An intelligent detection device for solar power generation

Abstract

The present invention discloses an intelligent detection device for solar power generation, which relates to the field of solar photovoltaic technology. The method includes: a position acquisition module acquires multiple photovoltaic panel positions, an irradiance set acquisition module calls a tester to monitor and acquire multiple periodic irradiance sets, a set generation module generates a detection window and frequency set based on this, a test channel acquisition module acquires K test channels after analysis, a detection data set acquisition module acquires a real-time detection data set, and a power generation extraction module extracts the power generation and generates intelligent detection results in combination with the data. The method solves the technical problem that the detection frequency and channel cannot be flexibly and accurately determined by comprehensively considering the distribution position of photovoltaic panels and the changes in the received irradiance during the existing photovoltaic thermal power generation, resulting in low comprehensiveness and poor accuracy of the intelligent detection results, and achieves the technical effect of improving power generation efficiency and stability and reducing operation and maintenance costs.

Description

Technical Field

[0001] The present application relates to the field of solar photovoltaic technology, and in particular to an intelligent detection device for solar power generation. Background Art

[0002] In the field of solar photovoltaic power generation, effective detection of photovoltaic panel performance is crucial, especially when the number of photovoltaic panels increases and the distribution range expands, related detection issues become more and more prominent, and scientific and reasonable allocation of detection resources and accurate acquisition of comprehensive detection data have become the key links to ensure the efficient and stable operation of photovoltaic systems. Traditional photovoltaic panel detection methods are usually extensive and one-sided, relying only on simple detection equipment or limited detection methods, and lack of comprehensive consideration of the location differences and irradiance changes of photovoltaic panels. There is a lack of in-depth analysis and effective use of a large amount of detection data, making it difficult to accurately understand the actual operating conditions and potential risks of each photovoltaic panel. There are unscientific phenomena in detection strategies and resource allocation, resulting in the lack of detection in some key areas and waste of detection resources in some areas. The design of the detection plan is relatively rigid and fixed, and cannot effectively adapt to the complex and changeable operation of photovoltaic panels.

[0003] In the current relevant technologies, when photovoltaic thermal power generation is carried out, it is impossible to comprehensively consider the distribution position of photovoltaic panels and the changes in the received irradiance to flexibly and accurately determine the detection frequency and channel, resulting in technical problems such as low comprehensiveness and poor accuracy of intelligent detection results. Summary of the invention

[0004] The present application provides an intelligent detection device for solar power generation, which adopts a position acquisition module to collect multiple photovoltaic panel positions, an irradiance set acquisition module calls a tester to monitor and obtain multiple periodic irradiance sets, a set generation module generates a detection window and a frequency set based on this, a test channel acquisition module obtains K test channels after analysis, a detection data set acquisition module obtains a real-time detection data set, and a power generation power extraction module extracts the power generation power and generates an intelligent detection result in combination with the data, thereby achieving the technical effect of improving power generation efficiency and stability and reducing operation and maintenance costs.

[0005] The present application provides an intelligent detection device for solar power generation, comprising:

[0006] A position acquisition module, the position acquisition module is used to interact with the target photovoltaic control center to collect multiple photovoltaic panel positions of multiple photovoltaic panels; an irradiance set acquisition module, the irradiance set acquisition module is used to call a multi-channel irradiance tester to perform continuous irradiance monitoring on the multiple photovoltaic panels in multiple monitoring cycles, and obtain multiple cycle continuous irradiance sets, each cycle continuous irradiance set is a summary set of irradiance data of a photovoltaic panel in multiple monitoring cycles; a set generation module, the set generation module is used to perform irradiance difference window segmentation on the multiple photovoltaic panels in one monitoring cycle based on the multiple cycle continuous irradiance sets, and generate multiple photovoltaic panel irradiance detection window sets and multiple window detection frequency sets; a test channel acquisition module, the test channel acquisition module is used to perform neighbor analysis on the multiple window detection frequency sets and the multiple photovoltaic panel positions, and execute test channel Nearest neighbor fusion, obtaining K test channels, wherein the K test channels include K channel window detection frequency sets, each channel window detection frequency set includes a channel high-frequency detection window set, a channel medium-frequency detection window set and a channel low-frequency detection window set, and each test channel is used to perform irradiance detection on multiple photovoltaic panels; a detection data set acquisition module, the detection data set acquisition module is used to obtain K channel real-time detection data sets, wherein the K channel real-time detection data sets are the detection data sets obtained by the multi-channel irradiance tester according to the K channel window detection frequency sets and the K test channels, performing real-time irradiance detection on the multiple photovoltaic panels; a power generation extraction module, the power generation extraction module is used to extract multiple real-time power generation powers of multiple photovoltaic panels, and perform data analysis in combination with the K channel real-time detection data sets to generate intelligent detection results.

[0007] An intelligent detection device for solar power generation proposed in this application, first, the position acquisition module collects multiple photovoltaic panel positions, the irradiance set acquisition module calls the tester to monitor and obtain multiple periodic irradiance sets, the set generation module generates a detection window and frequency set based on this, the test channel acquisition module obtains K test channels after analysis, the detection data set acquisition module obtains the real-time detection data set, the power generation extraction module extracts the power generation power and combines the data to generate intelligent detection results, thereby achieving the technical effect of improving power generation efficiency and stability and reducing operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic diagram of the structure of an intelligent detection device for solar power generation provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of the structure of a collection generation module of an intelligent detection device for solar power generation provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: position acquisition module 10 , irradiance set acquisition module 20 , set generation module 30 , test channel acquisition module 40 , detection data set acquisition module 50 , power generation extraction module 60 . DETAILED DESCRIPTION

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0013] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0014] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0015] The present application embodiment provides an intelligent detection device for solar power generation, such as Figure 1 As shown, the method includes:

[0016] Position acquisition module 10, the position acquisition module 10 is used to interact with the target photovoltaic control center to collect the positions of multiple photovoltaic panels of multiple photovoltaic panels. Specifically, the position acquisition module 10 obtains the position information of multiple photovoltaic panels from the target photovoltaic control center. The position information is a description of the specific location of multiple photovoltaic panels, covering its precise coordinates in geographic space and its relative position relationship with the surrounding environment. The position acquisition module 10 first adjusts its own communication parameters and settings to ensure smooth connection with the target photovoltaic control center, and then sends a connection request to the target photovoltaic control center, and attaches relevant authentication and authorization information. After receiving the request, the target photovoltaic control center verifies the information. Once the verification is passed, the position acquisition module 10 is allowed to establish a connection. After the connection is successful, the position acquisition module 10 sends a clear collection instruction to the target photovoltaic control center, indicating the required multiple photovoltaic panel position data. After receiving the instruction, the target photovoltaic control center searches and filters in its internal database to extract the location data that meets the requirements. Then, these data are preliminarily processed, such as cleaning up useless auxiliary information, correcting possible deviations, etc. After processing, the location data of multiple photovoltaic panels are transmitted to the location acquisition module 10. After receiving the data, the data is processed and analyzed, and the format of the data is unified and standardized, and the data of different formats are converted into a standard format for subsequent use. The accuracy and completeness of the data are carefully verified and compared with the preset standard or reference data. For example, the preset standard requires that the location data must contain coordinate values ​​accurate to a number of decimal places, and the received data will be checked to see if it meets this standard. If there is any discrepancy, take appropriate measures to correct it, or request the target photovoltaic centralized control center to resend it. The location acquisition module 10 finally successfully obtains accurate and complete location information of multiple photovoltaic panels.

[0017] The irradiance set acquisition module 20 is used to call a multi-channel irradiance tester to perform continuous irradiance monitoring on the multiple photovoltaic panels in multiple monitoring cycles, and obtain multiple cycle continuous irradiance sets, each cycle continuous irradiance set is a summary set of irradiance data of a photovoltaic panel in multiple monitoring cycles. Specifically, the irradiance set acquisition module 20 acquires monitoring data for multiple photovoltaic panels from the multi-channel irradiance tester. The data is obtained by continuous irradiance monitoring of each photovoltaic panel during multiple monitoring cycles, representing the irradiance changes of the photovoltaic panels in different time periods. The irradiance set acquisition module 20 first confirms that the communication with the multi-channel irradiance tester is normal and stable, and then issues a clear instruction to the tester, requiring continuous irradiance monitoring of multiple photovoltaic panels for multiple monitoring cycles. After receiving the instruction, the multi-channel irradiance tester simultaneously performs uninterrupted irradiance monitoring and data collection on multiple photovoltaic panels through multiple channels in each monitoring cycle. After a monitoring cycle, the tester will organize and summarize the irradiance data collected for each photovoltaic panel during this cycle to form a single photovoltaic panel. The irradiance data set of this monitoring cycle, when multiple monitoring cycles are completed, the tester successfully obtains the summary set of irradiance data of each photovoltaic panel in multiple monitoring cycles, and the set is transmitted to the irradiance set acquisition module 20. After receiving the data, a preliminary review and verification will be carried out, for example, to check whether the data is complete and whether there are obvious errors or abnormalities. For example, if the set monitoring cycle is once an hour and the monitoring is continuous for one day, then for each photovoltaic panel, the tester will collect its irradiance data every hour of this day, and summarize it into a set containing 24 hours of irradiance data at the end of the day, and then transmit it to the irradiance set acquisition module 20. The irradiance set acquisition module 20 is able to successfully obtain the continuous irradiance sets of multiple cycles of multiple photovoltaic panels, providing key data support for subsequent processing and analysis.

[0018] The set generation module 30 is used to perform irradiance difference window segmentation of the multiple photovoltaic panels within a monitoring cycle based on the multiple periodic continuous irradiance sets, and generate multiple photovoltaic panel irradiance detection window sets and multiple window detection frequency sets. Specifically, the set generation module 30 receives the multiple periodic continuous irradiance sets previously acquired, and the sets cover the irradiance data of multiple photovoltaic panels within multiple monitoring cycles. The set generation module 30 first ensures that the acquired irradiance set is accurate and complete, and then conducts a detailed analysis of the irradiance data of multiple photovoltaic panels within a monitoring cycle, compares the irradiance values ​​at each monitoring moment, and accurately finds the differences in irradiance changes. Based on these differences found, the set generation module 30 performs an irradiance difference window segmentation operation, and divides the entire monitoring cycle into different time period windows according to the characteristics of irradiance changes. While performing window segmentation, the set generation module 30 generates multiple light A set of photovoltaic panel irradiance detection windows, each set corresponds to a detection window of a specific photovoltaic panel in different time periods. The set generation module 30 also calculates the detection frequency of each window according to the window division status, and then generates a set of multiple window detection frequency sets. For example, in actual operation, if a monitoring cycle is set to one week, the set generation module 30 may divide it into different windows such as weekday mornings, weekday afternoons, weekend mornings, weekend afternoons, etc. according to the irradiance differences on different dates and time periods within the week, and calculates the detection frequency of each window. The set generation module 30 successfully generates multiple photovoltaic panel irradiance detection window sets and multiple window detection frequency sets.

[0019] In a possible implementation, the set generation module 30 includes: a detection window set composition unit, the detection window set composition unit is used for the multiple photovoltaic panel irradiance detection window sets including multiple high-frequency detection window sets, multiple medium-frequency detection window sets and multiple low-frequency detection window sets. Specifically, the detection window set composition unit obtains multiple photovoltaic panel irradiance detection window sets, and the sets contain relevant information about the irradiance detection of multiple photovoltaic panels under different conditions. The detection window set composition unit first ensures that the received detection window set is complete and accurate, and then performs a detailed classification operation on this set. During the classification process, different subsets are divided according to the detection frequency. Windows with a high detection frequency are organized into multiple high-frequency detection window sets. Windows usually correspond to time periods with frequent and significant irradiance changes, and therefore require closer and more frequent monitoring. Windows with medium detection frequencies are divided into multiple medium-frequency detection window sets. In the time periods corresponding to such windows, the irradiance changes are relatively For windows that are stable but still require a certain degree of attention and monitoring, and windows with low detection frequency are included in multiple low-frequency detection window sets. During the time period corresponding to the window, the irradiance may change little or be relatively stable, and the monitoring demand is relatively low. For example, if the monitoring cycle is set to one day, the daytime period with strong sunlight and frequent changes may be included in the high-frequency detection window; the morning and afternoon periods with relatively stable irradiance may belong to the medium-frequency detection window; and the night periods with basically constant irradiance may be designated as low-frequency detection windows. The detection window set composition unit successfully subdivides multiple photovoltaic panel irradiance detection window sets into multiple high-frequency detection window sets, multiple medium-frequency detection window sets and multiple low-frequency detection window sets.

[0020] In one possible implementation, Figure 2As shown, the set generation module 30 includes: a first-cycle continuous irradiance set extraction unit, which is used to extract the first-cycle continuous irradiance set from the multiple cycle continuous irradiance sets. Specifically, the first-cycle continuous irradiance set extraction unit performs a comprehensive scan and analysis on the multiple cycle continuous irradiance sets, obtains the relevant identification and feature information of each set, so as to accurately identify and distinguish the irradiance sets of different cycles. After determining the overall structure and composition of the multiple cycle continuous irradiance sets, the extraction unit will determine the specific identification or feature of the first cycle according to the preset rules or conditions, and perform accurate search and screening in the multiple cycle continuous irradiance sets to find the irradiance data set that meets the first cycle identification or feature. During the search process, the extraction unit will continuously compare and verify the found data set to ensure that it does belong to the first cycle. Once the first cycle continuous irradiance set is determined, the extraction unit will completely extract it from the multiple cycle continuous irradiance sets through data extraction and separation technical means. For example, in actual situations, if the multiple cycles are in weeks, the first cycle may be defined as the first week. According to this definition, the extraction unit will accurately find and extract the continuous irradiance set of the first week from the irradiance sets of all weeks.

[0021] The first cycle irradiance change curve generation unit is used to draw curves for multiple first cycle continuous irradiance sequences in the first cycle continuous irradiance set respectively, and generate multiple first cycle irradiance change curves. Specifically, the first cycle irradiance change curve generation unit first obtains the first cycle continuous irradiance set, processes the multiple first cycle continuous irradiance sequences in the set one by one, extracts the irradiance value and the corresponding time point information for each sequence, and uses specific drawing algorithms and tools to determine the scale and range of the coordinate axis based on the extracted data. Usually, time is used as the horizontal axis and the irradiance value is used as the vertical axis. In chronological order, the irradiance value corresponding to each time point is marked on the coordinate axis, and these marked points are connected to form a continuous line, thereby drawing the irradiance change curve of a single first cycle continuous irradiance sequence, repeating the above steps for each first cycle continuous irradiance sequence in the set, and finally generating multiple first cycle irradiance change curves.

[0022] A fitting unit, wherein the fitting unit is used to fit the multiple first-cycle irradiance change curves to generate a first fitting cycle irradiance change curve. Specifically, the fitting unit first obtains the multiple first-cycle irradiance change curves generated by the first-cycle irradiance change curve generation unit, and preprocesses the curves, including checking the integrity and accuracy of the data, removing possible outliers or noise data to improve the accuracy and reliability of the fitting, and selecting a suitable fitting algorithm and model, for example, including polynomial fitting, linear fitting, exponential fitting, etc. The specific selection depends on the characteristics of the irradiance data and the needs of the analysis. Using the fitting algorithm, the data points of the multiple first-cycle irradiance change curves are used as input to calculate the optimal fitting parameters so that the fitting curve can be as close to the original multiple curves as possible. In the fitting process, the fitting algorithm is continuously adjusted and optimized. The fitting parameters are optimized and the fitting effect is evaluated by comparing the deviation between the fitting curve and the original curve. When a satisfactory fitting effect is achieved, a first fitting cycle irradiance change curve is generated that can comprehensively reflect the characteristics of multiple first-cycle irradiance change curves. For example, assuming that multiple first-cycle irradiance change curves show the characteristics of approximate quadratic functions, the fitting unit may select a quadratic polynomial fitting algorithm and continuously adjust the quadratic term coefficient, the linear term coefficient and the constant term so that the fitting curve is highly consistent with the original curve in terms of overall trend and main characteristics. Finally, the fitting unit successfully integrates multiple first-cycle irradiance change curves into a representative first fitting cycle irradiance change curve.

[0023] A curve analysis unit, the curve analysis unit is used to analyze the first fitting cycle irradiance change curve, and determine the first photovoltaic panel irradiance detection window set and the first window detection frequency set. Specifically, the curve analysis unit obtains the first fitting cycle irradiance change curve, makes a preliminary observation and judgment on the overall shape and trend of the curve, analyzes the rising section, the falling section, the stable section and the key feature points such as the possible peaks and troughs of the curve, and determines the possible irradiance change interval based on the preliminary judgment of the curve characteristics. For example, the interval with more significant irradiance change is defined as the key detection interval, and the relatively stable interval is defined as the general detection interval. According to the defined interval, the detection window is further subdivided, and the size and time span of the window are set according to the change rate and amplitude of the curve. The window of the part with drastic change is smaller to improve the detection accuracy; the window of the part with gentle change is larger to reduce the detection cost. While determining the detection window, the number of times each window appears in the entire cycle is counted, so as to calculate the window detection frequency, and all windows and their corresponding detection frequencies are sorted and summarized, and finally the first photovoltaic panel irradiance detection window set and the first window detection frequency set are determined.

[0024] An irradiance set analysis unit is used to analyze the multiple periodic continuous irradiance sets to generate the multiple photovoltaic panel irradiance detection window sets and the multiple window detection frequency sets. Specifically, the irradiance set analysis unit obtains multiple periodic continuous irradiance sets, parses the irradiance set of each period, and analyzes the irradiance data change trends and patterns of each photovoltaic panel in different monitoring periods one by one. During the analysis process, the unit will pay attention to the fluctuation of the irradiance values, including peaks, troughs and relatively stable stages, and consider the similarities and differences of irradiance changes between different periods. Based on in-depth research on the data, the unit begins to divide the detection windows, and divides the time axis into windows of different lengths and intervals according to the amplitude and frequency of irradiance changes. For each divided detection window, the unit will count the frequency of its occurrence in multiple periods, thereby calculating the window detection frequency, and summarize and organize all detection windows and corresponding detection frequencies. According to the high and low frequencies, the detection windows are classified into different sets such as high frequency, medium frequency and low frequency. Finally, multiple photovoltaic panel irradiance detection window sets and multiple window detection frequency sets are generated.

[0025] In a possible implementation, the curve analysis unit includes: a directional mutation point extraction subunit, which is used to extract directional mutation points from the first fitting cycle irradiance change curve to obtain a first directional mutation point set. Specifically, the directional mutation point extraction subunit obtains data from the first fitting cycle irradiance change curve, calculates the slope of the curve point by point, and judges the change in direction by comparing the slopes of adjacent points. When the slopes of two adjacent points change in sign and this change exceeds a preset threshold, the point is marked as a directional mutation point. The subunit will also re-verify and confirm the extracted potential mutation points to ensure that they are indeed true directional mutation points, rather than misjudgments caused by data noise or other accidental factors. The subunit collects all determined directional mutation points to form a first directional mutation point set.

[0026] A neighboring point aggregation subunit is used to aggregate neighboring points according to the order of the directional mutation points in the first directional mutation point set and according to the preset time difference threshold, to obtain multiple aggregated first directional mutation point sets. Specifically, after obtaining the first directional mutation point set, the neighboring point aggregation subunit processes the mutation points according to the order in which the mutation points appear in time. For each mutation point, it calculates the time difference with the subsequent mutation point. If the difference is less than the preset time difference threshold, it is considered that the two mutation points are adjacent, and these adjacent mutation points are aggregated together to form multiple sets. All mutation points are processed in sequence to finally obtain multiple aggregated first directional mutation point sets.

[0027] The point aggregation amount identification subunit is used to identify the point aggregation amount of the multiple aggregated first direction mutation point sets respectively, and determine the multiple first aggregation window detection frequencies. Specifically, the point aggregation amount identification subunit analyzes each aggregated first direction mutation point set, counts the number of mutation points contained in each set, and this number is the point aggregation amount. By calculating and determining the point aggregation amounts of multiple sets, multiple first aggregation window detection frequencies are obtained.

[0028] The frequency clustering subunit is used to cluster the multiple first clustering window detection frequencies to generate a first photovoltaic panel irradiance detection window set and a first window detection frequency set, wherein the first photovoltaic panel irradiance detection window set includes a first high-frequency detection window set, a first medium-frequency detection window set and a first low-frequency detection window set. Specifically, after receiving multiple first clustering window detection frequencies, the frequency clustering subunit uses a clustering algorithm to process, sets the frequency ranges of high frequency, medium frequency and low frequency, compares and classifies each detection frequency with these ranges, and classifies the higher frequency into the first high-frequency detection window set, the moderate frequency into the first medium-frequency detection window set, and the lower frequency into the first low-frequency detection window set, and finally generates a first photovoltaic panel irradiance detection window set and a first window detection frequency set including different frequency window sets. For example, assuming that the first fitting period is one week, the directional mutation point extraction subunit finds some directional mutation points in the daily irradiance change curve to form a first directional mutation point set. The neighboring point aggregation subunit clusters mutation points at similar times in each day according to a preset time difference threshold within one day. The point cluster identification subunit calculates the number of points in each cluster and obtains the corresponding detection frequency. Based on these frequencies, the frequency clustering subunit classifies the detection windows within a week into high-frequency, medium-frequency and low-frequency sets, providing accurate guidance for subsequent photovoltaic panel monitoring and management.

[0029] In a possible implementation, the fitting unit includes: a first irradiance scatter point set extraction subunit, the first irradiance scatter point set extraction subunit is used to extract multiple first irradiance scatter point sets of the multiple first period irradiance change curves, wherein the multiple first irradiance scatter point sets include multiple first scatter point coordinates. Specifically, the first irradiance scatter point set extraction subunit performs data analysis on each first period irradiance change curve, selects specific points from the curve at certain intervals, and the irradiance value of the point and the corresponding time or other related parameters constitute the coordinates of the scatter point, that is, multiple first scatter point coordinates. Such an operation is performed on each curve, thereby extracting multiple first irradiance scatter point sets respectively.

[0030] The scatter point alignment subunit is used to perform initial irradiance scatter point alignment on the multiple first irradiance scatter point sets in the same coordinate system to obtain a first irradiance change fitting space. Specifically, after the scatter point alignment subunit obtains the multiple first irradiance scatter point sets, it places them all in the same coordinate system, determines a reference point, usually with the initial irradiance scatter point as a reference, and adjusts the positions of each scatter point set in this coordinate system to be relatively uniform and standardized, thereby forming a coherent first irradiance change fitting space.

[0031] The first straight line construction subunit is used to construct a first straight line, starting from the first straight line, iterating in the first irradiance change fitting space according to a preset vertical movement step length until the preset number of vertical iterations and / or the preset conditions are met, and a first positioning straight line is obtained, wherein the first straight line is a straight line that passes through the lowest point of the plurality of first irradiance scatter point sets in the first irradiance change fitting space and is parallel to the abscissa axis of the first irradiance change fitting space. The preset vertical movement step length is a distance preset by a person skilled in the art for a single up and down movement. Specifically, the first straight line construction subunit first finds the lowest point of the plurality of first irradiance scatter point sets in the first irradiance change fitting space, constructs a straight line passing through the lowest point and parallel to the abscissa axis as the first straight line, and iterates upward in the fitting space starting from the first straight line in units of the preset vertical movement step length, and makes a judgment each time it moves to check whether the preset number of vertical iterations is met, or whether other preset conditions are met, and continues the iterative process until the conditions are met, and the straight line finally determined is the first positioning straight line.

[0032] An angle update iteration subunit, the angle update iteration subunit is used to perform angle update iteration on the first positioning straight line to determine the first fitting period irradiance change curve. Specifically, after obtaining the first positioning straight line, the angle update iteration subunit updates and iterates its angle, continuously adjusts the inclination angle of the straight line, and calculates the degree of fit between the straight line and the irradiance scatter points after each adjustment, and continuously changes and evaluates the angle until the angle that can best fit the scatter points is found. The straight line corresponding to the angle finally determined is the first fitting period irradiance change curve. For example, it is assumed that multiple first period irradiance change curves are measurement results in different time periods. The first irradiance scatter point set extraction subunit extracts a scatter point set representing key information from these curves. The scatter point alignment subunit aligns them in the same coordinate system to facilitate subsequent processing. The first straight line construction subunit starts from the lowest point and gradually explores upward to find a suitable vertical position. The angle update iteration subunit then finely adjusts the straight line angle to obtain the most accurate fitting curve. Through the above process, the first fitting period irradiance change curve can be accurately determined, providing a reliable basis for further analysis and application.

[0033] In a possible implementation, the fitting unit further includes: a fitting space iteration subunit, which is used to take the first positioning straight line as the starting point, and iterate in the first irradiance change fitting space according to a preset angle moving step length until the preset angle iteration number is met to obtain the target positioning straight line. Specifically, the fitting space iteration subunit first takes the first positioning straight line as the starting reference, adjusts the angle of the straight line according to the preset angle moving step length, and after each angle adjustment, evaluates and compares in the first irradiance change fitting space, and continues to perform, and constantly tries with new angles until the preset angle iteration number is reached. Through such step-by-step angle adjustment and iteration, the target positioning straight line that can best match or meet specific conditions is finally found. Among them, the preset angle moving step length is the angle set by those skilled in the art for a single angle adjustment. For example, assuming that the preset angle moving step length is 5 degrees, and the preset angle iteration number is 50 times. Then the unit will start from the initial angle, increase by 5 degrees each time, repeat this process 50 times, and find the straight line that best meets the requirements in this series of angle changes.

[0034] The first irradiance scatter point capture subunit is used to capture multiple first irradiance scatter points whose distance to the target positioning line is a preset bandwidth, and obtain multiple captured first irradiance scatter points. Specifically, after obtaining the target positioning line, the first irradiance scatter point capture subunit calculates the distance from each first irradiance scatter point in the first irradiance change fitting space to the target positioning line. If this distance is less than or equal to the preset bandwidth set in advance, this scatter point will be marked as a captured point. By performing such distance calculation and judgment on all scattered points, multiple captured first irradiance scatter points are finally screened out. For example, assuming that the preset bandwidth is set to 10 unit distances. Then all scattered points within 10 unit distances from the target positioning line will be captured.

[0035] The curve fitting subunit is used to perform curve fitting on the multiple captured first irradiance scatter points to generate the first fitting period irradiance change curve. Specifically, after receiving the multiple captured first irradiance scatter points, the curve fitting subunit analyzes the distribution characteristics and trends of the scatter points, builds a curve model that can best describe the relationship between these scatter points, calculates and optimizes the parameters of the curve to make it as close to these scatter points as possible, thereby generating the first fitting period irradiance change curve, for example, using a polynomial curve fitting algorithm, determining the degree and coefficient of the polynomial according to the distribution of the scatter points, and finally obtaining the fitting curve, and successfully generating a curve that can accurately reflect the irradiance change in the first fitting period from the initial positioning straight line to the captured scatter points, and then to the curve fitting.

[0036] In a possible implementation, the first straight line construction subunit includes: a first iterative straight line acquisition microunit, the first iterative straight line acquisition microunit is used to take the first straight line as a starting point, take the upper side of the horizontal axis as a moving direction, and move in the first irradiance change fitting space according to the preset vertical moving step length to obtain a first iterative straight line. Specifically, the first iterative straight line acquisition microunit takes the first straight line as a starting position, clarifies that the moving direction is above the horizontal axis, and moves in the first irradiance change fitting space according to the preset vertical moving step length, and each time a step length is moved, a new position is obtained, thereby determining the first iterative straight line.

[0037] An aggregation granularity difference comparison microunit is used to compare the aggregation granularity difference between the first straight line and the first iterative straight line. If the aggregation granularity difference is greater than or equal to a preset aggregation granularity difference, the first iterative straight line is updated as the starting point, and continues to move in the first irradiance change fitting space until a preset number of vertical iterations is met / or a preset condition is met, to obtain the first positioning straight line, wherein the preset condition is that the aggregation granularity difference is less than the preset aggregation granularity difference. Specifically, after obtaining the first straight line and the first iterative straight line, the aggregation granularity difference comparison microunit will respectively calculate their aggregation granularity differences. The aggregation granularity refers to the number of irradiance scatter points with a preset bandwidth distance to the straight line, which reflects the degree of aggregation of irradiance scatter points around the straight line. The aggregation granularity difference between the first straight line and the first iterative straight line is compared. If this difference is greater than or equal to the preset aggregation granularity difference, it means that the degree of aggregation of irradiance scatter points at the location of the first iterative straight line has changed significantly, which is more advantageous. The first iterative straight line is updated to a new starting point, and continues to move in the same way in the first irradiance change fitting space. Repeat this process continuously, and compare and judge the aggregation granularity difference each time until the preset number of vertical iterations is met, or the aggregation granularity difference is less than the preset aggregation granularity difference, indicating that a relatively dense area has been reached. At this time, the iteration is stopped, and the current straight line is determined as the first positioning straight line. For example, assuming that the preset vertical movement step is 5 units, the preset aggregation granularity difference is 10, and there are 20 irradiance scatter points around the initial first straight line. The first movement results in the first iteration straight line, which has 35 scattered points around it and a clustering granularity difference of 15, which is greater than the preset value, so the movement continues with the first iteration straight line as the starting point. After multiple movements and comparisons, until the clustering granularity difference is less than the preset value after a certain movement, or the preset number of vertical iterations is reached, the straight line at this time is determined to be the first positioning straight line. Through calculation and comparison, the first positioning straight line that best reflects the irradiance scattered point aggregation characteristics can be accurately found in the first irradiance change fitting space, providing a key basis for subsequent analysis and processing.

[0038] The test channel acquisition module 40 is used to perform neighbor analysis on the multiple window detection frequency sets and the multiple photovoltaic panel positions, perform test channel neighbor fusion, and obtain K test channels, wherein the K test channels include K channel window detection frequency sets, each channel window detection frequency set includes a channel high-frequency detection window set, a channel medium-frequency detection window set, and a channel low-frequency detection window set, and each test channel is used to perform irradiance detection on multiple photovoltaic panels. Specifically, the test channel acquisition module 40 acquires multiple window detection frequency sets and the position information of multiple photovoltaic panels. For the position of each photovoltaic panel, the module 40 will analyze the position relationship of the surrounding adjacent photovoltaic panels, calculate the distance between the positions or use a specific spatial analysis method to determine which photovoltaic panels are adjacent in position. For photovoltaic panels with adjacent positions, the module 40 will further compare their window detection frequency sets, analyze the similarity and difference between the high-frequency detection window set, the medium-frequency detection window set, and the low-frequency detection window set in the frequency set. If the window detection frequency sets of adjacent photovoltaic panels are also similar, that is, they have similar requirements for detecting irradiance changes, then These photovoltaic panels with adjacent positions and similar detection frequencies are divided into the same test channel. By comprehensively analyzing and comparing the positions and window detection frequency sets of all photovoltaic panels, the division process is repeated continuously to finally obtain K test channels. Each test channel contains a group of photovoltaic panels with adjacent positions and similar detection requirements, and each channel has a corresponding channel window detection frequency set, in which the channel high-frequency detection window set, the channel medium-frequency detection window set and the channel low-frequency detection window set are divided in detail. For example, assuming that there are multiple photovoltaic panels distributed in an area, some of which are close to each other, and their window detection frequency sets are close in value and change trend. Then these photovoltaic panels will be divided into the same test channel so that they can be more efficiently tested and managed for irradiance. Finally, the test channel acquisition module 40 successfully determines K test channels that can effectively perform irradiance detection, providing reasonable organization and planning for subsequent detection work.

[0039] A detection data set acquisition module 50 is used to acquire K channel real-time detection data sets, wherein the K channel real-time detection data sets are detection data sets obtained by the multi-channel irradiance tester by performing real-time irradiance detection on the multiple photovoltaic panels based on the K channel window detection frequency sets and the K test channels. Specifically, the detection data set acquisition module 50 establishes an effective communication connection with the multi-channel irradiance tester. The multi-channel irradiance tester starts to perform real-time irradiance detection on multiple photovoltaic panels based on the previously determined K channel window detection frequency sets and K test channels. During the detection process, the tester will collect irradiance data at different frequencies in a targeted manner according to the window detection frequency set corresponding to each test channel, that is, the channel high-frequency detection window set, the channel medium-frequency detection window set and the channel low-frequency detection window set. After the detection is completed, the multi-channel irradiance tester will sort and summarize the detection data obtained for each test channel to form K channel real-time detection data sets. The detection data set acquisition module 50 receives the K channel real-time detection data sets from the multi-channel irradiance tester. For example, assuming that there are three test channels, each channel has a different detection frequency set. The multi-channel irradiance tester will perform high-frequency, medium-frequency and low-frequency irradiance detection on the corresponding photovoltaic panels according to the high-frequency, medium-frequency and low-frequency detection window sets of channel one, and record the data. Similarly, similar operations are performed on channel 2 and channel 3. Finally, the detection data set acquisition module 50 obtains the real-time detection data sets of the three channels. The detection data set acquisition module 50 obtains K channel real-time detection data sets that can reflect the real-time irradiance conditions of multiple photovoltaic panels, providing a basis for subsequent data analysis and processing.

[0040] The power generation extraction module 60 is used to extract multiple real-time power generation of multiple photovoltaic panels, and perform data analysis in combination with the K channel real-time detection data sets to generate intelligent detection results. Specifically, the power generation extraction module 60 uses a special power monitoring device or system to accurately extract multiple real-time power generation of each photovoltaic panel, and obtains K channel real-time detection data sets, which contain rich irradiance-related information. In the data analysis link, since it is known that irradiance will directly affect the power of solar thermal power generation, the module 60 will focus on in-depth analysis of the irradiance data, study the numerical value of the irradiance in each channel real-time detection data set, the change trend and the distribution in different time periods, and make one-to-one correspondence and association between the extracted multiple real-time power generation and irradiance data. For the case of high power generation, analyze whether the corresponding irradiance level is is also in a high state; for the moment when the power generation is low, check the irradiance value at this time and whether its change is abnormal. By establishing a mathematical model between power generation and irradiance, it is possible to use linear regression, correlation analysis and other methods to find out the internal relationship and law between the two. For example, if it is found that the irradiance is strong at a certain moment, but the corresponding power generation is lower than expected, it may mean that the photovoltaic panel has a fault or a decrease in efficiency; on the contrary, if the irradiance is weak but the power generation is relatively high, it may be necessary to further check the accuracy of the detection data or the performance optimization of the photovoltaic panel. After a comprehensive and in-depth analysis, various factors and possible situations are comprehensively considered to finally generate an intelligent detection result. This result may include an evaluation of the overall performance of the current solar thermal power generation system, indicating which photovoltaic panels have good power generation and which have potential problems, predicting the power generation in the future, and proposing specific improvement and maintenance suggestions for the problems found. The power generation extraction module 60 can effectively combine the power generation with the irradiance data to provide valuable intelligent detection results for the stable operation and optimization of the solar thermal power generation system.

[0041] In a possible implementation, the power generation extraction module 60 includes: a real-time power generation set acquisition unit, which is used to map and extract multiple real-time power generation of the multiple photovoltaic panels with the K test channels to obtain K real-time power generation sets. Specifically, the real-time power generation set acquisition unit first clarifies the division of the K test channels, maps and extracts multiple real-time power generation data of multiple photovoltaic panels according to the range of photovoltaic panels covered by each test channel, and groups the real-time power generation of photovoltaic panels belonging to the same test channel into one group. Through classification and screening, K real-time power generation sets that are independent of each other and corresponding to the test channels are finally obtained. For example, assuming that there are three test channels, each covering photovoltaic panels with different positions and characteristics. The unit will extract the real-time power generation of the photovoltaic panel belonging to the first test channel to form the first real-time power generation set, and so on to obtain all K sets.

[0042] An intelligent detection result generation unit, the intelligent detection result generation unit is used to use the detection and analysis unit to perform data analysis on the K real-time power generation sets and the K channel real-time detection data sets to generate the intelligent detection result. Specifically, the intelligent detection result generation unit obtains the K real-time power generation sets obtained by the real-time power generation set acquisition unit, and the K channel real-time detection data sets, and inputs the data into the detection and analysis unit. The detection and analysis unit compares the differences and similarities between the real-time power generation sets of different test channels, and combines the irradiance and other information in the corresponding channel real-time detection data set to perform correlation analysis and trend judgment. For example, it analyzes whether the change of the real-time power generation set in a certain test channel is consistent with the change of the irradiance of the channel. If it is inconsistent, it may mean that there is an equipment failure or other influencing factors. By comprehensively using various data analysis methods and algorithms, the detection and analysis unit deeply mines the potential information and rules in the data. Finally, the intelligent detection result generation unit generates intelligent detection results based on the output results of the detection and analysis unit, providing valuable reference and decision-making basis for the operation status evaluation, fault diagnosis, performance optimization, etc. of the photovoltaic panels, realizing the whole process from data acquisition to the generation of intelligent detection results, and providing strong support for the effective management and optimization of solar photovoltaic systems.

[0043] The embodiment of the present application uses a position acquisition module to collect multiple photovoltaic panel positions, the irradiance set acquisition module calls the tester to monitor and obtain multiple periodic irradiance sets, the set generation module generates a detection window and frequency set based on this, the test channel acquisition module obtains K test channels after analysis, the detection data set acquisition module obtains the real-time detection data set, the power generation extraction module extracts the power generation power and combines the data to generate intelligent detection results, thereby achieving the technical effect of improving power generation efficiency and stability and reducing operation and maintenance costs.

[0044] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0045] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An intelligent detection device for solar power generation, characterized in that: The device comprises: A position acquisition module, wherein the position acquisition module is used to interact with a target photovoltaic centralized control center to acquire multiple photovoltaic panel positions of multiple photovoltaic panels; An irradiance set acquisition module, the irradiance set acquisition module is used to call a multi-channel irradiance tester to perform continuous irradiance monitoring on the multiple photovoltaic panels in multiple monitoring cycles, and obtain multiple cycle continuous irradiance sets, each cycle continuous irradiance set is a summary set of irradiance data of a photovoltaic panel in multiple monitoring cycles; A set generation module, the set generation module is used to perform irradiance difference window segmentation within one monitoring cycle of the multiple photovoltaic panels based on the multiple periodic continuous irradiance sets, and generate multiple photovoltaic panel irradiance detection window sets and multiple window detection frequency sets; A test channel acquisition module, the test channel acquisition module is used to perform neighbor analysis on the multiple window detection frequency sets and the multiple photovoltaic panel positions, perform test channel neighbor fusion, and obtain K test channels, wherein the K test channels include K channel window detection frequency sets, each channel window detection frequency set includes a channel high-frequency detection window set, a channel medium-frequency detection window set and a channel low-frequency detection window set, and each test channel is used to perform irradiance detection on multiple photovoltaic panels; A detection data set acquisition module, the detection data set acquisition module is used to acquire K channel real-time detection data sets, wherein the K channel real-time detection data sets are detection data sets obtained by the multi-channel irradiance tester performing real-time irradiance detection on the multiple photovoltaic panels according to the K channel window detection frequency sets and the K test channels, and the multi-channel irradiance tester performs high-frequency, medium-frequency and low-frequency irradiance detection on the corresponding photovoltaic panels according to the high-frequency detection window set, medium-frequency detection window set and low-frequency detection window set of the test channels; The power generation extraction module is used to extract multiple real-time power generation of multiple photovoltaic panels, perform data analysis in combination with the K channels of real-time detection data sets, and generate intelligent detection results.

2. The device according to claim 1, characterized in that The set generation module comprises: A first periodic continuous irradiance set extraction unit, the first periodic continuous irradiance set extraction unit is used to extract a first periodic continuous irradiance set from the multiple periodic continuous irradiance sets; A first-cycle irradiance variation curve generating unit, the first-cycle irradiance variation curve generating unit is used to respectively draw curves for a plurality of first-cycle continuous irradiance sequences in the first-cycle continuous irradiance set to generate a plurality of first-cycle irradiance variation curves; A fitting unit, the fitting unit is used to fit the multiple first period irradiance change curves to generate a first fitting period irradiance change curve; A curve analysis unit, the curve analysis unit is used to analyze the first fitting period irradiance change curve to determine a first photovoltaic panel irradiance detection window set and a first window detection frequency set; An irradiance set analysis unit is used to analyze the multiple periodic continuous irradiance sets to generate the multiple photovoltaic panel irradiance detection window sets and the multiple window detection frequency sets.

3. The device according to claim 2, characterized in that The curve analysis unit comprises: A directional mutation point extraction subunit, wherein the directional mutation point extraction subunit is used to extract directional mutation points from the irradiance variation curve of the first fitting period to obtain a first directional mutation point set; A neighboring point aggregation subunit, the neighboring point aggregation subunit is used to aggregate neighboring points according to the sequence of the direction mutation points in the first direction mutation point set and according to a preset time difference threshold, to obtain multiple aggregated first direction mutation point sets; A point aggregation amount identification subunit, the point aggregation amount identification subunit is used to identify the point aggregation amounts of the plurality of aggregation first direction mutation point sets respectively, and determine the plurality of first aggregation window detection frequencies; A frequency clustering subunit is used to cluster the multiple first clustering window detection frequencies to generate a first photovoltaic panel irradiance detection window set and a first window detection frequency set.

4. The device according to claim 2, characterized in that The fitting unit comprises: A first irradiance scatter point set extraction subunit, the first irradiance scatter point set extraction subunit is used to respectively extract a plurality of first irradiance scatter point sets of the plurality of first period irradiance change curves, wherein the plurality of first irradiance scatter point sets include a plurality of first scatter point coordinates; A scatter point alignment subunit, the scatter point alignment subunit is used to perform initial irradiance scatter point alignment on the multiple first irradiance scatter point sets in the same coordinate system to obtain a first irradiance change fitting space; A first straight line construction subunit, the first straight line construction subunit is used to construct a first straight line, taking the first straight line as a starting point, and iterating in the first irradiance change fitting space according to a preset vertical movement step length until a preset number of vertical iterations and / or a preset condition is met, so as to obtain a first positioning straight line, wherein the first straight line is a straight line that passes through the lowest point of the plurality of first irradiance scatter point sets in the first irradiance change fitting space and is parallel to the abscissa axis of the first irradiance change fitting space; An angle update iteration subunit is used to perform angle update iteration on the first positioning straight line to determine the first fitting periodic irradiance variation curve.

5. The device according to claim 4, characterized in that The fitting unit further comprises: A fitting space iteration subunit, wherein the fitting space iteration subunit is used to iterate in the first irradiance change fitting space with the first positioning straight line as the starting point according to a preset angle moving step length until a preset angle iteration number is met to obtain a target positioning straight line; A first irradiance scatter point capturing subunit, the first irradiance scatter point capturing subunit being used to capture a plurality of first irradiance scatter points whose distance to the target positioning straight line is a preset bandwidth, to obtain a plurality of captured first irradiance scatter points; A curve fitting subunit is used to perform curve fitting on the plurality of captured first irradiance scatter points to generate the first fitting period irradiance variation curve.

6. The device according to claim 5, characterized in that The first straight line construction subunit comprises: A first iterative straight line acquisition micro-unit, wherein the first iterative straight line acquisition micro-unit is used to move in the first irradiance change fitting space according to the preset vertical movement step length with the first straight line as the starting point and the upper side of the horizontal coordinate axis as the moving direction, so as to obtain a first iterative straight line; An aggregation granularity difference comparison microunit is used to compare the aggregation granularity difference between the first straight line and the first iterative straight line. If the aggregation granularity difference is greater than or equal to a preset aggregation granularity difference, the first iterative straight line is updated as the starting point, and continues to move in the first irradiance change fitting space until a preset number of vertical iterations is met / or a preset condition is met, to obtain the first positioning straight line, wherein the preset condition is that the aggregation granularity difference is less than the preset aggregation granularity difference.

7. The device according to claim 1, characterized in that The power generation extraction module comprises: A real-time power generation set acquisition unit, the real-time power generation set acquisition unit is used to map and extract multiple real-time power generation of the multiple photovoltaic panels using the K test channels to obtain K real-time power generation sets; An intelligent detection result generating unit is used to utilize the detection and analysis unit to perform data analysis on the K real-time power generation power sets and the K channel real-time detection data sets to generate the intelligent detection result.

Images