CN105811881A - On-line photovoltaic array fault diagnosis system implementing method - Google Patents
On-line photovoltaic array fault diagnosis system implementing method Download PDFInfo
- Publication number
- CN105811881A CN105811881A CN201610364749.3A CN201610364749A CN105811881A CN 105811881 A CN105811881 A CN 105811881A CN 201610364749 A CN201610364749 A CN 201610364749A CN 105811881 A CN105811881 A CN 105811881A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic array
- circuit
- fault diagnosis
- voltage
- current
- 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.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 6
- 238000005070 sampling Methods 0.000 claims abstract description 10
- 238000004891 communication Methods 0.000 claims abstract description 3
- 230000007257 malfunction Effects 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 description 6
- 238000005286 illumination Methods 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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)
Abstract
The invention relates to an on-line photovoltaic array fault diagnosis system implementing method.The implementing method includes sampling input variables of a photovoltaic array fault diagnosis model through an inverter; transferring the input variables to an upper computer software through a communication circuit; processing the input variables through the upper computer software and inputting results to the fault diagnosis model; and displaying output results of the fault diagnosis model on an interface of the upper computer.According to the on-line photovoltaic array fault diagnosis system implementing method, traditional photovoltaic grid connected inverters are enabled to have a function of on-line photovoltaic array fault diagnosis.
Description
Technical field
The present invention relates to technical field of new energies, particularly a kind of online diagnosing failure of photovoltaic array network system realization.
Background technology
In photovoltaic generation, the fault of photovoltaic array is one of major reason affecting photovoltaic system generating efficiency, therefore monitoring in real time and its fault diagnosis is had great importance photovoltaic array fault.The major effect of photovoltaic array fault is hot spot phenomenon, so-called hot spot phenomenon refers to that photovoltaic array is in actual use, be likely to occur solar panel crackle or do not mate, internal Joint failure, local are blocked or make dirty etc. situation, causing that the characteristic of one piece or one group solaode is inharmonious with overall permanence, this causes the electric current that the electric current of its generation can produce less than other solaodes not being blocked.Therefore, according to Kirchhoff's second law, these solaodes being blocked will electronegative be pressed, form the load in circuit, and consume, with the form of heat, the energy that the solaode of other normal operation produces, this heat accumulates the encapsulating material that can destroy solar panel for a long time, even destroys the physical arrangement of solar panel, and will result in permanent damage.Simultaneously, when due to the reason such as shade, dust, some solar panel in photovoltaic array occurs that partial occlusion makes its external condition such as illumination and temperature change, the solaode output characteristics being blocked can change, photovoltaic array can be made to produce multimodal situation, the power of each peak value is different, if photovoltaic array longtime running can make the efficiency of whole system reduce at the peak value not being global maximum power point.Sum it up, the fault of photovoltaic array can reduce the generating efficiency of photovoltaic generating system, and hot spot phenomenon can shorten the life-span of solar panel, causes the increase of cost of electricity-generating.
Summary of the invention
In view of this, the purpose of the present invention is to propose to a kind of online diagnosing failure of photovoltaic array network system realization, the photovoltaic combining inverter improved is utilized to realize the sampling of diagnosing failure of photovoltaic array mode input amount, fault diagnosis model is realized by PC end host computer, the data collected by combining inverter are delivered to host computer and are processed, it is achieved that the on-line fault diagnosis that photovoltaic array is monitored in real time.
The present invention adopts below scheme to realize: a kind of online diagnosing failure of photovoltaic array network system realization, specifically includes following steps:
Step S1: traditional photovoltaic combining inverter is improved, samples to the input variable of diagnosing failure of photovoltaic array model；
Step S2: by the step S1 input variable sampled by telecommunication circuit, deliver to host computer；
Step S3: host computer adopts fault diagnosis algorithm that input variable is processed, and result is input in fault diagnosis model；
Step S4: host computer shows the output result of fault diagnosis model in interface.
Further, described traditional photovoltaic combining inverter is improved particularly as follows: on traditional photovoltaic combining inverter use voltage and current Hall element, in order to the output voltage of photovoltaic array and electric current to be measured, and MAX232 chip is used to realize the communication of controller and host computer in inverter control circuit；Meanwhile, the sample circuit of the combining inverter of this improvement also has a voltage sampling circuit that can external voltage be measured and a current sampling circuit that can foreign current be measured.
Further, described can to external voltage measurement voltage sampling circuit and one can to foreign current measurement current sampling circuit obtain open-circuit voltage and short circuit current in order to obtain normal moment photovoltaic array；The normal open-circuit voltage of moment photovoltaic array and the acquisition of short circuit current are by two blocks of external reference solar panel plates, namely for the photovoltaic array of m × x, measure the open-circuit voltage U of two pieces of external reference solar panels respectivelyocWith short circuit current Isc, then the open-circuit voltage of normal moment photovoltaic array is:
m×Uoc,
Short circuit current is:
n×Isc。
Further, described fault diagnosis model includes ground floor input layer, second layer hidden layer, third layer output layer；The input variable of described input layer is Ulastmpp、Ilastmpp、Uoc、Isc, wherein UlastmppRepresent the output voltage values of last local maximum power point of photovoltaic array, IlastmppRepresent the output current value of last local maximum power point of photovoltaic array, UocRepresent the open-circuit voltage with reference to solar panel, IscRepresent the short circuit current with reference to solar panel；Described hidden layer uses linear kernel function；Described output layer includes four kinds of malfunctions of respectively corresponding 1,2,3,4, and wherein 1 is corresponding normal, 2 corresponding short circuits, 3 corresponding open circuits, 4 corresponding shades；Wherein, input layer uses normalization to carry out pretreatment, and its process formula is:
Wherein,It is the input data after normalization.
Further, described fault diagnosis algorithm, particularly as follows: the fault type of photovoltaic array is divided into normal, short-circuit, open circuit and four kinds of types of shade, uses genetic algorithm combination supporting vector machine algorithm to realize the diagnosis of photovoltaic array fault type in host computer；Wherein genetic algorithm is for the optimal parameters selection of support vector machine Kernel Function.
Further, described host computer adopts MatlabGUI to write, in order to realize the input of photovoltaic array real time data, the genetic algorithm-operation of fault diagnosis model of support vector machine training, interface display.
Compared with prior art, the present invention realizes the measurement of diagnosing failure of photovoltaic array mode input variable by the combining inverter improved, the realization of fault diagnosis model is realized by the host computer of PC end, it is capable of photovoltaic array in the diagnosis being in normal, short-circuit, open circuit and four malfunctions of shade, and in host computer, displays early warning.
Accompanying drawing explanation
Fig. 1 is diagnosing failure of photovoltaic array model in the embodiment of the present invention.
Fig. 2 is normalized training two-dimensional distribution in the embodiment of the present invention.
Fig. 3 is diagnosing failure of photovoltaic array result schematic diagram in the embodiment of the present invention.
The host computer that Fig. 4 is in the embodiment of the present invention shows Fig. 1.
The host computer that Fig. 5 is in the embodiment of the present invention shows Fig. 2.
The host computer that Fig. 6 is in the embodiment of the present invention shows Fig. 3.
The host computer that Fig. 7 is in the embodiment of the present invention shows Fig. 4.
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention will be further described.
Present embodiments provide a kind of online diagnosing failure of photovoltaic array network system realization, specifically include following steps:
Step S1: traditional photovoltaic combining inverter is improved, samples to the input variable of diagnosing failure of photovoltaic array model；
Step S2: by the step S1 input variable sampled by telecommunication circuit, deliver to host computer；
Step S3: host computer adopts fault diagnosis algorithm that input variable is processed, and result is input in fault diagnosis model；
Step S4: host computer shows the output result of fault diagnosis model in interface.
In the present embodiment, for the photovoltaic array of 6x2, utilize the architecture of support vector machine to build the SVM diagnostic cast (as shown in Figure 1) of three layers, be ground floor input layer, second layer hidden layer and third layer output layer respectively.Wherein input layer is Ulastmpp、Ilastmpp、UocAnd Isc, the input variable of fault model such as table 1, hidden layer uses linear kernel function, and output layer is distinguished corresponding four kinds of malfunctions by 1,2,3 with 4, such as table 2.
Table 1 fault diagnosis model input variable
The implication of table 2 fault diagnosis model output layer
Wherein, input layer uses normalization to carry out pretreatment, and its formula is:
Wherein, UlastmppAnd IlastmppFor the voltage and current original input data that last maximum power point of photovoltaic array is corresponding；UocData are actually entered for photovoltaic array open-circuit voltage；IscData are actually entered for photovoltaic array short circuit current；WithFor the input data after normalization.
Having carried out preliminary experimental verification on the photovoltaic combining inverter improved, the photovoltaic array that 12 pieces of photovoltaic modules constitute 6x2 blocks research, adopts Asia to make every effort to overcome plate and blocks, and its shadow factor is about 0.6.
The acquisition of confirmatory experiment desired data, carries out at cloudy day and fine day respectively, measures corresponding voltage and the electric current of photovoltaic array last maximum power point at varying environment temperature and intensity of illumination, and measures its open-circuit voltage U respectively by two pieces of reference plates measurementsocWith short circuit current Isc, the therefore open-circuit voltage of the photovoltaic array in normal moment and electric current respectively 6 × UocWith 2 × Isc.Have passed through long test, achieve the data of 20290 groups altogether, randomly select 10145 groups of data as training set sample, and using remaining 10145 groups of data as test set sample.
Data can be obtained as in figure 2 it is shown, include normal condition, open fault state, short trouble state, shadow state respectively by drawing in two-dimensional coordinate system after normalization.Wherein shadow state can be allocated as not only triangle " △ ", round dot " ", five-pointed star " ☆ " and star word " * " respectively but also be represent four kinds in various degree under shade malfunction, but it is all classified as shade fault by us in testing.
Utilizing the algorithm model of design, recording its fault diagnosis accuracy is 99.9901% (10144/10145).Test result is drawn in two-dimensional coordinate system, as shown in Figure 3.Vertical coordinate is malfunction type, and abscissa is training or the numbering of test sample, it can be seen that only has a test sample and is diagnosed mistake.Adopting Matlab to write fault in diagnostic software at host computer, the result classified for various malfunctions shows as shown in Figure 4, and the data of input can be carried out real-time fault detect and classification by software, and result are shown on interface.
The foregoing is only presently preferred embodiments of the present invention, all equalizations done according to the present patent application the scope of the claims change and modify, and all should belong to the covering scope of the present invention.
Claims (6)
1. diagnosing failure of photovoltaic array network system realization one kind online, it is characterised in that: comprise the following steps:
Step S1: traditional photovoltaic combining inverter is improved, samples to the input variable of diagnosing failure of photovoltaic array model；
Step S2: by the step S1 input variable sampled by telecommunication circuit, deliver to host computer；
Step S3: host computer adopts fault diagnosis algorithm that input variable is processed, and result is input in fault diagnosis model；
Step S4: host computer shows the output result of fault diagnosis model in interface.
2. a kind of online diagnosing failure of photovoltaic array network system realization according to claim 1, it is characterized in that: described traditional photovoltaic combining inverter is improved particularly as follows: on traditional photovoltaic combining inverter use voltage and current Hall element, in order to the output voltage of photovoltaic array and electric current to be measured, and MAX232 chip is used to realize the communication of controller and host computer in inverter control circuit；Meanwhile, the sample circuit of the combining inverter of this improvement also has a voltage sampling circuit that can external voltage be measured and a current sampling circuit that can foreign current be measured.
