CN116797603B - Photovoltaic array fault diagnosis and positioning method - Google Patents
Photovoltaic array fault diagnosis and positioning method Download PDFInfo
- Publication number
- CN116797603B CN116797603B CN202311074882.1A CN202311074882A CN116797603B CN 116797603 B CN116797603 B CN 116797603B CN 202311074882 A CN202311074882 A CN 202311074882A CN 116797603 B CN116797603 B CN 116797603B
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- photovoltaic panel
- area
- areas
- heat
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000003745 diagnosis Methods 0.000 title claims abstract description 15
- 238000001931 thermography Methods 0.000 claims abstract description 27
- 238000003708 edge detection Methods 0.000 claims description 14
- 206010020843 Hyperthermia Diseases 0.000 claims description 12
- 230000036031 hyperthermia Effects 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 10
- YOBAEOGBNPPUQV-UHFFFAOYSA-N iron;trihydrate Chemical compound O.O.O.[Fe].[Fe] YOBAEOGBNPPUQV-UHFFFAOYSA-N 0.000 description 8
- 239000003086 colorant Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 241000219307 Atriplex rosea Species 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- 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 relates to the field of image processing, in particular to a photovoltaic array fault diagnosis and positioning method, which comprises the following steps: collecting a thermal imaging image and a photovoltaic array image of a photovoltaic panel; acquiring a misjudgment area and a high-heat area; obtaining normal values of all the high-heat areas according to the high-heat areas and the erroneous judgment areas; obtaining a normal value of a single high-heat region in a single photovoltaic panel according to the maximum high-heat region area and the area threshold; obtaining the high-temperature area quantity coefficient of the single photovoltaic plate according to the high-temperature area quantity of the single photovoltaic plate; obtaining the normal value of a single photovoltaic panel according to the normal values of all the high heat areas, the normal value of a single high heat area and the quantity coefficient; obtaining a fault photovoltaic panel and the rest photovoltaic panels according to the normal value of the single photovoltaic panel; clustering the rest photovoltaic panels to obtain suspected fault photovoltaic panels; and finally, positioning the specific positions of the fault photovoltaic panel and the suspected fault photovoltaic panel. The invention uses the image processing mode to diagnose, and improves the accuracy of fault diagnosis in the image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a photovoltaic array fault diagnosis and positioning method.
Background
Along with the rapid development of the new energy field, the photovoltaic array is increasingly widely applied in the new energy field, and the fault diagnosis and positioning of the photovoltaic array in the operation process are important means for improving the efficiency and maintenance cost of the photovoltaic power generation system. At present, related diagnosis and positioning technology becomes one of research hotspots in the field of new energy, and research and application at home and abroad are widely focused. However, due to the complexity and variability of the photovoltaic power generation system, the current fault diagnosis and positioning technology of the photovoltaic array still needs to be continuously improved and perfected so as to better meet the actual application requirements of the photovoltaic power generation system.
In traditional technical means, when the fault detection is carried out on the photovoltaic array, reflection of light possibly occurs on the photovoltaic array plate due to the influence of illumination, misjudgment possibly occurs when the photovoltaic plate is photographed, and inaccuracy is caused when the fault is detected on the photovoltaic plate only through the image of the photovoltaic plate.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method for diagnosing and locating a photovoltaic array fault, the method comprising:
collecting a thermal imaging image and a photovoltaic array image of each photovoltaic panel;
performing edge detection on the photovoltaic array image of each photovoltaic panel to obtain the total area of the misjudgment area of each photovoltaic panel; performing edge detection on the thermal imaging image of each photovoltaic panel to obtain a plurality of high-heat areas of each photovoltaic panel;
obtaining normal values of all the high-heat areas of each photovoltaic panel according to the areas of all the high-heat areas of each photovoltaic panel, the number of all the high-heat areas and the total area of the misjudgment areas;
obtaining a normal value of a single high-heat area of each photovoltaic panel according to the maximum high-heat area of each photovoltaic panel;
obtaining the high-temperature area quantity coefficient of each photovoltaic plate according to the quantity of the high-temperature areas of each photovoltaic plate and the average value of the quantity of the high-temperature areas of all the photovoltaic plates in the whole area;
