Photovoltaic power station IV and CV fusion diagnosis method and system

Abstract

The invention provides a photovoltaic power station IV and CV fusion diagnosis method and system, and relates to the technical field of IV and CV. The method comprises the following specific steps: obtaining operation data and operation states of a photovoltaic power station to be diagnosed in a historical time period, carrying out feature extraction on the data to obtain parameters such as an open-circuit voltage ratio and a crack severity index, and processing related parameters to obtain a diagnosis result; generating a battery comprehensive index for evaluating the health of the battery and a photovoltaic panel comprehensive index for evaluating the thermal stability of the photovoltaic panel, constructing an operation state recognition model, performing training by taking the comprehensive index of a historical time period as input and the operation state as a label, obtaining the comprehensive index of the current time period, inputting the comprehensive index into the trained model, and obtaining the operation state of the current time period. And accurate diagnosis of the running state of the photovoltaic power station is realized. According to the invention, the operation state of the photovoltaic power station is accurately judged, and the problem of inaccurate diagnosis possibly caused by simply fusing two diagnosis results in the prior art is avoided.

Description

Technical Field

[0001] The present invention relates to the technical fields of IV and CV, and specifically to a method and system for fusing IV and CV diagnosis in a photovoltaic power station. Background Art

[0002] With the growing global demand for clean energy, photovoltaic power stations, as a sustainable energy solution, have been widely applied and developed rapidly. Photovoltaic power stations convert solar energy into electrical energy, providing green electricity for society, which is of great significance for alleviating the energy crisis and reducing environmental pollution. However, with the continuous expansion of the scale of photovoltaic power stations and the increase in operating time, their reliability and stability face many challenges. The method for fusing IV and CV diagnosis in a photovoltaic power station aims to comprehensively utilize the electrical performance information obtained by IV diagnosis technology and the image information obtained by CV diagnosis technology. By deeply fusing the IV data and CV data, it gives full play to the advantages of the two technologies and makes up for each other's deficiencies, thereby improving the accuracy and reliability of fault diagnosis.

[0003] In the prior art, the IV&CV fusion diagnosis system disclosed in the publication number CN117353658A includes the following steps: a fusion diagnosis server, an IV diagnosis server, and a drone. The fusion diagnosis server is respectively communicatively connected to the IV diagnosis server and the drone, and is used to execute a diagnosis task after responding to a diagnosis task request, including: triggering the IV diagnosis server to perform IV diagnosis analysis on the current data and voltage data of photovoltaic modules in the target photovoltaic power station, and receiving the IV diagnosis analysis result sent by the IV diagnosis server; controlling the drone to fly, collecting images of the photovoltaic modules in the target photovoltaic power station to obtain photovoltaic module images, and identifying the photovoltaic module images to obtain a CV diagnosis analysis result; matching and fusing the IV diagnosis analysis result and the CV diagnosis analysis result to obtain a final diagnosis analysis result. This IV&CV fusion diagnosis system can improve the fault diagnosis rate of photovoltaic modules by fusing IV and CV to diagnose photovoltaic modules.

[0004] However, there are still the following deficiencies. From the above statements, the prior art has the problem of single data dimension. Relying only on the IV diagnosis analysis result and the CV image recognition result, it is difficult to detect potential faults related to heat, resulting in possible omission of diagnosis; at the same time, there is a lack of a fault training process, directly matching and fusing the diagnosis results. Facing complex and changeable fault situations, it is difficult to accurately judge the fault type; and the diagnosis process is not fine enough, simply fusing the two diagnosis results without detailed classification and identification of faults.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide a method and system for integrated diagnosis of IV and CV in a photovoltaic power station, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for integrated diagnosis of IV and CV in a photovoltaic power station, the specific steps include:

[0009] S1. Obtain the operation data and operation status of the photovoltaic power station to be diagnosed in the historical time period. The operation data includes IV data, image data, and infrared thermal imaging data, and the operation status includes normal, or one or more state combinations of hot spot, hidden crack, power attenuation, and poor solder joint contact;

[0010] S2. Extract features from the IV data, image data, and infrared thermal imaging data to obtain the characteristic parameters of the photovoltaic power station to be diagnosed in the historical time period, including the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cells, as well as the crack severity index and temperature deviation index on the surface of the photovoltaic panel;

[0011] S3. Process the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cells to generate a battery comprehensive index for evaluating the health status of the photovoltaic cells, and process the crack severity index and temperature deviation index on the surface of the photovoltaic panel to generate a photovoltaic panel comprehensive index for evaluating the thermal stability of the photovoltaic panel;

[0012] S4. Construct an operation status recognition model, use the battery comprehensive index and photovoltaic panel comprehensive index of each historical time period of the photovoltaic power station to be diagnosed as inputs, and the operation status as labels, and train the operation status recognition model;

[0013] S5. Obtain the battery comprehensive index and photovoltaic panel comprehensive index of the photovoltaic power station to be diagnosed in the current time period, input the trained operation status recognition model, and obtain the operation status of the photovoltaic power station to be diagnosed in the current time period.

[0014] Further, set the duration of each time period to 1 day, and the time intervals between adjacent time periods are equal. The formulas for calculating the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cells are as follows:

[0015]

[0016] Among them, OVR i is the open-circuit voltage ratio of the photovoltaic cells in the i-th historical time period, and SCR i is the short-circuit current ratio of the photovoltaic cells in the i-th historical time period, is the actual open-circuit voltage of the photovoltaic cells in the i-th historical time period, and V oc0 is the standard open-circuit voltage of the photovoltaic cells. is the actual short - circuit current of the photovoltaic cell in the i - th historical time period, V sc0 is the standard short - circuit current of the photovoltaic cell, i is the index of the historical time period, and i ∈ [1, Q], where Q is the total number of historical time periods.

[0017] Furthermore, feature extraction is performed on the image data to obtain the crack severity index on the surface of the photovoltaic panel. The specific process is as follows:

[0018] Convert the photovoltaic panel image into a grayscale image. For an RGB image, it is converted through the following formula:

[0019] Gray = 0.299R + 0.587G + 0.114B

[0020] where Gray is the grayscale value of the pixel, and R, G, B are the pixel values of the red channel, green channel, and blue channel respectively;

[0021] Use the Sobel operator to calculate the gradients in the horizontal and vertical directions:

[0022]

[0023] where, H x is the gradient in the horizontal direction, H y is the gradient in the vertical direction, I is the photovoltaic panel image, and * represents the convolution operation,

[0024] The gradient magnitude and direction are respectively:

[0025]

[0026] where, H is the gradient magnitude and θ is the gradient direction;

[0027] Compare the gradient magnitude H with two thresholds to identify the edge pixels in the image. The specific process is as follows:

[0028] When H > T high , the pixel is marked as a strong edge pixel;

[0029] When T low ≤ H ≤ T high , the pixel is marked as a weak edge pixel;

[0030] When H < T low , the pixel is marked as a non - edge pixel;

[0031] where, T high is the high threshold, and T low is the low threshold;

[0032] Starting from strong edge pixels, using connectivity analysis to also label the weak edge pixels connected to them as edge pixels, a complete and continuous edge image is obtained. Based on the edge image, the crack contour is extracted. The contour extraction algorithm is used to find the closed curve composed of continuous edge pixels in the image, which is the crack contour of the image.

[0033] Furthermore, for each detected crack contour, according to the following formula, calculate the crack severity index on the surface of the photovoltaic panel:

[0034]

[0035] where, LWZS i is the crack severity index on the surface of the photovoltaic panel in the i-th historical time period. The crack severity index is used to evaluate the severity of the cracks on the surface of the photovoltaic panel during this time period;

[0036] In the formula, A max,i is the maximum crack area on the surface of the photovoltaic panel in the i-th historical time period, and A total is the area of the region of the photovoltaic panel corresponding to the crack with the largest area in the image;

[0037] Calculate the temperature deviation index on the surface of the photovoltaic panel, and the formula is as follows:

[0038]

[0039] where, TDI i is the temperature deviation index on the surface of the photovoltaic panel in the i-th historical time period, T i is the average temperature on the surface of the photovoltaic panel in the i-th historical time period, and T0 is the ideal temperature for the normal operation of the photovoltaic panel;

[0040] Furthermore, process the open circuit voltage ratio and short circuit current ratio of the photovoltaic cell to generate the battery comprehensive index. The formula is as follows:

[0041] BATZS i = ω1OVR i + ω2SCR i

[0042] where, BATZS i is the battery comprehensive index in the i-th historical time period. The battery comprehensive index comprehensively evaluates the health status of the photovoltaic cell from two indicators: the open circuit voltage ratio and the short circuit current ratio;

[0043] In the formula, ω1 is the weight coefficient of the open circuit voltage ratio, and ω2 is the weight coefficient of the short circuit current ratio. On the basis of ω1 + ω2 = 1, let ω1 = ω2 = 0.5.

[0044] Further, the crack severity index and temperature deviation index on the surface of the photovoltaic panel are processed to generate a photovoltaic panel comprehensive index, and the formula is as follows:

[0045] PVZS i =γ1LWZS i +γ2TDI i

[0046] Where, PVZS i is the photovoltaic panel comprehensive index in the i-th historical time period. The photovoltaic panel comprehensive index comprehensively evaluates the thermal stability of the photovoltaic panel from two indicators: the crack severity index and the temperature deviation index;

[0047] In the formula, γ1 is the weight coefficient of the crack severity index, and γ2 is the weight coefficient of the temperature deviation index. On the basis of γ1 + γ2 = 1, let 0 < γ2 < γ1 < 1.

[0048] To achieve the above object, the present invention also provides the following technical solutions:

[0049] A photovoltaic power station IV, CV fusion diagnosis system, which is used to execute any one of the above-mentioned photovoltaic power station IV, CV fusion diagnosis methods, and includes:

[0050] A data acquisition module, which is used to obtain the operation data and operation status of the photovoltaic power station to be diagnosed in the historical time period. The operation data includes IV data, image data and infrared thermal imaging data, and the operation status includes normal, or one or a combination of multiple states such as hot spot, hidden crack, power attenuation and poor solder joint contact;

[0051] A feature extraction module, which is used to extract features from the IV data, image data and infrared thermal imaging data to obtain the characteristic parameters of the photovoltaic power station to be diagnosed in the historical time period, including the open circuit voltage ratio and short circuit current ratio of the photovoltaic cell, as well as the crack severity index and temperature deviation index on the surface of the photovoltaic panel;

[0052] A data calculation module, which is used to process the open circuit voltage ratio and short circuit current ratio of the photovoltaic cell to generate a battery comprehensive index for evaluating the health status of the photovoltaic cell, and process the crack severity index and temperature deviation index on the surface of the photovoltaic panel to generate a photovoltaic panel comprehensive index for evaluating the thermal stability of the photovoltaic panel;

[0053] An identification model construction module, which is used to construct an operation status identification model, taking the battery comprehensive index and photovoltaic panel comprehensive index of each historical time period of the photovoltaic power station to be diagnosed as inputs and the operation status as labels, and training the operation status identification model;

[0054] A test set construction module is used to obtain the comprehensive battery index and the comprehensive photovoltaic panel index of the photovoltaic power station to be diagnosed in the current time period, input the operation status recognition model that has completed training, and obtain the operation status of the photovoltaic power station to be diagnosed in the current time period.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0056] The present invention can comprehensively reflect the operation status of the photovoltaic power station from multiple perspectives. The IV data reflects the electrical performance of the photovoltaic cells, the image data identifies physical damages such as cracks on the surface of the photovoltaic panels, and the infrared thermal imaging data can monitor heat-related problems. The multiple data complement each other, providing a richer and more reliable basis for accurately judging the operation status of the photovoltaic power station;

[0057] The operation status recognition model that has been fully trained can better handle complex and changeable fault situations. In practical applications, multiple faults may occur simultaneously in the photovoltaic power station, or the fault manifestation forms may be complex. By learning various fault patterns in the historical data, the model can more accurately judge the current fault type, avoiding misjudgments that may be caused by simply matching the fusion results;

[0058] By combining the comprehensive battery index and the comprehensive photovoltaic panel index with the trained operation status recognition model, the operation status of the photovoltaic power station to be diagnosed in the current time period can be obtained more accurately, avoiding the problem of inaccurate diagnosis that may be caused by simply fusing the two diagnosis results in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0060] Figure 2 It is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0061] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0062] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0063] Embodiment 1:

[0064] Please refer to Figure 1 , the present invention provides a technical solution:

[0065] A method for diagnosing the integration of IV and CV in a photovoltaic power station, the specific steps include:

[0066] S1. Obtain the operation data and operation status of the photovoltaic power station to be diagnosed in the historical time period. The operation data includes IV data, image data and infrared thermal imaging data, and the operation status includes normal, or one or more state combinations of hot spot, hidden crack, power attenuation and poor solder joint contact;

[0067] S2. Extract features from the IV data, image data and infrared thermal imaging data to obtain the characteristic parameters of the photovoltaic power station to be diagnosed in the historical time period, including the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cells, and the crack severity index and temperature deviation index on the surface of the photovoltaic panel;

[0068] Among them, the IV data corresponds to the open-circuit voltage ratio and short-circuit current ratio, the image data corresponds to the crack severity index on the surface of the photovoltaic panel, and the infrared thermal imaging data corresponds to the temperature deviation index.

[0069] Among them, the crack severity index on the surface of the photovoltaic panel refers to the ratio of the area of the largest crack to the area of the photovoltaic panel in the image, and the temperature deviation index refers to the deviation between the highest temperature on the surface of the photovoltaic panel and the ideal temperature under normal operation.

[0070] On the basis of the above embodiment, set the duration of each time period to 1 day, and the time intervals between adjacent time periods are equal. Calculate the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cells, and the basis formulas are as follows:

[0071]

[0072] Among them, OVR i is the open-circuit voltage ratio of the photovoltaic cell in the i-th historical time period, and SCR i is the short-circuit current ratio of the photovoltaic cell in the i-th historical time period, is the actual open-circuit voltage of the photovoltaic cell in the i-th historical time period, V oc0 is the standard open-circuit voltage of the photovoltaic cell, is the actual short-circuit current of the photovoltaic cell in the i-th historical time period, V sc0 is the standard short-circuit current of the photovoltaic cell, i is the index of the historical time period, and i ∈ [1, Q], where Q is the total number of historical time periods;

[0073] Among them, the actual open-circuit voltage The actual short-circuit current is the average value obtained by multiple measurements in the i-th historical time period;

[0074] Feature extraction is performed on the image data to obtain the crack severity index on the surface of the photovoltaic panel. The specific process is as follows:

[0075] Convert the photovoltaic panel image into a grayscale image. For RGB images, convert through the following formula:

[0076] Gray = 0.299R + 0.587G + 0.114B

[0077] Among them, Gray is the grayscale value of the pixel, and R, G, and B are the pixel values of the red channel, green channel, and blue channel;

[0078] Use the Sobel operator to calculate the gradients in the horizontal and vertical directions:

[0079]

[0080] Among them, H x is the gradient in the horizontal direction, and H y is the gradient in the vertical direction, I is the photovoltaic panel image, and * represents the convolution operation,

[0081] The gradient magnitude and direction are respectively:

[0082]

[0083]

[0084] Among them, H is the gradient magnitude and θ is the gradient direction;

[0085] Compare the gradient magnitude H with two thresholds to identify the edge pixels in the image. The specific process is as follows:

[0086] When H > T high, the pixel is marked as a strong edge pixel;

[0087] When T low ≤ H ≤ T high , the pixel is marked as a weak edge pixel;

[0088] When H < T low , the pixel is marked as a non-edge pixel;

[0089] Among them, T high is the high threshold, and T low is the low threshold;

[0090] Starting from the strong edge pixels, using connectivity analysis, the weak edge pixels connected to them are also marked as edge pixels to obtain a complete and continuous edge image. Based on the edge image, the contour of the crack is extracted. Using the contour extraction algorithm, a closed curve composed of continuous edge pixels in the image is found, which is the crack contour of the image.

[0091] Among them, connectivity analysis is a prior art and will not be elaborated here;

[0092] Among them, the specific steps of the contour extraction algorithm for extracting the contour of the defect are as follows:

[0093] Perform binarization processing on the input edge image to ensure that there are only foreground (edge pixels) and background in the image;

[0094] Starting from the boundary of the image, find the first unvisited edge pixel as the starting point;

[0095] Start tracking adjacent edge pixels in a predetermined direction (such as clockwise), and record the pixel coordinates passed;

[0096] Continue tracking until returning to the starting point to form a closed contour;

[0097] Repeat the above steps until all edge pixels are visited, so as to extract the contour of the crack;

[0098] For each detected crack contour, according to the following formula, calculate the crack severity index on the surface of the photovoltaic panel:

[0099]

[0100] Among them, LWZS i is the crack severity index on the surface of the photovoltaic panel in the i-th historical time period. The crack severity index is used to evaluate the severity of the crack on the surface of the photovoltaic panel during this time period. And the larger the crack severity index, the larger the proportion of the crack in the photovoltaic panel, that is, the more severe the crack;

[0101] In the formula, A max,iis the maximum crack area on the surface of the photovoltaic panel in the i-th historical time period. Among them, multiple images are continuously collected in each historical time period, A max,i is the maximum crack area corresponding to the image collected last in each historical time period, A total is the area of the region of the photovoltaic panel corresponding to the crack with the largest area in the image;

[0102] Among them, according to the contour of the crack, the region surrounded by the edge is filled, and then the number of pixels in the filled region is calculated to obtain the maximum crack area A max,i , and through the contour extraction and area calculation algorithm, the area of the region of the photovoltaic panel corresponding to the crack with the largest area in the image is obtained A total ;

[0103] Calculate the temperature deviation index on the surface of the photovoltaic panel. The basis formula is as follows:

[0104]

[0105] Among them, TDI i is the temperature deviation index on the surface of the photovoltaic panel in the i-th historical time period, T i is the average temperature on the surface of the photovoltaic panel in the i-th historical time period, and T0 is the ideal temperature for the normal operation of the photovoltaic panel;

[0106] Among them, multiple infrared thermal imaging data are continuously collected in each historical time period, and they are averaged to obtain the temperature T on the surface of the photovoltaic panel i .

[0107] Based on the above embodiments, the actual open-circuit voltage, actual short-circuit current, standard open-circuit voltage, standard short-circuit current, the temperature on the surface of the photovoltaic panel, and the ideal temperature for normal operation of the photovoltaic cells are all data after averaging.

[0108] Based on the above embodiments, after calculating the open-circuit voltage ratio, short-circuit current ratio of the photovoltaic cells, and the crack severity index and temperature deviation index on the surface of the photovoltaic panel, these data are respectively subjected to maximum-minimum normalization processing, and then the normalized data is used for subsequent analysis processing, so that in the subsequent analysis processing process, various data can be analyzed and processed under the same dimension, avoiding the problem that some data are ignored due to different dimensions.

[0109] S3. Process the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cells to generate a battery comprehensive index for evaluating the health status of the photovoltaic cells, and process the crack severity index and temperature deviation index on the surface of the photovoltaic panel to generate a photovoltaic panel comprehensive index for evaluating the thermal stability of the photovoltaic panel;

[0110] Based on the above embodiments, data processing is performed on the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cell to generate a battery comprehensive index. The formula is as follows:

[0111] BATZS i = ω1OVR i + ω2SCR i

[0112] Where, BATZS i is the battery comprehensive index for the i-th historical time period. The battery comprehensive index comprehensively evaluates the health status of the photovoltaic cell from two indicators, namely the open-circuit voltage ratio and the short-circuit current ratio. And the larger the battery comprehensive index, the healthier the photovoltaic cell;

[0113] On this basis, it should be noted that: when the open-circuit voltage ratio OVR i increases, it means that the battery can output a voltage closer to the ideal value in the open-circuit state, greatly reducing the voltage drop caused by internal resistance loss, etc., increasing the health degree of the battery, and thus increasing the battery comprehensive index BATZS i ; when the short-circuit current ratio SCR i increases, it reflects that the collection and transmission efficiency of photo-generated carriers in the photovoltaic cell is improved, increasing the health degree of the battery, effectively collecting photo-generated electron-hole pairs, and in the short-circuit state, the internal charge transmission path is smooth, and the situation of carrier recombination or being trapped by traps rarely occurs, thus increasing the battery comprehensive index BATZS i . Therefore, the battery comprehensive index BATZS i and the open-circuit voltage ratio OVR i , the short-circuit current ratio SCR i are all positively correlated. Therefore, the above weighted summation formula is used to characterize the functional relationship between the battery comprehensive index BATZS i and the open-circuit voltage ratio OVR i , the short-circuit current ratio SCR i .

[0114] In the formula, ω1 is the weight coefficient of the open-circuit voltage ratio, and ω2 is the weight coefficient of the short-circuit current ratio;

[0115] The open-circuit voltage ratio reflects the voltage characteristics of the battery in the open-circuit state, while the short-circuit current ratio reflects the current characteristics of the battery in the short-circuit state. Both are crucial for the performance of the photovoltaic cell. Setting ω1 equal to ω2 can comprehensively and evenly consider the voltage and current performance of the photovoltaic cell.

[0116] Therefore, on the basis of ω1 + ω2 = 1, let ω1 = ω2 = 0.5.

[0117] On the basis of the above embodiments, the crack severity index and temperature deviation index on the surface of the photovoltaic panel are processed to generate a photovoltaic panel comprehensive index. The formula is as follows:

[0118] PVZS i =γ1LWZS i +γ2TDI i

[0119] Where, PVZS i is the photovoltaic panel comprehensive index for the i-th historical time period. The photovoltaic panel comprehensive index comprehensively evaluates the thermal stability of the photovoltaic panel from two indicators: the crack severity index and the temperature deviation index. And the larger the photovoltaic panel comprehensive index, the worse the thermal stability of the photovoltaic panel;

[0120] On this basis, it should be noted that: when the crack severity index LWZS i increases, it means that the crack situation on the surface of the photovoltaic panel becomes more serious. The existence and expansion of cracks will damage the structural integrity of the photovoltaic panel, affect its internal heat conduction path, and when the crack severity index LWZS i increases, the thermal resistance in the crack area will increase, and the heat conduction in the photovoltaic panel becomes more uneven, which will lead to a local temperature rise, making the thermal stability of the photovoltaic panel worse, and thus making the photovoltaic panel comprehensive index PVZS i increase; when the temperature deviation index TDI i increases, it indicates that the gap between the actual average temperature and the ideal average temperature during normal operation on the surface of the photovoltaic panel is increasing. Whether the actual temperature is higher or lower than the ideal temperature, a large temperature deviation will cause changes in the performance of the photovoltaic panel material, have a negative impact on the thermal stability of the photovoltaic panel, and thus make the photovoltaic panel comprehensive index PVZS i increase. Therefore, the photovoltaic panel comprehensive index PVZS i and the crack severity index LWZS i and the temperature deviation index TDI i are all positively correlated. Therefore, the above weighted summation formula is used to characterize the functional relationship between the photovoltaic panel comprehensive index PVZS i and the crack severity index LWZS i , and the temperature deviation index TDI i .

[0121] In the formula, γ1 is the weight coefficient of the crack severity index, and γ2 is the weight coefficient of the temperature deviation index;

[0122] Cracks on the surface of the photovoltaic panel will directly damage its internal structural integrity and heat conduction path. The existence of cracks may cause heat to concentrate in certain areas, forming hot spots, which will further trigger a series of thermal problems and seriously affect the thermal stability of the photovoltaic panel. Although temperature deviation will also affect the thermal stability, it usually has a long-term cumulative effect, and relatively speaking, it is not as direct and significant as the impact of cracks. Therefore, in order to more accurately reflect the thermal stability of the photovoltaic panel, a higher weight is assigned to the crack severity index, that is, γ1>γ2.

[0123] Therefore, on the basis of γ1 + γ2 = 1, let 0 < γ2 < γ1 < 1.

[0124] As an implementation method, the value range of γ1 is 0.5 - 1, and the value range of γ2 is 0 - 0.5. The specific values are set by technicians according to the actual situation and are not limited here.

[0125] S4. Construct a running state recognition model, use the battery comprehensive index and the photovoltaic panel comprehensive index of each historical time period of the photovoltaic power station to be diagnosed as inputs, and the running state as the label, and train the running state recognition model;

[0126] On the basis of the above embodiments, the running state recognition model is composed of a deep learning network based on a multi-layer perceptron. The deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. The first hidden layer, the second hidden layer, and the third hidden layer all have at least two neurons, and all use ReLU as the activation function;

[0127] In the running state recognition model, the input features of the deep learning network of the multi-layer perceptron include: the battery comprehensive index and the photovoltaic panel comprehensive index, 2 features.

[0128] The structure of the deep learning network of the multi-layer perceptron is as follows:

[0129] Input layer: Receive the input of 2 features;

[0130] First hidden layer: Has 128 neurons and uses ReLU as the activation function;

[0131] Second hidden layer: Has 64 neurons and also uses the ReLU activation function;

[0132] Third hidden layer: Has 32 neurons and uses the ReLU activation function;

[0133] Output layer: Has 1 neuron and outputs the running state.

[0134] The process of training the running state recognition model is as follows:

[0135] Taking the battery comprehensive index and the photovoltaic panel comprehensive index of each historical period of the photovoltaic power station to be diagnosed as inputs, and the operating state as labels for training, and using the mean square error as the loss function. When the mean square error is within the range of [0, 0.01], the training of the operating state recognition model is completed.

[0136] S5. Obtain the battery comprehensive index and the photovoltaic panel comprehensive index of the photovoltaic power station to be diagnosed in the current period, input the trained operating state recognition model, and obtain the operating state of the photovoltaic power station to be diagnosed in the current period.

[0137] Please refer to Figure 2 , the present invention also provides a technical solution:

[0138] A photovoltaic power station IV, CV fusion diagnosis system, the system is used to execute any one of the above-mentioned photovoltaic power station IV, CV fusion diagnosis methods, including:

[0139] A data acquisition module, which is used to obtain the operation data and operation state of the photovoltaic power station to be diagnosed in the historical period. The operation data includes IV data, image data, and infrared thermal imaging data. The operation state includes normal, or a combination of one or more states such as hot spot, hidden crack, power attenuation, and poor solder joint contact;

[0140] A feature extraction module, which is used to extract features from the IV data, image data, and infrared thermal imaging data to obtain the characteristic parameters of the photovoltaic power station to be diagnosed in the historical period, including the open circuit voltage ratio and short circuit current ratio of the photovoltaic cell, and the crack severity index and temperature deviation index on the surface of the photovoltaic panel;

[0141] A data calculation module, which is used to process the open circuit voltage ratio and short circuit current ratio of the photovoltaic cell to generate a battery comprehensive index for evaluating the health status of the photovoltaic cell, and process the crack severity index and temperature deviation index on the surface of the photovoltaic panel to generate a photovoltaic panel comprehensive index for evaluating the thermal stability of the photovoltaic panel;

[0142] An identification model construction module, which is used to construct an operating state recognition model. Taking the battery comprehensive index and the photovoltaic panel comprehensive index of each historical period of the photovoltaic power station to be diagnosed as inputs, and the operating state as labels, train the operating state recognition model;

[0143] A test set construction module, which is used to obtain the battery comprehensive index and the photovoltaic panel comprehensive index of the photovoltaic power station to be diagnosed in the current period, input the trained operating state recognition model, and obtain the operating state of the photovoltaic power station to be diagnosed in the current period.

[0144] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0145] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented by, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0146] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0147] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered by the protection scope of this application.

Claims

1. A method for fusing IV and CV diagnosis of a photovoltaic power station, characterized in that: The specific steps include: S1. Obtain the operation data and operation status of the photovoltaic power station to be diagnosed in the historical time period. The operation data includes IV data, image data, and infrared thermal imaging data. The operation status includes normal, or one or more combinations of states such as hot spots, hidden cracks, power attenuation, and poor solder joint contact; S2. Extract features from the IV data, image data, and infrared thermal imaging data to obtain the characteristic parameters of the photovoltaic power station to be diagnosed in the historical time period, including the open - circuit voltage ratio and short - circuit current ratio of the photovoltaic cells, as well as the crack severity index and temperature deviation index on the surface of the photovoltaic panel; S3. Process the open - circuit voltage ratio and short - circuit current ratio of the photovoltaic cells to generate a battery comprehensive index for evaluating the health status of the photovoltaic cells. Process the crack severity index and temperature deviation index on the surface of the photovoltaic panel to generate a photovoltaic panel comprehensive index for evaluating the thermal stability of the photovoltaic panel; S4. Construct an operation status recognition model. Use the battery comprehensive index and photovoltaic panel comprehensive index of each historical time period of the photovoltaic power station to be diagnosed as inputs and the operation status as labels to train the operation status recognition model; S5. Obtain the battery comprehensive index and photovoltaic panel comprehensive index of the photovoltaic power station to be diagnosed in the current time period, input them into the trained operation status recognition model, and obtain the operation status of the photovoltaic power station to be diagnosed in the current time period.

2. The photovoltaic power station IV, CV fusion diagnosis method according to claim 1, wherein: Set the duration of each time period to 1 day, and the time intervals between adjacent time periods are equal. Calculate the open - circuit voltage ratio and short - circuit current ratio of the photovoltaic cells. The basis formulas are as follows: Among them, OVR i is the open-circuit voltage ratio of the photovoltaic cell in the i-th historical time period, and SCR i is the short-circuit current ratio of the photovoltaic cell in the i-th historical time period, is the actual open-circuit voltage of the photovoltaic cell in the i-th historical time period, V oc0 is the standard open-circuit voltage of the photovoltaic cell, is the actual short-circuit current of the photovoltaic cell in the i-th historical time period, V sc0 is the standard short-circuit current of the photovoltaic cell, and i is the index of the historical time period, and i ∈ [1, Q], where Q is the total number of historical time periods.

3. The PV power station IV, CV fusion diagnosis method according to claim 1, characterized in that: Extract features from the image data to obtain the crack severity index on the surface of the photovoltaic panel. The specific process is as follows: Convert the photovoltaic panel image into a grayscale image. For an RGB image, the conversion is through the following formula: Gray = 0.299R + 0.587G + 0.114B where Gray is the grayscale value of the pixel, and R, G, and B are the pixel values of the red channel, green channel, and blue channel; Use the Sobel operator to calculate the gradients in the horizontal and vertical directions: Among them, H x is the gradient in the horizontal direction, H y is the gradient in the vertical direction, I is the photovoltaic panel image, and * represents the convolution operation. The gradient magnitude and direction are respectively: where H is the gradient magnitude and θ is the gradient direction; Compare the gradient magnitude H with two thresholds to identify the edge pixels in the image. The specific process is as follows: When H > T high , the pixel is marked as a strong edge pixel; When T low ≤H≤T high , the pixel is marked as a weak edge pixel; When H < T low , the pixel is marked as a non-edge pixel; Among them, T high is the high threshold, and T low is the low threshold; Starting from the strong edge pixels, use connectivity analysis to also mark the weak edge pixels connected to them as edge pixels, obtaining a complete and continuous edge image. Based on the edge image, extract the contour of the crack. Use the contour extraction algorithm to find the closed curve composed of continuous edge pixels in the image, which is the crack contour of the image.

4. The photovoltaic power station IV and CV fusion diagnosis method according to claim 3, wherein: For each detected crack contour, calculate the crack severity index on the surface of the photovoltaic panel according to the following formula: Among them, LWZS i is the crack severity index of the photovoltaic panel surface in the i-th historical time period. The crack severity index is used to evaluate the severity of the cracks on the photovoltaic panel surface during this time period; Where, A max,i is the maximum crack area on the surface of the photovoltaic panel in the i-th historical time period, and A total is the area of the region of the photovoltaic panel corresponding to the crack with the largest area in the image; Calculate the temperature deviation index on the surface of the photovoltaic panel. The basis formula is as follows: Among them, TDI i is the temperature deviation index on the surface of the photovoltaic panel in the i-th historical time period, T i is the average temperature on the surface of the photovoltaic panel in the i-th historical time period, and T0 is the ideal temperature for the normal operation of the photovoltaic panel.

5. The method for IV and CV fusion diagnosis of a photovoltaic power station according to claim 2, wherein: Process the open - circuit voltage ratio and short - circuit current ratio of the photovoltaic cells to generate a battery comprehensive index. The basis formula is as follows: BATZS i = ω1OVR i + ω2SCR i Among them, BATZS i is the comprehensive battery index for the i-th historical time period. The comprehensive battery index comprehensively evaluates the health status of the photovoltaic battery from two indicators: the open-circuit voltage ratio and the short-circuit current ratio; In the formula, ω1 is the weight coefficient of the open - circuit voltage ratio, ω2 is the weight coefficient of the short - circuit current ratio. On the basis of ω1 + ω2 = 1, let ω1 = ω2 = 0.

5.

6. The method for diagnosing the integration of IV and CV of a photovoltaic power station according to claim 4, wherein: The crack severity index and temperature deviation index on the surface of the photovoltaic panel are processed to generate a photovoltaic panel comprehensive index, and the basis formula is as follows: PVZS i = γ1LWZS i + γ2TDI i Among them, PVZS i is the comprehensive index of the photovoltaic panel in the i-th historical time period. The comprehensive index of the photovoltaic panel comprehensively evaluates the thermal stability of the photovoltaic panel from two indicators, namely, the crack severity index and the temperature deviation index; In the formula, γ1 is the weight coefficient of the crack severity index, γ2 is the weight coefficient of the temperature deviation index. On the basis of γ1 + γ2 = 1, let 0 < γ2 < γ1 < 1.

7. A photovoltaic power station IV and CV fusion diagnosis system, which is used to execute any one of the photovoltaic power station IV and CV fusion diagnosis methods described in claims 1-6, and is characterized in that: It includes: A data acquisition module, which is used to obtain the operation data and operation status of the photovoltaic power station to be diagnosed in the historical time period. The operation data includes IV data, image data, and infrared thermal imaging data. The operation status includes normal, or one or more state combinations of hot spot, hidden crack, power attenuation, and poor solder joint contact; A feature extraction module, which is used to extract features from the IV data, image data, and infrared thermal imaging data to obtain the characteristic parameters of the photovoltaic power station to be diagnosed in the historical time period, including the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cell, as well as the crack severity index and temperature deviation index on the surface of the photovoltaic panel; A data calculation module, which is used to process the open-circuit voltage ratio and short-circuit current ratio of the photovoltaic cell to generate a battery comprehensive index for evaluating the health status of the photovoltaic cell, and process the crack severity index and temperature deviation index on the surface of the photovoltaic panel to generate a photovoltaic panel comprehensive index for evaluating the thermal stability of the photovoltaic panel; An identification model construction module, which is used to construct an operation status identification model. Taking the battery comprehensive index and photovoltaic panel comprehensive index of each historical time period of the photovoltaic power station to be diagnosed as inputs and the operation status as labels, the operation status identification model is trained; A test set construction module, which is used to obtain the battery comprehensive index and photovoltaic panel comprehensive index of the photovoltaic power station to be diagnosed in the current time period, input the trained operation status identification model, and obtain the operation status of the photovoltaic power station to be diagnosed in the current time period.

Images