Photovoltaic equipment detection method and system based on machine vision

Abstract

The invention provides a photovoltaic equipment detection method and system based on machine vision, and relates to the technical field of machine vision. The method comprises the following steps: firstly, determining an equipment relation graph based on a battery piece image corresponding to at least one photovoltaic battery piece; secondly, determining a battery piece state vector corresponding to a target photovoltaic battery piece based on a battery piece relation graph corresponding to the target photovoltaic battery piece in the equipment relation graph; and then, based on a matching relationship between the battery piece state vector corresponding to the target photovoltaic battery piece and the battery piece state vector corresponding to the at least one piece of photovoltaic battery piece state information to be confirmed, analyzing at least one piece of photovoltaic battery piece state information corresponding to the target photovoltaic battery piece. Based on the method, the problem of relatively low reliability of photovoltaic equipment detection in the prior art can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision, and in particular to a photovoltaic equipment detection method and system based on machine vision. Background Art

[0002] The detection of photovoltaic equipment is an important guarantee for the stable output of photovoltaic equipment. For example, when defects (such as cracks, poor connections, deformation, etc.) are detected in photovoltaic equipment, the photovoltaic equipment should be updated and maintained in time. Among them, traditional detection technology is generally based on manual detection. This method has the problems of high labor costs and low detection efficiency, and is also prone to missed detection. In the existing technology, detection is generally based on image recognition technology. However, research has found that detection based on conventional image recognition technology has the problem of low reliability. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a photovoltaic device detection method and system based on machine vision, so as to improve the problem of relatively low reliability of photovoltaic device detection in the prior art.

[0004] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions: A photovoltaic device detection method based on machine vision, comprising: Determine a device relationship map based on a cell image corresponding to at least one photovoltaic cell, wherein the device relationship map includes a cell member corresponding to the photovoltaic cell, an image member corresponding to the cell image, and a relationship representation line, wherein the relationship representation line is used to reflect that there is a correlation between the photovoltaic cell corresponding to the cell member and the cell image corresponding to the image member; Based on the cell relationship graph corresponding to the target photovoltaic cell in the device relationship graph, determining the cell state vector corresponding to the target photovoltaic cell, wherein the cell relationship graph corresponding to the target photovoltaic cell includes a target cell member corresponding to the target photovoltaic cell and at least one image member connected to the target cell member through the relationship representation line, and the cell state vector is used to reflect the state semantics of the target photovoltaic cell; Based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed, at least one photovoltaic cell state information corresponding to the target photovoltaic cell is analyzed, wherein the cell state vector corresponding to the photovoltaic cell state information is used to reflect the defect state semantics of the photovoltaic cell state information.

[0005] In some preferred embodiments, in the above-mentioned photovoltaic device detection method based on machine vision, the step of determining the cell state vector corresponding to the target photovoltaic cell based on the cell relationship map corresponding to the target photovoltaic cell in the device relationship map includes: Determining an image member set based on at least one image member in the cell relationship graph connected to the target cell member through the relationship representation line; Determine a cell state vector corresponding to the image member set, wherein the cell state vector corresponding to the image member set is used to reflect the state semantics of at least one cell image having a correlation relationship with the target photovoltaic cell; Based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target photovoltaic cell is determined.

[0006] In some preferred embodiments, in the above-mentioned photovoltaic device detection method based on machine vision, the step of determining the image member set based on at least one image member having the relationship characterization line with the target cell member in the cell relationship map includes: For each image member of at least one image member connected to the target cell member through a relationship characterization line, based on the image acquisition time configured on the relationship characterization line between the image member and the target cell member, the order relationship of the image member in the image member set is obtained, wherein the cell image corresponding to the image member refers to a historical cell image formed by historically acquiring images of the photovoltaic cell corresponding to the target cell member, the historical cell image being member attribute data of the image member in the device relationship map, and the member attribute data of the target cell member in the device relationship map including a current cell image formed by currently acquiring images of the corresponding photovoltaic cell; According to the corresponding sequential relationship, at least one image member connected to the target cell member through the relationship characterization line is combined to form a corresponding image member set.

[0007] In some preferred embodiments, in the above-mentioned photovoltaic device detection method based on machine vision, the step of determining the cell state vector corresponding to the image member set includes: Acquire member attribute data corresponding to at least one image member included in the image member set, wherein the member attribute data corresponding to the image member at least includes a cell image corresponding to the image member; Loading member attribute data corresponding to each of the at least one image member so that the photovoltaic cell mining model acquires the member attribute data; Using the feature space mapping unit included in the photovoltaic cell mining model, the member attribute data corresponding to each of the at least one image member is subjected to a feature space mapping operation, and a photovoltaic image mapping vector corresponding to the image member set is output; The deep semantic mining unit in the photovoltaic cell mining model is used to perform a deep semantic mining operation on the photovoltaic image mapping vector corresponding to the image member set, and the cell state vector corresponding to the image member set is output.

[0008] In some preferred embodiments, in the above-mentioned photovoltaic device detection method based on machine vision, the cell relationship map also includes at least one related cell member connected to the target cell member through a relationship characterization line, and the photovoltaic cell corresponding to the related cell member and the photovoltaic cell corresponding to the target cell member have a correlation relationship in electrical properties, and the correlation relationship includes series connection and / or parallel connection; The step of determining the cell state vector corresponding to the target photovoltaic cell based on the cell state vector corresponding to the image member set includes: Using the feature space mapping unit included in the photovoltaic cell mining model, feature space mapping operations are performed on the member attribute data corresponding to the target cell member corresponding to the target photovoltaic cell and the member attribute data corresponding to at least one related cell member connected to the target cell member through a relationship characterization line, and a photovoltaic image mapping vector corresponding to the target cell member and a photovoltaic image mapping vector corresponding to the at least one related cell member are output; Utilizing the deep semantic mining unit in the photovoltaic cell mining model, respectively performing deep semantic mining operations on the photovoltaic image mapping vector corresponding to the target cell member and the photovoltaic image mapping vector corresponding to each of the at least one related cell member, and outputting the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell member; The cell state vector corresponding to the target photovoltaic cell is determined based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell member.

[0009] In some preferred embodiments, in the above-mentioned photovoltaic device detection method based on machine vision, the step of determining the cell state vector corresponding to the target photovoltaic cell based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell members includes: According to the order relationship between the image members in the image member set, an association mining operation is performed on each local vector in the cell state vector corresponding to the image member set, and a first association mining vector corresponding to the image member set is output; According to the order relationship of the image members in the image member set, each local vector in the cell state vector corresponding to the image member set is subjected to adjacent difference operation, and a corresponding local difference vector set is output; According to the order relationship of the image members in the image member set, an association mining operation is performed on each local difference vector in the local difference vector set, and a second association mining vector corresponding to the image member set is output; Performing a vector aggregation operation on a first association mining vector corresponding to the image member set and a second association mining vector corresponding to the image member set, and outputting an aggregated association mining vector corresponding to the image member set; Based on the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members, an association focusing mining operation is performed on the cell state vector corresponding to the target cell member, and the cell state vector corresponding to the target photovoltaic cell is output.

[0010] In some preferred embodiments, in the above-mentioned photovoltaic device detection method based on machine vision, the steps of performing an association focused mining operation on the cell state vector corresponding to the target cell member based on the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members, and outputting the cell state vector corresponding to the target photovoltaic cell, include: Respectively taking the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members as vectors to be aggregated, so as to obtain a plurality of vectors to be aggregated; For each of the vectors to be aggregated, an association analysis operation is performed between the vector to be aggregated and the cell state vector corresponding to the target cell member, and a correlation characterization parameter corresponding to the vector to be aggregated is output; based on the correlation characterization parameter, an update operation is performed on the vector to be aggregated, and an association focus mining vector corresponding to the vector to be aggregated is output; The central vector of the multiple associated focused mining vectors corresponding to the multiple vectors to be aggregated is determined, and the central vector and the cell state vector corresponding to the target cell member are superimposed to output the cell state vector corresponding to the target photovoltaic cell.

[0011] In some preferred embodiments, in the above-mentioned photovoltaic equipment detection method based on machine vision, the step of analyzing at least one photovoltaic cell state information corresponding to the target photovoltaic cell based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed, comprises: Obtaining a cell state vector corresponding to at least one photovoltaic cell state information to be confirmed; For each photovoltaic cell state information in at least one photovoltaic cell state information to be confirmed, determining a vector association parameter between a cell state vector corresponding to the target photovoltaic cell and a cell state vector corresponding to the photovoltaic cell state information; Among the at least one photovoltaic cell state information to be confirmed, determine the photovoltaic cell state information to be confirmed whose vector associated parameter is greater than a predetermined reference vector associated parameter, and determine the photovoltaic cell state information as the photovoltaic cell state information corresponding to the target photovoltaic cell.

[0012] In some preferred embodiments, in the above-mentioned photovoltaic device detection method based on machine vision, the step of obtaining a cell state vector corresponding to at least one photovoltaic cell state information to be confirmed comprises: For each photovoltaic cell state information in at least one photovoltaic cell state information to be confirmed, at least one photovoltaic cell state association information corresponding to the photovoltaic cell state information is expanded, wherein the photovoltaic cell state association information and the photovoltaic cell state information have related defect state semantics; Using the first feature space projection unit included in the state information mining model, at least one state information unit included in the photovoltaic cell state information is subjected to a feature space projection operation, and a state information projection vector corresponding to the photovoltaic cell state information is output; Using the second feature space projection unit included in the state information mining model, respectively perform a feature space projection operation on at least one state information unit included in each of the at least one photovoltaic cell state association information, and output a state information projection vector corresponding to the photovoltaic cell state association information; Using the vector aggregation unit included in the state information mining model, the state information projection vector corresponding to the photovoltaic cell state information and the state information projection vector corresponding to the photovoltaic cell state association information are subjected to vector aggregation operation, and the corresponding state information aggregation vector is output; The deep semantic representation unit included in the state information mining model is used to perform a deep semantic representation operation on the state information aggregation vector, and a cell state vector corresponding to the photovoltaic cell state information is output.

[0013] An embodiment of the present invention further provides a photovoltaic device detection system based on machine vision, including a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the above-mentioned photovoltaic device detection method based on machine vision.

[0014] A photovoltaic device detection method and system based on machine vision provided by an embodiment of the present invention can determine a device relationship map based on a cell image corresponding to at least one photovoltaic cell; secondly, based on the cell relationship map corresponding to the target photovoltaic cell in the device relationship map, determine the cell state vector corresponding to the target photovoltaic cell; then, based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vectors corresponding to at least one photovoltaic cell state information to be confirmed, analyze at least one photovoltaic cell state information corresponding to the target photovoltaic cell. Based on the above content, since the cell relationship map corresponding to the target photovoltaic cell includes the target cell member corresponding to the target photovoltaic cell and at least one image member connected to the target cell member by the relationship characterization line, when determining the cell state vector based on the cell relationship map, not only the information of the target cell member but also the information of the image member is referenced, so that the semantic information included in the cell state vector is richer, so that when analyzing the photovoltaic cell state information based on the cell state vector, there can be a more comprehensive analysis basis, so that the reliability of the analysis result is higher, that is, the reliability of the obtained photovoltaic cell state information is higher, and therefore, the problem of relatively low reliability of photovoltaic equipment detection existing in the prior art can be improved.

[0015] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A structural block diagram of a photovoltaic device detection system based on machine vision provided in an embodiment of the present invention.

[0017] Figure 2 A schematic flow chart of the steps of a photovoltaic device detection method based on machine vision provided in an embodiment of the present invention.

[0018] Figure 3 A schematic diagram of a device relationship map provided in an embodiment of the present invention.

[0019] Figure 4 A flowchart of association mining provided by an embodiment of the present invention.

[0020] Figure 5A flowchart of determining a local difference vector provided by an embodiment of the present invention.

[0021] Figure 6 A flowchart of multiple vector fusion provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0023] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] like Figure 1 As shown, an embodiment of the present invention provides a photovoltaic device detection system based on machine vision. The photovoltaic device detection system based on machine vision may include a memory and a processor. In detail, the memory and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, they can be electrically connected to each other through one or more communication buses or signal lines. The memory may store at least one software function module (computer program) that may exist in the form of software or firmware. The processor may be used to execute the executable computer program stored in the memory, thereby realizing the photovoltaic device detection method based on machine vision provided by the embodiment of the present invention (as described later).

[0025] Optionally, the memory may be, but not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0026] and, Figure 1 The structure shown is for illustration only. The photovoltaic device detection system based on machine vision may also include Figure 1 More or fewer components as shown, or with Figure 1 The different configurations shown, for example, may include a communication unit for information exchange with other devices. In an alternative example, the photovoltaic device detection system based on machine vision may be a server with data processing capabilities.

[0027] Combination Figure 2 The embodiment of the present invention also provides a photovoltaic device detection method based on machine vision, which can be applied to the photovoltaic device detection system based on machine vision. The method steps defined in the process related to the photovoltaic device detection method based on machine vision can be implemented by the photovoltaic device detection system based on machine vision.

[0028] The following will Figure 2 The specific process shown is explained in detail.

[0029] Step S110, determining a device relationship map based on a cell image corresponding to at least one photovoltaic cell.

[0030] In an embodiment of the present invention, the photovoltaic device detection system based on machine vision can determine a device relationship map based on a cell image corresponding to at least one photovoltaic cell. The device relationship map includes a cell member corresponding to the photovoltaic cell, an image member corresponding to the cell image, and a relationship characterization line, and the relationship characterization line is used to reflect that there is a correlation between the photovoltaic cell corresponding to the cell member and the cell image corresponding to the image member. For example, the cell image is formed by performing an image acquisition operation on the corresponding photovoltaic cell. It should be noted that the solution provided by the embodiment of the present invention can be applied before the photovoltaic device is officially used, and can also be applied to the photovoltaic device during its official use. When it is applied to the official use, when performing an image acquisition operation through an image acquisition device such as a camera, due to the presence of a packaging glass layer, an additional light source (such as an LED lamp) can be used to ensure uniform lighting, so as to improve the clarity of the image by providing sufficient light. In addition, a high-definition industrial camera can also be used. In addition, a photovoltaic cell may refer to a photovoltaic cell in the conventional sense, or may refer to a component after a plurality of photovoltaic cells are connected in series or in parallel. That is to say, in the embodiment of the present invention, the granularity of the division of photovoltaic cells in the photovoltaic device is not limited and can be selected according to actual needs. The device relationship map formed can be as follows: Figure 3 shown.

[0031] Step S120, determining a cell state vector corresponding to the target photovoltaic cell based on the cell relationship map corresponding to the target photovoltaic cell in the device relationship map.

[0032] In an embodiment of the present invention, the photovoltaic device detection system based on machine vision can determine the cell state vector corresponding to the target photovoltaic cell based on the cell relationship map corresponding to the target photovoltaic cell in the device relationship map. The cell relationship map corresponding to the target photovoltaic cell includes a target cell member corresponding to the target photovoltaic cell and at least one image member (such as Figure 3 The cell member A, image member 11, image member 12, image member 13 and image member 14 in the cell state vector are used to reflect the state semantics of the target photovoltaic cell, that is, the corresponding vector is obtained by semantically mining the information in the cell relationship graph.

[0033] Step S130, based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed, analyzing at least one photovoltaic cell state information corresponding to the target photovoltaic cell.

[0034] In an embodiment of the present invention, the photovoltaic equipment detection system based on machine vision can analyze at least one photovoltaic cell state information corresponding to the target photovoltaic cell (such as the most matching photovoltaic cell state information) based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed (predetermined state classification label). The cell state vector corresponding to the photovoltaic cell state information is used to reflect the defect state semantics of the photovoltaic cell state information, such as cracks, poor connection, deformation, etc. Based on this, after each photovoltaic cell is taken as a target photovoltaic cell for corresponding processing, the photovoltaic cell state information corresponding to each photovoltaic cell can be obtained.

[0035] Based on the above content, since the cell relationship map corresponding to the target photovoltaic cell includes the target cell member corresponding to the target photovoltaic cell and at least one image member connected to the target cell member by the relationship characterization line, when determining the cell state vector based on the cell relationship map, not only the information of the target cell member but also the information of the image member is referenced, so that the semantic information included in the cell state vector is richer, so that when analyzing the photovoltaic cell state information based on the cell state vector, there can be a more comprehensive analysis basis, so that the reliability of the analysis result is higher, that is, the reliability of the obtained photovoltaic cell state information is higher, and therefore, the problem of relatively low reliability of photovoltaic equipment detection existing in the prior art can be improved.

[0036] It should be noted that for step S120, the specific method of determining the cell state vector corresponding to the target photovoltaic cell is not limited and can be selected according to actual needs.

[0037] For example, in an alternative implementation, in order to ensure that the determined cell state vector has a high semantic representation capability, the above-mentioned step S120 may further include step S121, step S122 and step S123, and the specific content of each step is described as follows.

[0038] Step S121 : determining an image member set based on at least one image member in the cell relationship graph that is connected to the target cell member through the relationship representation line.

[0039] In an embodiment of the present invention, after determining the cell relationship map corresponding to the target photovoltaic cell in the device relationship map, an image member set can be determined based on at least one image member in the cell relationship map that is connected to the target cell member through the relationship characterization line, that is, each image member that has a correlation with the target cell member is screened out to form a set, namely, the image member set is obtained.

[0040] Step S122, determining the cell state vector corresponding to the image member set.

[0041] In an embodiment of the present invention, after obtaining the image member set, the cell state vector corresponding to the image member set can be determined. The cell state vector corresponding to the image member set is used to reflect the state semantics of at least one cell image that has a correlation with the target photovoltaic cell. For example, when cell member A is the target cell member, the corresponding cell state vector can be used to reflect the state semantics of the cell image corresponding to image member 11, the cell image corresponding to image member 12, the cell image corresponding to image member 13, and the cell image corresponding to image member 14.

[0042] Step S123: determining a cell state vector corresponding to the target photovoltaic cell based on the cell state vector corresponding to the image member set.

[0043] In the embodiment of the present invention, after obtaining the cell state vector corresponding to the image member set, the cell state vector corresponding to the target photovoltaic cell can be determined based on the cell state vector corresponding to the image member set. That is, the cell state vector corresponding to the target photovoltaic cell at least includes the semantic information in the cell state vector corresponding to the image member set.

[0044] It is understandable that, in the above step S121, the specific method of determining the image member set is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to facilitate subsequent semantic mining, the above step S121 may include: First, for each image member of at least one image member connected to the target cell member through a relationship characterization line, based on the image acquisition time configured on the relationship characterization line between the image member and the target cell member, the order relationship of the image member in the image member set can be obtained, wherein the cell image corresponding to the image member refers to a historical cell image formed by historically acquiring images of the photovoltaic cell corresponding to the target cell member, and the historical cell image is used as member attribute data of the image member in the device relationship map, and the member attribute data of the target cell member in the device relationship map includes a current cell image formed by currently acquiring images of the corresponding photovoltaic cell. It should be noted that during the formal use of the photovoltaic device, the image acquisition device can be used to regularly acquire images of the photovoltaic cell, so that at least one frame of cell image can be formed for one photovoltaic cell, that is, there is at least one image member connected to the corresponding cell member (one frame of cell image is used as one image member); Secondly, at least one image member connected to the target cell member through a relationship characterization line can be combined according to the corresponding sequence relationship to form a corresponding image member set. For example, the image members can be sorted and combined according to the sequence relationship of image acquisition time from early to late to form a corresponding image member set. Based on this, since the image member set carries the image acquisition time of the cell image, the state of the photovoltaic cell is characterized as it changes over time.

[0045] It is understandable that, in the above step S122, the specific method of determining the cell state vector corresponding to the image member set is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to ensure the semantic representation capability of the mined cell state vector, the above step S122 may include: First, member attribute data corresponding to at least one image member included in the image member set may be obtained, wherein the member attribute data corresponding to the image member at least includes a cell image corresponding to the image member, for example, the cell image may be directly used as the corresponding member attribute data; Secondly, member attribute data corresponding to each of the at least one image member is loaded so that the photovoltaic cell mining model acquires the member attribute data; Then, the feature space mapping unit included in the photovoltaic cell mining model can be used to perform a feature space mapping operation on the member attribute data corresponding to each of the at least one image member, and output a photovoltaic image mapping vector corresponding to the image member set. It should be noted that the feature space mapping unit can be a convolutional network, which is used to perform convolution processing on the cell image to achieve a feature space mapping operation, thereby obtaining a photovoltaic image mapping vector corresponding to the image member set. Specifically, after obtaining the convolution vectors corresponding to each of the cell images, the convolution vectors can be spliced ​​and combined to form a photovoltaic image mapping vector corresponding to the image member set. Finally, the deep semantic mining unit in the photovoltaic cell mining model can be used to perform deep semantic mining operations on the photovoltaic image mapping vectors corresponding to the image member set, and output the cell state vectors corresponding to the image member set. That is, the photovoltaic image mapping vectors can be further mined to obtain the deep semantic information therein, that is, the cell state vectors corresponding to the image member set. Specifically, in an alternative embodiment, the photovoltaic image mapping vectors corresponding to the image member set include convolution vectors corresponding to each of the cell images. Thus, for each convolution vector, the convolution vector can be self-attention processed (that is, the deep semantic mining unit can be a self-attention network) to obtain the corresponding local vectors. Finally, the local vectors are merged together to form the cell state vectors corresponding to the image member set.

[0046] It is understandable that, in the above step S123, the specific method of determining the cell state vector corresponding to the target photovoltaic cell is not limited and can be selected according to actual needs. For example, in an alternative embodiment, the cell relationship map also includes at least one related cell member connected to the target cell member through a relationship characterization line (for example, Figure 3 When the cell member B in is taken as the target cell member, the related cell members include a volt cell member A and a volt cell member C), there is a correlation in electrical properties between the photovoltaic cells corresponding to the related cell members and the photovoltaic cells corresponding to the target cell member, and the correlation includes a series connection and / or a parallel connection. Based on this, in order to further ensure the semantic representation capability of the mined cell state vector, the above-mentioned step S123 may include step S123a, step S123b and step S123c, and the specific contents of each step are described as follows.

[0047] Step S123a, utilizing the feature space mapping unit included in the photovoltaic cell mining model, respectively performs feature space mapping operations on the member attribute data corresponding to the target cell member corresponding to the target photovoltaic cell and the member attribute data corresponding to at least one related cell member connected to the target cell member through a relationship characterization line, and outputs a photovoltaic image mapping vector corresponding to the target cell member and a photovoltaic image mapping vector corresponding to the at least one related cell member.

[0048] In the embodiment of the present invention, the feature space mapping unit included in the photovoltaic cell mining model can be used to perform feature space mapping operations on the member attribute data corresponding to the target cell member corresponding to the target photovoltaic cell and the member attribute data corresponding to at least one related cell member connected to the target cell member through a relationship characterization line, and output the photovoltaic image mapping vector corresponding to the target cell member and the photovoltaic image mapping vector corresponding to at least one related cell member. In other words, the member attribute data (cell image) corresponding to the target cell member can be convolved to obtain the corresponding photovoltaic image mapping vector, and the member attribute data corresponding to the related cell member can be convolved to obtain the corresponding photovoltaic image mapping vector.

[0049] Step S123b, utilizing the deep semantic mining unit in the photovoltaic cell mining model, respectively perform deep semantic mining operations on the photovoltaic image mapping vector corresponding to the target cell member and the photovoltaic image mapping vector corresponding to each of the at least one related cell members, and output the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell members.

[0050] In an embodiment of the present invention, after obtaining the corresponding photovoltaic image mapping vector, the deep semantic mining unit in the photovoltaic cell mining model can be used to perform deep semantic mining operations on the photovoltaic image mapping vector corresponding to the target cell member and the photovoltaic image mapping vector corresponding to each of the at least one related cell member, and output the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell member. In other words, the photovoltaic image mapping vector corresponding to the target cell member can be processed by self-attention to obtain the corresponding cell state vector, and the photovoltaic image mapping vector corresponding to the related cell member can be processed by self-attention to obtain the corresponding cell state vector.

[0051] Step S123c, determining the cell state vector corresponding to the target photovoltaic cell based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell members.

[0052] In the embodiment of the present invention, after obtaining the corresponding cell state vector, the cell state vector corresponding to the target photovoltaic cell can be determined based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target cell member, and the cell state vector corresponding to each of the at least one related cell member. Based on this, the cell state vector corresponding to the target photovoltaic cell carries the historical image semantics (i.e., the cell state vector corresponding to the image member set), the current image semantics (i.e., the cell state vector corresponding to the target cell member), and the current image semantics of the related photovoltaic cell (i.e., the cell state vector corresponding to each of the at least one related cell member), so that it can have better semantic representation capabilities, so as to facilitate subsequent state determination.

[0053] It can be understood that, in the above-mentioned step S123c, the specific method of determining the cell state vector corresponding to the target photovoltaic cell (i.e., fusing the three image semantics) is not limited and can be selected according to actual needs. For example, in an alternative embodiment, in order to be able to more reliably fuse the three image semantics so that the reliability of the determined cell state vector is higher, the above-mentioned step S123c can further include step c1, step c2, step c3, step c4 and step c5, and the specific content of each step is described as follows.

[0054] Step c1, according to the order relationship of each image member in the image member set, perform association mining operation on each local vector in the cell state vector corresponding to the image member set, and output a first association mining vector corresponding to the image member set.

[0055] In an embodiment of the present invention, an association mining operation may be performed on each local vector in the cell state vector corresponding to the image member set according to the order relationship of each image member in the image member set, and a first association mining vector corresponding to the image member set may be output. Figure 4For each image member (such as the second one) other than the first image member in the image member set, the output vector corresponding to the previous image member (such as the first one) can be multiplied with the local vector corresponding to the current image member (such as the second one) to obtain the corresponding correlation representation parameter, and then the local vector is weighted based on the correlation representation parameter to obtain the corresponding weighted vector, and the weighted vector and the local vector are superimposed to obtain the corresponding output vector. Among them, the output vector corresponding to the first image member is the corresponding local vector, and the output vector corresponding to the last image member is used as the first correlation mining vector corresponding to the image member set.

[0056] Step c2, according to the corresponding order relationship of each image member in the image member set, perform a difference operation to the adjacent local vectors in the battery cell state vector corresponding to the image member set, and output a corresponding local difference vector set.

[0057] In an embodiment of the present invention, each local vector in the cell state vector corresponding to the image member set may be subjected to adjacent difference operations according to the order relationship of the image members in the image member set, and a corresponding set of local difference vectors may be output. Exemplarily, the second local vector may be subjected to difference calculation with the first local vector to obtain a first local difference vector, the third local vector may be subjected to difference calculation with the second local vector to obtain a second local difference vector, the fourth local vector may be subjected to difference calculation with the third local vector to obtain a third local difference vector, and so on. In this way, the local difference vectors in the set of local difference vectors may carry the change information between the historical cell images, and this change information has a certain characterization capability for the defective state that has occurred. In addition, in other embodiments, combined with Figure 5 , image difference calculation can also be performed on the cell image corresponding to each image member in the image member set (that is, the pixel value difference calculation of the corresponding position between the subsequent frame and the previous frame is performed). In this way, a differential image set can be obtained, and then, the feature space mapping operation and deep semantic mining operation as mentioned above are performed on each frame of the differential image set to obtain a corresponding local difference vector set.

[0058] Step c3, performing an association mining operation on each local difference vector in the local difference vector set according to the corresponding order relationship of each image member in the image member set, and outputting a second association mining vector corresponding to the image member set.

[0059] In the embodiment of the present invention, an association mining operation can be performed on each local difference vector in the local difference vector set according to the order relationship of each image member in the image member set, and a second association mining vector corresponding to the image member set can be output. The specific method of the association mining operation is as described above.

[0060] Step c4: performing a vector aggregation operation on the first association mining vector corresponding to the image member set and the second association mining vector corresponding to the image member set, and outputting an aggregated association mining vector corresponding to the image member set.

[0061] In an embodiment of the present invention, a vector aggregation operation may be performed on the first association mining vector corresponding to the image member set and the second association mining vector corresponding to the image member set to output an aggregated association mining vector corresponding to the image member set. Exemplarily, the first association mining vector and the second association mining vector may be superimposed, averaged, or concatenated to achieve corresponding aggregation, thereby obtaining a corresponding aggregated association mining vector.

[0062] Step c5, performing an association focused mining operation on the cell state vector corresponding to the target cell member based on the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members, and outputting the cell state vector corresponding to the target photovoltaic cell.

[0063] In an embodiment of the present invention, an association focused mining operation can be performed on the cell state vector corresponding to the target cell member based on the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell member, and the cell state vector corresponding to the target photovoltaic cell can be output. In other words, the semantic information represented by the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell member needs to be integrated into the cell state vector corresponding to the target cell member, so that the semantic information of the cell state vector corresponding to the target photovoltaic cell is richer.

[0064] It is understandable that in the above step c5, the specific method of performing the associated focus mining operation is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to enable the semantic information represented by multiple vectors to be fully integrated to obtain a more reliable battery cell state vector, Figure 6 , the above step c5 may include: First, the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members can be respectively used as vectors to be aggregated to obtain a plurality of vectors to be aggregated, that is, the plurality of vectors to be aggregated are respectively the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members as vectors to be aggregated; Secondly, for each of the vectors to be aggregated, an association analysis operation may be performed between the vector to be aggregated and the cell state vector corresponding to the target cell member, and a correlation characterization parameter corresponding to the vector to be aggregated may be output, and based on the correlation characterization parameter, an update operation may be performed on the vector to be aggregated, and a correlation focused mining vector corresponding to the vector to be aggregated may be output; illustratively, the vector to be aggregated and the cell state vector may be multiplied to obtain a corresponding correlation characterization parameter, and then, the vector to be aggregated may be weighted based on the correlation characterization parameter to obtain a corresponding correlation aggregation mining vector, so that the semantic information represented by the correlation aggregation mining vector may be more focused on features related to the cell state vector, that is, the cell state vector may be integrated into the vector to be aggregated; Then, the center vector of the multiple associated focusing mining vectors corresponding to the multiple vectors to be aggregated can be determined, and the center vector and the cell state vector corresponding to the target cell member can be superimposed to output the cell state vector corresponding to the target photovoltaic cell; illustratively, the mean vector of the multiple associated focusing mining vectors can be calculated as the center vector; or the mean vector of the multiple associated focusing mining vectors, and then the associated focusing mining vector with the smallest cosine distance with the mean vector in the multiple associated focusing mining vectors can be used as the center vector; the multiple associated focusing mining vectors can also be clustered to obtain multiple corresponding cluster centers (the specific number can be configured according to actual needs, such as 2, 3, 4, etc.), and then the mean of the multiple cluster centers is calculated to obtain the center vector.

[0065] It should be noted that for step S130, the specific method of analyzing the status information of at least one photovoltaic cell corresponding to the target photovoltaic cell is not limited and can be selected according to actual needs. For example, in an alternative embodiment, in order to reliably analyze the status information of at least one photovoltaic cell corresponding to the target photovoltaic cell, the above-mentioned step S130 can further include step S131, step S132 and step S133, and the specific content of each step is described as follows.

[0066] Step S131, obtaining a cell state vector corresponding to at least one photovoltaic cell state information to be confirmed.

[0067] In the embodiment of the present invention, a cell state vector corresponding to at least one photovoltaic cell state information to be confirmed may be obtained first, wherein the cell state vector is used to reflect the semantic information of the corresponding photovoltaic cell state information to be confirmed.

[0068] Step S132, for each photovoltaic cell state information in at least one photovoltaic cell state information to be confirmed, determine a vector association parameter between a cell state vector corresponding to the target photovoltaic cell and a cell state vector corresponding to the photovoltaic cell state information.

[0069] In an embodiment of the present invention, for each photovoltaic cell status information in at least one photovoltaic cell status information to be confirmed, a vector association parameter between a cell state vector corresponding to the target photovoltaic cell and a cell state vector corresponding to the photovoltaic cell status information is determined. Exemplarily, the cosine similarity between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to the photovoltaic cell status information can be calculated as the corresponding vector association parameter.

[0070] Step S133, among the at least one photovoltaic cell state information to be confirmed, determine the photovoltaic cell state information to be confirmed whose vector association parameter is greater than the predetermined reference vector association parameter, and determine the photovoltaic cell state information as the photovoltaic cell state information corresponding to the target photovoltaic cell.

[0071] In an embodiment of the present invention, it is possible to determine, from the at least one photovoltaic cell status information to be confirmed, the photovoltaic cell status information to be confirmed whose vector associated parameters are greater than the predetermined reference vector associated parameters, and determine the photovoltaic cell status information as the photovoltaic cell status information corresponding to the target photovoltaic cell. In this way, at least one photovoltaic cell status information can be obtained, such as a photovoltaic cell that may have defects such as warping and cracks at the same time.

[0072] It can be understood that, in the above step S131, the specific method of obtaining the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to make the semantic information of the cell state vector corresponding to each photovoltaic cell state information more abundant and accurate, the above step S131 can further include: First, for each photovoltaic cell state information in at least one photovoltaic cell state information to be confirmed, at least one photovoltaic cell state association information corresponding to the photovoltaic cell state information can be expanded, wherein the photovoltaic cell state association information and the photovoltaic cell state information have related defect state semantics, such as synonyms or synonymous sentences; Secondly, the first feature space projection unit included in the state information mining model can be used to perform a feature space projection operation on at least one state information unit included in the photovoltaic cell state information, and output a state information projection vector corresponding to the photovoltaic cell state information. Exemplarily, the first feature space projection unit can be a word embedding model, and the state information unit can refer to a word obtained by performing word segmentation processing on the photovoltaic cell state information, such as "having", "wider", "of", and "crack". In this way, each word can be subjected to word embedding processing respectively to obtain a corresponding word embedding vector, and then the word embedding vectors are spliced ​​and combined to form a corresponding state information projection vector. For example, each word embedding vector embeddings = {"having": [0.12, 0.45, -0.78, 0.36,...], "wider": [0.32, 0.54, -0.34, 0.29, ...], "of": [0.15, -0.04, 0.22, 0.51,...],"crack": [-0.41, 0.22, 0.87, -0.67, ...]}; Then, the second feature space projection unit included in the state information mining model can be used to perform feature space projection operations on at least one state information unit included in each of the at least one photovoltaic cell state association information, and output a state information projection vector corresponding to the photovoltaic cell state association information; illustratively, the second feature space projection unit can be the same word embedding model as the first feature space projection unit; Further, the vector aggregation unit included in the state information mining model can be used to perform vector aggregation operations on the state information projection vector corresponding to the photovoltaic cell state information and the state information projection vector corresponding to the photovoltaic cell state association information, and output a corresponding state information aggregation vector; illustratively, each state information projection vector can be superimposed or spliced ​​to achieve vector aggregation and obtain a corresponding state information aggregation vector; Finally, the deep semantic representation unit included in the state information mining model can be used to perform a deep semantic representation operation on the state information aggregation vector to output the cell state vector corresponding to the photovoltaic cell state information; exemplarily, the deep semantic representation operation can refer to self-attention processing, and correspondingly, the deep semantic representation unit can be a self-attention network.

[0073] In addition, it should be noted that the state information mining model can be trained together with the aforementioned photovoltaic cell mining model, that is, first, a sample device relationship graph can be determined, and then, based on the sample device relationship graph, the cell state vector corresponding to the corresponding sample photovoltaic cell is mined through the initial photovoltaic cell mining model, and, through the initial state information mining model, the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed is mined, and then, at least one photovoltaic cell state information corresponding to the sample photovoltaic cell is determined, and then, the at least one photovoltaic cell state information and the actual state of the sample photovoltaic cell (defect label, which can be formed by manual annotation) are calculated for error, and then, along the direction of reducing the calculated error, the model parameters of the initial state information mining model and the initial photovoltaic cell mining model are adjusted until the error converges, thereby obtaining the final state information mining model and the photovoltaic cell mining model, so that the above-mentioned steps S120 and S130 can be performed through the final state information mining model and the photovoltaic cell mining model, thereby realizing reliable detection of the defect state of the photovoltaic device.

[0074] In addition, the above-mentioned cell image may be a segmented image, that is, after the original image is acquired through image acquisition equipment such as industrial cameras, the original image may include multiple photovoltaic cells. Therefore, the original image may be segmented through an image segmentation model (the specific composition of the image segmentation model can refer to the relevant prior art and is not specifically limited here) to form cell images corresponding to each photovoltaic cell. In other words, in some application scenarios, when the particle size or size of the photovoltaic cell is large, the acquired original image can also be directly used as the cell image corresponding to the photovoltaic cell.

[0075] In addition, the above-mentioned series connection or parallel connection can be determined by manual marking or by the distribution positions between the corresponding photovoltaic cells. For example, the photovoltaic cells in the same column can be connected in series, and the photovoltaic cells in different columns can be connected in parallel. These can be configured accordingly according to the actual situation.

[0076] In summary, the present invention provides a photovoltaic device detection method and system based on machine vision, which can determine the device relationship map based on the cell image corresponding to at least one photovoltaic cell; secondly, based on the cell relationship map corresponding to the target photovoltaic cell in the device relationship map, determine the cell state vector corresponding to the target photovoltaic cell; then, based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed, analyze at least one photovoltaic cell state information corresponding to the target photovoltaic cell. Based on the above content, since the cell relationship map corresponding to the target photovoltaic cell includes the target cell member corresponding to the target photovoltaic cell and at least one image member connected to the target cell member by the relationship characterization line, when determining the cell state vector based on the cell relationship map, not only the information of the target cell member but also the information of the image member is referenced, so that the semantic information included in the cell state vector is richer, so that when analyzing the photovoltaic cell state information based on the cell state vector, there can be a more comprehensive analysis basis, so that the reliability of the analysis result is higher, that is, the reliability of the obtained photovoltaic cell state information is higher, and therefore, the problem of relatively low reliability of photovoltaic equipment detection existing in the prior art can be improved.

[0077] In several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed apparatus and method can also be implemented in other ways. The apparatus and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the apparatus, method and computer program product according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0078] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0079] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code. It should be noted that in this article, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0080] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A photovoltaic equipment detection method based on machine vision, characterized in that: include: Determine a device relationship map based on a cell image corresponding to at least one photovoltaic cell, wherein the device relationship map includes a cell member corresponding to the photovoltaic cell, an image member corresponding to the cell image, and a relationship representation line, wherein the relationship representation line is used to reflect that there is a correlation between the photovoltaic cell corresponding to the cell member and the cell image corresponding to the image member; Based on the cell relationship graph corresponding to the target photovoltaic cell in the device relationship graph, determining the cell state vector corresponding to the target photovoltaic cell, wherein the cell relationship graph corresponding to the target photovoltaic cell includes a target cell member corresponding to the target photovoltaic cell and at least one image member connected by a relationship representation line to the target cell member, and the cell state vector is used to reflect the state semantics of the target photovoltaic cell; Based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed, at least one photovoltaic cell state information corresponding to the target photovoltaic cell is analyzed, wherein the cell state vector corresponding to the photovoltaic cell state information is used to reflect the defect state semantics of the photovoltaic cell state information.

2. The photovoltaic equipment detection method based on machine vision according to claim 1, characterized in that: The step of determining the cell state vector corresponding to the target photovoltaic cell based on the cell relationship graph corresponding to the target photovoltaic cell in the device relationship graph includes: Determining an image member set based on at least one image member in the cell relationship graph connected to the target cell member through the relationship representation line; Determine a cell state vector corresponding to the image member set, wherein the cell state vector corresponding to the image member set is used to reflect the state semantics of at least one cell image having a correlation relationship with the target photovoltaic cell; Based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target photovoltaic cell is determined.

3. The photovoltaic equipment detection method based on machine vision according to claim 2, characterized in that: The step of determining the image member set based on at least one image member having the relationship characterization line with the target cell member in the cell relationship map comprises: For each image member of at least one image member connected to the target cell member through a relationship characterization line, based on the image acquisition time configured on the relationship characterization line between the image member and the target cell member, the order relationship of the image member in the image member set is obtained, wherein the cell image corresponding to the image member refers to a historical cell image formed by historically acquiring images of the photovoltaic cell corresponding to the target cell member, the historical cell image being member attribute data of the image member in the device relationship map, and the member attribute data of the target cell member in the device relationship map including a current cell image formed by currently acquiring images of the corresponding photovoltaic cell; According to the corresponding sequential relationship, at least one image member connected to the target cell member through the relationship characterization line is combined to form a corresponding image member set.

4. The photovoltaic equipment detection method based on machine vision according to claim 2, characterized in that: The step of determining the cell state vector corresponding to the image member set includes: Acquire member attribute data corresponding to at least one image member included in the image member set, wherein the member attribute data corresponding to the image member at least includes a cell image corresponding to the image member; Loading member attribute data corresponding to each of the at least one image member so that the photovoltaic cell mining model acquires the member attribute data; Using the feature space mapping unit included in the photovoltaic cell mining model, the member attribute data corresponding to each of the at least one image member is subjected to a feature space mapping operation, and a photovoltaic image mapping vector corresponding to the image member set is output; The deep semantic mining unit in the photovoltaic cell mining model is used to perform a deep semantic mining operation on the photovoltaic image mapping vector corresponding to the image member set, and the cell state vector corresponding to the image member set is output.

5. The photovoltaic equipment detection method based on machine vision according to claim 2, characterized in that: The cell relationship map also includes at least one related cell member connected to the target cell member through a relationship characterization line, and the photovoltaic cell corresponding to the related cell member has a correlation relationship in electrical properties with the photovoltaic cell corresponding to the target cell member, and the correlation relationship includes series connection and / or parallel connection; The step of determining the cell state vector corresponding to the target photovoltaic cell based on the cell state vector corresponding to the image member set includes: Using the feature space mapping unit included in the photovoltaic cell mining model, feature space mapping operations are performed on the member attribute data corresponding to the target cell member corresponding to the target photovoltaic cell and the member attribute data corresponding to at least one related cell member connected to the target cell member through a relationship characterization line, and a photovoltaic image mapping vector corresponding to the target cell member and a photovoltaic image mapping vector corresponding to the at least one related cell member are output; Utilizing the deep semantic mining unit in the photovoltaic cell mining model, respectively performing deep semantic mining operations on the photovoltaic image mapping vector corresponding to the target cell member and the photovoltaic image mapping vector corresponding to each of the at least one related cell member, and outputting the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell member; The cell state vector corresponding to the target photovoltaic cell is determined based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target cell member and the cell state vector corresponding to each of the at least one related cell member.

6. The photovoltaic equipment detection method based on machine vision according to claim 5, characterized in that: The step of determining the cell state vector corresponding to the target photovoltaic cell based on the cell state vector corresponding to the image member set, the cell state vector corresponding to the target cell member, and the cell state vector corresponding to each of the at least one related cell members comprises: According to the order relationship between the image members in the image member set, an association mining operation is performed on each local vector in the cell state vector corresponding to the image member set, and a first association mining vector corresponding to the image member set is output; According to the order relationship of the image members in the image member set, each local vector in the cell state vector corresponding to the image member set is subjected to adjacent difference operation, and a corresponding local difference vector set is output; According to the order relationship of the image members in the image member set, an association mining operation is performed on each local difference vector in the local difference vector set, and a second association mining vector corresponding to the image member set is output; Performing a vector aggregation operation on a first association mining vector corresponding to the image member set and a second association mining vector corresponding to the image member set, and outputting an aggregated association mining vector corresponding to the image member set; Based on the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members, an association focusing mining operation is performed on the cell state vector corresponding to the target cell member, and the cell state vector corresponding to the target photovoltaic cell is output.

7. The photovoltaic equipment detection method based on machine vision according to claim 6, characterized in that: The step of performing an association focused mining operation on the cell state vector corresponding to the target cell member based on the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members, and outputting the cell state vector corresponding to the target photovoltaic cell, comprises: Respectively taking the aggregated association mining vector corresponding to the image member set and the cell state vector corresponding to each of the at least one related cell members as vectors to be aggregated, so as to obtain a plurality of vectors to be aggregated; For each of the vectors to be aggregated, an association analysis operation is performed between the vector to be aggregated and the cell state vector corresponding to the target cell member, and a correlation characterization parameter corresponding to the vector to be aggregated is output; based on the correlation characterization parameter, an update operation is performed on the vector to be aggregated, and an association focus mining vector corresponding to the vector to be aggregated is output; The central vector of the multiple associated focused mining vectors corresponding to the multiple vectors to be aggregated is determined, and the central vector and the cell state vector corresponding to the target cell member are superimposed to output the cell state vector corresponding to the target photovoltaic cell.

8. The photovoltaic equipment detection method based on machine vision according to any one of claims 1 to 7, characterized in that: The step of analyzing at least one photovoltaic cell state information corresponding to the target photovoltaic cell based on the matching relationship between the cell state vector corresponding to the target photovoltaic cell and the cell state vector corresponding to at least one photovoltaic cell state information to be confirmed comprises: Obtaining a cell state vector corresponding to at least one photovoltaic cell state information to be confirmed; For each photovoltaic cell state information in at least one photovoltaic cell state information to be confirmed, determining a vector association parameter between a cell state vector corresponding to the target photovoltaic cell and a cell state vector corresponding to the photovoltaic cell state information; Among the at least one photovoltaic cell state information to be confirmed, determine the photovoltaic cell state information to be confirmed whose vector associated parameter is greater than a predetermined reference vector associated parameter, and determine the photovoltaic cell state information as the photovoltaic cell state information corresponding to the target photovoltaic cell.

9. The photovoltaic equipment detection method based on machine vision according to claim 8, characterized in that: The step of obtaining a cell state vector corresponding to at least one photovoltaic cell state information to be confirmed comprises: For each photovoltaic cell state information in at least one photovoltaic cell state information to be confirmed, at least one photovoltaic cell state association information corresponding to the photovoltaic cell state information is expanded, wherein the photovoltaic cell state association information and the photovoltaic cell state information have related defect state semantics; Using the first feature space projection unit included in the state information mining model, at least one state information unit included in the photovoltaic cell state information is subjected to a feature space projection operation, and a state information projection vector corresponding to the photovoltaic cell state information is output; Using the second feature space projection unit included in the state information mining model, respectively perform a feature space projection operation on at least one state information unit included in each of the at least one photovoltaic cell state association information, and output a state information projection vector corresponding to the photovoltaic cell state association information; Using the vector aggregation unit included in the state information mining model, the state information projection vector corresponding to the photovoltaic cell state information and the state information projection vector corresponding to the photovoltaic cell state association information are subjected to vector aggregation operation, and the corresponding state information aggregation vector is output; The deep semantic representation unit included in the state information mining model is used to perform a deep semantic representation operation on the state information aggregation vector, and a cell state vector corresponding to the photovoltaic cell state information is output.

10. A photovoltaic equipment detection system based on machine vision, characterized in that: It comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the photovoltaic device detection method based on machine vision as described in any one of claims 1 to 9.

Images