obtaining the normal value of each photovoltaic panel according to the normal values of all the high heat areas of each photovoltaic panel, the normal value of the single high heat area and the number coefficient of the high heat areas;
screening the photovoltaic panels according to the normal value of each photovoltaic panel to obtain a fault photovoltaic panel and the rest photovoltaic panels; clustering the rest photovoltaic panels to obtain suspected fault photovoltaic panels;
the specific positions of the fault photovoltaic panel and the suspected fault photovoltaic panel in the photovoltaic array are obtained, and the fault diagnosis and positioning of the photovoltaic array are completed;
the specific acquisition steps of the normal values of all the high heat areas are as follows:
in the method, in the process of the invention,indicate->No. 4 of the individual photovoltaic panels>Area of the high heat region, ">Indicate->Misjudgment area of individual photovoltaic panels, < >>Representing the number of hyperthermia areas of the ith photovoltaic panel,/->Represents the number of all photovoltaic panels, +.>Representing the total area threshold of all high-temperature areas of a monolithic photovoltaic panel, +.>Representing a step function +.>Normal values representing all the hyperthermia regions;
the specific acquisition steps of the normal value of the single high-heat area of each photovoltaic panel are as follows:
the formula for the normal value of the single high heat zone of each photovoltaic panel is:
in the method, in the process of the invention,representing a single high-heat area threshold value for a preset single photovoltaic panel, < >>Indicate->Maximum high-heat area of individual photovoltaic panels,/->Normal values representing the individual high heat zones in the ith photovoltaic panel;
the specific acquisition steps of the high-temperature area quantity coefficient of each photovoltaic panel are as follows:
the formula of the high-temperature area quantity coefficient of each photovoltaic panel is as follows:
in the method, in the process of the invention,indicate->Number of high-temperature areas of the individual photovoltaic panels, < >>Representing the number of high heat areas of the photovoltaic panel over the entire areaAverage value of quantity->Representing a preset threshold value, < >>Indicate->High-heat area quantity coefficient of individual photovoltaic panels, < >>An exponential function based on a natural number is represented.
Further, the edge detection is performed on the photovoltaic array image of each photovoltaic panel to obtain the total area of the misjudgment area of each photovoltaic panel, which comprises the following specific steps:
carrying out canny edge detection on the photovoltaic array image of each photovoltaic panel to obtain all closed areas connected by edge lines, then carrying out circumscribed rectangle on the closed areas, and marking the area of each closed area asThe area of the circumscribed rectangle of each closed region is denoted +.>Calculate the area of each occlusion region +.>Area of circumscribed rectangle with each closed region +.>Is recorded as the degree of difference for each region;
when (when)When the t closed region is marked as a misjudgment region, R represents a preset difference threshold value, < ->Represents the t thThe degree of difference in the occlusion regions; and then summing the areas of all misjudgment areas of each photovoltaic panel to obtain the total area of the misjudgment areas of each photovoltaic panel.
Further, the edge detection is performed on the thermal imaging image of each photovoltaic panel to obtain a plurality of high heat areas of each photovoltaic panel, which comprises the following specific steps:
and (3) carrying out thermal imaging on each photovoltaic panel by using canny edge detection, acquiring all closed areas connected by edge lines, and marking the closed areas in the thermal imaging as high-heat areas to obtain a plurality of high-heat areas of each photovoltaic panel.
Further, the specific acquisition steps of the normal value of the single photovoltaic panel are as follows:
the formula for the normal value of a single photovoltaic panel is:
in the method, in the process of the invention,normal values representing all hyperthermia areas, +.>Normal value representing the single hyperthermia region in the ith photovoltaic panel, < >>Indicate->High-heat area quantity coefficient of individual photovoltaic panels, < >>The normal value of the ith photovoltaic panel is indicated.
Further, the specific acquisition steps of the fault photovoltaic panel are as follows:
a photovoltaic panel with a normal value of 0 for a single photovoltaic panel was noted as a faulty photovoltaic panel.
Further, the specific acquisition steps of the remaining photovoltaic panels are as follows:
all photovoltaic panels except the failed photovoltaic panel were noted as remaining photovoltaic panels.
Further, the clustering of the remaining photovoltaic panels to obtain suspected fault photovoltaic panels comprises the following specific steps:
the remaining photovoltaic panels are clustered according to the normal value of a single photovoltaic panel by using k-means, the photovoltaic panels are clustered into two types, and all photovoltaic panels in the type with the smallest sum of the normal values of all the photovoltaic panels are marked as suspected fault photovoltaic panels.
The technical scheme of the invention has the beneficial effects that: the normal values of all the high-heat areas, the normal values of the single high-heat areas in the single photovoltaic panel and the high-heat area quantity coefficients of the single photovoltaic panel are obtained by obtaining the misjudgment areas in the photovoltaic array image and the high-heat areas in the thermal imaging image, the influence of light on photographing is reduced through the normal values and the coefficients, namely the normal values of the single high-heat areas in the single photovoltaic panel and the high-heat area quantity coefficients of the single photovoltaic panel are calculated to obtain the normal values of the single photovoltaic panel, and the faulty photovoltaic panel is obtained by using k-means detection according to the normal values of the single photovoltaic panel. According to the invention, the interference of textures of the photovoltaic panels in the process of acquiring images is eliminated by analyzing the misjudgment areas, the normal value of each high-heat area after the influence of light on each photovoltaic panel is eliminated is obtained by the misjudgment areas and the high-heat areas of each photovoltaic panel, and finally, the accuracy of identifying the faults of the photovoltaic panels is improved by clustering the normal values of the high-heat areas.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart showing the steps of a method for diagnosing and locating faults in a photovoltaic array according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of a photovoltaic array fault diagnosis and positioning method according to the invention, which are provided by the invention, with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the photovoltaic array fault diagnosis and positioning method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for diagnosing and locating a fault of a photovoltaic array according to an embodiment of the invention is shown, the method includes the following steps:
step S001: a photovoltaic array image and a thermographic image are acquired.
It should be noted that, in this embodiment, since the fault diagnosis and positioning of the photovoltaic array are related, the image of the photovoltaic panel needs to be collected to analyze the abnormal area on the photovoltaic panel, and since the photovoltaic panel is mainly used for generating electricity, the temperature of the photovoltaic panel can be different due to the generation of electricity, and the temperature difference has a certain influence on the fault analysis, the influence of the illumination on the circuit in the photovoltaic panel needs to be analyzed through the thermal imaging.
Specifically, an unmanned aerial vehicle is used for collecting images from left to right and then from top to bottom according to the arrangement of single photovoltaic panels right above the photovoltaic array panels, and gray scale is carried out to obtain a photovoltaic array image of each photovoltaic panel; and then using a thermal imager to collect thermal imaging images of the photovoltaic panels from left to right and from top to bottom according to the arrangement of the single photovoltaic panels, and carrying out graying to obtain the thermal imaging image of each photovoltaic panel.
Step S002: the method comprises the steps of pre-screening a photovoltaic panel surface misjudgment area through a photovoltaic array image, carrying out internal fault detection according to a thermal imaging image by combining the pre-screened misjudgment area, analyzing and quantifying a normal value of the photovoltaic panel, defining a fault photovoltaic panel according to a result value, and screening a suspected fault photovoltaic panel.
The erroneous judgment region is pre-screened by the photovoltaic array image, and when the thermal imaging image is detected, the portion with the erroneous judgment region needs to be removed. The main two misjudgment modes in the thermal imaging are reflection of sunlight on the photovoltaic panel and shadow areas which are partially blocked, and the areas can also show highlighting similar to high-temperature areas in the thermal imaging, so that the detection result is unreasonable if the areas are used for thermal imaging detection. Therefore, it is necessary to judge the misjudgment area of each photovoltaic panel. If the shape characteristics and the position distribution characteristics of the erroneous judgment area are known, the area of the erroneous judgment area can be obtained through a calculation or estimation method. The reflection of sunlight on the photovoltaic panel is quite approximately circular in shape and is distributed mostly in the non-edge area of the photovoltaic panel, while the partially shaded area is approximately rectangular in shape and is distributed mostly in the edge of the photovoltaic panel.
It should be further noted that, because there are many textures in a single photovoltaic panel, when the edge of the single photovoltaic panel is detected, the textures inside will have a certain influence; also because the textures in a single photovoltaic panel are staggered horizontally and vertically, the edge-detected closed areas are regular rectangles. Since a regular rectangle is to be excluded when performing fault detection of the photovoltaic panel, influence upon detection of a fault region is prevented. However, when the regular rectangles are eliminated, the formed closed areas are not rectangles, but are close to rectangles when the edges of the textures of the photovoltaic panel are detected due to errors of edge detection, so that the closed areas are circumscribed by rectangles, the difference degree between the area of each closed area and the area of the circumscribed rectangle of each closed area is obtained, and when the difference degree between the two areas is smaller, the closed areas are considered to be the regular rectangles formed by the textures in the photovoltaic panel; when the degree of difference between the two areas is large, the closed region is considered to be a closed region formed by the presence of a failure of the photovoltaic panel.
Specifically, a canny edge detection is performed on the photovoltaic array image of each photovoltaic panel, all closed areas connected by edge lines are obtained, and then the closed areas are subjected to circumscribed rectangle. The area of each closed region is noted asThe area of the circumscribed rectangle of each closed region is denoted +.>Calculate the area of each occlusion region +.>Area of circumscribed rectangle with each closed region +.>Is recorded as the degree of difference for each region. Expressed by the formula:
in the method, in the process of the invention,represents the area of the t-th closed region, +.>The area of the circumscribed rectangle representing the t-th closed region, < > and>indicating the degree of difference in the t-th occlusion region.
A difference threshold R is preset, where the embodiment is described by taking r=0.8 as an example, and the embodiment is not specifically limited, where R may be determined according to the specific implementation situation. When (when)When it means that the t-th closed area is a regular rectangle in the photovoltaic panel, when +.>And when the t closed region is an irregular rectangle, the t closed region is a misjudgment region. And then summing the areas of all misjudgment areas of each photovoltaic panel to obtain the total area of the misjudgment areas of each photovoltaic panel.
And (3) detecting the thermal imaging of each photovoltaic panel by using a canny edge, acquiring all closed areas connected by edge lines, and marking the closed areas in the thermal imaging as high-temperature areas, so as to obtain all the high-temperature areas of each photovoltaic panel. After obtaining the total area of the misjudgment area of each photovoltaic panel, when the detection of the high-heat area is carried out through the thermal imaging, the real high-heat area of the photovoltaic panel is obtained by subtracting the total area of the misjudgment area corresponding to the photovoltaic panel from the high-heat area obtained by each photovoltaic panel. Wherein, there are a plurality of photovoltaic boards of arranging rule in the photovoltaic array.
And carrying out internal fault detection according to the thermographic image by combining the pre-screened misjudgment area, and analyzing and quantifying the normal value of the photovoltaic panel.
Note that, the thermal imaging camera has different color code ranges, and the thermal distribution corresponds to different color changes. The thermal imaging camera color code range adopted by the photovoltaic array is usually an iron red color code, and the color code mainly consists of black, gray and iron red, and is particularly suitable for high-temperature measurement. Generally, black represents low temperature, gray represents medium temperature, and iron red represents high temperature, and the iron red color scale can clearly display a high temperature region relative to other color scales, which is suitable for a scene of a photovoltaic array. However, in the case of reasonable color scale arrangement, in general, the difference between the colors of the high temperature area and the low temperature area in the thermal imaging picture is obvious, because the thermal imaging camera can map different temperatures of the surface of the object into different colors, and the colors can clearly show the heat distribution and change of the surface of the material. This example is described only in terms of the iron red scale. In the thermographic image, different colors of different temperatures are displayed by regions, and therefore, the temperature color of the high-heat region appears to be iron red in the iron red scale range.
Further, the statistical calculation of the area of the region of the iron-red color range is performed by the color-based image segmentation technique. The larger the area of the red iron area, the larger the area of the high heat portion of the area, and if the area is too large, the problem may be caused in the photovoltaic panel. In addition, there may be several high heat areas on a photovoltaic panel, and an excessive number of high heat areas may also indicate that the photovoltaic panel may be problematic. In comparing the high-temperature area of the photovoltaic panel, it is considered that the area where the photovoltaic panel is located is compared with other photovoltaic panels in the area, specifically, the light irradiation and solar radiation energy received by the photovoltaic panels in different areas may be different, which may affect the surface temperature of the photovoltaic panels, and the factors such as the environmental temperature and pollution level where the photovoltaic panels in different areas are located may also have differences, which may further affect the surface temperature of the photovoltaic panels and the changes. Thus, rather than simply comparing the entire photovoltaic array, it is desirable to consider the surface temperature differences that may exist for different areas of the photovoltaic panel when determining the high heat areas of the photovoltaic panel surface.
Specifically, when detecting internal faults of a photovoltaic panel through a thermal imaging of the photovoltaic panel, the detection of the photovoltaic panel which may have the internal faults is considered by taking the area of the high-heat area and the number of the high-heat areas of the surface of the photovoltaic panel as the difference degree of the parameters in all the photovoltaic panels in the area where the photovoltaic panel is located. Presetting a total area threshold value of all high heat areas of a single photovoltaic panelWherein the present embodiment is +.>The embodiment is not particularly limited, and is exemplified by =50 square centimeters, whereDepending on the particular implementation.
Then in all photovoltaic panels of the whole, the calculation formula of the normal values of all the high-temperature areas is:
in the method, in the process of the invention,indicate->No. 4 of the individual photovoltaic panels>Area of the high heat region, ">Indicate->Misjudgment area of individual photovoltaic panels, < >>Representing the number of hyperthermia areas of the ith photovoltaic panel,/->Represents the number of all photovoltaic panels, +.>Representing the total area threshold of all high-temperature areas of a monolithic photovoltaic panel, +.>Representing a step function +.>Indicating normal values for all regions of hyperthermia.
Wherein, the liquid crystal display device comprises a liquid crystal display device,the high-temperature area threshold value of the whole area is obtained according to the number of the photovoltaic panels of the whole area and the total area threshold value of all the high-temperature areas of the single photovoltaic panel; by->Accumulating all high-temperature areas of the single photovoltaic plate, and subtracting misjudgment area of each photovoltaic plate>Regarding the error result of the single photovoltaic panel as a high-heat area after the single photovoltaic panel is processed; by the formula +.>Obtaining the areas of the high-temperature areas of all the photovoltaic panels in the whole area, if the areas of the high-temperature areas of the whole area after the collection and the treatment are larger than the threshold value of the areas of the high-temperature areas of the whole area, the problem of the whole area of the photovoltaic panel is proved to exist, and the method is that>. This includes cases where the accumulated high heat area exceeds the single photovoltaic panel high heat area threshold due to the single high heat area exceeding the threshold and the excessive number of high heat areas.
It should be noted that if only one threshold is defined for the area of the high-heat area of the whole area, it is possible that the area of the high-heat area of the area exceeds the threshold because the high-heat area of some photovoltaic panels is too large, and the area of the high-heat area is not directly related to the photovoltaic panels with the small area of the other high-heat areas, so that it is unnecessary to overhaul the whole area, and the threshold needs to be set for detecting Gao Reou areas of the single photovoltaic panels.
Specifically, a single high-temperature area threshold of a single photovoltaic panel is presetWherein the present embodiment is +.>The embodiment is not particularly limited, and is exemplified by =10 square cm, where +.>Depending on the particular implementation. And obtaining the normal value of the high heat area of the single photovoltaic plate according to the high heat area threshold value of the single photovoltaic plate and the maximum high heat area of the single photovoltaic plate. Expressed by the formula:
in the method, in the process of the invention,a single high-heat area threshold representing a single photovoltaic panel,/->Indicate->Maximum high-heat area of individual photovoltaic panels,/->Representing a step function +.>Representing the normal value for a single high heat region in the ith photovoltaic panel.
Wherein if there is no problem in the area of the high-temperature area of the whole area, that is, the normal value of the high-temperature area of the whole area is not equal to 0, fault diagnosis is required for the single photovoltaic panel in the area. The failed photovoltaic panel is screened by the area of the high heat region of the individual photovoltaic panel. There may be several high heat areas on a photovoltaic panel, but if the maximum area of the high heat area on a photovoltaic panel exceeds the area threshold of a single high heat area, the problem of the photovoltaic panel can be determined。
It should be noted that if the number of high heat areas of a certain photovoltaic panel is too large compared with other photovoltaic panels in the area, the photovoltaic panel is problematic, so the determination is further made according to the number of high heat areas of a single photovoltaic panel.
Specifically, a threshold k is preset, where the embodiment is described by taking k=5 as an example, and the embodiment is not specifically limited, where k may be determined according to the specific implementation. The coefficients of the individual photovoltaic panels are obtained from the number of high heat areas of the individual photovoltaic panels, expressed by the formula:
in the method, in the process of the invention,indicate->Number of high-temperature areas of the individual photovoltaic panels, < >>Representing the number average of the high-temperature areas of the photovoltaic panel in the whole area, +.>Representing threshold value->Indicate->High-heat area quantity coefficient of individual photovoltaic panels, < >>An exponential function based on a natural number is represented.
Wherein, when the number of high heat areas of the photovoltaic panel is larger,the smaller the resulting value of (2).
According to normal values of all high-temperature areasNormal value of single high heat zone in ith photovoltaic panel/>And->High-temperature area quantity coefficient of individual photovoltaic panels +.>The normal value of the ith photovoltaic panel is obtained and expressed as:
in the method, in the process of the invention,normal values representing all hyperthermia areas, +.>Normal value representing the single hyperthermia region in the ith photovoltaic panel, < >>Indicate->High-heat area quantity coefficient of individual photovoltaic panels, < >>The normal value of the ith photovoltaic panel is indicated.
Wherein whenThe smaller the time, the more pronounced the fault that the ith photovoltaic panel was present. When->Description of->Or (b)The area of the middle photovoltaic panel Gao Reou domain exceeds the area threshold of the photovoltaic panel Gao Reou domain, so will +.>The photovoltaic panel of (2) is denoted as a faulty photovoltaic panel, excluding +.>And (3) carrying out k-means clustering on the rest photovoltaic panels to screen out suspected fault photovoltaic panels.
Is completely dischargedAfter the photovoltaic panel of (2), there is also a photovoltaic panel high heat zone with an area equal to the area threshold of the photovoltaic panel high heat zone, i.e.>Or->0.5, so the normal value of the ith photovoltaic panel is +.>Or (b)The method comprises the steps of carrying out a first treatment on the surface of the Except for this case, the rest->Or->Are all 1, i.e.)>I.e. when neither result value exceeds the respective threshold value, the +>The result value of (2) is related to the number of high hot spots, the more high hot spots are, the +.>The smaller the resulting value of (2); if->And->Just equal to the respective threshold value, would result in +.>The resulting values of (a) are smaller than those of other photovoltaic panels. The threshold is defined as the maximum limit of the area of Gao Reou domain, and if the threshold is equal, the threshold is indicated to be exceeded, so the photovoltaic panel is treated as suspected fault.
Step S003: and clustering according to the normal value of the photovoltaic panel to determine the photovoltaic panel with the fault.
Will beAfter the photovoltaic panels of (2) are excluded, the rest of the photovoltaic panels are clustered using k-means, and since the normal value of each photovoltaic panel is calculated in the previous step, the step clusters according to the normal value of each photovoltaic panel. In this embodiment, the number of clusters is equal to 2, which is not specifically limited, and the number of clusters may be determined according to the specific implementation situation.
At this time, the k-means cluster divides the rest of the photovoltaic panels into two types, and as the smaller the normal value of the photovoltaic panel is, the more suspected fault photovoltaic panel is, so the type with the smallest sum of the normal values of the photovoltaic panels is taken as the suspected fault photovoltaic panel; and finally, positioning the suspected fault photovoltaic plates and the fault photovoltaic plates, and determining the positions of each suspected fault photovoltaic plate and each fault photovoltaic plate.
This embodiment is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The photovoltaic array fault diagnosis and positioning method is characterized by comprising the following steps of:
collecting a thermal imaging image and a photovoltaic array image of each photovoltaic panel;
performing edge detection on the photovoltaic array image of each photovoltaic panel to obtain the total area of the misjudgment area of each photovoltaic panel; performing edge detection on the thermal imaging image of each photovoltaic panel to obtain a plurality of high-heat areas of each photovoltaic panel;
obtaining normal values of all the high-heat areas of each photovoltaic panel according to the areas of all the high-heat areas of each photovoltaic panel, the number of all the high-heat areas and the total area of the misjudgment areas;
obtaining a normal value of a single high-heat area of each photovoltaic panel according to the maximum high-heat area of each photovoltaic panel;
obtaining the high-temperature area quantity coefficient of each photovoltaic plate according to the quantity of the high-temperature areas of each photovoltaic plate and the average value of the quantity of the high-temperature areas of all the photovoltaic plates in the whole area;
obtaining the normal value of each photovoltaic panel according to the normal values of all the high heat areas of each photovoltaic panel, the normal value of the single high heat area and the number coefficient of the high heat areas;
screening the photovoltaic panels according to the normal value of each photovoltaic panel to obtain a fault photovoltaic panel and the rest photovoltaic panels; clustering the rest photovoltaic panels to obtain suspected fault photovoltaic panels;
the specific positions of the fault photovoltaic panel and the suspected fault photovoltaic panel in the photovoltaic array are obtained, and the fault diagnosis and positioning of the photovoltaic array are completed;
the specific acquisition steps of the normal values of all the high heat areas are as follows:
in the method, in the process of the invention,indicate->No. 4 of the individual photovoltaic panels>Area of the high heat region, ">Indicate->Misjudgment area of individual photovoltaic panels, < >>Representing the number of hyperthermia areas of the ith photovoltaic panel,/->Represents the number of all photovoltaic panels, +.>Representing the total area threshold of all high-temperature areas of a monolithic photovoltaic panel, +.>Representing a step function +.>Normal values representing all the hyperthermia regions;
the specific acquisition steps of the normal value of the single high-heat area of each photovoltaic panel are as follows:
the formula for the normal value of the single high heat zone of each photovoltaic panel is:
in the method, in the process of the invention,representing a single high-heat area threshold value for a preset single photovoltaic panel, < >>Indicate->Maximum high-heat area of individual photovoltaic panels,/->Normal values representing the individual high heat zones in the ith photovoltaic panel;
the specific acquisition steps of the high-temperature area quantity coefficient of each photovoltaic panel are as follows:
the formula of the high-temperature area quantity coefficient of each photovoltaic panel is as follows:
in the method, in the process of the invention,indicate->Number of high-temperature areas of the individual photovoltaic panels, < >>Representing the number average of the high-temperature areas of the photovoltaic panel in the whole area, +.>Representing a preset threshold value, < >>Indicate->High-heat area quantity coefficient of individual photovoltaic panels, < >>An exponential function based on a natural number is represented.
2. The method for diagnosing and positioning a photovoltaic array according to claim 1, wherein the step of performing edge detection on the photovoltaic array image of each photovoltaic panel to obtain the total area of the misjudgment area of each photovoltaic panel comprises the following specific steps:
carrying out canny edge detection on the photovoltaic array image of each photovoltaic panel to obtain all closed areas connected by edge lines, then carrying out circumscribed rectangle on the closed areas, and marking the area of each closed area asThe area of the circumscribed rectangle of each closed region is denoted +.>Calculate the area of each occlusion region +.>Area of circumscribed rectangle with each closed regionIs recorded as the degree of difference for each region;
when (when)When the t closed region is marked as a misjudgment region, R represents a preset difference threshold value, < ->Indicating the degree of difference in the t-th occlusion region; and then summing the areas of all misjudgment areas of each photovoltaic panel to obtain the total area of the misjudgment areas of each photovoltaic panel.
3. The method for diagnosing and positioning a photovoltaic array according to claim 1, wherein the edge detection of the thermally formed image of each photovoltaic panel is performed to obtain a plurality of high heat areas of each photovoltaic panel, comprising the following specific steps:
and (3) carrying out thermal imaging on each photovoltaic panel by using canny edge detection, acquiring all closed areas connected by edge lines, and marking the closed areas in the thermal imaging as high-heat areas to obtain a plurality of high-heat areas of each photovoltaic panel.
4. The method for diagnosing and locating a photovoltaic array according to claim 1, wherein the specific obtaining steps of the normal value of the single photovoltaic panel are as follows:
the formula for the normal value of a single photovoltaic panel is:
in the method, in the process of the invention,normal values representing all hyperthermia areas, +.>Normal value representing the single hyperthermia region in the ith photovoltaic panel, < >>Indicate->High-heat area quantity coefficient of individual photovoltaic panels, < >>The normal value of the ith photovoltaic panel is indicated.
5. The method for diagnosing and locating a photovoltaic array according to claim 1, wherein the specific steps of obtaining the faulty photovoltaic panel are as follows:
a photovoltaic panel with a normal value of 0 for a single photovoltaic panel was noted as a faulty photovoltaic panel.
6. The method for diagnosing and locating a photovoltaic array according to claim 1, wherein the specific steps of obtaining the remaining photovoltaic panels are as follows:
all photovoltaic panels except the failed photovoltaic panel were noted as remaining photovoltaic panels.
7. The method for diagnosing and locating a photovoltaic array fault according to claim 1, wherein the step of clustering the remaining photovoltaic panels to obtain a suspected fault photovoltaic panel comprises the following specific steps:
the remaining photovoltaic panels are clustered according to the normal value of a single photovoltaic panel by using k-means, the photovoltaic panels are clustered into two types, and all photovoltaic panels in the type with the smallest sum of the normal values of all the photovoltaic panels are marked as suspected fault photovoltaic panels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311074882.1A CN116797603B (en) | 2023-08-25 | 2023-08-25 | Photovoltaic array fault diagnosis and positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311074882.1A CN116797603B (en) | 2023-08-25 | 2023-08-25 | Photovoltaic array fault diagnosis and positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116797603A CN116797603A (en) | 2023-09-22 |
| CN116797603B true CN116797603B (en) | 2023-10-24 |
Family
ID=88048350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311074882.1A Active CN116797603B (en) | 2023-08-25 | 2023-08-25 | Photovoltaic array fault diagnosis and positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116797603B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107453709A (en) * | 2017-07-03 | 2017-12-08 | 重庆大学 | The photovoltaic hot spot method for diagnosing faults that a kind of isolation mech isolation test merges with intersecting measurement |
| KR102133224B1 (en) * | 2020-03-26 | 2020-07-13 | 주식회사 스카이텍 | An automatic diagnosis system of solar array that is using a CAD design drawing that overlapped pictures taken by a thermal imaging camera of a drone |
| CN111860404A (en) * | 2020-07-28 | 2020-10-30 | 华润智慧能源有限公司 | Photovoltaic panel hot spot positioning method and system |
| CN114782880A (en) * | 2022-06-22 | 2022-07-22 | 索日新能源科技(南通)有限公司 | Monitoring system for off-grid photovoltaic power generation system |
-
2023
- 2023-08-25 CN CN202311074882.1A patent/CN116797603B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107453709A (en) * | 2017-07-03 | 2017-12-08 | 重庆大学 | The photovoltaic hot spot method for diagnosing faults that a kind of isolation mech isolation test merges with intersecting measurement |
| KR102133224B1 (en) * | 2020-03-26 | 2020-07-13 | 주식회사 스카이텍 | An automatic diagnosis system of solar array that is using a CAD design drawing that overlapped pictures taken by a thermal imaging camera of a drone |
| CN111860404A (en) * | 2020-07-28 | 2020-10-30 | 华润智慧能源有限公司 | Photovoltaic panel hot spot positioning method and system |
| CN114782880A (en) * | 2022-06-22 | 2022-07-22 | 索日新能源科技(南通)有限公司 | Monitoring system for off-grid photovoltaic power generation system |
Non-Patent Citations (1)
| Title |
|---|
| 一种新型光伏阵列多传感器故障检测定位方法;张晓娜;高德东;刘海雄;叶军;王珊;;可再生能源(02);第12-18页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116797603A (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Spataru et al. | Automatic detection and evaluation of solar cell micro-cracks in electroluminescence images using matched filters | |
| CN110376198B (en) | Cervical liquid-based cell slice quality detection system | |
| Di Tommaso et al. | A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle | |
| CN110071692B (en) | Photovoltaic module fault determination method and device and controller | |
| CN111751002B (en) | Intelligent charged equipment fault diagnosis method based on infrared thermal imaging | |
| CN115439474B (en) | Rapid positioning method for power equipment fault | |
| KR101806217B1 (en) | Method and apparatus for detecting malfunction panel from UAV thermal infrared images of photovoltaic modules | |
| Kurukuru et al. | Machine learning framework for photovoltaic module defect detection with infrared images | |
| CN115115634B (en) | Photovoltaic array hot spot detection method based on infrared image | |
| CN109345586A (en) | Electrical equipment discharge characteristic extracting method based on ultraviolet imagery technology | |
| CN115115643B (en) | Method for detecting production defects of photovoltaic cell panel | |
| CN114743115A (en) | Shelter recognition method and fault early warning system for photovoltaic electronic equipment | |
| CN108572011A (en) | A kind of photovoltaic battery panel dust stratification condition monitoring system and computational methods based on machine vision | |
| US20230042106A1 (en) | System and method for the statistical analysis of images of photovoltaic panels | |
| CN112446863A (en) | Photovoltaic array hot spot detection method and detection system based on image processing | |
| Guerriero et al. | Automatic edge identification for accurate analysis of thermographic images of solar panels | |
| CN115940809A (en) | Solar panel fault detection method based on power data and visual analysis | |
| CN116797603B (en) | Photovoltaic array fault diagnosis and positioning method | |
| CN114782442A (en) | Photovoltaic cell panel intelligent inspection method and system based on artificial intelligence | |
| So et al. | Estimating the electricity generation capacity of solar photovoltaic arrays using only color aerial imagery | |
| CN116503633B (en) | Intelligent detection control method for switch cabinet state based on image recognition | |
| CN116188510B (en) | Enterprise emission data acquisition system based on multiple sensors | |
| CN114581407B (en) | Self-adaptive defect detection method for photovoltaic module | |
| Rodriguez et al. | Segmentation and error detection of PV modules | |
| CN110610474A (en) | Solar panel defect real-time detection method based on infrared image |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |