Intelligent photovoltaic junction box test method and system

Abstract

The invention relates to the technical field of fault detection, in particular to an intelligent photovoltaic junction box testing method and system, and the method specifically comprises the steps: constructing a voltage and current dissimilarity index based on the data changes of the current and voltage of an intelligent photovoltaic junction box at adjacent moments, and constructing an electrical parameter abnormal coefficient through combining the correlation between the voltage and the environment temperature; based on the correlation between the internal temperature of the photovoltaic junction box and the time sequence of other parameters, the fault confidence coefficient of the photovoltaic junction box is constructed in combination with the electrical parameter abnormal coefficient; according to the method and the device, the anomaly detection of the photovoltaic junction box is carried out based on the fault confidence coefficient, the influence of environmental factors on related data of the photovoltaic junction box is reduced, the problem that when temperature threshold detection is carried out in an existing photovoltaic junction box detection technology, threshold setting is unreasonable, and false detection is easily caused is solved, the detection precision of the photovoltaic junction box is improved, and false detection is avoided.

Description

Technical Field

[0001] The present application relates to the field of fault detection technology, and in particular to a method and system for testing an intelligent photovoltaic junction box. Background Art

[0002] As global demand for renewable energy grows, solar photovoltaic (PV) power generation systems, a crucial component of clean energy, are expanding in scope and scale. PV junction boxes, critical components connecting solar panels to external circuits, not only transmit current but also protect PV panels from electrical faults. Due to their prolonged exposure to the elements, PV junction boxes are susceptible to environmental impacts and can lead to malfunctions. Therefore, performance testing of PV junction boxes is essential to ensure the stable operation of PV power generation systems.

[0003] The existing method of detecting photovoltaic junction boxes is usually a simple temperature detection method, which determines the status of the photovoltaic junction box by comparing the temperature of the photovoltaic junction box with a set threshold. However, it does not take into account the impact of environmental factors on the relevant data of the photovoltaic junction box when the photovoltaic power generation components are generating photovoltaic power, resulting in poor detection accuracy and easy to cause false detection. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method and system for testing an intelligent photovoltaic junction box. The technical solutions adopted are as follows: In a first aspect, an embodiment of the present application provides a method for testing a smart photovoltaic junction box, the method comprising the following steps: Real-time collection of the current and voltage flowing through the smart photovoltaic junction box, as well as the internal temperature and ambient temperature of the smart photovoltaic junction box, to construct current sequence, voltage sequence, internal temperature sequence and ambient temperature sequence; Based on the data changes of the neighborhood of the data points in the first-order difference sequence of the current sequence and the voltage sequence, the change fluctuation coefficients of the current sequence and the voltage sequence are respectively constructed; based on the change fluctuation coefficients, the voltage-current dissimilarity index of the intelligent photovoltaic junction box is constructed; The voltage variation index of the photovoltaic junction box is constructed based on the difference between the data fluctuation characteristics of the voltage sequence and the ambient temperature sequence; the correlation between the voltage sequence and the ambient temperature sequence is analyzed, and the electrical parameter anomaly coefficient of the photovoltaic junction box is constructed by combining the voltage-current difference index and the voltage variation index; A temperature response index of the photovoltaic junction box is constructed based on the correlation between the internal temperature sequence and the current sequence, voltage sequence, and ambient temperature sequence; a temperature difference sequence is constructed based on the difference between the internal temperature sequence and the ambient temperature sequence; a temperature normality coefficient of the photovoltaic junction box is constructed based on the change trend of the data in the internal temperature, ambient temperature, and temperature difference sequence, combined with the temperature response index; and a fault confidence level of the photovoltaic junction box is constructed based on the electrical parameter abnormality coefficient and the temperature normality coefficient. Fault analysis of photovoltaic junction boxes is performed based on the fault confidence level of the photovoltaic junction boxes.

[0005] In one embodiment, the process of obtaining the change fluctuation coefficient is: The extreme point detection algorithm is used to obtain the extreme points in the first-order difference sequence of the current sequence, and the coefficient of variation of the sequence composed of all data in the neighborhood window of each extreme point is calculated. The variance of the coefficient of variation of all extreme points is calculated and recorded as B; the ratio of the number of extreme points to the number of elements in the first-order difference sequence of the current sequence is calculated and recorded as D; the change fluctuation coefficient of the current sequence is recorded as , The expression is: ; Based on the voltage sequence, the variation fluctuation coefficient of the voltage sequence is obtained by adopting the same calculation method as the variation fluctuation coefficient of the current sequence.

[0006] In one embodiment, the expression of the voltage-current difference index is: , where A is the voltage and current difference index of the photovoltaic junction box, 、 are the fluctuation coefficients of the current and voltage series, respectively.

[0007] In one embodiment, the process of obtaining the voltage variation index is as follows: The first-order difference sequence of the voltage sequence is recorded as the voltage change sequence, and the first-order difference sequence of the ambient temperature sequence is recorded as the ambient temperature change sequence. The metric distance between the voltage change sequence and the ambient temperature change sequence is used as the voltage change index of the photovoltaic junction box.

[0008] In one embodiment, the expression of the electrical parameter anomaly coefficient is: , where K is the electrical parameter anomaly coefficient of the photovoltaic junction box; A and F are the voltage-current difference index and voltage variation index of the photovoltaic junction box, respectively; X is the correlation between the voltage series and the ambient temperature series; It is an artificially preset extremely small positive number.

[0009] In one embodiment, the process of obtaining the temperature response index is as follows: The correlation between the internal temperature sequence and the current sequence is recorded as the first correlation; the correlation between the internal temperature sequence and the ambient temperature sequence is recorded as the second correlation; and the sum of the first correlation and the second correlation is used as the temperature response index of the photovoltaic junction box.

[0010] In one embodiment, the process of obtaining the temperature normal coefficient is as follows: The mean of all elements in the first-order difference sequence of the internal temperature series is recorded as ; The mean of all elements in the first-order difference sequence of the ambient temperature series is recorded as ; The temperature difference index of the photovoltaic junction box is recorded as W, and the expression of W is: ; The temperature difference series is fitted by a fitting algorithm to obtain a fitting straight line, and the absolute value of the slope of the fitting straight line is recorded as H; The temperature normal coefficient of the photovoltaic junction box is recorded as G, and the expression of G is: , where P is the temperature corresponding index of the photovoltaic junction box, It is an artificially preset extremely small positive number.

[0011] In one embodiment, the fault confidence level is expressed as: , where L is the fault confidence of the photovoltaic junction box, K is the electrical parameter abnormality coefficient of the photovoltaic junction box, and G is the temperature normality coefficient of the photovoltaic junction box. It is an artificially preset extremely small positive number.

[0012] In one embodiment, the fault analysis of the photovoltaic junction box based on the fault confidence level of the photovoltaic junction box is specifically performed as follows: For any photovoltaic junction box in the photovoltaic power generation system, calculate the absolute value of the difference between the fault confidence of the any photovoltaic junction box and each of the remaining photovoltaic junction boxes, and record it as a first absolute value of the difference; calculate the mean of all the first absolute values ​​of the difference of the any photovoltaic junction box, and record it as a first mean; and record the product of the first mean and the fault confidence of the any photovoltaic junction box as the outlier fault confidence of the any photovoltaic junction box; The outlier fault confidence of all PV junction boxes is used as the input of the anomaly detection algorithm, and the output is the outlier point among all outlier fault confidences. The PV junction box corresponding to the outlier point is determined to be a faulty junction box.

[0013] In a second aspect, an embodiment of the present application further provides an intelligent photovoltaic junction box testing system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0014] The embodiments of the present application have at least the following beneficial effects: This application analyzes the data changes of the current and voltage of the smart photovoltaic junction box at adjacent moments, constructs the voltage and current difference index of the smart photovoltaic junction box, preliminarily evaluates the performance of the photovoltaic junction box, and avoids the problem that the change of light intensity will affect the abnormal detection of voltage and current; based on the difference between the data fluctuation characteristics of voltage and ambient temperature, and the correlation between the time series of voltage and ambient temperature, the electrical parameter anomaly coefficient is constructed in combination with the voltage and current difference index, and the change relationship between voltage and ambient temperature is analyzed to further evaluate the device status of the photovoltaic junction box; considering that if the photovoltaic junction box is abnormal, it will cause abnormal temperature rise, based on the internal temperature of the photovoltaic junction box The correlation between the temperature confidence and the time series of other parameters is calculated, and the fault confidence of the photovoltaic junction box is constructed in combination with the electrical parameter anomaly coefficient. Whether the temperature change of the photovoltaic junction box conforms to the normal law is evaluated, thereby improving the accuracy of the fault analysis of the photovoltaic junction box. Based on the difference between the fault confidence of each photovoltaic junction box and that of other photovoltaic junction boxes, the outlier fault confidence of each photovoltaic junction box is constructed, and then the anomaly detection of each photovoltaic junction box is performed. This reduces the influence of environmental factors on the relevant data of the photovoltaic junction box, avoids the problem of false detection caused by unreasonable threshold setting when the existing photovoltaic junction box detection technology uses temperature threshold detection, improves the detection accuracy of the photovoltaic junction box, and avoids false detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 A flowchart of a method for testing an intelligent photovoltaic junction box according to an embodiment of the present application; Figure 2 Schematic diagram of the process of obtaining the temperature corresponding index. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effectiveness of this application's implementation of the intended invention, the following, in conjunction with the accompanying drawings and preferred embodiments, provides a detailed description of the specific implementation, structure, features, and effectiveness of a smart photovoltaic junction box testing method and system proposed in this application. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0019] The specific scheme of the intelligent photovoltaic junction box testing method and system provided by the present application is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flowchart of a method for testing an intelligent photovoltaic junction box provided by one embodiment of the present application, the method comprising the following steps: Step S1 : collecting the current and voltage flowing through the smart photovoltaic junction box, as well as the internal temperature of the smart photovoltaic junction box and the ambient temperature in real time, and constructing a current sequence, a voltage sequence, an internal temperature sequence and an ambient temperature sequence.

[0021] The photovoltaic junction box is connected to a photovoltaic power generation module and an electrical device at both ends. The photovoltaic power generation module transmits the direct current generated by the photovoltaic junction box to the electrical device through the photovoltaic junction box. This application uses the control center of the smart photovoltaic junction box to collect real-time current and voltage data flowing through the smart photovoltaic junction box, as well as temperature data inside the smart photovoltaic junction box. At the same time, a temperature sensor is placed 5 cm away from the photovoltaic junction box to collect real-time temperature data of the environment in which the smart photovoltaic junction box is located.

[0022] Preferably, for the collection of various relevant parameters of the smart photovoltaic junction box, in the embodiment of the present application, the data collection time interval is set to 1 second. As other embodiments of the present application, the implementer can set the data collection time interval according to actual conditions.

[0023] The time series of collected current data is recorded as the current series, the time series of voltage data is recorded as the voltage series, the time series of PV junction box temperature data is recorded as the internal temperature series, and the time series of ambient temperature data is recorded as the ambient temperature series. To eliminate the dimensionality effects between different parameter data, the data in each series is normalized using the Z-score.

[0024] Step S2: constructing the variation fluctuation coefficients of the current sequence and the voltage sequence based on the data changes in the neighborhood of the data points in the first-order difference sequences of the current sequence and the voltage sequence; and constructing the voltage-current dissimilarity index of the smart photovoltaic junction box based on the variation fluctuation coefficients.

[0025] The power generation of photovoltaic power generation modules is greatly affected by the intensity of solar radiation. Since the intensity of solar radiation rises first and then falls during the day, the power generation generated by photovoltaic power generation modules also rises first and then falls.

[0026] Since the PV junction box extracts the DC power generated by the PV modules, and the power generation of the PV modules varies relatively steadily between consecutive data collection moments, if the PV junction box is operating properly, the current flowing through it will also vary relatively steadily between consecutive data collection moments. Furthermore, although the voltage of the PV modules is significantly affected by ambient temperature—the higher the temperature, the lower the voltage—the ambient temperature varies relatively steadily between consecutive data collection moments, so the voltage of the PV junction box will also vary relatively steadily between consecutive data collection moments.

[0027] Therefore, when the photovoltaic junction box has problems such as diode burnout, heat dissipation failure, and material aging, the current path will be blocked, causing the current to fluctuate violently and the voltage to become unstable, resulting in the current change degree at two adjacent moments being inconsistent, and the voltage change degree at two adjacent moments being inconsistent; at the same time, the failure of the photovoltaic junction box will also cause the temperature to rise, further affecting the safety and service life of the junction box and its surrounding components.

[0028] (1) Due to the large overall changes in temperature and light intensity during the day, the overall changes in the amount of electricity generated by photovoltaic power generation components are also large. Therefore, under normal circumstances, the overall data of the current and voltage of the junction box also show large changes. Therefore, when analyzing the abnormal data fluctuations in the current and voltage series, it is necessary to avoid the influence of the normal fluctuation characteristics of the data on the analysis of abnormal data. Therefore, simple variance, standard deviation and other methods cannot be used to calculate the degree of fluctuation of the current and voltage series.

[0029] The first-order difference sequence of the current sequence is obtained and recorded as the current change sequence. The current change sequence can reflect the degree of change of the current at adjacent moments.

[0030] The extreme point detection algorithm is used to obtain each extreme point in the current change sequence. A neighborhood window of each extreme point is constructed with each extreme point as the center. Preferably, in one embodiment of the present application, the size of the neighborhood window is set to As another embodiment of the present application, the implementer can set the size of the neighborhood window according to the actual situation. Among them, the extreme point detection algorithm is a well-known technology, and the specific process will not be repeated here.

[0031] The coefficient of variation of the sequence composed of all data within the neighborhood window of each extreme point is calculated as the local fluctuation index of each extreme point. The coefficient of variation is well known in the art, and the specific process is not repeated here. It should be noted that when there is insufficient data in the neighborhood window, data is filled by taking the mean of the existing data in the neighborhood window.

[0032] The smaller the local fluctuation index of each extreme point, the more consistent the data in the neighborhood window of each extreme point is. In the period corresponding to the neighborhood window, the degree of change of the current is relatively consistent, and the greater the possibility that the fluctuation at the corresponding extreme point is normal fluctuation.

[0033] (2) Calculate the variance of the local fluctuation index of all extreme points in the current change sequence, and record it as the extreme point fluctuation index of the current change sequence. The larger the extreme point fluctuation index, the greater the fluctuation difference between the extreme points, reflecting that the data changes more drastically in the current sequence.

[0034] (3) The fluctuation coefficient of the current sequence is calculated based on the extreme point fluctuation index of the current change sequence and the proportion of extreme points in the current change sequence. The expression is: , where is the fluctuation coefficient of the current sequence; B is the fluctuation index of the extreme point of the current change sequence; D is the ratio of the number of extreme points in the current change sequence to the number of all elements in the current change sequence.

[0035] If the extreme point fluctuation index is larger, it means that the difference in the local fluctuation degree between different extreme points in the current change sequence is greater, and the less it conforms to the normal current fluctuation characteristics of the photovoltaic junction box; if the extreme point proportion is larger, it means that there are more extreme points in the current change sequence, reflecting more frequent sudden changes in the current data; therefore, if the change fluctuation coefficient of the current sequence is larger, it means that the change degree of the current flowing through the photovoltaic junction box at adjacent moments is more inconsistent, and the possibility of the photovoltaic junction box failure is greater.

[0036] (4) Based on the voltage sequence, the same calculation method as the current sequence variation fluctuation coefficient is used to obtain the voltage sequence variation fluctuation coefficient, which is recorded as .

[0037] (5) Further, based on the above analysis, the voltage and current difference index of the photovoltaic junction box is constructed, denoted as A. The expression of A is: .

[0038] Under normal circumstances, the fluctuation coefficients of the voltage and current of the photovoltaic junction box are very small, so the absolute value of the difference between the two is small, and the sum is also small; when the photovoltaic junction box is abnormal, the current and voltage will fluctuate violently, and the fluctuation coefficients of the voltage and current will be large. Furthermore, there is a difference between the degree of change of the current and the degree of change of the voltage, so the absolute value of the difference between the two is large; therefore, the larger A is, the more likely the photovoltaic junction box is in an abnormal state.

[0039] Step S3: constructing a voltage variation index of the photovoltaic junction box based on the difference between the data fluctuation characteristics of the voltage sequence and the ambient temperature sequence; analyzing the correlation between the voltage sequence and the ambient temperature sequence, and constructing an electrical parameter anomaly coefficient of the photovoltaic junction box by combining the voltage-current difference index and the voltage variation index.

[0040] If the PV junction box is operating properly, the voltage will slowly decrease as the ambient temperature rises and slowly increase as the ambient temperature drops, with the voltage change proportional to the ambient temperature change. If the PV junction box fails, the voltage will fluctuate, changing the relationship between voltage and ambient temperature.

[0041] (1) The first-order difference sequence of the voltage sequence is recorded as the voltage change sequence, and the first-order difference sequence of the ambient temperature sequence is recorded as the ambient change sequence; the DTW distance between the voltage change sequence and the ambient change sequence is calculated and recorded as the voltage change index of the photovoltaic junction box. If the DTW distance is smaller, it means that the voltage change is closer to the ambient temperature change time, the change degree of the voltage and the ambient temperature is more similar, and it is more consistent with the voltage change characteristics under the normal operation of the photovoltaic junction box; if the DTW distance is larger, it means that the change pattern between the two sequences is more inconsistent, and the difference between the corresponding change degrees is greater, reflecting that the voltage is no longer only affected by temperature and the possibility of multiple fluctuations is greater.

[0042] (2) Based on the above analysis, the electrical parameter anomaly coefficient of the photovoltaic junction box is constructed, and the expression is: , where K is the electrical parameter anomaly coefficient of the photovoltaic junction box; A is the voltage and current difference index of the photovoltaic junction box; F is the voltage variation index of the photovoltaic junction box; X is the correlation between the voltage sequence and the ambient temperature sequence, specifically the absolute value of the Pearson correlation coefficient between the voltage sequence and the ambient temperature sequence; is a very small positive number preset by humans, and its function is to avoid the denominator being 0. The value of is set to 0.01. As other embodiments of this application, the implementer can set it according to the actual situation. The Pearson correlation coefficient is a well-known technology, and the specific process will not be repeated here.

[0043] It should be noted that for the calculation of voltage-temperature correlation, this application only provides one correlation calculation method. There are many existing correlation calculation methods, and implementers can also use other correlation algorithms to calculate voltage-temperature correlation. This application does not make specific restrictions.

[0044] A larger voltage-current dissimilarity index indicates a greater disparity in the degree of change in voltage and current at adjacent moments, which suggests a poor fit for a good PV junction box. A larger voltage variation index (F) indicates a greater likelihood that voltage and temperature are no longer proportional. A smaller voltage-temperature correlation indicates a weaker correlation between voltage and temperature, and a greater likelihood that voltage will no longer change with temperature. Therefore, a larger electrical parameter anomaly coefficient (K) indicates drastic voltage and current fluctuations, a greater likelihood that voltage is no longer affected by temperature, and a higher likelihood that the PV junction box is abnormal.

[0045] Step S4: constructing a temperature response index of the photovoltaic junction box based on the correlation between the internal temperature sequence and the current sequence, voltage sequence, and ambient temperature sequence; constructing a temperature difference sequence based on the difference between the internal temperature sequence and the ambient temperature sequence; constructing a temperature normal coefficient of the photovoltaic junction box based on the change trend of the data in the internal temperature, ambient temperature, and temperature difference sequence in combination with the temperature response index; and constructing a fault confidence level of the photovoltaic junction box based on the electrical parameter abnormality coefficient and the temperature normal coefficient.

[0046] Furthermore, if a PV junction box malfunctions, it not only causes changes in related electrical parameters but also increases the temperature inside the junction box. However, given the direct impact of ambient temperature on the temperature of the PV junction box, a rise in ambient temperature will also cause the temperature of the PV junction box to rise. Therefore, comprehensive temperature monitoring of the PV junction box based on ambient temperature changes is necessary to avoid misjudgments.

[0047] If the PV junction box is in good condition, as the radiation intensity increases, the current flowing through the PV junction box increases along with the power generation. According to Joule's law, the increased current generates more heat, which in turn increases the temperature of the PV junction box. At the same time, rising ambient temperature will also affect the temperature of the PV junction box. Conversely, as the radiation intensity decreases, the power generation decreases, and the ambient temperature drops, the temperature of the PV junction box will also decrease. There is a strong correlation between the temperature of the PV junction box, the current, and the ambient temperature.

[0048] (1) Calculate the absolute value of the Pearson correlation coefficient between the internal temperature series and the current series, which is recorded as the first correlation; calculate the absolute value of the Pearson correlation coefficient between the internal temperature series and the ambient temperature series, which is recorded as the second correlation. The Pearson correlation coefficient is a well-known technology, and the specific process will not be repeated here.

[0049] It should be noted that for the calculation of the first correlation and the second correlation, this application only provides a correlation calculation method. There are many existing correlation algorithms, and implementers can also use other correlation algorithms to calculate the first correlation and the second correlation. This application does not make specific restrictions.

[0050] The sum of the first correlation and the second correlation is used as the temperature response index of the photovoltaic junction box. The larger the temperature response index, the greater the possibility that the temperature of the photovoltaic junction box conforms to normal temperature changes.

[0051] In summary, the steps for obtaining the temperature response index are as follows: Step S401, record the correlation between the internal temperature sequence and the current sequence as the first correlation; Step S402, record the correlation between the internal temperature sequence and the ambient temperature sequence as the second correlation; Step S403, take the sum of the first correlation and the second correlation as the temperature response index of the photovoltaic junction box. The schematic diagram of the temperature response index acquisition process is shown in the figure. Figure 2 shown.

[0052] (2) Furthermore, the temperature difference between the temperature of the PV junction box and the ambient temperature can be analyzed to further distinguish between temperature changes caused by natural conditions and abnormal temperature rise caused by potential faults.

[0053] The absolute value of the difference between each element in the internal temperature sequence and the element at the same moment in the ambient temperature sequence is calculated and recorded as the first absolute value of the difference. The sequence consisting of the first absolute values ​​of the difference at all moments is recorded as the temperature difference sequence.

[0054] If the PV junction box is in good condition and the internal cooling system is functioning properly, dissipating the heat generated by the high current, the temperature difference sequence will be relatively stable with minimal fluctuations. However, if the PV junction box malfunctions and experiences abnormal temperature rise, and the cooling system is unable to dissipate the heat in time, the temperature difference sequence will fluctuate significantly, and the temperature difference will become larger over time.

[0055] The temperature difference series is fitted using the least squares method to obtain a fitted line. The absolute value of the slope of the fitted line is recorded as the rise index of the temperature difference series. The larger the rise index, the greater the temperature difference between the PV junction box and the ambient temperature over time, and the less it meets the characteristics of a good PV junction box.

[0056] (3) Obtain the first-order difference sequence of the internal temperature sequence and the ambient temperature sequence respectively, and calculate the mean of all elements in the first-order difference sequence of the internal temperature sequence, which is recorded as the internal change index ; Calculate the mean of all elements in the first-order difference sequence of the ambient temperature series, recorded as the environmental change index The internal change index and the environmental change index reflect the rate of change of the two temperature series in continuous time. The larger the value, the more drastic the temperature rise rate.

[0057] The temperature difference index of the photovoltaic junction box is set based on the difference between the internal change index and the environmental change index. The expression is: , where W is the temperature difference index of the photovoltaic junction box, is the internal temperature variation index of the PV junction box, is the environmental variation index of ambient temperature.

[0058] The larger the temperature difference index is, the greater the difference between the temperature rise rate of the photovoltaic junction box and the ambient temperature rise rate is, and the faster the overall temperature rise rate of the photovoltaic junction box is.

[0059] (4) Based on the above analysis, the temperature normal coefficient of the photovoltaic junction box is constructed, and the expression is: , where G is the temperature normal coefficient of the photovoltaic junction box, P is the temperature corresponding index of the photovoltaic junction box, H is the rising index of the temperature difference sequence, and W is the temperature difference index of the photovoltaic junction box. It is an artificially preset minimum positive number, whose function is to prevent the denominator from being 0.

[0060] A larger temperature response index (P) indicates a stronger correlation between the internal temperature of the PV junction box and the current and ambient temperature, and a more consistent change. A smaller rise index (H) indicates that the temperature difference between the internal temperature of the PV junction box and the ambient temperature remains similar over time. A smaller temperature difference index (W) indicates a smaller difference in the rate of increase between the internal temperature of the PV junction box and the ambient temperature. If W = 0, the average rate of increase in the ambient temperature is faster, reflecting better heat dissipation performance. Therefore, a larger temperature normality coefficient (G) indicates that the temperature changes of the PV junction box more closely conform to good junction box characteristics, and the likelihood that the PV junction box is in a normal state is greater.

[0061] (5) The fault confidence of the photovoltaic junction box is constructed based on the electrical parameter abnormal coefficient K and the temperature normal coefficient G of the photovoltaic junction box, which is recorded as L. The expression of L is: .

[0062] If the abnormal coefficient K of the electrical parameter is larger and the normal coefficient G of the temperature is smaller, the fault confidence L is larger, which reflects that the possibility of abnormal voltage, current and temperature is greater, and the possibility of failure of the photovoltaic junction box is greater.

[0063] Step S5: performing fault analysis on the photovoltaic junction box based on the fault confidence level of the photovoltaic junction box.

[0064] Because multiple PV junction boxes exist in the same PV power generation system, for any PV junction box in the system, the absolute value of the difference between the fault confidence level of that PV junction box and that of each of the remaining PV junction boxes is calculated, recorded as the first absolute value of the difference. The mean of all the absolute values ​​of the first differences for that PV junction box is calculated, recorded as the first mean. The product of the first mean and the fault confidence level of that PV junction box is recorded as the outlier fault confidence level of that PV junction box. The outlier fault confidence level reflects the difference between the fault confidence levels of each PV junction box and all the remaining PV junction boxes, thereby further preventing false detections.

[0065] The outlier fault confidence scores of all PV junction boxes are used as input to the LOF anomaly detection algorithm. The algorithm then identifies outliers in the outlier fault confidence scores and identifies the PV junction box corresponding to the outlier as a faulty junction box. The faulty junction box is then promptly repaired. The LOF anomaly detection algorithm is well known, and the detailed process is omitted here.

[0066] It should be noted that for the detection of abnormal points of the outlier fault confidence of all photovoltaic junction boxes, this application only provides one abnormality detection method. There are many existing abnormality detection methods. Implementers can also use other abnormality detection algorithms to obtain the abnormal points of the outlier fault confidence of all photovoltaic junction boxes. This application does not make specific restrictions.

[0067] Based on the same inventive concept as the above method, an embodiment of the present application also provides an intelligent photovoltaic junction box testing system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned intelligent photovoltaic junction box testing methods are implemented.

[0068] In summary, the embodiment of the present application provides a method for testing a smart photovoltaic junction box. By analyzing the data changes of the current and voltage of the smart photovoltaic junction box at adjacent moments, a voltage and current difference index of the smart photovoltaic junction box is constructed to preliminarily evaluate the performance of the photovoltaic junction box, thereby avoiding the problem that changes in light intensity may affect the detection of voltage and current anomalies. Based on the difference between the data fluctuation characteristics of voltage and ambient temperature, and the correlation between the time series of voltage and ambient temperature, an electrical parameter anomaly coefficient is constructed in combination with the voltage and current difference index, and the change relationship between voltage and ambient temperature is analyzed to further evaluate the device status of the photovoltaic junction box. Considering that if an abnormality occurs in the photovoltaic junction box, it will cause abnormal rise Based on the correlation between the internal temperature of the photovoltaic junction box and the time series of other parameters, the fault confidence of the photovoltaic junction box is constructed in combination with the abnormal coefficient of the electrical parameters. Whether the temperature change of the photovoltaic junction box conforms to the normal law is evaluated, thereby improving the accuracy of the fault analysis of the photovoltaic junction box. Based on the difference between the fault confidence of each photovoltaic junction box and that of other photovoltaic junction boxes, the outlier fault confidence of each photovoltaic junction box is constructed, and then the abnormality detection of each photovoltaic junction box is performed, which reduces the influence of environmental factors on the relevant data of the photovoltaic junction box and avoids the problem of false detection caused by unreasonable threshold setting when the existing photovoltaic junction box detection technology uses temperature threshold detection. The detection accuracy of the photovoltaic junction box is improved and false detection is avoided.

[0069] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the above descriptions are of specific embodiments of the present application. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] The various embodiments in this application are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0071] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for testing an intelligent photovoltaic junction box, characterized in that: The method comprises the following steps: Real-time collection of the current and voltage flowing through the smart photovoltaic junction box, as well as the internal temperature of the smart photovoltaic junction box and the ambient temperature, to construct a current sequence, a voltage sequence, an internal temperature sequence and an ambient temperature sequence; Based on the data changes of the neighborhood of the data points in the first-order difference sequence of the current sequence and the voltage sequence, the change fluctuation coefficients of the current sequence and the voltage sequence are respectively constructed; based on the change fluctuation coefficients, the voltage and current dissimilarity index of the intelligent photovoltaic junction box is constructed; The voltage variation index of the photovoltaic junction box is constructed based on the difference between the data fluctuation characteristics of the voltage sequence and the ambient temperature sequence; the correlation between the voltage sequence and the ambient temperature sequence is analyzed, and the electrical parameter abnormality coefficient of the photovoltaic junction box is constructed by combining the voltage-current difference index and the voltage variation index; Based on the correlation between the internal temperature sequence and the current sequence, voltage sequence and ambient temperature sequence, a temperature response index of the photovoltaic junction box is constructed; based on the difference between the internal temperature sequence and the ambient temperature sequence, a temperature difference sequence is constructed; based on the change trend of the data in the internal temperature, ambient temperature and temperature difference sequence, a temperature normal coefficient of the photovoltaic junction box is constructed in combination with the temperature response index; based on the electrical parameter abnormality coefficient and the temperature normal coefficient, a fault confidence of the photovoltaic junction box is constructed; The fault analysis of photovoltaic junction box is carried out based on the fault confidence of photovoltaic junction box.

2. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The process of obtaining the variation fluctuation coefficient is as follows: The extreme point detection algorithm is used to obtain the extreme points in the first-order difference sequence of the current sequence, and the coefficient of variation of the sequence composed of all data in the neighborhood window of each extreme point is calculated. The variance of the coefficient of variation of all extreme points is calculated, which is recorded as B; the ratio of the number of extreme points to the number of elements in the first-order difference sequence of the current sequence is calculated, which is recorded as D; the change fluctuation coefficient of the current sequence is recorded as , The expression is: ; Based on the voltage sequence, the variation fluctuation coefficient of the voltage sequence is obtained by adopting the same calculation method as the variation fluctuation coefficient of the current sequence.

3. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The expression of the voltage-current dissimilarity index is: , where A is the voltage and current difference index of the photovoltaic junction box, , are the fluctuation coefficients of the current series and voltage series respectively.

4. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The process of obtaining the voltage change index is as follows: The first-order difference sequence of the voltage sequence is recorded as the voltage change sequence, and the first-order difference sequence of the ambient temperature sequence is recorded as the ambient temperature change sequence; the metric distance between the voltage change sequence and the ambient temperature change sequence is taken as the voltage change index of the photovoltaic junction box.

5. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The expression of the electrical parameter abnormal coefficient is: , where K is the electrical parameter anomaly coefficient of the photovoltaic junction box; A and F are the voltage and current difference index and voltage change index of the photovoltaic junction box respectively; X is the correlation between the voltage sequence and the ambient temperature sequence; It is an extremely small positive number preset artificially.

6. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The process of obtaining the temperature corresponding index is as follows: The correlation between the internal temperature sequence and the current sequence is recorded as the first correlation; the correlation between the internal temperature sequence and the ambient temperature sequence is recorded as the second correlation; and the sum of the first correlation and the second correlation is used as the temperature response index of the photovoltaic junction box.

7. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The process of obtaining the temperature normal coefficient is as follows: The mean of all elements in the first-order difference sequence of the internal temperature series is recorded as ; The mean of all elements in the first-order difference sequence of the ambient temperature series is recorded as ; The temperature difference index of the photovoltaic junction box is recorded as W, and the expression of W is: ; The temperature difference series is fitted by a fitting algorithm to obtain a fitting straight line, and the absolute value of the slope of the fitting straight line is recorded as H; The temperature normal coefficient of the photovoltaic junction box is recorded as G, and the expression of G is: , where P is the temperature response index of the photovoltaic junction box, It is an extremely small positive number preset artificially.

8. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The expression of the fault confidence is: , where L is the fault confidence of the photovoltaic junction box, K is the electrical parameter abnormality coefficient of the photovoltaic junction box, and G is the temperature normality coefficient of the photovoltaic junction box. It is an extremely small positive number preset artificially.

9. A method for testing an intelligent photovoltaic junction box according to claim 1, characterized in that: The fault analysis of the photovoltaic junction box based on the fault confidence of the photovoltaic junction box is specifically as follows: For any photovoltaic junction box in the photovoltaic power generation system, calculate the absolute value of the difference between the fault confidence of any photovoltaic junction box and each of the remaining photovoltaic junction boxes, and record it as the first absolute value of the difference; calculate the mean of all the first absolute values ​​of the difference of any photovoltaic junction box, and record it as the first mean; record the product of the first mean and the fault confidence of any photovoltaic junction box as the outlier fault confidence of any photovoltaic junction box; The outlier fault confidence of all photovoltaic junction boxes is used as the input of the anomaly detection algorithm, and the output is the abnormal point among all the outlier fault confidences. The photovoltaic junction box corresponding to the abnormal point is determined as a faulty junction box.

10. An intelligent photovoltaic junction box testing system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images