CN112730968A - Neural network-based photovoltaic grid-connected power station fault type detection device - Google Patents
Neural network-based photovoltaic grid-connected power station fault type detection device Download PDFInfo
- Publication number
- CN112730968A CN112730968A CN202110046104.6A CN202110046104A CN112730968A CN 112730968 A CN112730968 A CN 112730968A CN 202110046104 A CN202110046104 A CN 202110046104A CN 112730968 A CN112730968 A CN 112730968A
- Authority
- CN
- China
- Prior art keywords
- module
- photovoltaic
- current
- output
- value
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 title claims abstract description 13
- 238000005286 illumination Methods 0.000 claims abstract description 29
- 238000004891 communication Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 229910002056 binary alloy Inorganic materials 0.000 claims description 2
- 238000010248 power generation Methods 0.000 description 4
- 230000000903 blocking effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/25—Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
-
- 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
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Photovoltaic Devices (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
A photovoltaic grid-connected power station fault type detection device based on a neural network is characterized by comprising: the device comprises a photovoltaic module array, a measuring module, a control module, a communication module and an illumination measuring instrument; and detecting whether the photovoltaic array has fault types such as hot spots, hidden cracks, sheltering and the like by adopting a BP neural network calculation method according to the illumination value output by the current illumination measuring instrument and the current and voltage values of the photovoltaic array.
Description
Technical Field
The invention relates to a photovoltaic grid-connected power station fault type detection device based on environmental illumination measurement, and belongs to the technical field of solar photovoltaic power generation.
Background
With the urgent need of new energy application, the scale of solar photovoltaic power generation is continuously enlarged, and each link of operation, maintenance, management and the like of photovoltaic power generation urgently needs intelligent transformation and upgrading to improve efficiency and reduce cost. Therefore, the working state of each photovoltaic cell panel needs to be known accurately in real time. Although some monitoring methods exist at present, the operation state of the photovoltaic module cannot be judged correctly. Such as the technical method disclosed in patent application No. 2020203163891 "a component level photovoltaic power plant fault detection system". Because the working state of the photovoltaic cell module is greatly influenced by the illumination, the operating state of the photovoltaic module cannot be accurately judged only by detecting the voltage of the output end. Generally, the user can know the fault, the burning and even the development of a disaster accident of a certain battery panel only when the certain battery panel is in fault, the burning and even the development of the disaster accident, and the serious loss is caused at night. The existing photovoltaic power station can only monitor a string of photovoltaic modules, cannot consider the influence of environmental illumination, cannot determine the type of a fault, and cannot meet the operation and maintenance requirements of a large-scale photovoltaic power station.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a photovoltaic grid-connected power station fault type detection device based on a neural network, which can detect and judge the fault type of a photovoltaic component; it is characterized by comprising: the device comprises a photovoltaic module array, a measuring module, a control module, a communication module and an illumination measuring instrument; the photovoltaic array is formed by connecting a plurality of photovoltaic modules in series; the measuring module comprises a voltage sampling module and a current sampling module; the output end of the photovoltaic module array is connected with the input end of the measuring module; the output end of the measuring module is connected with the input end of the control module; the output end of the control module is connected with the input end of the communication module;
the communication module is used for transmitting the current system state and the fault detection result.
The illuminance measuring instrument is arranged near the field of the photovoltaic module, and the output end of the illuminance measuring instrument is connected with the input end of the control module and used for measuring the solar irradiation quantity of the current environmental field; the control module detects whether the photovoltaic array has faults such as hot spots, hidden cracks, sheltering and the like by adopting a BP neural network calculation method according to the illumination value output by the current illumination measuring instrument and the current and voltage values of the photovoltaic array, and the steps are as follows:
step 1 obtaining BP neural network learning sample
Selecting sunny weather, carrying out integral point division on time periods from 6 morning to 6 evening, respectively selecting three conditions of normal operation, shadow shielding, hot spot or hidden crack of a photovoltaic module, setting G as illumination, V as voltage, I as current and t as time, wherein t is 1,21,G2,...,GmVoltage value V1,V2,..., VmValue of current I1,I2,...,ImAnd collecting sample values for more than 50 days as BP neural network learning samples.
1) Selecting input and output samples;
converting the values of time t, illumination G, voltage V and current I into binary; when the photovoltaic array generates electricity normally, the output d is equal to 0; when the photovoltaic array has hot spots or hidden crack faults, the output d is equal to 1; when the photovoltaic array has a shadow blocking fault, the output d is equal to-1. Then:
2) selecting a primary weight w;
3) repeating the following process, inputting all samples until convergence;
(1) input sample x, calculate the layer outputs:
yl=f(vtl)=f(wlyl-1)
(2) calculating an output layer error:
(3) calculating the local gradient deltaj,δk
(4) Correcting the weight of the output layer:
wk←wk+ηΔwk
(5) correcting the weight of the hidden layer:
wj←wj+ηΔwj
(6) enter new sample x until all samples are entered and E<EmaxAnd then the process is finished.
Step 4, obtaining the current illumination value, voltage value and current value
Reading an illuminance value of the illuminance measuring instrument; acquiring a voltage value V through a photovoltaic array terminal voltage sampling module; and acquiring a current value I through a photovoltaic array end current sampling module, and sending the current value I to a control module.
Step 5, adopting BP neural network to detect
The current time t, the illumination value G, the voltage value V and the current value I are input into the BP neural network as an input vector x, and then an output value d of the network can be calculated. When the output value d is equal to 0, the photovoltaic array is considered to be normal, when d is equal to 1, the photovoltaic array is considered to have hot spots or hidden crack faults, and when d is equal to-1, the photovoltaic array is considered to have shadow shielding faults.
The photovoltaic module fault type detection method has the beneficial effects that the fault type detection of the photovoltaic module can be realized according to the measured value of an environment illumination measuring instrument and the current and voltage parameters of the photovoltaic module.
Drawings
FIG. 1 is a schematic structural diagram of a fault type detection device of a photovoltaic grid-connected power station based on a neural network.
FIG. 2 is a flow chart of a computing method employing a BP neural network.
FIG. 3 shows that whether the photovoltaic module has faults such as hidden cracks, hot spots and the like is judged according to the combination of the current value and the voltage value of the kth photovoltaic module.
Detailed description of the preferred embodiments
The device for detecting the fault type of the photovoltaic grid-connected power station based on the neural network as shown in the attached figure 1 is characterized by comprising the following components: the device comprises a photovoltaic array, a measuring module, a control module, a communication module and an illumination measuring instrument; the photovoltaic array is formed by connecting a plurality of photovoltaic modules in series; the measuring module comprises a voltage sampling module and a current sampling module; the output end of the photovoltaic array is connected with the input end of the measuring module; the output end of the measuring module is connected with the input end of the control module; the output end of the control module is connected with the input end of the communication module;
the communication module is used for transmitting the current system state and the fault detection result.
The illuminance measuring instrument is installed near the field of the photovoltaic module, and the output end of the illuminance measuring instrument is connected with the input end of the control module and used for measuring the solar irradiation amount of the current environment field.
As shown in fig. 2 and fig. 3, the control module detects whether the photovoltaic module has hot spots, hidden cracks, shelters and other faults by adopting a calculation method of a BP neural network according to the illuminance value output by the current illuminance measuring instrument and the current and voltage values of the photovoltaic module, and the steps are as follows:
step 1 obtaining BP neural network learning sample
Selecting sunny weather, carrying out integral point division on time periods from 6 morning to 6 evening, respectively selecting three conditions of normal operation, shadow shielding, hot spot or hidden crack of a photovoltaic module, setting G as illumination, V as photovoltaic module voltage, I as current and t as time, wherein t is 1,21,G2,...,GmVoltage value V of photovoltaic module1,V2,...,VmValue of current I1,I2,...,ImAnd collecting sample values for more than 50 days as BP neural network learning samples.
1) Selecting input and output samples;
converting values of time t, illumination G, photovoltaic module voltage V and current I into binary systems; when the photovoltaic array generates electricity normally, the output d is equal to 0; when the photovoltaic array has hot spots or hidden crack faults, the output d is equal to 1; when the photovoltaic array has a shadow blocking fault, the output d is equal to-1. Then:
2) selecting a primary weight w;
3) repeating the following process, inputting all samples until convergence;
(1) input sample x, calculate the layer outputs:
yl=f(vtl)=f(wlyl-1)
(2) calculating an output layer error:
(3) calculating the local gradient deltaj,δk
(4) Correcting the weight of the output layer:
wk←wk+ηΔwk
(5) correcting the weight of the hidden layer:
wj←wj+ηΔwj
(6) enter new sample x until all samples are entered and E<EmaxAnd then the process is finished.
Step 4, acquiring the current illumination value, the voltage value and the current value of the photovoltaic module
Reading an illuminance value of the illuminance measuring instrument; acquiring a voltage value V through a photovoltaic array terminal voltage sampling module; and acquiring a current value I through a photovoltaic array end current sampling module, and sending the current value I to a control module.
Step 5, adopting BP neural network to detect
The current time t, the illumination value G, the voltage value V and the current value I are input into the BP neural network as an input vector x, and then an output value d of the network can be calculated. When the output value d is equal to 0, the photovoltaic array is considered to be normal, when d is equal to 1, the photovoltaic array is considered to have hot spots or hidden crack faults, and when d is equal to-1, the photovoltaic array is considered to have shadow shielding faults.
Therefore, the states of all positions of the photovoltaic module are distinguished, the position illumination of normal power generation is normal, the position illumination shielded by the shadow can be reduced, and the position illumination with hot spots and hidden cracks can be increased.
The components, processes and letters that are not described in detail in this embodiment are well known in the art and are not described in detail herein.
Claims (2)
1. A photovoltaic grid-connected power station fault type detection device based on a neural network is characterized by comprising: the device comprises a photovoltaic array, a measuring module, a control module, a communication module and an illumination measuring instrument; the photovoltaic array is formed by connecting a plurality of photovoltaic modules in series;
the output end of the photovoltaic array is connected with the input end of the measuring module; the output end of the measuring module is connected with the input end of the control module; the output end of the control module is connected with the input end of the communication module;
the measuring module comprises voltage sampling modules and current sampling modules, the number of the voltage sampling modules is the same as that of the photovoltaic modules, the input end of each voltage sampling module is connected with the output end of the corresponding photovoltaic module, and the input end of each current sampling module is connected with the output end of any photovoltaic module and used for collecting the output voltage and the output current of the photovoltaic array in real time;
the communication module is used for transmitting the current system state and the fault detection result.
2. The device for detecting the fault type of the photovoltaic grid-connected power station based on the neural network as claimed in claim 1, wherein the illuminance measuring instrument is installed near a photovoltaic module field, and the output end of the illuminance measuring instrument is connected with the input end of the control module and is used for measuring the solar irradiation amount of the current environmental field; the control module detects whether the photovoltaic module has faults such as hot spots, hidden cracks, sheltering and the like by adopting a BP neural network calculation method according to the illumination value output by the illumination measuring instrument and the current and voltage values of the photovoltaic module at present, and the steps are as follows:
step 1 obtaining BP neural network learning sample
Selecting sunny weather, carrying out integral point division on time periods from 6 morning to 6 evening, respectively selecting three conditions of normal operation, shadow shielding, hot spot or hidden crack of a photovoltaic module, setting G as illumination, V as voltage of the photovoltaic module, I as current and t as time, wherein t is 1,21,G2,...,GmVoltage value V of photovoltaic module1,V2,...,VmValue of current I1,I2,...,ImCollecting sample values for more than 50 days as BP neural network learning samples;
step 2, learning by adopting BP neural network
1) Selecting input and output samples;
converting values of time t, illumination G, voltage V and current I of the photovoltaic module into binary systems; when the photovoltaic array generates electricity normally, the output d is equal to 0; when the photovoltaic array has hot spots or hidden crack faults, the output d is equal to 1; when the photovoltaic array has a shadow shielding fault, the output d is equal to-1
Then:
2) selecting a primary weight w;
3) repeating the following process, inputting all samples until convergence;
(1) input sample x, calculate the layer outputs:
yl=f(vtl)=f(wlyl-1)
(2) calculating an output layer error:
(3) calculating the local gradient deltaj,δk
(4) Correcting the weight of the output layer:
wk←wk+ηΔwk
(5) correcting the weight of the hidden layer:
wj←wj+ηΔwj
(6) enter new sample x until all samples are entered and E < EmaxThen the process is finished;
step 4, acquiring the current illumination value, the voltage value and the current value of the photovoltaic module
Reading an illuminance value of the illuminance measuring instrument; acquiring a voltage value V of the photovoltaic module through a voltage sampling module; acquiring a current value I through a current sampling module, and sending the current value I to a control module;
step 5, adopting BP neural network to detect
Inputting the current time t, the illumination value G, the voltage value V and the current value I of the photovoltaic module as input vectors x into the BP neural network, and calculating an output value d of the network;
when the output value d is equal to 0, the photovoltaic module is considered to be normal, when the output value d is equal to 1, the photovoltaic module is considered to have hot spot or hidden crack fault, and when the output value d is equal to-1, the photovoltaic module is considered to have shadow shielding fault.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110046104.6A CN112730968A (en) | 2021-01-14 | 2021-01-14 | Neural network-based photovoltaic grid-connected power station fault type detection device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110046104.6A CN112730968A (en) | 2021-01-14 | 2021-01-14 | Neural network-based photovoltaic grid-connected power station fault type detection device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112730968A true CN112730968A (en) | 2021-04-30 |
Family
ID=75592926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110046104.6A Pending CN112730968A (en) | 2021-01-14 | 2021-01-14 | Neural network-based photovoltaic grid-connected power station fault type detection device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112730968A (en) |
-
2021
- 2021-01-14 CN CN202110046104.6A patent/CN112730968A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105375878B (en) | A kind of method of on-line checking and assessment photovoltaic system efficiency | |
CN108964606B (en) | Hot spot fault detection method for photovoltaic system | |
US8461718B2 (en) | Photovoltaic array systems, methods, and devices with bidirectional converter | |
CN104601108A (en) | Small photovoltaic power station fault diagnosis method | |
CN106100579B (en) | A kind of photovoltaic plant method for diagnosing faults based on data analysis | |
Ma et al. | Photovoltaic module current mismatch fault diagnosis based on IV data | |
CN113037214B (en) | Photovoltaic module shadow shielding fault diagnosis method based on S-V curve | |
WO2017169473A1 (en) | Power generation diagnosis method and power generation diagnosis device for photovoltaic power generation system | |
CN107945046B (en) | New energy power station output data restoration method and device | |
CN104485889A (en) | Failure detection method for photovoltaic power generation units with multiple same mounting dip angles | |
JP2022042469A (en) | Power generation prediction and efficiency diagnosis system for photovoltaic power generation facility using frbfnn model | |
CN111027723A (en) | Photovoltaic and building integrated system and method | |
Djalab et al. | Robust method for diagnosis and detection of faults in photovoltaic systems using artificial neural networks | |
CN110022130A (en) | A kind of photovoltaic array fault test set and method | |
CN111711414B (en) | Photovoltaic power station fault detection device with maximum power | |
Wang et al. | A linear integer programming model for fault diagnosis in active distribution systems with bi-directional fault monitoring devices installed | |
CN117332920A (en) | New energy station operation fault evolution analysis method | |
CN112730968A (en) | Neural network-based photovoltaic grid-connected power station fault type detection device | |
CN112630522A (en) | Photovoltaic grid-connected power station fault type detection device based on temperature lattice measurement | |
CN112630521A (en) | Photovoltaic grid-connected power station fault detection device based on BP neural network | |
CN112564624A (en) | Photovoltaic off-grid power station fault detection device based on illumination measurement and neural network | |
CN112564619A (en) | Photovoltaic off-grid power station fault detection device based on temperature measurement | |
CN115296615A (en) | Hopfield neural network-based photovoltaic power station fault diagnosis method | |
CN110868155A (en) | Method for measuring matching loss of photovoltaic string | |
CN112564623A (en) | Neural network fault detection device of photovoltaic off-grid power station |
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 |