures cannot be mutually referenced and compared, and comparison needs to be carried out under the same calibration. The method comprises the following steps of finding corresponding normal current and voltage sequence data in a platform by using normal components in field manual operation and maintenance data, obtaining the normal sequence data by an average value correcting method, and carrying out standardization processing on all data to be tested as follows:
in the formula (I), the compound is shown in the specification,
is a normalized sequence number; x is the number ofiIs a filtered sequence number;
and
is an extreme value in the normal sequence; i is the time. The final time period was 6: 00-19: 00 and the magnitude of the value is mapped to [0,1]]Current and voltage time series of intervals.
Step three: and D, calculating the skewness S of the current and voltage time sequences obtained in the step two, and eliminating the current and voltage time sequences with poor symmetry and S less than or equal to 0.30 to obtain the time sequence to be diagnosed. The calculation expression is as follows:
in the formula, xiAnd (3) the current or voltage sequence value at the ith moment, n is the total number of the sequence, mu is the sequence mean value, and sigma is the sequence standard deviation. In the current time series diagram of fig. 3, the time series curve is distorted due to weather changes, etc., the distortion is not caused by the component itself, and the current and voltage time series of the component day are generally symmetrical under normal conditions, so in order to eliminate the influence of the external environment, the method described herein removes the external environmental disturbance factors such as asymmetry, wherein a positive deviation represents that the curve is shifted to the left, a negative deviation represents that the curve is shifted to the right, and zero represents complete symmetry. Test experiment calculation shows that when the skewness satisfies S is less than or equal to 0.30, the curve is considered to be approximately symmetrical and meets the requirement of the fitting precision of the subsequent function.
Step four: fitting the voltage time series to Sigmoid functional form:
in the formula, ViIs the voltage sequence value at the ith time, VhIs the peak voltage, tiIs the ith time, t0K is the knee tangent slope at the knee corresponding time.
Due to symmetry, the first half 6 of the voltage time series is chosen: 00-12: fitting is performed for 30 time periods, and the error sum of squares e is used2：
The formula (4) is respectively paired with Vh、tiAnd k, and the partial derivative is obtained, and V (t) is obtained by making the partial derivative 0i) A function.
The current time series is fitted to the Gauss function form:
in the formula IiIs the current sequence value at the ith moment, IhIs the peak value of the current, tmidD is the line width at the time when the peak corresponds to the time.
Carrying out logarithmic transformation as formula (6) by using the current time sequence, solving according to the least square principle, and calculating to obtain Ih、tmidAnd d three Gauss function parameters are as formula (7), and I (t) is fittedi)。
Step five: from I (t)i) Middle extracted current peak value IhB, carrying out the following steps of; from V (t)i) V of middle extraction voltage peak valueh. Calculating a characteristic parameter of the hot spot degree: current and voltage fill factor ηIAnd ηVThe fault is characterized by the degree of drop in normal current and voltage, as in equation (8).
In the formula, the superscript "-" indicates failure, and the rest is normal.
Step six: and constructing a fuzzy inference fault diagnosis model, and diagnosing whether hot spot faults occur to components in the photovoltaic array, wherein the fuzzy inference fault diagnosis model comprises the input of fuzzy subsets and the definition of domains of discourse, the definition of membership function and the establishment of a rule base. And finally, judging whether hot spots occur or not by outputting the language value, and realizing degree estimation by using an accurate value corresponding to the language value. Fig. 4 is a schematic diagram illustrating a model structure of a fuzzy inference system according to an exemplary embodiment of the present specification. The specific implementation mode is as follows:
taking the constructed fault feature vector as the input of a fuzzy inference system, and determining an input fuzzy subset and a discourse domain according to the numerical distribution condition of the feature vector; designing forms and parameters of membership functions according to the variation rule of the eigenvector numerical value; establishing a fuzzy rule according to the corresponding relation between the characteristic vector and the fault type and the fuzzy subset quantization result by combining with field operation and maintenance knowledge experience; and obtaining a hot spot fault judgment result and an accurate degree value by adopting a Mamdani fuzzy reasoning method.
1) Determining fault vector fuzzy subsets and domains of discourse
In order to determine the fuzzy subsets and domains of the fault vectors, the photovoltaic arrays operating in four states are selected, four characteristic quantities are calculated, and variation numerical values of the characteristic quantities are obtained, as shown in table 1.
TABLE 1 feature vectors in four states
From the 4 characteristic amount variation intervals of table 1, the input amount can be set to the following 4 variables: peak current value IhThe language value of (1) is { NB, NM, NS, NZ }, and the domain of discourse is defined as {0.60, 0.75, 0.85, 1 }. Peak voltage value VhThe language value is { NB, NM, NS, NZ }, and the domain of discourse is defined as {0.50, 0.60, 0.70, 1 }. Current fill factor ηIThe language value is { PZ, PS, PM, PB }, and the domain is defined as {0, 0.15, 0.25, 0.40 }. Voltage fill factor ηVThe language value is { PZ, PS, PM, PB }, and the domain is defined as {0, 0.15, 0.25, 0.30 }. The output quantity D is a hot spot diagnosis result, and only needs to judge whether the hot spot is detected, so that three language values are set, and Z represents normal; PS denotes no hot spot failure; PB indicates hot spots.
2) Determining a fault vector fuzzy membership function
In order to determine the fuzzy membership function of the fault vector, the form and the parameters of the membership function can be designed according to the variation rule of the feature vector number and by combining with the on-site operation and maintenance fault experience. When the component fails, the fault change trend is not linear and is changed in a non-linear way, for example, the current time sequence is a bell-shaped transformation which is similar to a normal distribution, so I is selectedhAnd ηIIs a bell-shaped membership function. And the voltage time sequence shows the trend of firstly rising sharply and then falling sharply and smoothly, so the trapezoidal membership function is selected. And because the different fault states have evolution relations and slow evolution trends, the bell-shaped membership function is selected as the hot spot diagnosis result D.
3) Rule base
A rule base is established according to the influence of the current/voltage peak value and the filling factor on the hot spot, and two problems are mainly solved: the qualitative reason judgment is realized, and whether the array is in a normal, non-hot spot fault, light hot spot or severe hot spot state is judged according to rules 1 to 4 in the table 2. Secondly, the rule after the rule 4 realizes degree estimation, an accurate value corresponding to the interval of [0,1] after the rule is defuzzified is output, and the larger the numerical value is, the higher the degree is in the fault state. Part of the rules are summarized as follows:
TABLE 2 Hot Spot Fault rule Table
With the above rule base, fig. 5 is a schematic diagram of a time series of current and voltage of a hot spot fault according to an exemplary embodiment of the present specification, where η isIAnd ηVAt the same time, it is greatly reduced, and when the light intensity is strong, IhAnd VhAnd the output quantity obtained by the diagnosis method is PB, the diagnosis result is consistent with the actual hot spot fault phenomenon, and the corresponding accurate value of the output quantity is 0.8672, which indicates that the hot spot degree is heavier. In addition, diagnosis is performed using normal component time-series data, ηIAnd ηVDoes not substantially decrease and is illuminated under strong light IhAnd VhThe output quantity is Z in the diagnosis method, which shows that the diagnosis result is in accordance with the actual component, and the output quantity is largerThe corresponding accurate value of the quantity is 0.9751, which indicates that although the state of the component is normal, the accurate value is close to 1, which indicates that the component may be converted from a normal state to a fault state and may be degraded into mild hot spots later, and therefore, the diagnosis method provided by the invention not only can realize hot spot fault diagnosis, but also can predict the later development of the state of the photovoltaic component to a certain extent, and realize degree estimation.
In addition, because the photovoltaic array direct current end current and voltage time sequence operation data in the detection data of the intelligent photovoltaic platform indicate the position serial number of the photovoltaic array data acquisition point, the on-site fault assembly can be positioned only by corresponding the time sequence data with the hot spot fault diagnosed to the acquisition point serial number of the time sequence data.
According to the photovoltaic module hot spot fault diagnosis method, the hot spot fault of the photovoltaic module in the distributed photovoltaic power station can be effectively detected, and the fault degree can be evaluated. The invention is put into trial use in a distributed photovoltaic power station.
The above description is given of specific embodiments in engineering applications, but the present invention is not limited to the described embodiments. The basic principle method of the present invention is to provide the above basic solution, and variations, modifications, substitutions and changes of the embodiments are possible without departing from the principle and spirit of the present invention.
Claims (4)
1. A hot spot fault diagnosis method for a photovoltaic module is characterized by comprising the following steps: the method comprises the following steps of detecting current and voltage time sequence operation data of a direct current end of a photovoltaic array in data by using an intelligent photovoltaic platform used in a production management system of a photovoltaic operation enterprise, constructing the current and voltage time sequence into Gauss and Sigmoid function forms through the algorithm steps provided by the patent, extracting four hot spot fault characteristics, using the four hot spot fault characteristics as input of a fuzzy inference system, diagnosing whether a hot spot fault occurs and evaluating the fault degree of the hot spot fault through the fuzzy inference system, wherein the specific algorithm steps are as follows:
the method comprises the following steps: the method comprises the following steps of detecting current and voltage time sequence operation data of a direct current end of a photovoltaic array in the data by using an intelligent photovoltaic platform used in a production management system of a photovoltaic operation enterprise, neglecting low irradiance sequence data such as dark night, rainy days and the like in the operation data, and selecting 6 which is relatively sufficient in light intensity in the current and voltage time sequence in one day: 00-19: the time period is 00, the sampling period is 5 minutes/time, and 156 data points in total are a group of original diagnostic data;
step two: filtering original diagnostic data by adopting a moving average algorithm, eliminating noise fluctuation in a time sequence, obtaining a normal sequence by adopting a mean value correcting method, and carrying out standardization processing to obtain a current and voltage time sequence mapped in a [0,1] numerical interval;
step three: calculating the skewness S of the current and voltage time sequences obtained in the step two, and eliminating the current and voltage time sequences with poor symmetry and S less than or equal to 0.30 to obtain a time sequence to be diagnosed;
step four: fitting the voltage time series to a Sigmoid function V (t)i) And due to symmetry, selecting the first half part 6 of the voltage time sequence obtained in the third step: 00-12: fitting is carried out for 30 time periods to obtain V (t)i) Function, fitting the current time series to Gauss function I (t)i) And fitting to determine I (t) by using the current time sequence obtained in the step threei) From I (t)i) Extracting a current peak value I for representing the peak value change of the current sequencehFrom V (t)i) Extracting V representing voltage peak value when the voltage is stablehCalculating a characteristic parameter eta of hot spot degreeIAnd ηVWherein the current and voltage fill factor ηIAnd ηVCharacterizing the degree of the drop of the fault and the normal current and voltage;
step five: and finally, judging whether hot spots occur or not by outputting a language value, and realizing degree estimation by using an accurate value corresponding to the language value.
2. The photovoltaic module hot spot fault diagnosis method according to claim 1, characterized in that: separating the photovoltaic moduleScattered current and voltage time sequences are constructed in a Gauss and Sigmoid continuous function form, the influence of a sampling period is reduced, the Gauss and Sigmoid function parameters can represent hot spot fault characteristics, and a fault characteristic index I can be extractedhAnd VhAnd the reduction degree of the hot spot fault and the normal current and voltage is represented by calculating the current and voltage filling factors;
which calculates the current and voltage fill factor etaIAnd ηVAs shown in formula (1) and formula (2):
the superscript "" in the formula (1) and the formula (2) indicates a fault, and the rest is normal.
3. The photovoltaic module hot spot fault diagnosis method according to claim 1, characterized in that: through actual state data with different hot spot degrees, a fuzzy inference fault diagnosis model is constructed to diagnose the hot spot fault, the development condition of the component can be predicted to a certain extent, the degree is estimated, the language value of the output hot spot diagnosis result D is used as the diagnosis result of whether the hot spot fault is a non-hot spot fault or a normal state, the accurate value corresponding to the D is used as the degree estimation, and the numerical value is more serious as being closer to 1.
4. The photovoltaic module hot spot fault diagnosis method according to claim 1, characterized in that: compared with an infrared scanning method, the method can position the array position of the hot spot fault of the photovoltaic module only by the acquisition point number of the electrical data of the photovoltaic power station, and has the advantages of high diagnosis speed and low cost.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210171455.4A CN114499409A (en) | 2022-02-24 | 2022-02-24 | Photovoltaic module hot spot fault diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210171455.4A CN114499409A (en) | 2022-02-24 | 2022-02-24 | Photovoltaic module hot spot fault diagnosis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114499409A true CN114499409A (en) | 2022-05-13 |
Family
ID=81483899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210171455.4A Withdrawn CN114499409A (en) | 2022-02-24 | 2022-02-24 | Photovoltaic module hot spot fault diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114499409A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115455730A (en) * | 2022-09-30 | 2022-12-09 | 南京工业大学 | Photovoltaic module hot spot fault diagnosis method based on complete neighborhood preserving embedding |
-
2022
- 2022-02-24 CN CN202210171455.4A patent/CN114499409A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115455730A (en) * | 2022-09-30 | 2022-12-09 | 南京工业大学 | Photovoltaic module hot spot fault diagnosis method based on complete neighborhood preserving embedding |
| CN115455730B (en) * | 2022-09-30 | 2023-06-20 | 南京工业大学 | Photovoltaic module hot spot fault diagnosis method based on complete neighborhood preserving embedding |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109842373B (en) | Photovoltaic array fault diagnosis method and device based on space-time distribution characteristics | |
| CN110286333B (en) | Fault diagnosis method for lithium power battery system | |
| CN108763654A (en) | A kind of electrical equipment fault prediction technique based on Weibull distribution and hidden Semi-Markov Process | |
| Leva et al. | PV module fault diagnosis based on microconverters and day-ahead forecast | |
| CN110133400B (en) | Dynamic power system anomaly detection method fused with recursion state estimation | |
| CN110879377B (en) | Metering device fault tracing method based on deep belief network | |
| CN109472097B (en) | Fault diagnosis method for online monitoring equipment of power transmission line | |
| CN114114002B (en) | Online fault diagnosis and state evaluation method for oxide arrester | |
| CN112883634B (en) | DC measurement system state prediction method and system based on multi-dimensional analysis | |
| CN111669123A (en) | Method and device for fault diagnosis of photovoltaic string | |
| Shi et al. | Study of wind turbine fault diagnosis and early warning based on SCADA data | |
| CN116308304A (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| CN115293372A (en) | Photovoltaic string fault diagnosis method based on multi-dimension and multi-parameter numerical analysis | |
| CN114499409A (en) | Photovoltaic module hot spot fault diagnosis method | |
| CN110412417B (en) | Micro-grid data fault diagnosis method based on intelligent power monitoring instrument | |
| CN110443481B (en) | Power distribution automation terminal state evaluation system and method based on hybrid K-nearest neighbor algorithm | |
| CN109086891B (en) | Hot spot fault diagnosis method based on fuzzy logic reasoning | |
| Liu et al. | The life prediction of PEMFC based on group method of data handling with Savitzky–Golay smoothing | |
| CN117365677A (en) | Steam turbine unit performance health state evaluation method | |
| CN116819382A (en) | DC-DC converter state monitoring method based on digital twin | |
| CN116664098A (en) | Abnormality detection method and system for photovoltaic power station | |
| CN116452041A (en) | Power distribution network reliability assessment method based on cross entropy important sampling | |
| CN116070368A (en) | Method for predicting residual life of high-speed bearing of offshore wind turbine | |
| CN114186756A (en) | Method for predicting energy storage capacity of storage battery of power distribution network terminal | |
| CN114692729A (en) | New energy station bad data identification and correction method based on deep learning |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220513 |