CN115021675A - Distributed photovoltaic power station fault diagnosis method and device based on AMI data - Google Patents
Distributed photovoltaic power station fault diagnosis method and device based on AMI data Download PDFInfo
- Publication number
- CN115021675A CN115021675A CN202210494740.XA CN202210494740A CN115021675A CN 115021675 A CN115021675 A CN 115021675A CN 202210494740 A CN202210494740 A CN 202210494740A CN 115021675 A CN115021675 A CN 115021675A
- Authority
- CN
- China
- Prior art keywords
- power station
- fault
- distributed photovoltaic
- data
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000010248 power generation Methods 0.000 claims abstract description 97
- 238000012417 linear regression Methods 0.000 claims abstract description 56
- 238000012360 testing method Methods 0.000 claims abstract description 48
- 238000012549 training Methods 0.000 claims abstract description 36
- 230000002159 abnormal effect Effects 0.000 claims description 48
- 229910021421 monocrystalline silicon Inorganic materials 0.000 claims description 12
- 229910021420 polycrystalline silicon Inorganic materials 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 229910021417 amorphous silicon Inorganic materials 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013024 troubleshooting Methods 0.000 abstract description 9
- 239000011159 matrix material Substances 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance 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
-
- 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
Abstract
The invention provides a distributed photovoltaic power station fault diagnosis method and device based on AMI data, wherein the method comprises the following steps: constructing a training sample library and a testing sample library of the distributed photovoltaic power station; establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library; calculating a linear regression function of the power generation operation model; identifying a fault power station in the test sample library according to the linear regression function; and fault diagnosis is carried out on the fault power station by adopting AMI data. According to the distributed photovoltaic power station fault diagnosis method and system, the faults of the distributed photovoltaic power station can be quickly identified, accurately positioned and diagnosed according to the AMI data, so that the fault troubleshooting efficiency can be improved, and the influence on the photovoltaic power generation efficiency after the power station faults are reduced.
Description
Technical Field
The invention relates to the technical field of power station fault detection, in particular to a distributed photovoltaic power station fault diagnosis method based on AMI data and a distributed photovoltaic power station fault diagnosis device based on the AMI data.
Background
In recent years, with the problems of exhaustion of fossil energy, destruction of ecological environment, global energy safety and the like becoming more apparent, the development of renewable energy is imminent. Solar energy is used as a representative of novel energy, and has the natural advantages of cleanness, environmental protection, reproducibility, sustainability and the like, so that the technology in the field of photovoltaic power generation can be rapidly developed.
However, when the photovoltaic power station generally works in a severe outdoor environment for a long time, some failure problems inevitably occur, and if the failure problems cannot be found and processed in time, not only the power station cannot work normally, but also accidents may occur seriously, for example, a hot spot effect of a photovoltaic array may cause a fire. Therefore, the operation state of the photovoltaic power station is timely, comprehensively and accurately monitored and evaluated to avoid faults and cascading faults, and the method has important significance for optimizing maintenance strategies of the distributed photovoltaic power station and realizing large-scale safe and efficient grid connection of distributed photovoltaic power generation.
Disclosure of Invention
The invention aims to solve the technical problems and provides a distributed photovoltaic power station fault diagnosis method based on AMI data, which can realize rapid identification, accurate positioning and fault reason diagnosis of faults of the distributed photovoltaic power station only through the AMI data, thereby improving the fault troubleshooting efficiency and reducing the influence on the photovoltaic power generation efficiency after the power station faults.
The technical scheme adopted by the invention is as follows:
a distributed photovoltaic power station fault diagnosis method based on AMI data comprises the following steps: constructing a training sample library and a testing sample library of the distributed photovoltaic power station; establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library; calculating a linear regression function of the power generation operation model; identifying a faulty power station in the test sample library according to the linear regression function; and adopting AMI data to carry out fault diagnosis on the fault power station.
According to an embodiment of the present invention, the performing fault diagnosis on the faulty power station by using AMI data specifically includes the following steps: obtaining voltage data, current data, correlation meter power data and voltage data measured by the same meter box of the fault power station according to the AMI data; judging whether the voltage data and the current data of the fault power station are abnormal or not; if the voltage data are normal and the current data are abnormal, judging whether the power data of the correlation meter are abnormal or not; if the associated meter power data is normal, judging that the fault of the fault power station is a meter fault; if the power data of the association meter is abnormal, judging that the fault of the fault power station is an intra-station fault; if the voltage data are abnormal and the current data are normal, judging whether the voltage data of the meter in the same meter box are abnormal or not; if the voltage data of the meters in the same meter box is normal, judging that the fault of the fault power station is a meter measuring fault; if the voltage data measured by the meter of the same meter box is abnormal, judging that the fault of the fault power station is an off-station fault; if the voltage data and the current data are both abnormal, judging whether the power data of the correlation meter is abnormal; if the power data of the associated meter is normal, judging that the fault of the fault power station is a fault of the associated meter; if the power data of the associated meter is abnormal, judging whether the voltage data of the meter in the same meter box is abnormal; if the voltage data measured by the meter in the same meter box is normal, judging that the fault of the power station with the fault is an in-station fault; and if the voltage data measured by the meter of the same meter box is abnormal, judging that the fault of the fault power station is an off-station fault.
According to one embodiment of the invention, the building of the training sample library and the testing sample library of the distributed photovoltaic power station specifically comprises the following steps: acquiring first-class power station operation information and first-class power station environment information of a normally-operated distributed photovoltaic power station; constructing the training sample library according to the first type of power station operation information and the first type of power station environment information; acquiring second-class power station operation information and second-class power station environment information of a distributed photovoltaic power station to be detected; and constructing the test sample library according to the second type of power station operation information and the second type of power station environment information.
According to an embodiment of the present invention, the establishing of the power generation operation model of the distributed photovoltaic power station according to the training sample library specifically includes the following steps: determining the type of a photovoltaic component of a normally operating distributed photovoltaic power station in the training sample library; classifying the normally-running distributed photovoltaic power stations in the training sample library according to the types of the photovoltaic components; and establishing the power generation operation model according to the classification result.
According to one embodiment of the invention, the power generation operation model is:
y＝f(x 1 ,x 2 ,x 3 ,x 4 ,x 5 )
wherein y represents the unit power generation amount of the normally operating distributed photovoltaic power station, and x 1 Representing the mean solar irradiance, x, of the power station area 2 Representing the mean temperature of the plant environment, x 3 Representing the average humidity, x, of the plant environment 4 Representing the mean ground pressure, x, of the plant 5 Representing the average wind speed of the plant environment.
According to one embodiment of the invention, the photovoltaic module types include single crystal silicon photovoltaic modules, polycrystalline silicon photovoltaic modules, amorphous silicon photovoltaic modules, double-sided single crystal silicon photovoltaic modules and double-sided polycrystalline silicon photovoltaic modules.
According to an embodiment of the present invention, the calculating the linear regression function of the power generation operation model specifically includes the following steps: processing the power generation operation model by adopting linear regression fitting to obtain a linear regression function of the power generation operation model; and defining the normal power generation threshold value of the distributed photovoltaic power station according to the linear regression function.
According to one embodiment of the invention, the linear regression function is:
y＝ε+β 1 x 1 +.....+β 5 x 5
wherein ε represents the fitting intercept of the power generation operation model to the linear regression function, β 1 Regression coefficient, beta, representing the mean solar irradiance of a power station area 2 Regression coefficient, beta, representing the average temperature of the plant environment 3 Regression coefficient, beta, representing the average humidity of the plant environment 4 Regression coefficient, beta, representing the mean ground pressure of a power station 5 A regression coefficient representing the average wind speed of the plant environment.
According to an embodiment of the present invention, the identifying the faulty power station in the test sample library according to the linear regression function specifically includes the following steps: classifying and processing the distributed photovoltaic power stations to be tested in the test sample library according to the linear regression function and the normal power generation threshold; and identifying the fault power station in the test sample library according to the classification result.
A distributed photovoltaic power plant fault diagnosis device based on AMI data includes: the system comprises a sample module, a data processing module and a data processing module, wherein the sample module is used for constructing a training sample library and a testing sample library of the distributed photovoltaic power station; the modeling module is used for establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library; a calculation module for calculating a linear regression function of the power generation operation model; the identification module is used for identifying the fault power station in the test sample library according to the linear regression function; and the diagnosis module is used for carrying out fault diagnosis on the fault power station by adopting AMI data.
The invention has the beneficial effects that:
according to the distributed photovoltaic power station fault diagnosis method, the distributed photovoltaic power station fault can be quickly identified, accurately positioned and diagnosed due to the fault only through AMI data, so that the fault troubleshooting efficiency can be improved, and the influence on the photovoltaic power generation efficiency after the power station fault is reduced.
Drawings
FIG. 1 is a flow chart of a distributed photovoltaic power plant fault diagnosis method based on AMI data according to an embodiment of the present invention;
FIG. 2 is a flow chart of fault diagnosis for a faulty power station using AMI data, in accordance with an embodiment of the present invention;
fig. 3 is a block diagram illustrating a distributed photovoltaic power plant fault diagnosis apparatus based on AMI data according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of a distributed photovoltaic power plant fault diagnosis method based on AMI data according to an embodiment of the present invention.
As shown in fig. 1, the distributed photovoltaic power station fault diagnosis method based on AMI data according to the embodiment of the present invention includes the following steps:
and S1, constructing a training sample library and a testing sample library of the distributed photovoltaic power station.
Specifically, first-class power station operation information and first-class power station environment information of a normally-operating distributed photovoltaic power station can be acquired, then a training sample library can be constructed according to the first-class power station operation information and the first-class power station environment information, then second-class power station operation information and second-class power station environment information of the distributed photovoltaic power station to be tested can be acquired, and finally a testing sample library can be constructed according to the second-class power station operation information and the second-class power station environment information.
The first-class power station operation information of the plurality of groups of normally-operated distributed photovoltaic power stations can comprise power station file information and power station measuring meter information of the plurality of groups of normally-operated distributed photovoltaic power stations; the first-class power station environmental information of the plurality of groups of normally operating distributed photovoltaic power stations can comprise meteorological environmental information of the plurality of groups of normally operating distributed photovoltaic power stations; in addition, the second type of power station operation information of the distributed photovoltaic power station to be detected can comprise power station file information, power station meter information, correlation meter information and same meter box meter information in an AMI system of the distributed photovoltaic power station to be detected; the second type of power station environment information of the distributed photovoltaic power station to be tested can comprise meteorological environment information in an AMI system of the distributed photovoltaic power station to be tested.
More specifically, the power station archive information of the multiple groups of normally-operating distributed photovoltaic power stations and distributed photovoltaic power stations to be tested can include corresponding power station house numbers, installed capacities and photovoltaic module type information; the power station measuring meter information of the plurality of groups of normally operating distributed photovoltaic power stations and distributed photovoltaic power stations to be tested can comprise corresponding daily generated energy, high-density voltage, current and power information; the correlation meter information of the multiple groups of normally-operated distributed photovoltaic power stations and the distributed photovoltaic power station to be tested can comprise corresponding on-line electric quantity, high-density voltage, current and power information; the meter information of the same meter box of the multiple groups of normally operating distributed photovoltaic power stations and the distributed photovoltaic power station to be tested can comprise corresponding high-density voltage, current and power information; the meteorological environment information of the multiple groups of normally-operated distributed photovoltaic power stations and the distributed photovoltaic power stations to be detected can comprise corresponding power station area solar average irradiance, power station area environment average temperature, power station area environment average humidity, power station area ground average air pressure and power station area environment average air speed.
And S2, establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library.
Specifically, the photovoltaic module type of the normally operating distributed photovoltaic power station in the training sample library can be determined, then the normally operating distributed photovoltaic power station in the training sample library can be classified according to the photovoltaic module type, and then the power generation operation model can be established according to the classification result. The photovoltaic module types can include monocrystalline silicon photovoltaic modules, polycrystalline silicon photovoltaic modules, amorphous silicon photovoltaic modules, double-sided monocrystalline silicon photovoltaic modules and double-sided polycrystalline silicon photovoltaic modules.
More specifically, the distributed photovoltaic power stations which normally operate in the training sample library can be classified according to the types of the photovoltaic components, namely monocrystalline silicon photovoltaic components, polycrystalline silicon photovoltaic components, amorphous silicon photovoltaic components, double-sided monocrystalline silicon photovoltaic components and double-sided polycrystalline silicon photovoltaic components, and a power generation operation model can be respectively established for each type of the distributed photovoltaic power stations which normally operate.
The power generation operation model of each type of normally-operated distributed photovoltaic power station can be expressed as follows:
y＝f(x 1 ,x 2 ,x 3 ,x 4 ,x 5 )
wherein y represents the unit power generation amount of each type of normally operating distributed photovoltaic power station, and x 1 Representing the mean solar irradiance, x, of the power station area 2 Representing the mean temperature of the plant environment, x 3 Representing the average humidity, x, of the plant environment 4 Representing the mean pressure, x, of the ground of the station 5 Representing the average wind speed of the plant environment.
S3, a linear regression function of the power generation operation model is calculated.
Specifically, the power generation operation model may be processed by linear regression fitting to obtain a linear regression function of the power generation operation model, and the normal power generation threshold of the distributed photovoltaic power station may be defined according to the linear regression function.
More specifically, it may be firstly set that a matrix formed by meteorological environment information of various normally operating distributed photovoltaic power stations in the training sample library is X, and a matrix formed by unit power generation of various normally operating distributed photovoltaic power stations is Y (unit power generation of distributed photovoltaic power station to be measured is power generation/power station capacity), then:
X＝[x ij ] 5×5
wherein i denotes each photovoltaic module type, and i 1, 2.., 5, j denotes a meteorological environment information type of the photovoltaic power plant, and j 1, 2.., 5;
further, the formula expansion may be:
further, the meteorological environment information matrix X inverse matrix sigma of various normally-running distributed photovoltaic power stations can be calculated -1 ：
Further, the regression coefficient β of the power generation operation model fitting linear regression function may be calculated:
further, the fitting intercept ε of the power generation operation model fitting linear regression function may be calculated:
from this, the linear regression function of the power generation operation model can be obtained as:
y＝ε+β 1 x 1 +.....+β 5 x 5
where ε represents the fitting intercept of the power generation operation model fitting linear regression function, β 1 Regression coefficient, beta, representing the mean solar irradiance of a power station area 2 Coefficient of regression, beta, representing the average temperature of the plant environment 3 Regression coefficient, beta, representing the average humidity of the plant environment 4 Regression coefficient, beta, representing the mean ground pressure of a power station 5 A regression coefficient representing the average wind speed of the plant environment.
And S4, identifying the fault power station in the test sample library according to the linear regression function.
Specifically, the distributed photovoltaic power stations to be tested in the test sample library can be classified according to the linear regression function and the normal power generation threshold, and then the fault power stations in the test sample library can be identified according to the classification result.
More specifically, the data in the test sample library can be substituted into a linear regression function to obtain a test value of unit power generation of the distributed photovoltaic power station to be tested, the test value of the unit power generation can be compared with an actual value of the unit power generation, and the distributed photovoltaic power station to be tested in the test sample library can be classified by combining a normal power generation threshold. For example, if the generated energy test value/generated energy actual value is greater than the normal generation threshold value, the distributed photovoltaic power station to be tested is judged to be a high-efficiency operating power station, if the generated energy test value/generated energy actual value is less than the normal generation threshold value, the distributed photovoltaic power station to be tested is judged to be a normal operating power station, and if the generated energy test value/generated energy actual value is equal to the normal generation threshold value, the distributed photovoltaic power station to be tested is judged to be a fault operating power station. Therefore, the power station in the power failure area can be subjected to differentiated collaborative troubleshooting, and the troubleshooting efficiency can be improved.
And S5, adopting AMI data to carry out fault diagnosis on the fault power station.
Specifically, as shown in fig. 2, the step S5 may further include the following steps:
s501, obtaining voltage data, current data, correlation meter power data and voltage data measured by a meter with a meter box of a fault power station according to AMI data, wherein the voltage data and the current data of the fault power station can be obtained from the data measured by the power station of the fault power station;
s502, judging whether the voltage data and the current data of the fault power station are abnormal or not, wherein if the voltage data are normal and the current data are abnormal, executing a step S503, if the voltage data are abnormal and the current data are normal, executing a step S506, and if the voltage data and the current data are both abnormal, executing a step S509;
s503, judging whether the power data of the association meter is abnormal, wherein if the power data of the association meter is normal, executing the step S504, and if the power data of the association meter is abnormal, executing the step S505;
s504, judging the fault of the fault power station as a fault of the measuring meter;
s505, judging that the fault of the fault power station is an intra-station fault;
s506, judging whether the voltage data measured by the meter in the same meter box is abnormal or not, wherein if the voltage data measured by the meter in the same meter box is normal, executing the step S507, and if the voltage data measured by the meter in the same meter box is abnormal, executing the step S508;
s507, judging the fault of the fault power station as a fault of the measuring meter;
s508, judging that the fault of the fault power station is an off-station fault, namely a superior power grid fault;
s509, judging whether the power data of the association meter is abnormal, wherein if the power data of the association meter is normal, executing the step S510, and if the power data of the association meter is abnormal, executing the step S511;
s510, judging the fault of the fault power station as a fault of a measuring meter;
s511, judging whether the voltage data measured by the meter in the same meter box is abnormal, wherein if the voltage data measured by the meter in the same meter box is normal, executing the step S512, and if the voltage data measured by the meter in the same meter box is abnormal, executing the step S513;
s512, judging that the fault of the fault power station is an intra-station fault;
and S513, judging that the fault of the fault power station is an off-station fault, namely a fault of an upper-level power grid.
The practical application process of the distributed photovoltaic power station fault diagnosis method based on the AMI data of the present invention will be described below by taking the training sample library shown in table 1 and the testing sample library shown in table 2 as examples.
TABLE 1
TABLE 2
In an embodiment of the present invention, the data in table 1 may be substituted into the above step S3, i.e. the process of calculating the linear regression function of the power generation operation model, so that the fitting intercept epsilon of the power generation operation model fitting the linear regression function is specifically 0.125, and the regression coefficient β of the solar average irradiance of the power station region is obtained 1 Specifically 0.605, regression coefficient beta of the average temperature of the power station environment 2 Specifically 0.153, regression coefficient beta of the average humidity of the power station environment 3 Specifically 0.336, regression coefficient beta of the mean ground pressure of the plant 4 Specifically 0.129, regression coefficient beta of the average wind speed of the power station environment 5 Specifically, 0.146, from this, the linear regression function of the power generation operation model can be calculated as:
y＝0.125+0.605×10 -2 x 1 +0.153×10 -1 x 2 +0.336×10 -2 x 3 +0.129×10 -1 x 4 +0.146x 5 。
further, the normal power generation threshold of the distributed photovoltaic power plant may be defined according to a linear regression function of the power generation operation model, for example, the normal power generation threshold ρ may be defined in a range of [0.3, 0.8 ].
Further, the normal power generation threshold value can be used ρ Identification of the score to be tested in Table 2Whether the distributed photovoltaic power station is a faulty power station or not can be determined, and specifically, the distributed photovoltaic power stations 1,2, 3, 4, 5, 6, 7, 8, 9 and 10 to be tested and the normal power generation threshold in table 2 can be respectively determined ρ The relationship (2) of (c). Wherein, the generated energy test value/generated energy actual value of the distributed photovoltaic power stations 3, 5 and 10 to be tested is equal to the normal power generation threshold value ρ Namely, the ratios 0.562, 0.389 and 0.618 of the distributed photovoltaic power stations 3, 5 and 10 to be tested all belong to the range [0.3, 0.8] of the normal power generation threshold value rho]Therefore, the distributed photovoltaic power stations 3, 5 and 10 to be tested can be identified as fault power stations.
Further, corresponding power station measurement meter data (voltage data and current data), associated meter power data and meter voltage data of the same meter box can be respectively obtained from the AMI data of the distributed photovoltaic power stations 3, 5 and 10 to be measured, and the data is specifically shown in table 3.
TABLE 3
Further, the data in the table 3 may be substituted into the step S3, that is, in the process of performing fault diagnosis on the faulty power station by using the AMI data, the fault of the distributed photovoltaic power station 3 to be detected may be diagnosed as a meter fault, the fault of the distributed photovoltaic power station 5 to be detected is an off-station fault, that is, an upper-level grid fault, and the fault of the distributed photovoltaic power station 10 to be detected is an in-station fault.
The invention has the following beneficial effects:
according to the distributed photovoltaic power station fault diagnosis method, the distributed photovoltaic power station fault can be quickly identified, accurately positioned and diagnosed due to the fault only through AMI data, so that the fault troubleshooting efficiency can be improved, and the influence on the photovoltaic power generation efficiency after the power station fault is reduced.
Corresponding to the distributed photovoltaic power station fault diagnosis method based on the AMI data in the embodiment, the invention also provides a distributed photovoltaic power station fault diagnosis device based on the AMI data.
As shown in fig. 3, the distributed photovoltaic power plant fault diagnosis apparatus based on AMI data according to the embodiment of the present invention includes a sample module 10, a modeling module 20, a calculation module 30, an identification module 40, and a diagnosis module 50. The sample module 10 is used for constructing a training sample library and a testing sample library of the distributed photovoltaic power station; the modeling module 20 is used for establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library; the calculation module 30 is used for calculating a linear regression function of the power generation operation model; the identification module 40 is used for identifying the fault power station in the test sample library according to a linear regression function; the diagnosis module 50 is used for performing fault diagnosis on the fault power station by adopting AMI data.
In an embodiment of the present invention, the sample module 10 may be specifically configured to obtain first-class power station operation information and first-class power station environment information of a normally operating distributed photovoltaic power station, then construct a training sample library according to the first-class power station operation information and the first-class power station environment information, further obtain second-class power station operation information and second-class power station environment information of a distributed photovoltaic power station to be tested, and finally construct a test sample library according to the second-class power station operation information and the second-class power station environment information.
The first-class power station operation information of the plurality of groups of normally-operated distributed photovoltaic power stations can comprise power station file information and power station measuring meter information of the plurality of groups of normally-operated distributed photovoltaic power stations; the first-class power station environmental information of the plurality of groups of normally operating distributed photovoltaic power stations can comprise meteorological environmental information of the plurality of groups of normally operating distributed photovoltaic power stations; in addition, the second type of power station operation information of the distributed photovoltaic power station to be detected can comprise power station file information, power station meter information, correlation meter information and same meter box meter information in an AMI system of the distributed photovoltaic power station to be detected; the second type of power station environment information of the distributed photovoltaic power station to be tested can comprise meteorological environment information in an AMI system of the distributed photovoltaic power station to be tested.
More specifically, the power station archive information of the multiple groups of normally-operating distributed photovoltaic power stations and distributed photovoltaic power stations to be tested can include corresponding power station house numbers, installed capacities and photovoltaic module type information; the power station measuring meter information of the plurality of groups of normally operating distributed photovoltaic power stations and distributed photovoltaic power stations to be tested can comprise corresponding daily generated energy, high-density voltage, current and power information; the correlation meter information of the multiple groups of normally-operated distributed photovoltaic power stations and the distributed photovoltaic power station to be tested can comprise corresponding on-line electric quantity, high-density voltage, current and power information; the meter information of the same meter box of the multiple groups of normally operating distributed photovoltaic power stations and the distributed photovoltaic power station to be tested can comprise corresponding high-density voltage, current and power information; the meteorological environment information of the multiple groups of normally-operated distributed photovoltaic power stations and the distributed photovoltaic power stations to be detected can comprise corresponding power station area solar average irradiance, power station area environment average temperature, power station area environment average humidity, power station area ground average air pressure and power station area environment average air speed.
In an embodiment of the present invention, the modeling module 20 may be specifically configured to determine a photovoltaic module type of a distributed photovoltaic power station that normally operates in the training sample library, and then classify the distributed photovoltaic power station that normally operates in the training sample library according to the photovoltaic module type, so as to establish a power generation operation model according to a classification result. The photovoltaic module types can include monocrystalline silicon photovoltaic modules, polycrystalline silicon photovoltaic modules, amorphous silicon photovoltaic modules, double-sided monocrystalline silicon photovoltaic modules and double-sided polycrystalline silicon photovoltaic modules.
More specifically, the distributed photovoltaic power stations which normally operate in the training sample library can be classified according to the types of the photovoltaic components, namely monocrystalline silicon photovoltaic components, polycrystalline silicon photovoltaic components, amorphous silicon photovoltaic components, double-sided monocrystalline silicon photovoltaic components and double-sided polycrystalline silicon photovoltaic components, and a power generation operation model can be respectively established for each type of the distributed photovoltaic power stations which normally operate.
The power generation operation model of each type of normally-operated distributed photovoltaic power station can be expressed as follows:
y＝f(x 1 ,x 2 ,x 3 ,x 4 ,x 5 )
wherein y represents the unit power generation amount of each type of normally operating distributed photovoltaic power station, and x 1 Representing the mean solar irradiance, x, of the power station area 2 Indicating the average temperature of the power station environmentDegree, x 3 Representing the average humidity, x, of the plant environment 4 Representing the mean pressure, x, of the ground of the station 5 Representing the average wind speed of the plant environment.
In an embodiment of the present invention, the calculation module 30 may be specifically configured to process the power generation operation model by using linear regression fitting to obtain a linear regression function of the power generation operation model, and may define the normal power generation threshold of the distributed photovoltaic power station according to the linear regression function.
More specifically, it may be preset that a matrix formed by meteorological environment information of various normally operating distributed photovoltaic power stations in the training sample library is X, and a matrix formed by unit power generation of various normally operating distributed photovoltaic power stations is Y (unit power generation of distributed photovoltaic power station to be measured is power generation of power station/power station capacity), then:
X＝[x ij ] 5×5
wherein i denotes each photovoltaic module type, and i 1, 2.., 5, j denotes a meteorological environment information type of the photovoltaic power plant, and j 1, 2.., 5;
further, the formula expansion may be:
further, the meteorological environment information matrix X inverse matrix sigma of various normally-running distributed photovoltaic power stations can be calculated -1 ：
Further, the regression coefficient β of the power generation operation model fitting linear regression function may be calculated:
further, the fitting intercept ε of the power generation operation model fitting linear regression function may be calculated:
from this, the linear regression function of the power generation operation model can be obtained as:
y＝ε+β 1 x 1 +.....+β 5 x 5
where ε represents the fitting intercept of the power generation operation model fitting linear regression function, β 1 Regression coefficient, beta, representing the mean solar irradiance of a power station area 2 Regression coefficient, beta, representing the average temperature of the plant environment 3 Regression coefficient, beta, representing the average humidity of the plant environment 4 Coefficient of regression, beta, representing the mean ground pressure of the station 5 And the regression coefficient represents the average wind speed of the power station environment.
In an embodiment of the present invention, the identification module 40 may be specifically configured to classify and process the distributed photovoltaic power stations to be tested in the test sample library according to the linear regression function and the normal power generation threshold, and then identify the faulty power stations in the test sample library according to the classification result.
More specifically, the data in the test sample library can be substituted into a linear regression function to obtain a test value of unit power generation of the distributed photovoltaic power station to be tested, the test value of the unit power generation can be compared with an actual value of the unit power generation, and the distributed photovoltaic power station to be tested in the test sample library can be classified by combining a normal power generation threshold. For example, if the generated energy test value/generated energy actual value is greater than the normal generation threshold value, the distributed photovoltaic power station to be tested is judged to be a high-efficiency operating power station, if the generated energy test value/generated energy actual value is less than the normal generation threshold value, the distributed photovoltaic power station to be tested is judged to be a normal operating power station, and if the generated energy test value/generated energy actual value is equal to the normal generation threshold value, the distributed photovoltaic power station to be tested is judged to be a fault operating power station. Therefore, the power station in the power failure area can be subjected to differentiated collaborative troubleshooting, and the troubleshooting efficiency can be improved.
In one embodiment of the present invention, as shown in FIG. 2, the operation of the diagnostic module 50 may include the following steps:
s501, obtaining voltage data, current data, correlation meter power data and voltage data measured by a meter with a meter box of a fault power station according to AMI data, wherein the voltage data and the current data of the fault power station can be obtained from the data measured by the power station of the fault power station;
s502, judging whether voltage data and current data of the fault power station are abnormal or not, wherein if the voltage data are normal and the current data are abnormal, executing S503, if the voltage data are abnormal and the current data are normal, executing S506, and if the voltage data and the current data are both abnormal, executing S509;
s503, judging whether the power data of the correlation meter is abnormal, wherein if the power data of the correlation meter is normal, executing the step S504, and if the power data of the correlation meter is abnormal, executing the step S505;
s504, judging the fault of the fault power station as a fault of the measuring meter;
s505, judging that the fault of the fault power station is an intra-station fault;
s506, judging whether the voltage data measured by the meter in the same meter box is abnormal, wherein if the voltage data measured by the meter in the same meter box is normal, executing the step S507, and if the voltage data measured by the meter in the same meter box is abnormal, executing the step S508;
s507, judging the fault of the fault power station as a fault of the measuring meter;
s508, judging that the fault of the fault power station is an off-station fault, namely a superior power grid fault;
s509, judging whether the power data of the association meter is abnormal, wherein if the power data of the association meter is normal, executing the step S510, and if the power data of the association meter is abnormal, executing the step S511;
s510, judging the fault of the fault power station as a fault of a measuring meter;
s511, judging whether the voltage data measured by the meter in the same meter box is abnormal, wherein if the voltage data measured by the meter in the same meter box is normal, executing the step S512, and if the voltage data measured by the meter in the same meter box is abnormal, executing the step S513;
s512, judging that the fault of the fault power station is an intra-station fault;
and S513, judging that the fault of the fault power station is an off-station fault, namely a fault of an upper-level power grid.
The practical application process of the distributed photovoltaic power station fault diagnosis device based on the AMI data of the present invention will be described below by taking the training sample library shown in table 1 and the testing sample library shown in table 2 as examples.
TABLE 1
TABLE 2
In one embodiment of the present invention, the data in Table 1 can be substituted into the calculation module 30 to calculate the linear regression function of the power generation operation model, so that the fitting intercept ε of the power generation operation model fitting the linear regression function is specifically 0.125, and the regression coefficient β of the solar average irradiance of the power station region is obtained 1 Specifically 0.605, regression coefficient beta of the average temperature of the power station environment 2 Specifically 0.153, regression coefficient beta of the average humidity of the power station environment 3 Specifically 0.336, regression coefficient beta of the mean ground pressure of the plant 4 Specifically 0.129, regression coefficient beta of the average wind speed of the power station environment 5 Specifically, 0.146, and thus,the linear regression function of the power generation operation model can be calculated as:
y＝0.125+0.605×10 -2 x 1 +0.153×10 -1 x 2 +0.336×10 -2 x 3 +0.129×10 -1 x 4 +0.146x 5 。
further, the normal power generation threshold of the distributed photovoltaic power plant may be defined according to a linear regression function of the power generation operation model, for example, the normal power generation threshold ρ may be defined in a range of [0.3, 0.8 ].
Further, whether the distributed photovoltaic power station to be tested in table 2 is a faulty power station or not can be identified by the identification module 40 according to the normal power generation threshold ρ, and specifically, the relationship between the distributed photovoltaic power stations to be tested 1,2, 3, 4, 5, 6, 7, 8, 9, 10 in table 2 and the normal power generation threshold ρ can be respectively determined. The generated energy test value/generated energy actual value of the distributed photovoltaic power stations 3, 5, and 10 to be tested is equal to the normal generation threshold value ρ, that is, the ratios 0.562, 0.389, and 0.618 of the distributed photovoltaic power stations 3, 5, and 10 to be tested all belong to the range of the normal generation threshold value ρ [0.3, 0.8], so that the distributed photovoltaic power stations 3, 5, and 10 to be tested can be identified as faulty power stations.
Further, corresponding power station measurement meter data (voltage data and current data), correlation meter power data and same meter box meter voltage data can be respectively obtained from AMI data of the distributed photovoltaic power stations 3, 5 and 10 to be measured, and are specifically shown in table 3.
TABLE 3
Further, the data in the table 3 can be substituted into the diagnosis module 50, and it can be obtained that the fault of the distributed photovoltaic power station 3 to be detected is a meter fault, the fault of the distributed photovoltaic power station 5 to be detected is an off-station fault, that is, a higher-level power grid fault, and the fault of the distributed photovoltaic power station 10 to be detected is an in-station fault.
The invention has the following beneficial effects:
according to the distributed photovoltaic power station fault diagnosis method and system, the faults of the distributed photovoltaic power station can be quickly identified, accurately positioned and diagnosed due to the faults only through AMI data, so that the fault troubleshooting efficiency can be improved, and the influence on the photovoltaic power generation efficiency after the power station faults are reduced.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The meaning of "plurality" is two or more unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature "under," "beneath," and "under" a second feature may be directly under or obliquely under the second feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Claims (10)
1. A distributed photovoltaic power station fault diagnosis method based on AMI data is characterized by comprising the following steps:
constructing a training sample library and a testing sample library of the distributed photovoltaic power station;
establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library;
calculating a linear regression function of the power generation operation model;
identifying a faulty power station in the test sample library according to the linear regression function;
and adopting AMI data to carry out fault diagnosis on the fault power station.
2. The fault diagnosis method for the distributed photovoltaic power station based on the AMI data as set forth in claim 1, wherein the fault diagnosis for the faulty power station using the AMI data specifically includes the steps of:
obtaining voltage data, current data, correlation meter power data and voltage data measured by the same meter box of the fault power station according to the AMI data;
judging whether the voltage data and the current data of the fault power station are abnormal or not;
if the voltage data are normal and the current data are abnormal, judging whether the power data of the correlation meter are abnormal or not;
if the associated meter power data is normal, judging that the fault of the fault power station is a meter fault;
if the power data of the association meter is abnormal, judging that the fault of the fault power station is an intra-station fault;
if the voltage data are abnormal and the current data are normal, judging whether the voltage data of the meter in the same meter box are abnormal or not;
if the voltage data of the meters in the same meter box is normal, judging that the fault of the fault power station is a meter measuring fault;
if the voltage data measured by the meter of the same meter box is abnormal, judging that the fault of the fault power station is an off-station fault;
if the voltage data and the current data are both abnormal, judging whether the power data of the correlation meter is abnormal;
if the associated meter power data is normal, judging that the fault of the fault power station is a meter fault;
if the power data of the associated meter is abnormal, judging whether the voltage data of the meter in the same meter box is abnormal;
if the voltage data measured by the meter in the same meter box is normal, judging that the fault of the fault power station is an in-station fault;
and if the voltage data measured by the meter with the meter box is abnormal, judging that the fault of the fault power station is an off-station fault.
3. The AMI data-based distributed photovoltaic power station fault diagnosis method of claim 1, wherein the building of the training sample library and the testing sample library of the distributed photovoltaic power station specifically comprises the following steps:
acquiring first-class power station operation information and first-class power station environment information of a normally-operated distributed photovoltaic power station;
constructing the training sample library according to the first type of power station operation information and the first type of power station environment information;
acquiring second type power station operation information and second type power station environment information of a distributed photovoltaic power station to be detected;
and constructing the test sample library according to the second type of power station operation information and the second type of power station environment information.
4. The AMI data-based distributed photovoltaic power plant fault diagnosis method of claim 3, wherein the establishing of the power generation operation model of the distributed photovoltaic power plant according to the training sample library specifically comprises the following steps:
determining the type of a photovoltaic component of a normally operating distributed photovoltaic power station in the training sample library;
classifying the normally-running distributed photovoltaic power stations in the training sample library according to the types of the photovoltaic components;
and establishing the power generation operation model according to the classification result.
5. The AMI data-based distributed photovoltaic power plant fault diagnosis method of claim 4, wherein the power generation operation model is:
y＝f(x 1 ,x 2 ,x 3 ,x 4 ,x 5 )
wherein y represents the unit power generation amount of the normally operating distributed photovoltaic power station, and x 1 Representing the mean solar irradiance, x, of the power station area 2 Representing the mean temperature of the plant environment, x 3 Representing the average humidity, x, of the plant environment 4 Representing the mean pressure, x, of the ground of the station 5 Representing the average wind speed of the plant environment.
6. The AMI data based distributed photovoltaic power plant fault diagnosis method of claim 5, wherein said photovoltaic module types include single crystal silicon photovoltaic modules, polycrystalline silicon photovoltaic modules, amorphous silicon photovoltaic modules, double sided single crystal silicon photovoltaic modules and double sided polycrystalline silicon photovoltaic modules.
7. The AMI data-based distributed photovoltaic power plant fault diagnosis method of claim 4, wherein said calculating a linear regression function of said power generation operation model comprises the steps of:
processing the power generation operation model by adopting linear regression fitting to obtain a linear regression function of the power generation operation model;
and defining the normal power generation threshold value of the distributed photovoltaic power station according to the linear regression function.
8. The AMI data-based distributed photovoltaic power plant fault diagnosis method of claim 7, wherein the linear regression function is:
y＝ε+β 1 x 1 +.....+β 5 x 5
wherein ε represents the fitting intercept of the power generation operation model to the linear regression function, β 1 Regression coefficient, beta, representing the mean solar irradiance of a power station area 2 Regression coefficient, beta, representing the average temperature of the plant environment 3 Regression coefficient, beta, representing the average humidity of the plant environment 4 Regression coefficient, beta, representing the mean ground pressure of a power station 5 A regression coefficient representing the average wind speed of the plant environment.
9. The AMI data-based distributed photovoltaic power plant fault diagnosis method of claim 7, wherein said identifying faulty power plants in said test sample library according to said linear regression function, comprises in particular the steps of:
classifying and processing the distributed photovoltaic power stations to be tested in the test sample library according to the linear regression function and the normal power generation threshold;
and identifying the fault power station in the test sample library according to the classification result.
10. A distributed photovoltaic power plant fault diagnosis device based on AMI data, characterized by includes:
the system comprises a sample module, a data processing module and a data processing module, wherein the sample module is used for constructing a training sample library and a testing sample library of the distributed photovoltaic power station;
the modeling module is used for establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library;
a calculation module for calculating a linear regression function of the power generation operation model;
the identification module is used for identifying the fault power station in the test sample library according to the linear regression function;
and the diagnosis module is used for carrying out fault diagnosis on the fault power station by adopting AMI data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210494740.XA CN115021675A (en) | 2022-05-07 | 2022-05-07 | Distributed photovoltaic power station fault diagnosis method and device based on AMI data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210494740.XA CN115021675A (en) | 2022-05-07 | 2022-05-07 | Distributed photovoltaic power station fault diagnosis method and device based on AMI data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115021675A true CN115021675A (en) | 2022-09-06 |
Family
ID=83069530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210494740.XA Pending CN115021675A (en) | 2022-05-07 | 2022-05-07 | Distributed photovoltaic power station fault diagnosis method and device based on AMI data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115021675A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116155763A (en) * | 2022-12-23 | 2023-05-23 | 比昂精准数字科技(成都)有限公司 | Priori knowledge-based Internet of things fault detection method for solar insecticidal lamp |
-
2022
- 2022-05-07 CN CN202210494740.XA patent/CN115021675A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116155763A (en) * | 2022-12-23 | 2023-05-23 | 比昂精准数字科技(成都)有限公司 | Priori knowledge-based Internet of things fault detection method for solar insecticidal lamp |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107346899A (en) | A kind of photovoltaic power station system stability assessment method and system | |
| CN111082749B (en) | Photovoltaic string running state identification method, device and storage medium | |
| JP6093465B1 (en) | Power generation diagnosis method and power generation diagnosis apparatus for solar power generation system | |
| CN108092622B (en) | Photovoltaic string fault diagnosis method based on resistance calculation | |
| CN111614317B (en) | IV curve scanning-based diagnosis method for shadow shielding of photovoltaic panel | |
| JP6185206B1 (en) | Method and apparatus for detecting abnormalities or signs of abnormalities in a photovoltaic system | |
| Kim et al. | Fault detection for photovoltaic systems using multivariate analysis with electrical and environmental variables | |
| Livera et al. | Failure diagnosis of short-and open-circuit fault conditions in PV systems | |
| CN107065829A (en) | A kind of photovoltaic module pollution diagnosis method supervised based on solar power generation under big data is excavated | |
| CN104485889A (en) | Failure detection method for photovoltaic power generation units with multiple same mounting dip angles | |
| CN115021675A (en) | Distributed photovoltaic power station fault diagnosis method and device based on AMI data | |
| Kohno et al. | Fault-diagnosis architecture for large-scale photovoltaic power plants that does not require additional sensors | |
| Leloux et al. | Automatic fault detection on BIPV systems without solar irradiation data | |
| TWI671996B (en) | Method for judging the orientation of a solar power module | |
| Oozeki et al. | An evaluation method for PV system to identify system losses by means of utilizing monitoring data | |
| Benninger et al. | Anomaly detection by comparing photovoltaic systems with machine learning methods | |
| van Sark et al. | PV system monitoring and characterization | |
| King et al. | Array performance characterization and modeling for real-time performance analysis of photovoltaic systems | |
| KR102645222B1 (en) | PV system diagnostic device through voltage and current estimation of solar modules | |
| Qamar et al. | Performance Analysis of First Grid Connected PV Power Plant in Subtropical Climate of Pakistan | |
| Harrou et al. | Fault Detection in Solar PV Systems Using Hypothesis Testing | |
| Zhao et al. | Fault Monitoring Strategy for PV System Based on IV Feature Library | |
| TW201537888A (en) | Diagnostic method for solar apparatus | |
| JP2023152514A (en) | Soundness diagnosis system and method for photovoltaic power generation device | |
| Wang et al. | Fault Diagnosis Method of Photovoltaic Array Based on BP 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 |