3. a kind of online diagnosing failure of photovoltaic array network system realization according to claim 2, it is characterised in that: described can to external voltage measurement voltage sampling circuit and one can to foreign current measurement current sampling circuit obtain open-circuit voltage and short circuit current in order to obtain normal moment photovoltaic array；The normal open-circuit voltage of moment photovoltaic array and the acquisition of short circuit current are by two blocks of external reference solar panel plates, namely for the photovoltaic array of m × x, measure the open-circuit voltage U of two pieces of external reference solar panels respectivelyocWith short circuit current Isc, then the open-circuit voltage of normal moment photovoltaic array is:
m×Uoc,
Short circuit current is:
n×Isc。
4. a kind of online diagnosing failure of photovoltaic array network system realization according to claim 1, it is characterised in that: described fault diagnosis model includes ground floor input layer, second layer hidden layer, third layer output layer；The input variable of described input layer is Ulastmpp、Ilastmpp、Uoc、Isc, wherein UlastmppRepresent the output voltage values of last local maximum power point of photovoltaic array, IlastmppRepresent the output current value of last local maximum power point of photovoltaic array, UocRepresent the open-circuit voltage with reference to solar panel, IscRepresent the short circuit current with reference to solar panel；Described hidden layer uses linear kernel function；Described output layer includes four kinds of malfunctions of respectively corresponding 1,2,3,4, and wherein 1 is corresponding normal, 2 corresponding short circuits, 3 corresponding open circuits, 4 corresponding shades；Wherein, input layer uses normalization to carry out pretreatment, and its process formula is:
Wherein,It is the input data after normalization.
5. a kind of online diagnosing failure of photovoltaic array network system realization according to claim 1, it is characterized in that: described fault diagnosis algorithm, particularly as follows: the fault type of photovoltaic array is divided into normal, short-circuit, open circuit and four kinds of types of shade, uses genetic algorithm combination supporting vector machine algorithm to realize the diagnosis of photovoltaic array fault type in host computer；Wherein genetic algorithm is for the optimal parameters selection of support vector machine Kernel Function.
6. a kind of online diagnosing failure of photovoltaic array network system realization according to claim 1, it is characterized in that: described host computer adopts MatlabGUI to write, in order to realize the input of photovoltaic array real time data, the genetic algorithm-operation of fault diagnosis model of support vector machine training, interface display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610364749.3A CN105811881B (en) | 2016-05-27 | 2016-05-27 | A kind of online diagnosing failure of photovoltaic array network system realization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610364749.3A CN105811881B (en) | 2016-05-27 | 2016-05-27 | A kind of online diagnosing failure of photovoltaic array network system realization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105811881A true CN105811881A (en) | 2016-07-27 |
| CN105811881B CN105811881B (en) | 2017-09-15 |
Family
ID=56452216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610364749.3A Active CN105811881B (en) | 2016-05-27 | 2016-05-27 | A kind of online diagnosing failure of photovoltaic array network system realization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105811881B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106992540A (en) * | 2017-04-20 | 2017-07-28 | 中南大学 | A kind of photovoltaic system and its open fault diagnostic method without power of communications optimizer |
| CN108111115A (en) * | 2017-11-24 | 2018-06-01 | 郑州中能光电设备有限公司 | The maintenance device and method of a kind of photovoltaic generation |
| CN108875796A (en) * | 2018-05-28 | 2018-11-23 | 福州大学 | Diagnosing failure of photovoltaic array method based on linear discriminant analysis and support vector machines |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323507A1 (en) * | 2010-02-26 | 2012-12-20 | Yoshiaki Hasegawa | Fault detection apparatus and fault detection method |
