CN115829922B - Method, device, equipment and medium for detecting spacing of battery pieces - Google Patents
Method, device, equipment and medium for detecting spacing of battery pieces Download PDFInfo
- Publication number
- CN115829922B CN115829922B CN202211164165.3A CN202211164165A CN115829922B CN 115829922 B CN115829922 B CN 115829922B CN 202211164165 A CN202211164165 A CN 202211164165A CN 115829922 B CN115829922 B CN 115829922B
- Authority
- CN
- China
- Prior art keywords
- interval
- battery
- pitch
- spacing
- picture
- 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 72
- 238000005070 sampling Methods 0.000 claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 2
- 238000012512 characterization method Methods 0.000 abstract description 6
- 239000005038 ethylene vinyl acetate Substances 0.000 description 10
- 229920001200 poly(ethylene-vinyl acetate) Polymers 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 9
- 238000010248 power generation Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 239000005341 toughened glass Substances 0.000 description 6
- 229910021419 crystalline silicon Inorganic materials 0.000 description 5
- 230000005611 electricity Effects 0.000 description 5
- 238000010606 normalization Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000004913 activation Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 229910021420 polycrystalline silicon Inorganic materials 0.000 description 4
- 238000007789 sealing Methods 0.000 description 4
- 239000004065 semiconductor Substances 0.000 description 4
- 239000010409 thin film Substances 0.000 description 4
- 229910000838 Al alloy Inorganic materials 0.000 description 3
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 229920005591 polysilicon Polymers 0.000 description 3
- 239000000741 silica gel Substances 0.000 description 3
- 229910002027 silica gel Inorganic materials 0.000 description 3
- 229920002725 thermoplastic elastomer Polymers 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 239000000853 adhesive Substances 0.000 description 2
- 230000001070 adhesive effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- VXUYXOFXAQZZMF-UHFFFAOYSA-N titanium(IV) isopropoxide Chemical compound CC(C)O[Ti](OC(C)C)(OC(C)C)OC(C)C VXUYXOFXAQZZMF-UHFFFAOYSA-N 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 239000004816 latex Substances 0.000 description 1
- 229920000126 latex Polymers 0.000 description 1
- 230000001795 light effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 229910021421 monocrystalline silicon Inorganic materials 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000002210 silicon-based material Substances 0.000 description 1
- 229920002379 silicone rubber Polymers 0.000 description 1
- 239000004945 silicone rubber Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000004078 waterproofing Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Image Analysis (AREA)
- Secondary Cells (AREA)
Abstract
The application discloses a method, a device, equipment and a medium for detecting the spacing of battery pieces, and relates to the technical field of deep learning. The method is applied to a cell piece of a cell plate in a photovoltaic module and comprises the following steps: acquiring interval pictures of a plurality of battery pieces in real time; inputting the interval picture into an interval detection model to obtain the confidence coefficient of the interval of the characterization battery piece; when the confidence coefficient reaches a preset standard, determining that the spacing of the battery pieces is qualified; the method comprises the following steps of: acquiring sampling interval pictures of a plurality of battery pieces; and constructing a distance detection model according to the sampling distance picture and based on a depth learning algorithm. By introducing the interval detection model, the confidence corresponding to each interval picture is detected in real time according to the interval detection model, and the manual mode is replaced by the interval detection model, so that the interval between the battery pieces is efficiently and accurately detected.
Description
Technical Field
The application relates to the technical field of deep learning, in particular to a method, a device, equipment and a medium for detecting the spacing of battery pieces.
Background
With the gradual rise of solar energy, the application of the solar energy is more and more, and the solar panel manufactured by utilizing the solar energy is also applied to various fields. In still other fields, various technologies applied to photovoltaic solar panels are of great interest. In order to meet the requirements of customers on the spacing of each battery piece in a battery plate on a photovoltaic module, the existing method is that technicians manually set the spacing between the battery pieces and judge whether the spacing meets the standard of the photovoltaic module. Such a method is extremely inefficient and manual setup affects its accuracy.
In view of the above-mentioned problems, it is a matter of great effort for a person skilled in the art to find out how to efficiently and accurately detect whether the spacing between the battery pieces meets the criteria of the photovoltaic module.
Disclosure of Invention
The application aims to provide a method, a device, equipment and a medium for detecting the spacing between battery pieces, which are used for efficiently and accurately detecting the spacing between the battery pieces.
In order to solve the above technical problems, the present application provides a method for detecting a spacing between battery pieces, which is applied to a battery piece of a battery board in a photovoltaic module, and includes:
Acquiring interval pictures of a plurality of battery pieces in real time;
Inputting the interval picture into an interval detection model to obtain the confidence coefficient of the interval of the characterization battery piece;
When the confidence coefficient reaches a preset standard, determining that the spacing of the battery pieces is qualified;
The method comprises the following steps of: acquiring sampling interval pictures of a plurality of battery pieces; and constructing a distance detection model according to the sampling distance picture and based on a depth learning algorithm.
Preferably, acquiring the sampling interval pictures of the plurality of battery pieces includes:
preferably, determining the sampling interval picture according to the position includes:
And (3) expanding preset unit pixel values along each side of the battery piece on the condition that the position of the battery piece is used, and setting a picture containing the preset unit pixel values as a sampling interval picture.
Preferably, when the confidence level does not reach the preset standard, the method further comprises:
binarization processing is carried out on the interval picture, and a corresponding pixel histogram is obtained;
Counting the maximum value of the pixel histogram;
Judging whether the maximum value reaches a threshold value or not;
If the maximum value does not reach the threshold value, determining that the spacing of the battery pieces is unqualified;
if the maximum value reaches the threshold value, judging whether the frequency of the maximum value reaching the threshold value is not less than the preset frequency;
if the times are smaller than the preset times, determining that the spacing of the battery pieces is unqualified;
if the times are not less than the preset times, determining that the spacing between the battery pieces is qualified.
Preferably, after determining that the spacing of the battery pieces is not acceptable, the method further comprises:
And marking the interval pictures with unqualified intervals.
Preferably, after obtaining the sampling pitch pictures of the plurality of battery pieces, before constructing the pitch detection model based on the depth learning algorithm according to the sampling pitch pictures, the method further comprises:
And preprocessing the sampling interval picture.
In order to solve the technical problem, the application also provides a device for detecting the spacing of the battery pieces, which comprises:
The acquisition module is used for acquiring the interval pictures of the plurality of battery pieces in real time;
The input module is used for inputting the interval picture into the interval detection model to obtain the confidence coefficient of the interval of the characterization battery piece, wherein the interval detection model construction step comprises the following steps: acquiring sampling interval pictures of a plurality of battery pieces; constructing a distance detection model according to the sampling distance picture and based on a depth learning algorithm;
and the first determining module is used for determining that the spacing of the battery pieces is qualified when the confidence coefficient reaches a preset standard.
Furthermore, the device comprises the following modules:
And the expansion module is used for expanding preset unit pixel values along each side of the battery piece on the condition of the position of the battery piece, and setting a picture containing the preset unit pixel values as the sampling interval picture.
Preferably, when the confidence coefficient does not reach the preset standard, the method further includes:
The binarization module is used for carrying out binarization processing on the interval picture and obtaining a corresponding pixel histogram;
The statistics module is used for counting the maximum value of the pixel histogram;
The first judging module is used for judging whether the maximum value reaches a threshold value or not;
If the maximum value does not reach the threshold value, triggering a second determining module for determining that the spacing of the battery pieces is unqualified;
if the maximum value reaches the threshold value, triggering a second judging module, wherein the second judging module is used for judging whether the frequency of the maximum value reaching the threshold value is not less than a preset frequency;
if the times are smaller than the preset times, triggering the second determining module, wherein the second determining module is used for determining that the spacing of the battery pieces is unqualified;
and if the times are not smaller than the preset times, triggering the first determining module to determine that the spacing of the battery pieces is qualified.
Preferably, the method further comprises:
And the marking module is used for marking the interval pictures with unqualified intervals.
Preferably, the method further comprises:
and the preprocessing module is used for preprocessing the sampling interval picture.
In order to solve the above technical problem, the present application further provides an apparatus for detecting a pitch of a battery sheet, including:
A memory for storing a computer program;
And the processor is used for pointing to a computer program and realizing the steps of the method for detecting the spacing of the battery pieces.
In order to solve the above technical problem, the present application further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method for detecting the spacing of all the battery pieces.
The application provides a method for detecting the spacing of battery pieces, which is applied to the battery pieces of a battery plate in a photovoltaic module and comprises the following steps: acquiring interval pictures of a plurality of battery pieces in real time; inputting the interval picture into an interval detection model to obtain the confidence coefficient of the interval of the characterization battery piece; when the confidence coefficient reaches a preset standard, determining that the spacing of the battery pieces is qualified; the method comprises the following steps of: acquiring sampling interval pictures of a plurality of battery pieces; and constructing a distance detection model according to the sampling distance picture and based on a depth learning algorithm. By introducing the interval detection model, the confidence corresponding to each interval picture is detected in real time according to the interval detection model, and the manual mode is replaced by the interval detection model, so that the interval between the battery pieces is efficiently and accurately detected.
The application also provides a device, equipment and medium for detecting the spacing of the battery pieces, and the effects are the same as the above.
Drawings
For a clearer description of embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described, it being apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.
Fig. 1 is a flowchart of a method for detecting a pitch of a battery slice according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a pitch detection model structure according to an embodiment of the present application;
FIG. 3 is a pixel histogram according to an embodiment of the present application;
fig. 4 is a block diagram of an apparatus for detecting a pitch of a battery sheet according to an embodiment of the present application;
fig. 5 is a block diagram of an apparatus for detecting a pitch of a battery sheet according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by a person of ordinary skill in the art without making any inventive effort are within the scope of the present application.
The application provides a method, a device, equipment and a medium for detecting the spacing between battery pieces, which can efficiently and accurately detect the spacing between the battery pieces.
In order to better understand the aspects of the present application, the present application will be described in further detail with reference to the accompanying drawings and detailed description.
Fig. 1 is a flowchart of a method for detecting a pitch of a battery plate according to an embodiment of the present application. As shown in fig. 1, the method for detecting the spacing of the battery pieces is applied to the battery pieces of the battery plates in the photovoltaic module, and includes:
S10: and acquiring interval pictures of the plurality of battery pieces in real time.
S11: and inputting the interval picture into an interval detection model to obtain the confidence coefficient for representing the interval of the battery piece.
S12: and when the confidence coefficient reaches a preset standard, determining that the spacing of the battery pieces is qualified.
The method comprises the following steps of: acquiring sampling interval pictures of a plurality of battery pieces; and constructing a distance detection model according to the sampling distance picture and based on a depth learning algorithm.
The solar panel is also called a solar chip or a photocell, and is a photoelectric semiconductor sheet which directly generates electricity by utilizing sunlight. The single solar cell cannot be directly used as a power supply. Several individual solar cell strings or panels must be connected in parallel and tightly packaged into an assembly for use as a power source. A solar panel (which may also be referred to as a solar cell module) is a module in which a plurality of solar cells are assembled in units of a group, and is a core part of a solar power generation system, and is the most important part of the solar power generation system.
The luminous principle is as follows: the solar light irradiates on the p-n junction of the semiconductor to form a new hole-electron pair, under the action of the electric field of the p-n junction, holes flow from the p region to the n region, electrons flow from the n region to the p region, and current is formed after a circuit is connected.
Solar power generation has two modes, one is a light-heat-electricity conversion mode and the other is a light-electricity direct conversion mode.
Among them, the photo-thermal-electric conversion mode generates electricity by using thermal energy generated by solar radiation, and generally, the absorbed thermal energy is converted into vapor by a solar collector (the process is a photo-thermal conversion process), and various devices are driven to generate electricity (the process is a thermal-electric conversion process).
The photoelectric-electric direct conversion mode is to directly convert solar radiation energy into electric energy by utilizing photoelectric effect, and the basic device of photoelectric-electric conversion is a solar panel. A solar panel is a device that directly converts solar light energy into electric energy due to a photovoltaic effect, and may be a semiconductor photodiode on which solar light energy is converted into electric energy when the solar light is irradiated, thereby generating electric current.
Currently, crystalline silicon materials (including polycrystalline silicon and monocrystalline silicon) are the most dominant photovoltaic materials, with market share above 90%, and remain the dominant materials for solar cells for a considerable period of time in the future. The demand for polysilicon comes mainly from semiconductors and solar cells. According to different purity requirements, the method is divided into an electronic grade and a solar grade. Wherein, the electronic grade polysilicon accounts for about 55 percent, and the solar grade polysilicon accounts for about 45 percent.
A common solar panel is provided in this embodiment, which is generally composed of tempered glass, ethylene-vinyl acetate copolymer (EVA), a battery sheet, a back sheet, an aluminum alloy, a junction box, silicone rubber, and the like.
The toughened glass is used for protecting a power generation main body (such as a battery piece), the light transmittance of the toughened glass is required to reach more than 91%, and the toughened glass is required to be subjected to super-white toughening treatment. The aluminum alloy is used for protecting the pressing piece and plays a certain role in sealing and supporting.
The chemical formula of the ethylene-vinyl acetate copolymer is C6H10O2, commonly known as latex powder, and the ethylene-vinyl acetate copolymer is used for bonding and fixing toughened glass and a power generation main body (such as a battery piece), the service life of the component is directly influenced by the quality of transparent EVA materials, and EVA exposed in air is easy to age and yellow, so that the light transmittance of the component is influenced, and the power generation quality of the component is influenced. Besides the quality of EVA, the lamination process of the assembly manufacturer has great influence, for example, the EVA adhesive strength is not up to the standard, and the EVA, toughened glass and a backboard are not strong enough in adhesive strength, so that the EVA can be aged in advance, and the service life of the assembly is influenced.
The main power generation body (such as a battery piece) is mainly used for generating power, and crystalline silicon solar battery pieces and thin film solar battery pieces are mainstream in the market of the main power generation body. The implementation thereof may be determined according to the specific implementation scenario.
It is clear that the crystalline silicon solar cell has relatively low equipment cost, but the cost of consuming the cell is very high, the photoelectric conversion efficiency is also high, and the crystalline silicon solar cell is suitable for generating electricity in the outdoor sunlight. The thin film solar cell has higher relative equipment cost, but the cost of consuming the cell is very low, the photoelectric conversion efficiency is generally more than half of that of the crystalline silicon cell, and it can be understood that the weak light effect is very good, and the thin film solar cell can generate electricity under the common light (in living scenes, the solar cell on the calculator is the thin film solar cell).
The backboard is used for sealing, insulating and waterproofing. Materials such as ageing-resistant isopropyl titanate (Titanium (IV) isopropoxide, TPT) or thermoplastic elastomers (Thermoplastic Elastomer, TPE) are generally used. The silica gel plays a sealing role and is used for sealing the junction of the component and the aluminum alloy frame and the junction of the component and the junction box. In consideration of the requirements of simple and convenient process, easy operation, low cost and the like, silica gel is generally used. It is understood that the key point of the whole solar panel is whether the solar panel can meet the requirements of the back plate and the silica gel.
The terminal box is used for protecting the whole power generation system, plays the role of a current transfer station, and if the module is short-circuited, the terminal box automatically breaks a plurality of battery pieces which are well short-circuited, so that the whole system is prevented from being burnt out, the most critical in the terminal box is the selection of diodes, and the corresponding diodes are different according to different types of battery pieces in the module.
In addition, the deep learning algorithm (DEEP LEARNING, DL) referred to in the present application is one of the machine learning (MACHINE LEARNING, ML). The algorithm can be equally applied to artificial intelligence (ARTIFICIAL INTELLIGENCE, AI). The motivation for deep learning is to build, simulate a neural network for analysis learning of the human brain, which mimics the mechanisms of the human brain to interpret data, such as images, sounds and text. Deep learning is one type of unsupervised learning. The concept of deep learning is derived from the study of artificial neural networks. The multi-layer sensor with multiple hidden layers is a deep learning structure. Deep learning forms more abstract high-level representation attribute categories or features by combining low-level features to discover distributed feature representations of data.
Depth is understood to mean, among other things, the generation of an output from an input. The calculations involved may be represented by a flow graph (flow graph). A flow graph is a graph that can represent computations in which each node represents a basic computation and results in a computed value (the result of the computation being applied to the child node of that node). Such a set of computations may be allowed in each node and graph structure and define a family of functions. The input node has no parent node and the output node has no child node. One particular attribute of such a flow graph is depth, i.e. the length of the longest path from one input to one output.
Fig. 2 is a schematic diagram of a pitch detection model structure according to an embodiment of the present application. This spacing detection model may also be referred to as the solar CELL DISTANCE network model. As shown in fig. 2, after passing through the network input channels (in the embodiment of the present application, the number of the network input channels is 3), the network input channels are divided into 6 branches, and first, the network input channels enter a convolution layer (Conv), a batch normalization layer (BN) and an activation layer (ReLu) in sequence through a fifth branch (branch with reference number 5); the first branch (branch numbered 1), the second branch (branch numbered 2), the third branch (branch numbered 3), the fourth branch (branch numbered 4), the sixth branch (branch numbered 6) add up to the result of the fifth branch at the end and continue to input to the following logic. The number of bits of output data of the four groups of convolution layers (Conv), bulk normalization layers (BN), and activation layers (ReLu) in the drawing is 64, 128, 512, and 1024 channels in the order of the convolution layers (Conv), bulk normalization layers (BN), and activation layers (ReLu) in fig. 2. The convolution layer (Conv) performs position one-to-one point multiplication addition by using a convolution kernel; a batch normalization layer (BN) for normalization; an activation layer (ReLu) for performing a nonlinear transformation; full Connection (FC) is used for each point to computationally sum with parameters on the feature map (which can be understood as pitch pictures); the prediction result (Pred) represents the result of the model prediction.
After obtaining the sampling interval pictures of the plurality of battery pieces, before constructing the interval detection model based on the depth learning algorithm according to the sampling interval pictures, the method further comprises the following steps:
And preprocessing the sampling interval picture.
The sample interval pictures are classified into two general categories, NG and OK. Wherein NG represents string pitch coincidence and/or sheet pitch coincidence; OK indicates that no string pitch overlap and/or chip pitch overlap has occurred. The sampling interval pictures are divided into sampling string interval pictures and sampling sheet interval pictures; it will be appreciated that the pitch pictures can also be divided into two categories, string pitch pictures and slice pitch pictures, respectively.
It should be further noted that, obtaining the sampling interval pictures of the plurality of battery slices includes:
Wherein the cutting is performed around the determined position of the battery piece by the cutting pattern model. And (3) expanding preset unit pixel values along each side of the battery piece on the condition that the position of the battery piece is used, and setting a picture containing the preset unit pixel values as a sampling interval picture.
In the present embodiment, the preset unit may be set to 20. At this time, it can be understood that the battery piece position can be regarded as a rectangle, the four sides of the rectangle are respectively expanded according to 20 pixel values, and the picture including the 20 pixel values is set as a sampling interval picture for deep learning.
And inputting the space pictures of the plurality of battery pieces obtained in real time into a space detection model after deep learning, scaling the string space pictures into rectangular pictures with the height of 450 and the width of 80, and scaling the piece space pictures into rectangular pictures with the height of 80 and the width of 450 (namely, the string space pictures are understood to be horizontal bar pictures and the piece space pictures are vertical bar pictures). It should be noted that, when the battery slice position is initially determined, the plurality of battery slices of the entity are mapped to the display screen of the terminal according to a certain proportion by a software program, so that a technician can observe in real time. And pictures classified as NG and OK are also displayed on the display screen of the terminal.
The relevant judgment of the confidence level can be understood as follows from the examples mentioned in the above embodiments: the above mentioned string pitch picture scaled to be high 450 and wide 80 and the chip pitch picture scaled to be high 80 and wide 450, the confidence levels obtained by the pitch detection model were 0.89 and 0.73, respectively. At this time, if the preset standard is 0.8, the pitch of the string pitch picture with the confidence degree of 0.89 is determined to be qualified.
The application provides a method for detecting the spacing of battery pieces, which is applied to the battery pieces of a battery plate in a photovoltaic module and comprises the following steps: acquiring interval pictures of a plurality of battery pieces in real time; inputting the interval picture into an interval detection model to obtain the confidence coefficient of the interval of the characterization battery piece; when the confidence coefficient reaches a preset standard, determining that the spacing of the battery pieces is qualified; the method comprises the following steps of: acquiring sampling interval pictures of a plurality of battery pieces; and constructing a distance detection model according to the sampling distance picture and based on a depth learning algorithm. By introducing the interval detection model, the confidence corresponding to each interval picture is detected in real time according to the interval detection model, and the manual mode is replaced by the interval detection model, so that the interval between the battery pieces is efficiently and accurately detected.
On the basis of the above embodiment, as a more preferable embodiment, when the confidence coefficient does not reach the preset standard, the method further includes:
binarization processing is carried out on the interval picture, and a corresponding pixel histogram is obtained;
In the case of binarizing the pitch image, it is necessary to calculate the number of horizontal white pixels and obtain a pixel histogram, as shown in fig. 3. Fig. 3 is a pixel histogram provided in an embodiment of the present application.
Counting the maximum value of the pixel histogram;
Judging whether the maximum value reaches a threshold value or not;
If the maximum value does not reach the threshold value, determining that the spacing of the battery pieces is unqualified;
if the maximum value reaches the threshold value, judging whether the frequency of the maximum value reaching the threshold value is not less than the preset frequency;
if the times are smaller than the preset times, determining that the spacing of the battery pieces is unqualified;
if the times are not less than the preset times, determining that the spacing between the battery pieces is qualified.
In the present embodiment, the maximum value of the pixel histogram is generally set to 114750, which is obtained from a picture width of 450 and a white pixel value of 255 (picture classified as OK). The picture width is multiplied by the white pixel value. Therefore, when the maximum value does not reach the threshold value, the spacing of the battery pieces is determined to be unqualified. The maximum in fig. 3 can be seen directly as less than 114750.
On the basis of the above embodiment, as a more preferable embodiment, after determining that the pitch of the battery pieces is not qualified, the method further includes:
And marking the interval pictures with unqualified intervals.
In view of the convenience of the technician in knowing where the pitch is unacceptable, the unacceptable pitch picture is marked for more efficient adjustment.
In the foregoing embodiments, a method for detecting the pitch of the battery pieces is described in detail, and the application also provides a corresponding embodiment of the device for detecting the pitch of the battery pieces. It should be noted that the present application describes an embodiment of the device portion from two angles, one based on the angle of the functional module and the other based on the angle of the hardware.
Fig. 4 is a block diagram of an apparatus for detecting a pitch of a battery sheet according to an embodiment of the present application. As shown in fig. 4, the present application further provides a device for detecting a pitch of a battery slice, including:
An acquiring module 40, configured to acquire space pictures of a plurality of battery slices in real time;
The input module 41 is configured to input the pitch image to a pitch detection model, and obtain a confidence coefficient representing a pitch of the battery piece, where the pitch detection model building step includes: acquiring sampling interval pictures of a plurality of battery pieces; constructing a distance detection model according to the sampling distance picture and based on a depth learning algorithm;
The first determining module 42 is configured to determine that the spacing between the battery cells is acceptable when the confidence reaches a preset standard.
Furthermore, the device comprises the following modules:
And the expansion module is used for expanding preset unit pixel values along each side of the battery piece on the condition of the position of the battery piece, and setting a picture containing the preset unit pixel values as the sampling interval picture.
Preferably, when the confidence coefficient does not reach the preset standard, the method further includes:
The binarization module is used for carrying out binarization processing on the interval picture and obtaining a corresponding pixel histogram;
The statistics module is used for counting the maximum value of the pixel histogram;
The first judging module is used for judging whether the maximum value reaches a threshold value or not;
If the maximum value does not reach the threshold value, triggering a second determining module for determining that the spacing of the battery pieces is unqualified;
if the maximum value reaches the threshold value, triggering a second judging module, wherein the second judging module is used for judging whether the frequency of the maximum value reaching the threshold value is not less than a preset frequency;
if the times are smaller than the preset times, triggering the second determining module, wherein the second determining module is used for determining that the spacing of the battery pieces is unqualified;
and if the times are not smaller than the preset times, triggering the first determining module to determine that the spacing of the battery pieces is qualified.
Preferably, the method further comprises:
And the marking module is used for marking the interval pictures with unqualified intervals.
Preferably, the method further comprises:
and the preprocessing module is used for preprocessing the sampling interval picture.
Because the device for detecting the spacing of the battery pieces and the method for detecting the spacing of the battery pieces are the same conception, the device for detecting the spacing of the battery pieces has the same technical effect as the method for detecting the spacing of the battery pieces, and the spacing pictures of a plurality of battery pieces are obtained in real time; inputting the interval picture into an interval detection model to obtain the confidence coefficient of the interval of the characterization battery piece; when the confidence coefficient reaches a preset standard, determining that the spacing of the battery pieces is qualified; the method comprises the following steps of: acquiring sampling interval pictures of a plurality of battery pieces; and constructing a spacing detection model based on a depth learning algorithm according to the sampling spacing pictures, wherein the spacing detection model is introduced, and the confidence corresponding to each spacing picture is detected in real time according to the spacing detection model, so that the manual mode is replaced by the spacing detection model, and the spacing between the battery pieces is efficiently and accurately detected.
Since the embodiments of the apparatus portion and the embodiments of the method portion correspond to each other, the embodiments of the apparatus portion are referred to the description of the embodiments of the method portion, and are not repeated herein.
Fig. 5 is a block diagram of an apparatus for detecting a pitch of a battery piece according to an embodiment of the present application, where, as shown in fig. 5, the apparatus for detecting a pitch of a battery piece includes:
a memory 50 for storing a computer program;
a processor 51 for implementing the steps of the method of detecting the pitch of the battery cells as mentioned in the above embodiments when executing a computer program.
The device for detecting the distance between the battery pieces provided in this embodiment may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like.
Processor 51 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 51 may be implemented in at least one hardware form of Digital Signal Processing (DSP), field-Programmable gate array (fieldprogrammable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 51 may also include a main processor and a coprocessor, the main processor being a processor for processing data in an awake state, also referred to as a central processor (Central Processing Unit, CPU); a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 51 may be integrated with an image processor (Graphics Processing Unit, GPU) for rendering and rendering of content to be displayed by the display screen. In some embodiments, the processor 51 may also include an artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) processor for processing computing operations related to machine learning.
Memory 50 may include one or more computer-readable storage media, which may be non-transitory. Memory 50 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 50 is at least used to store a computer program that, when loaded and executed by the processor 51, enables the implementation of the relevant steps of the method for detecting the pitch of the battery cells disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 50 may also include an operating system, data, etc., and the storage manner may be transient storage or permanent storage. The operating system may include Windows, unix, linux, among other things. The data may include, but is not limited to, a method of detecting the pitch of the battery cells, and the like.
In some embodiments, the device for detecting the spacing of the battery pieces can further comprise a display screen, an input-output interface, a communication interface, a power supply and a communication bus.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is not limiting of the apparatus for detecting the spacing of the battery cells and may include more or fewer components than shown.
The device for detecting the spacing of the battery pieces provided by the embodiment of the application comprises the memory 50 and the processor 51, wherein the processor 51 can realize the method for detecting the spacing of the battery pieces when executing the program stored in the memory 50.
Finally, the application also provides a corresponding embodiment of the computer readable storage medium. The computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps as described in the method embodiments above.
It will be appreciated that the methods of the above embodiments, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium for performing all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random-access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The method, the device, the equipment and the medium for detecting the spacing of the battery pieces are described in detail. In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the application can be made without departing from the principles of the application and these modifications and adaptations are intended to be within the scope of the application as defined in the following claims.
It should also be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A method of detecting the spacing of battery cells, the method being applied to battery cells of a panel in a photovoltaic module, comprising:
Acquiring interval pictures of a plurality of battery pieces in real time;
inputting the interval picture into an interval detection model to obtain the confidence coefficient for representing the interval of the battery piece; when the confidence reaches a preset standard, determining that the spacing of the battery pieces is qualified;
the step of constructing the interval detection model comprises the following steps: acquiring sampling interval pictures of a plurality of battery pieces; constructing the interval detection model based on a depth learning algorithm according to the sampling interval picture;
When the confidence level does not reach the preset standard, the method further comprises:
performing binarization processing on the interval picture to obtain a corresponding pixel histogram;
Counting the maximum value of the pixel histogram;
Judging whether the maximum value reaches a threshold value or not;
if the maximum value does not reach the threshold value, determining that the spacing of the battery pieces is unqualified;
If the maximum value reaches the threshold value, judging whether the frequency of the maximum value reaching the threshold value is not less than a preset frequency;
if the times are smaller than the preset times, determining that the spacing of the battery pieces is unqualified;
And if the times are not smaller than the preset times, determining that the spacing of the battery pieces is qualified.
2. The method of claim 1, wherein the obtaining a plurality of sample pitch pictures of the battery cells comprises:
And expanding preset unit pixel values along each side of the battery piece on the condition that the position of the battery piece is used, and setting a picture containing the preset unit pixel values as the sampling interval picture.
3. The method of detecting a pitch of battery cells according to claim 1, further comprising, after said determining that said pitch of said battery cells is failed:
and marking the interval picture with unqualified interval.
4. The method of detecting a pitch of battery cells according to claim 1, further comprising, after the acquiring of the sampling pitch pictures of the plurality of battery cells, before the constructing the pitch detection model from the sampling pitch pictures and based on a deep learning algorithm:
and preprocessing the sampling interval picture.
5. An apparatus for detecting a pitch of battery cells, comprising:
The acquisition module is used for acquiring the interval pictures of the plurality of battery pieces in real time;
The input module is used for inputting the interval picture into an interval detection model to obtain the confidence coefficient for representing the interval of the battery piece, wherein the interval detection model construction step comprises the following steps: acquiring sampling interval pictures of a plurality of battery pieces; constructing the interval detection model based on a depth learning algorithm according to the sampling interval picture;
the first determining module is used for determining that the spacing of the battery pieces is qualified when the confidence reaches a preset standard;
When the confidence level does not reach the preset standard, the method further comprises:
The binarization module is used for carrying out binarization processing on the interval picture and obtaining a corresponding pixel histogram;
The statistics module is used for counting the maximum value of the pixel histogram;
The first judging module is used for judging whether the maximum value reaches a threshold value or not;
If the maximum value does not reach the threshold value, triggering a second determining module for determining that the spacing of the battery pieces is unqualified;
if the maximum value reaches the threshold value, triggering a second judging module, wherein the second judging module is used for judging whether the frequency of the maximum value reaching the threshold value is not less than a preset frequency;
if the times are smaller than the preset times, triggering the second determining module, wherein the second determining module is used for determining that the spacing of the battery pieces is unqualified;
and if the times are not smaller than the preset times, triggering the first determining module to determine that the spacing of the battery pieces is qualified.
6. The apparatus for detecting a pitch of battery cells according to claim 5, wherein the acquisition module comprises:
And the expansion module is used for expanding preset unit pixel values along each side of the battery piece on the condition that the position of the battery piece is used as a condition, and setting the picture containing the preset unit pixel values as the sampling interval picture.
7. The apparatus for detecting a pitch of battery cells according to claim 6, further comprising:
And the marking module is used for marking the interval pictures with unqualified intervals.
8. The apparatus for detecting a pitch of battery cells according to claim 6, further comprising:
and the preprocessing module is used for preprocessing the sampling interval picture.
9. An apparatus for detecting a pitch of battery cells, comprising:
A memory for storing a computer program;
a processor for implementing the steps of the method of detecting the pitch of the battery cells according to any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the method of detecting the pitch of battery cells according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211164165.3A CN115829922B (en) | 2022-09-23 | 2022-09-23 | Method, device, equipment and medium for detecting spacing of battery pieces |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211164165.3A CN115829922B (en) | 2022-09-23 | 2022-09-23 | Method, device, equipment and medium for detecting spacing of battery pieces |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115829922A CN115829922A (en) | 2023-03-21 |
| CN115829922B true CN115829922B (en) | 2024-06-04 |
Family
ID=85523840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211164165.3A Active CN115829922B (en) | 2022-09-23 | 2022-09-23 | Method, device, equipment and medium for detecting spacing of battery pieces |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115829922B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094964A (en) * | 2023-08-17 | 2023-11-21 | 正泰集团研发中心(上海)有限公司 | Battery piece spacing detection method and device, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551133A (en) * | 2015-11-16 | 2016-05-04 | 新达通科技股份有限公司 | Banknote splicing seam or crease recognition method and system |
| CN111968082A (en) * | 2020-07-30 | 2020-11-20 | 陕西科技大学 | Product packaging defect detection and identification method based on machine vision |
| CN112325772A (en) * | 2020-10-28 | 2021-02-05 | 中国电力科学研究院有限公司 | Punching size measuring method, system, equipment and medium based on machine vision |
| CN112697814A (en) * | 2020-12-15 | 2021-04-23 | 电子科技大学 | Cable surface defect detection system and method based on machine vision |
| CN114563942A (en) * | 2022-01-28 | 2022-05-31 | 福建瑞达精工股份有限公司 | Clock three-pointer parallelism measuring method, device and storage medium |
| CN114581362A (en) * | 2021-07-22 | 2022-06-03 | 正泰集团研发中心(上海)有限公司 | Photovoltaic module defect detection method and device, electronic equipment and readable storage medium |
| CN114972150A (en) * | 2021-02-24 | 2022-08-30 | 正泰集团研发中心(上海)有限公司 | Photovoltaic module size defect detection method |
| CN115063421A (en) * | 2022-08-16 | 2022-09-16 | 成都数联云算科技有限公司 | Pole piece region detection method, system and device, medium and defect detection method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11107238B2 (en) * | 2019-12-13 | 2021-08-31 | Zebra Technologies Corporation | Method, system and apparatus for detecting item facings |
| WO2022074085A1 (en) * | 2020-10-07 | 2022-04-14 | Crest Solutions Limited | A line clearance system |
-
2022
- 2022-09-23 CN CN202211164165.3A patent/CN115829922B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551133A (en) * | 2015-11-16 | 2016-05-04 | 新达通科技股份有限公司 | Banknote splicing seam or crease recognition method and system |
| CN111968082A (en) * | 2020-07-30 | 2020-11-20 | 陕西科技大学 | Product packaging defect detection and identification method based on machine vision |
| CN112325772A (en) * | 2020-10-28 | 2021-02-05 | 中国电力科学研究院有限公司 | Punching size measuring method, system, equipment and medium based on machine vision |
| CN112697814A (en) * | 2020-12-15 | 2021-04-23 | 电子科技大学 | Cable surface defect detection system and method based on machine vision |
| CN114972150A (en) * | 2021-02-24 | 2022-08-30 | 正泰集团研发中心(上海)有限公司 | Photovoltaic module size defect detection method |
| CN114581362A (en) * | 2021-07-22 | 2022-06-03 | 正泰集团研发中心(上海)有限公司 | Photovoltaic module defect detection method and device, electronic equipment and readable storage medium |
| CN114563942A (en) * | 2022-01-28 | 2022-05-31 | 福建瑞达精工股份有限公司 | Clock three-pointer parallelism measuring method, device and storage medium |
| CN115063421A (en) * | 2022-08-16 | 2022-09-16 | 成都数联云算科技有限公司 | Pole piece region detection method, system and device, medium and defect detection method |
Non-Patent Citations (1)
| Title |
|---|
| 基于Halcon的排钉检测算法研究;殷弋;陈晓荣;;信息技术;20150425(第04期);第176-180页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115829922A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Alsafasfeh et al. | Unsupervised fault detection and analysis for large photovoltaic systems using drones and machine vision | |
| Dhimish et al. | Comparing Mamdani Sugeno fuzzy logic and RBF ANN network for PV fault detection | |
| Dhimish et al. | Fault detection algorithm for grid-connected photovoltaic plants | |
| EP3416283B1 (en) | Battery pack string fault identification method in photoelectric system, apparatus and device | |
| Apostolou et al. | Comparison of the indoor performance of 12 commercial PV products by a simple model | |
| Siddique et al. | Parameter extraction algorithm for one-diode model of PV panels based on datasheet values | |
| Torres Lobera et al. | Operation of TUT solar PV power station research plant under partial shading caused by snow and buildings | |
| Baig et al. | Numerical modelling and experimental validation of a low concentrating photovoltaic system | |
| Wang et al. | Fault diagnosis method of photovoltaic array based on support vector machine | |
| JP7268250B2 (en) | Method and apparatus for string connection of photovoltaic modules, and devices and storage media thereof | |
| Dhimish et al. | Photovoltaic hot-spots fault detection algorithm using fuzzy systems | |
| CN115829922B (en) | Method, device, equipment and medium for detecting spacing of battery pieces | |
| EP4071579A1 (en) | Photovoltaic module control method and photovoltaic system | |
| Monokroussos et al. | Effects of spectrum on the power rating of amorphous silicon photovoltaic devices | |
| US20220398361A1 (en) | Method and apparatus for modeling photovoltaic power curve, and computer device and storage medium thereof | |
| Swart et al. | Varying percentages of full uniform shading of a PV module in a controlled environment yields linear power reduction | |
| Vimalarani et al. | Modeling and performance analysis of the solar photovoltaic cell model using Embedded MATLAB | |
| Al Mansur et al. | Electrical experimental data collection of polycrystalline and monocrystalline photovoltaic modules in an indoor environment using artificial sun simulator | |
| Rangel-Kuoppa | Solar cell parameter accuracy improvement, via refinement of the Co-Content function. Part 1: theoretical analysis | |
| Carr et al. | Thermal model in digital twin of vertical PV system helps to explain unexpected yield gains | |
| CN114127960B (en) | Solar cell stack manufacturing device, solar cell stack, and solar cell stack manufacturing method | |
| Tsai | Complete PV model considering its thermal dynamics | |
| Wheeler et al. | Degradation pathway models for photovoltaics module lifetime performance | |
| Azkona et al. | Detection, Characterization and Modeling of Localized Defects and Thermal Breakdown in Photovoltaic Panels from Thermal Images and IV Curves | |
| CN107271916A (en) | A kind of cell plate group string method for detecting health status |
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 | ||
| CB02 | Change of applicant information |
Address after: 314400 No. 1 Jisheng Road, Jiaxing City, Zhejiang Province, Jianshan New District, Haining City Applicant after: Zhengtai Xinneng Technology Co.,Ltd. Address before: 314400 No. 1 Jisheng Road, Jiaxing City, Zhejiang Province, Jianshan New District, Haining City Applicant before: Zhengtai Xinneng Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |