CN110907473A - Photovoltaic module overhauling method, device, equipment and storage medium - Google Patents
Photovoltaic module overhauling method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110907473A CN110907473A CN201911205375.0A CN201911205375A CN110907473A CN 110907473 A CN110907473 A CN 110907473A CN 201911205375 A CN201911205375 A CN 201911205375A CN 110907473 A CN110907473 A CN 110907473A
- Authority
- CN
- China
- Prior art keywords
- image
- photovoltaic module
- broken
- scanning
- quasi
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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 application discloses a photovoltaic module overhauling method, which comprises the steps of collecting a scanning image obtained by scanning and shooting toughened glass of a photovoltaic module; analyzing and identifying the scanned image, and judging whether tempered glass corresponding to the scanned image is broken or not; and if so, outputting the scanning image and the position information of the photovoltaic module with the broken toughened glass. When the photovoltaic module is overhauled, the image of the surface of the toughened glass is collected through the camera device, whether the toughened glass of the photovoltaic module is broken or not is identified in an image identification mode, and a worker can perform one-step identification and judgment; the workload of the staff for patrolling and examining the photovoltaic module is reduced to a great extent, and the timeliness of the photovoltaic module breakage condition inspection and maintenance is improved. The application also provides a photovoltaic module overhauling device, equipment and a computer readable storage medium, and the photovoltaic module overhauling device has the beneficial effects.
Description
Technical Field
The present disclosure relates to the field of solar cell technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for repairing a photovoltaic module.
Background
The photovoltaic module is one of important parts of a solar cell and mainly comprises front toughened glass, a first transparent adhesive layer, a cell sheet layer, a second transparent adhesive layer, a back plate and the like. The front toughened glass plays an important role in protecting the cell sheet layer from water, heat, electricity, light and the like.
Although tempered glass is glass which is hard and has a low probability of breakage, in practical applications, a breakage phenomenon, such as being hit by a falling sharp stone, is inevitable. Once the tempered glass of the photovoltaic module breaks, the following hazards will occur: 1) the insulation of a photovoltaic system is reduced, and people are easy to get an electric shock; 2) the weather resistance of the photovoltaic module is reduced, and the service life is shortened; 3) the mechanical impact strength of the photovoltaic module is reduced; 4) the light transmittance of the photovoltaic module is affected, and therefore the power generation capacity is affected. Therefore, the broken toughened glass is found out in time in the operation and maintenance of the power station so as to replace the photovoltaic assembly, and the method is very important. At present, however, the photovoltaic modules are inspected one by one only by operation and maintenance personnel, so that the inspection efficiency is low, the workload is large, and the manpower is seriously wasted.
Content of application
The application aims to provide a photovoltaic module overhauling method, working efficiency of overhauling of the breaking condition of the toughened glass of the photovoltaic module is improved, and labor cost of operation of a photovoltaic power station is saved.
In order to solve the technical problem, the present application provides a photovoltaic module maintenance method, including:
acquiring a scanning image obtained by scanning and shooting the toughened glass of the photovoltaic assembly by a camera device;
analyzing and identifying the scanned image, and judging whether tempered glass corresponding to the scanned image is broken or not;
and if so, outputting the scanning image and the position information corresponding to the broken photovoltaic module of the toughened glass.
Optionally, the analyzing and recognizing the scanned image, and determining whether the tempered glass corresponding to the scanned image is broken includes:
carrying out gray level processing on the scanned image to obtain a gray level image;
judging whether the gray level image has a quasi-circular figure or not;
if the quasi-circular figure exists in the gray level image, judging whether crack lines communicated with the quasi-circular figure exist around the quasi-circular figure;
and if crack lines communicated with the quasi-circular pattern exist around the quasi-circular pattern, the tempered glass corresponding to the scanned image is broken.
Optionally, the determining whether a crack line communicating with the quasi-circular pattern exists around the quasi-circular pattern includes:
finding out an edge line on the gray level image based on an edge detection algorithm;
and judging whether edge lines communicated with the similar circular pattern exist or not, if so, judging whether included angles between adjacent edge lines in a plurality of edge lines communicated with the similar circular pattern are within a preset range or not, and if so, judging that the edge lines are crack lines.
Optionally, the analyzing and recognizing the scanned image, and determining whether the tempered glass corresponding to the scanned image is broken includes:
collecting a fracture pattern sample of tempered glass of a photovoltaic module in advance;
obtaining a classifier for identifying the broken image of the toughened glass through the learning of a neural network;
and distinguishing whether the scanned image is an image with broken toughened glass or not according to the classifier.
Optionally, after outputting the scanned image and the position information corresponding to the photovoltaic module with the broken tempered glass, the method further includes:
highlighting and marking the cracking point and the cracking line of the scanned image, and extracting the characteristics of the cracking point and the cracking line to obtain cracking information;
storing the scanned image, the scanned image with the highlighted mark and the corresponding rupture information into a database; wherein the fracture information includes at least a fracture point area and a crack line length.
The application also provides a photovoltaic module's maintenance device, includes:
the image acquisition module is used for acquiring a scanning image obtained by scanning and shooting the toughened glass of the photovoltaic assembly by the camera device;
the identification judging module is used for analyzing and identifying the scanned image and judging whether tempered glass corresponding to the scanned image is broken or not;
and the information output module is used for outputting the scanning image and the position information of the photovoltaic assembly with the broken toughened glass.
Optionally, the identification and judgment module is configured to perform gray processing on the scanned image to obtain a gray image; judging whether the gray level image has a quasi-circular figure or not; if the quasi-circular figure exists in the gray level image, judging whether crack lines communicated with the quasi-circular figure exist around the quasi-circular figure; and if crack lines communicated with the quasi-circular pattern exist around the quasi-circular pattern, the tempered glass corresponding to the scanned image is broken.
The application also provides maintenance equipment of the photovoltaic modules, which comprises a camera device for scanning and shooting the scanning images of the toughened glass on each photovoltaic module in the photovoltaic system;
and the processor is connected with the camera device and is used for realizing the operation steps of executing the photovoltaic module overhauling method according to the scanning image.
Optionally, the camera device is an unmanned aerial vehicle with a camera.
The present application also provides a computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of servicing a photovoltaic module as set forth in any of the above.
The photovoltaic module overhauling method comprises the steps of collecting a scanning image obtained by scanning and shooting toughened glass of a photovoltaic module; analyzing and identifying the scanned image, and judging whether tempered glass corresponding to the scanned image is broken or not; and if so, outputting the scanning image and the position information of the photovoltaic module with the broken toughened glass.
When the photovoltaic module is overhauled, the image on the surface of the toughened glass is collected through the camera device, whether the toughened glass of the photovoltaic module is broken or not is identified in an image identification mode, and after the scanned image is primarily screened, the scanned image and the position information corresponding to the photovoltaic module screened out to be possible to be broken are output so as to be used for a worker to perform one-step identification and judgment and timely replace the photovoltaic module corresponding to the toughened glass which is actually broken; the workload of the staff for patrolling and examining the photovoltaic module is reduced to a great extent, and the timeliness of the photovoltaic module breakage condition inspection and maintenance is improved.
The application also provides a photovoltaic module overhauling device, equipment and a computer readable storage medium, and the photovoltaic module overhauling device has the beneficial effects.
Drawings
For a clearer explanation of the embodiments or technical solutions of the prior art of the present application, the drawings needed for the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a photovoltaic module maintenance method provided in an embodiment of the present application;
fig. 2 is a structural block diagram of an overhaul device of a photovoltaic module provided in an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the disclosure, the following detailed description will be given with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As shown in fig. 1, fig. 1 is a schematic flow chart of a method for repairing a photovoltaic module according to an embodiment of the present application, where the method for repairing a photovoltaic module includes:
step S11: acquiring a scanning image obtained by scanning and shooting the toughened glass of the photovoltaic assembly by a camera device;
this camera device can be the unmanned aerial vehicle who carries the camera, can carry out the shooting of photovoltaic module of large tracts of land, can also be the camera that sets up at the peripheral position of photovoltaic module, to this, do not specifically prescribe a limit in this application, as long as camera device can closely shoot photovoltaic module last toughened glass's image one by one can.
Step S12: carrying out image analysis and identification on the scanned image of each photovoltaic module, and judging whether tempered glass corresponding to the scanned image is broken or not;
step S13: and outputting the scanning image and the position information corresponding to the broken photovoltaic module of the toughened glass.
Specifically, can number every photovoltaic module according to the position in advance to set up the serial number data plate on photovoltaic module's frame, when shooing photovoltaic module, also can in the image with this serial number data plate. Of course, the images of each photovoltaic module can be captured according to a certain sequence track, and the capturing sequence represents the position of the photovoltaic module. So that the damaged photovoltaic module is replaced and repaired in time.
In the embodiment, the photovoltaic modules are inspected block by replacing manual work through image scanning and shooting, so that the workload of maintenance and inspection of the photovoltaic modules by operation and maintenance personnel is reduced to a great extent, and for certain photovoltaic modules of which the installation positions are inconvenient to inspect manually, the photovoltaic modules can be detected in a mode of shooting images, so that the working difficulty of detection of the photovoltaic modules is further reduced; in addition, the toughened glass breakage condition on each photovoltaic module is preliminarily screened by collecting the scanning image, so that the workload of operation and maintenance personnel for checking one by one is reduced, and only after the scanning image is analyzed and identified, the toughened glass which is possibly broken is considered to be further identified, so that the workload of the operation and maintenance personnel is further reduced.
According to the method and the device, the toughened glass on the photovoltaic assembly is shot one by the camera device, so that the problems of manual block-by-block inspection and large workload are avoided; and carry out analysis and identification to the scanning image of shooting scanning, tentatively select the toughened glass's that has the condition of breaking image, further reduced fortune dimension personnel work load that the image looked over one by one, and then improved the work efficiency that toughened glass breaks and overhauls on the photovoltaic module, make things convenient for fortune dimension personnel in time to discover the toughened glass breakage condition on the photovoltaic module and take corresponding maintenance measure, guaranteed photovoltaic power plant's normal operating.
Based on the foregoing embodiment, in another specific embodiment of the present application, the process of analyzing and identifying the scanned image may specifically include:
carrying out gray level processing on the scanned image to obtain a gray level image;
judging whether the gray level image has a quasi-circular figure or not;
if the quasi-circular pattern exists in the gray level image, judging whether crack lines communicated with the quasi-circular pattern exist around the quasi-circular pattern;
if crack lines communicated with the quasi-circular pattern exist around the quasi-circular pattern, the tempered glass corresponding to the scanned image is broken.
In the case of tempered glass, when it is broken, broken glass fragments do not fall directly due to their own characteristics, but form spider-web-like crack lines radiating outward from the breaking point, and the closer to the breaking point, the more dense the cracks, and the position closest to the breaking point approximately forms a circular broken region.
Based on the particularity of the breaking pattern when the toughened glass breaks, the breaking pattern in the scanning pattern can be detected in two parts:
the first part is the detection and identification of a circle-like area near the center area of the rupture point.
Firstly, preprocessing a scanned image, converting a color scanned image into a gray image, filtering the gray image to reduce image noise, and sharpening the gray image to make the contour and the edge of the gray image clearer and the like; and then detecting according to the characteristics of the breaking points of the tempered glass of the photovoltaic module in the photovoltaic power station.
According to the characteristic that the breaking point of the toughened glass on the photovoltaic module is generally similar to a circle, a circle-like pattern library of the breaking point is established in advance. In practical use, the tempered glass is often broken by the impact of a sharp object, and obvious impact points similar to a circular pattern can appear. In the image processing, the circular-like image characteristics are obvious and easy to process, so that the fracture point detection can be used as a first condition for glass fracture judgment to accelerate the system judgment speed. The method is used for carrying out image segmentation on the preprocessed image. Because the grey value of the breaking point of the toughened glass is obviously different from the grey value of the background, the breaking point image can be divided by adopting a threshold value division method, and then mathematical morphology processing is carried out to obtain a better quasi-circular target graph. If the inscribed circle of the quasi-circular target graph identified by the cracking point detection algorithm can cover more than 80% of the area of the quasi-circular target graph, the graph of the cracking point area is shown when the quasi-circular target graph is possible to a great extent.
Of course, neural network training can also be used to obtain a circle-like pattern recognition model of the fracture points. For example, a Support Vector Machine (SVM) learning algorithm is used, which is a neural network algorithm for classification and regression and is commonly used for the binarization problem. Firstly, reading a large amount of data of fracture point image samples, then detecting a target fracture point by adopting a sliding window method (sliding window) or Selective search (Selective), establishing a classifier for an RGB image of the fracture point or converting the RGB image into data of a gray graph by adopting an SVM model, training the classifier by adopting a fracture point image sample training set, and finally obtaining a classifier model capable of identifying the fracture point image. There are other ways to identify the pattern of the breaking point, which are not listed in this application.
Because the identified quasi-circular pattern may also be bird droppings, leaves and other foreign matters, after the quasi-circular pattern is detected and identified to be a possible breaking point in the scanned image, the second step needs to detect whether a crack line exists around the quasi-circular pattern or not for further confirming whether tempered glass on the photovoltaic module is broken or not.
Optionally, in another specific embodiment of the present application, the detection process of the crack line is specifically as follows:
finding out an edge line on the gray level image based on an edge detection algorithm;
and judging whether edge lines communicated with the similar circular pattern exist or not, if so, judging whether included angles between adjacent edge lines in the plurality of edge lines communicated with the similar circular pattern are within a preset range or not, and if so, judging that the edge lines are crack lines.
It should be noted that, in the digital image processing technology, since the edge of the object represents the image in a discontinuous form, when the tempered glass of the photovoltaic module is broken, the crack line forms a texture pattern on the surface of the tempered glass, and the edge line of the texture pattern is the crack line. An edge detection algorithm may be employed to extract the crack lines. The edge detection algorithm has a plurality of methods, or a plurality of methods can be combined for use, pixel points with violently changed gray values are marked out to form an edge point set, and according to the characteristics that crack lines are continuous and linear, the edge points are connected, filled and grown into linear, so that edge lines are formed.
After obtaining the edge line, it is necessary to further determine whether the edge line is connected to the quasi-circular figure. Specifically, if the pixel point coordinates of the edge line are located in the area range of the quasi-circular figure, it is indicated that the edge line is communicated with the quasi-circular figure. If the edge line exists at every interval of a certain angle (for example, about 30 degrees) around the quasi-circular pattern, the edge line is considered as a crack line, so that the tempered glass of the photovoltaic module can be judged to be cracked, otherwise, the tempered glass of the photovoltaic module is not cracked.
In the embodiment, based on the particularity of the pattern texture of the fracture of the tempered glass, the circular fracture point pattern of the fracture pattern and the fracture line surrounding the fracture point are identified and analyzed, and compared with the fracture line, the circular fracture point is easier to identify, so that the circular-like pattern can be used as a first condition for identifying the fracture of the tempered glass, the speed of identifying and screening the scanned image is increased, most of images of the tempered glass without fracture are eliminated, the calculation amount is reduced for the identification calculation of the subsequent fracture line, and the calculation speed is increased. And considering that the local shielding, the leaves, the bird droppings and other reasons can also generate the quasi-circular pattern, whether crack lines exist around the quasi-circular area or not is further identified, and the accuracy of identifying the cracking pattern is further improved to a certain extent.
The mode of the last toughened glass's of analysis discernment pattern that breaks of photovoltaic module that provides in this embodiment, the operation is simple swift, can accurately screen the image that the cracked toughened glass probably appears in the at utmost, reduces the work load of inspection for fortune dimension personnel for find photovoltaic module's the cracked promptness of toughened glass.
Based on the above embodiment, except that the scanned image can be directly subjected to image processing, and then subjected to recognition analysis, and whether the tempered glass is broken or not is judged, the scanned image with broken patterns can be recognized in a neural network training mode, and in another specific embodiment of the present application, the process of analyzing and recognizing the broken patterns of the scanned image specifically includes:
collecting a fracture pattern sample of tempered glass of a photovoltaic module in advance;
obtaining a fracture pattern model for identifying the fractured image of the toughened glass through the learning of a neural network;
and identifying and analyzing whether the scanned image is an image of the tempered glass with the fracture according to the fracture pattern model.
In this embodiment, the rupture pattern is not divided into two parts for identification, but is identified as a whole. Before fracture pattern recognition, a large number of fracture pattern samples of tempered glass on a photovoltaic module are collected in advance, training of a neural network is performed based on the fracture pattern samples, and a fracture pattern model is obtained, specifically, the process of obtaining the fracture pattern model may refer to the creation process of a fracture point graph classifier in the above real-time example, and only the adopted image samples are different, which is not repeated in this embodiment. After a fracture pattern model is commonly obtained, when the shot scanning image of each photovoltaic module can be identified and judged, the judgment can be directly carried out based on the fracture pattern model.
Of course, there are other similar embodiments for identifying a rupture pattern in this application, which are not listed here.
Based on any of the above embodiments, after the scanned image with the burst pattern is screened out, the scanned image needs to be provided to the operation and maintenance personnel, and the operation and maintenance personnel further screen out the scanned image. However, for the fracture pattern on the tempered glass, no matter human eyes observe the actual photovoltaic module or the shot scanning image, the crack lines in the fracture pattern are relatively thin, and certain difficulty is brought to the observation of operation and maintenance personnel. For this reason, in another specific embodiment of the present application, after identifying the fracture pattern in the sweep table image, the method may further include:
highlighting and marking the cracking points and the cracking lines of the scanned image, and extracting the characteristics of the cracking points and the cracking lines to obtain cracking information;
storing the scanned image, the scanned image with the highlighted mark and the corresponding rupture information into a database; wherein the fracture information includes at least a fracture point area and a crack line length.
Specifically, the quasi-circular cracking points and cracking lines in the cracking pattern are highlighted, for example, filled or circled with lines of a conspicuous color. So that the serviceman can see the rupture pattern more clearly.
Further, because the scanned image has a certain scaling relative to the actual photovoltaic module, for this reason, the area of the quasi-circular fracture point and the length of the fracture line in the scanned image can be marked, so that the operation and maintenance personnel can have a clearer and more vivid cognition on the real shape and size of the fracture pattern, and the identification capability of the operation and maintenance personnel on the fracture pattern is improved.
The photovoltaic module maintenance device provided by the embodiment of the application is introduced below, and the photovoltaic module maintenance device described below and the photovoltaic module maintenance method described above can be referred to correspondingly.
Fig. 2 is a structural block diagram of an overhaul device of a photovoltaic module provided in an embodiment of the present application, and the overhaul device of the photovoltaic module with reference to fig. 2 may include:
the image acquisition module 100 is used for acquiring a scanning image obtained by scanning and shooting the tempered glass of the photovoltaic assembly by the camera device;
the identification and judgment module 200 is used for analyzing and identifying the scanned image and judging whether the tempered glass corresponding to the scanned image is broken or not;
and the information output module 300 is used for outputting the scanning image and the position information of the photovoltaic module with the broken toughened glass.
Optionally, in another specific embodiment of the present application, the identification and determination module is specifically configured to perform gray processing on the scanned image to obtain a gray image; judging whether the gray level image has a quasi-circular figure or not; if the quasi-circular figure exists in the gray level image, judging whether crack lines communicated with the quasi-circular figure exist around the quasi-circular figure; and if crack lines communicated with the quasi-circular pattern exist around the quasi-circular pattern, the tempered glass corresponding to the scanned image is broken.
Optionally, in another specific embodiment of the present application, the identification and determination module is specifically configured to find an edge line on the grayscale image based on an edge detection algorithm; and judging whether edge lines communicated with the similar circular pattern exist or not, if so, judging whether included angles between adjacent edge lines in a plurality of edge lines communicated with the similar circular pattern are within a preset range or not, and if so, judging that the edge lines are crack lines.
Optionally, in another specific embodiment of the present application, the identification and judgment module is specifically configured to collect a breaking pattern sample of tempered glass of a photovoltaic module in advance; obtaining a classifier for identifying the broken image of the toughened glass through the learning of a neural network; and distinguishing whether the scanned image is an image with broken toughened glass or not according to the classifier.
Optionally, in another specific embodiment of the present application, the information output module is specifically configured to, after outputting the scanned image and the position information corresponding to the photovoltaic module in which the tempered glass is broken, perform protruding marking on a breaking point and a breaking line of the scanned image, and perform feature extraction on the breaking point and the breaking line to obtain breaking information; storing the scanned image, the scanned image with the highlighted mark and the corresponding rupture information into a database; wherein the fracture information includes at least a fracture point area and a crack line length.
The photovoltaic module overhaul device of this embodiment is used to implement the foregoing photovoltaic module overhaul method, and therefore specific embodiments of the photovoltaic module overhaul device may be found in the foregoing example portions of the photovoltaic module overhaul method, for example, the image acquisition module 100, the identification and judgment module 200, and the information output module 300 are respectively used to implement steps S11, S12, and S13 in the foregoing photovoltaic module overhaul method, so that specific embodiments thereof may refer to descriptions of corresponding respective partial embodiments, and are not described herein again.
The present application still further provides an embodiment of a photovoltaic module's overhaul device, and this overhaul device specifically can include:
the camera device is used for scanning and shooting a scanned image of the toughened glass on each photovoltaic module in the photovoltaic system;
and the processor is connected with the camera device and is used for realizing the operation steps of the photovoltaic module overhauling method according to any embodiment according to the scanning image.
Specifically, camera device in this embodiment can be the unmanned aerial vehicle that has the camera, also can be the camera of setting in photovoltaic module peripheral position. But for the unmanned aerial vehicle that has the camera, unmanned aerial vehicle's shooting area is wider, and shooting angle and shooting distance have more controllability and flexibility. Therefore, the adoption of the unmanned aerial vehicle with the camera is a preferable scheme.
Adopt camera device and treater cooperation to use in this embodiment, realized patrolling and examining the automation of the toughened glass condition of breaking of photovoltaic module, reduced the work load that the operation and maintenance personnel overhauld at to a great extent, be convenient for in time discover that toughened glass breaks and in time change, be favorable to guaranteeing photovoltaic module's security and the normal operating of maintaining photovoltaic power plant.
Also provided in the present application is a computer readable storage medium having a computer program stored thereon, which, when being executed by a processor, realizes the steps of the method for servicing a photovoltaic module as described in any one of the above.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of computer-readable storage medium known in the art.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Claims (10)
1. A photovoltaic module overhauling method is characterized by comprising the following steps:
acquiring a scanning image obtained by scanning and shooting the toughened glass of the photovoltaic assembly by a camera device;
analyzing and identifying the scanned image, and judging whether tempered glass corresponding to the scanned image is broken or not;
and if so, outputting the scanning image and the position information corresponding to the broken photovoltaic module of the toughened glass.
2. The photovoltaic module overhauling method of claim 1, wherein the analyzing and identifying the scanning image and the judging whether the tempered glass corresponding to the scanning image is broken comprise:
carrying out gray level processing on the scanned image to obtain a gray level image;
judging whether the gray level image has a quasi-circular figure or not;
if the quasi-circular figure exists in the gray level image, judging whether crack lines communicated with the quasi-circular figure exist around the quasi-circular figure;
and if crack lines communicated with the quasi-circular pattern exist around the quasi-circular pattern, the tempered glass corresponding to the scanned image is broken.
3. The method for repairing a photovoltaic module according to claim 2, wherein the determining whether a crack line communicating with the quasi-circular pattern exists around the quasi-circular pattern comprises:
finding out an edge line on the gray level image based on an edge detection algorithm;
and judging whether edge lines communicated with the similar circular pattern exist or not, if so, judging whether included angles between adjacent edge lines in a plurality of edge lines communicated with the similar circular pattern are within a preset range or not, and if so, judging that the edge lines are crack lines.
4. The photovoltaic module overhauling method of claim 1, wherein the analyzing and identifying the scanning image and the judging whether the tempered glass corresponding to the scanning image is broken comprise:
collecting a fracture pattern sample of tempered glass of a photovoltaic module in advance;
obtaining a classifier for identifying the broken image of the toughened glass through the learning of a neural network;
and distinguishing whether the scanned image is an image with broken toughened glass or not according to the classifier.
5. The photovoltaic module overhauling method according to any one of claims 1 to 4, wherein after outputting the scanned image and the position information corresponding to the photovoltaic module with the broken toughened glass, the overhauling method further comprises the following steps:
highlighting and marking the cracking point and the cracking line of the scanned image, and extracting the characteristics of the cracking point and the cracking line to obtain cracking information;
storing the scanned image, the scanned image with the highlighted mark and the corresponding rupture information into a database; wherein the fracture information includes at least a fracture point area and a crack line length.
6. A photovoltaic module's maintenance device which characterized in that includes:
the image acquisition module is used for acquiring a scanning image obtained by scanning and shooting the toughened glass of the photovoltaic assembly by the camera device;
the identification judging module is used for analyzing and identifying the scanned image and judging whether tempered glass corresponding to the scanned image is broken or not;
and the information output module is used for outputting the scanning image and the position information of the photovoltaic assembly with the broken toughened glass.
7. The photovoltaic module overhauling device of claim 6, wherein the identification and judgment module is used for carrying out gray scale processing on the scanned image to obtain a gray scale image; judging whether the gray level image has a quasi-circular figure or not; if so, judging whether crack lines communicated with the similar circular pattern exist around the similar circular pattern; and if so, breaking the tempered glass corresponding to the scanned image.
8. The photovoltaic module overhauling equipment is characterized by comprising a camera device for scanning and shooting a scanning image of toughened glass on each photovoltaic module in a photovoltaic system;
and the processor is connected with the camera device and is used for realizing the operation steps of executing the photovoltaic module overhauling method according to any one of claims 1 to 5 according to the scanning image.
9. The photovoltaic module servicing apparatus of claim 8, wherein the camera is a drone with a camera.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method of servicing a photovoltaic module according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911205375.0A CN110907473B (en) | 2019-11-29 | 2019-11-29 | Photovoltaic module overhauling method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911205375.0A CN110907473B (en) | 2019-11-29 | 2019-11-29 | Photovoltaic module overhauling method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110907473A true CN110907473A (en) | 2020-03-24 |
| CN110907473B CN110907473B (en) | 2023-04-07 |
Family
ID=69820914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911205375.0A Active CN110907473B (en) | 2019-11-29 | 2019-11-29 | Photovoltaic module overhauling method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110907473B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110235868A1 (en) * | 2010-03-26 | 2011-09-29 | Kuo Cooper S K | Inspection System |
| CN105447851A (en) * | 2015-11-12 | 2016-03-30 | 刘新辉 | Glass panel sound hole defect detection method and system |
| CN107358603A (en) * | 2017-07-18 | 2017-11-17 | 京东方科技集团股份有限公司 | Method of testing substrate, substrate detection apparatus and computer-readable recording medium |
| CN108171190A (en) * | 2018-01-05 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of optical finger print recognition methods, terminal and computer readable storage medium |
| CN108986081A (en) * | 2018-06-28 | 2018-12-11 | 湖南红太阳新能源科技有限公司 | Photovoltaic component glass crack detecting method, device, equipment and storage medium |
| CN109155062A (en) * | 2016-05-13 | 2019-01-04 | 贝尔隆国际有限公司 | Analysis on cracks device and method |
| CN109490310A (en) * | 2018-10-18 | 2019-03-19 | 广州建设工程质量安全检测中心有限公司 | A kind of curtain wall monitoring system based on unmanned plane |
| CN109613002A (en) * | 2018-11-21 | 2019-04-12 | 腾讯科技（深圳）有限公司 | A kind of glass defect detection method, apparatus and storage medium |
| CN109668909A (en) * | 2017-10-13 | 2019-04-23 | 南京敏光视觉智能科技有限公司 | A kind of glass defect detection method |
| US20190294106A1 (en) * | 2018-03-22 | 2019-09-26 | National Taiwan Normal University | Complex Defect Diffraction Model and Method for Defect Inspection of Transparent Substrate |
-
2019
- 2019-11-29 CN CN201911205375.0A patent/CN110907473B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110235868A1 (en) * | 2010-03-26 | 2011-09-29 | Kuo Cooper S K | Inspection System |
| CN105447851A (en) * | 2015-11-12 | 2016-03-30 | 刘新辉 | Glass panel sound hole defect detection method and system |
| CN109155062A (en) * | 2016-05-13 | 2019-01-04 | 贝尔隆国际有限公司 | Analysis on cracks device and method |
| CN107358603A (en) * | 2017-07-18 | 2017-11-17 | 京东方科技集团股份有限公司 | Method of testing substrate, substrate detection apparatus and computer-readable recording medium |
| CN109668909A (en) * | 2017-10-13 | 2019-04-23 | 南京敏光视觉智能科技有限公司 | A kind of glass defect detection method |
| CN108171190A (en) * | 2018-01-05 | 2018-06-15 | 深圳市金立通信设备有限公司 | A kind of optical finger print recognition methods, terminal and computer readable storage medium |
| US20190294106A1 (en) * | 2018-03-22 | 2019-09-26 | National Taiwan Normal University | Complex Defect Diffraction Model and Method for Defect Inspection of Transparent Substrate |
| CN108986081A (en) * | 2018-06-28 | 2018-12-11 | 湖南红太阳新能源科技有限公司 | Photovoltaic component glass crack detecting method, device, equipment and storage medium |
| CN109490310A (en) * | 2018-10-18 | 2019-03-19 | 广州建设工程质量安全检测中心有限公司 | A kind of curtain wall monitoring system based on unmanned plane |
| CN109613002A (en) * | 2018-11-21 | 2019-04-12 | 腾讯科技（深圳）有限公司 | A kind of glass defect detection method, apparatus and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110907473B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111275679B (en) | Image-based solar cell defect detection system and method | |
| CN110211101A (en) | A kind of rail surface defect rapid detection system and method | |
| CN107876425A (en) | A kind of bearing defect detecting system device of view-based access control model | |
| CN111127448B (en) | Method for detecting air spring fault based on isolated forest | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN107886047A (en) | A kind of detecting system and method for vehicle annual test survey report | |
| CN106841214A (en) | A kind of non-contact wind power blade dust storm erosion degree detection method | |
| CN109946304A (en) | Surface defects of parts on-line detecting system and detection method based on characteristic matching | |
| CN112819844B (en) | Image edge detection method and device | |
| CN108508023B (en) | Defect detection system for contact end jacking bolt in railway contact network | |
| CN110728269B (en) | High-speed rail contact net support pole number plate identification method based on C2 detection data | |
| CN116805302A (en) | Cable surface defect detection device and method | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN109521021A (en) | A kind of nuclear power plant containment shell appearance inspecting system and method | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN111667473A (en) | Insulator hydrophobicity grade judging method based on improved Canny algorithm | |
| CN114723668A (en) | Cathode copper quality detection method and system based on area-array camera | |
| CN110907473B (en) | Photovoltaic module overhauling method, device, equipment and storage medium | |
| CN113962929A (en) | Photovoltaic cell assembly defect detection method and system and photovoltaic cell assembly production line | |
| CN117152161A (en) | Shaving board quality detection method and system based on image recognition | |
| CN116818763A (en) | Rapid detection method for surface defects of wind power blade | |
| CN110070520B (en) | Pavement crack detection model construction and detection method based on deep neural network | |
| CN114881984A (en) | Detection method and device for rice processing precision, electronic equipment and medium | |
| CN114332146A (en) | Fragment glass contour extraction method | |
| CN111610205A (en) | X-ray image defect detection device for metal parts |
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 |