| CN104767482A (en) * | 2014-01-02 | 2015-07-08 | 上海岩芯电子科技有限公司 | Method for diagnosing aging and short circuit of photovoltaic module online |
| CN104796082A (en) * | 2015-04-22 | 2015-07-22 | 中国科学院广州能源研究所 | System and method for diagnosing faults of photovoltaic power generation systems in online manner |
| CN105141255A (en) * | 2015-08-12 | 2015-12-09 | 河海大学常州校区 | Fault diagnosis method of photovoltaic array |
-
2016
- 2016-05-27 CN CN201610364749.3A patent/CN105811881B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323507A1 (en) * | 2010-02-26 | 2012-12-20 | Yoshiaki Hasegawa | Fault detection apparatus and fault detection method |
| CN104767482A (en) * | 2014-01-02 | 2015-07-08 | 上海岩芯电子科技有限公司 | Method for diagnosing aging and short circuit of photovoltaic module online |
| CN104796082A (en) * | 2015-04-22 | 2015-07-22 | 中国科学院广州能源研究所 | System and method for diagnosing faults of photovoltaic power generation systems in online manner |
| CN105141255A (en) * | 2015-08-12 | 2015-12-09 | 河海大学常州校区 | Fault diagnosis method of photovoltaic array |
Non-Patent Citations (1)
| Title |
|---|
| 王元章 等.: "基于BP神经网络的光伏阵列故障诊断研究", 《电力系统保护与控制》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106992540A (en) * | 2017-04-20 | 2017-07-28 | 中南大学 | A kind of photovoltaic system and its open fault diagnostic method without power of communications optimizer |
| CN106992540B (en) * | 2017-04-20 | 2019-09-03 | 中南大学 | A kind of photovoltaic system and its open-circuit fault diagnostic method of no power of communications optimizer |
| CN108111115A (en) * | 2017-11-24 | 2018-06-01 | 郑州中能光电设备有限公司 | The maintenance device and method of a kind of photovoltaic generation |
| CN108875796A (en) * | 2018-05-28 | 2018-11-23 | 福州大学 | Diagnosing failure of photovoltaic array method based on linear discriminant analysis and support vector machines |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105811881B (en) | 2017-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7256566B2 (en) | Method and apparatus for determining a maximum power point of photovoltaic cells | |
| Gokmen et al. | Simple diagnostic approach for determining of faulted PV modules in string based PV arrays | |
| CN107395119B (en) | A kind of Fault Locating Method of photovoltaic array | |
| Hu et al. | Efficiency improvement of nonuniformly aged PV arrays | |
| Dhimish et al. | Multi‐layer photovoltaic fault detection algorithm | |
| Sarikh et al. | Fault diagnosis in a photovoltaic system through IV characteristics analysis | |
| CN107180983A (en) | A kind of SOFC pile method for diagnosing faults and system | |
| CN105811881B (en) | A kind of online diagnosing failure of photovoltaic array network system realization | |
| CN108680486A (en) | A kind of photovoltaic module long-term weatherability performance test method | |
| Chen et al. | A novel fault diagnosis method of PV based-on power loss and IV characteristics | |
| Dhimish et al. | Detecting defective bypass diodes in photovoltaic modules using Mamdani fuzzy logic system | |
| CN109613841A (en) | A kind of solar photovoltaic assembly parameter identification method under malfunction | |
| Ahmed et al. | PV-standalone monitoring system performance using LabVIEW | |
| CN108306615B (en) | Method and system for diagnosing fault type of photovoltaic array | |
| CN114710115A (en) | Photovoltaic array fault defect diagnosis system and method | |
| Xu et al. | A fault diagnosis method for PV arrays based on new feature extraction and improved the Fuzzy C-Mean clustering | |
| CN106653642A (en) | Test system and test method for testing forward and reverse conversion capability of photovoltaic bypass diode | |
| Lodhi et al. | Performance evaluation of faults in a photovoltaic array based on VI and VP characteristic curve | |
| CN103595236B (en) | Photovoltaic inverter starting-up control, device and solar power system | |
| Garro et al. | Reliability analysis of residential photovoltaic systems | |
| Hu et al. | Theoretical analysis and implementation of photovoltaic fault diagnosis | |
| Baba et al. | On‐site detection of bypass circuit opening failure in photovoltaic array under power generation operation | |
| King et al. | Array performance characterization and modeling for real-time performance analysis of photovoltaic systems | |
| Yi et al. | Simulation study on characteristics of photovoltaic array under partial shading | |
| CN105207619A (en) | Diagnosis method for photovoltaic component |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |