Photovoltaic module hot spot diagnosis and self-adaptive cleaning method and system

Abstract

The invention discloses a hot spot diagnosis and self-adaptive cleaning method and system for a photovoltaic module, and the method comprises the steps: obtaining the temperature distribution data of the surface of the photovoltaic module in real time through a rapid temperature measurement module in the cleaning process of a cleaning robot; based on the temperature distribution data, a suspected hot spot area with temperature difference abnormity is identified; the cleaning robot is controlled to move to the suspected hot spot area, high-precision temperature scanning is executed through a hot spot diagnosis module, and the hot spot position and range are determined; and performing surface state analysis on the confirmed hot spot area, and generating a self-adaptive cleaning instruction based on an analysis result. According to the invention, through a cleaning and detection dual-stage cooperation mechanism and a dynamic parameter optimization strategy, the accuracy of hot spot diagnosis and self-adaptive cleaning of the photovoltaic module and the operation and maintenance decision efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic component cleaning, and in particular to a method and system for diagnosing and adaptively cleaning hot spots of photovoltaic components. Background Art

[0002] Current photovoltaic module cleaning and hot spot detection technology mainly involves installing temperature sensors on photovoltaic cleaning robots and determining hot spots using fixed temperature difference thresholds.

[0003] The existing technology has the following technical defects: the judgment accuracy is low, the static threshold cannot adapt to the dynamic changes in ambient temperature, and the false alarm rate increases significantly during the morning and evening hours; there is a lack of a re-inspection mechanism for abnormal areas, and the preliminary detection results need to be manually checked for the second time, and there is redundancy in the operation and maintenance process; it is unable to automatically distinguish between battery defect-type hot spots and stain-type hot spots, resulting in operation and maintenance personnel frequently performing invalid on-site inspections and serious waste of resources.

[0004] The above problems have led to low efficiency and increased costs in the operation and maintenance of photovoltaic power stations. A new technical solution is urgently needed to improve the accuracy of hot spot diagnosis and adaptive cleaning of photovoltaic modules and the efficiency of operation and maintenance decision-making. Summary of the Invention

[0005] The main purpose of the present invention is to propose a method for hot spot diagnosis and adaptive cleaning of photovoltaic modules, aiming to solve the technical problems of low accuracy and low operation and maintenance efficiency in the prior art of hot spot diagnosis and adaptive cleaning of photovoltaic modules.

[0006] To achieve the above objectives, the present invention provides a first aspect of a photovoltaic module hot spot diagnosis and adaptive cleaning method, comprising: Step S100: During the cleaning process of the cleaning robot, the temperature distribution data on the surface of the photovoltaic module is obtained in real time through the rapid temperature measurement module; Step S200: identifying suspected hot spot areas with abnormal temperature differences based on the temperature distribution data; Step S300: Controlling the cleaning robot to move to the suspected hot spot area, and performing a high-precision temperature scan through the hot spot diagnosis module to confirm the location and range of the hot spot; Step S400: performing surface condition analysis on the identified hot spot area, and generating an adaptive cleaning instruction based on the analysis result.

[0007] Preferably, in step S100, the step of obtaining temperature distribution data on the surface of the photovoltaic module in real time by using the rapid temperature measurement module includes: Step S110: When the cleaning robot moves along the surface of the photovoltaic module, the temperature data of multiple locations on the surface of the photovoltaic module are synchronously collected at a preset sampling frequency through the multi-temperature sensor array on board; Step S120: Calculating the spatial coordinates of each temperature sampling point on the surface of the photovoltaic module according to the position distribution of the multi-temperature sensor array and the real-time displacement data of the robot; Step S130: Integrate the temperature values ​​corresponding to the spatial coordinates to generate a real-time two-dimensional temperature distribution map of the photovoltaic module surface.

[0008] Preferably, in step S200, the step of identifying suspected hot spot areas with temperature abnormalities based on the temperature distribution data includes: Step S210: Based on the real-time two-dimensional temperature distribution map, the photovoltaic module cells are divided into grid units according to their physical structure, and each grid unit includes at least one temperature sampling point; Step S220: Calculate the absolute value of the temperature difference between each grid cell and its adjacent grid cells. If the difference exceeds a first threshold, mark the grid cell as a suspected abnormal cell. Step S230: spatially cluster adjacent suspected abnormal units to form a continuous cluster area; if the cluster area meets any of the following conditions, it is determined to be a suspected hot spot area: the absolute value of the maximum temperature difference in the area exceeds the second threshold, or the absolute value of the highest temperature in the area exceeds the safety threshold.

[0009] Preferably, the first threshold and the second threshold are dynamically set by the following steps: Step S231: collecting operating electrical parameters and environmental parameters of the target photovoltaic module in real time, wherein the operating electrical parameters include operating current and operating voltage, and the environmental parameters include irradiance and ambient temperature; Step S232: generating an electrical parameter correction coefficient according to the deviation between the operating electrical parameter and the rated electrical parameter; Step S233: determining a temperature reference value based on the matching result between the ambient temperature and the historical temperature database, and generating an environmental correction coefficient in combination with the real-time irradiance; Step S234: matching a reference threshold from a preset database according to the target PV module model, and dynamically adjusting the electrical parameter correction coefficient and the environmental correction coefficient to generate a first threshold; Step S235: Based on the first threshold and the preset level difference ratio, generate a second threshold that is greater than the first threshold.

[0010] Preferably, in step S220, the step of calculating the absolute value of the temperature difference between each grid unit and the adjacent grid units includes: Step S221: determining a set of adjacent grid cells of the current grid cell according to the physical structure of the target photovoltaic module cell; Step S222: generating a representative temperature value of the current grid cell based on a preset temperature feature extraction rule; Step S223: Calculate the absolute value of the difference between the current grid cell representative temperature value and the representative temperature value of each adjacent grid cell; Step S224: selecting the maximum value among the absolute values ​​of the differences as the absolute value of the temperature difference between the current grid unit and the adjacent grid unit.

[0011] Preferably, in step S222, the temperature feature extraction rule is set to extract a representative temperature value from the grid unit temperature data, and its implementation method includes extracting the highest temperature value of all temperature sampling points, or calculating the arithmetic average temperature value of all temperature sampling points, or calculating the weighted average temperature value based on the position weight.

[0012] Preferably, in step S300, the step of performing a high-precision temperature scan by the hot spot diagnosis module to confirm the location and range of the hot spot includes: Step S310: Controlling the cleaning robot to move to the suspected hot spot area, wherein the hot spot diagnosis module includes an infrared temperature sensor; Step S320: performing a high-precision temperature scan using the infrared temperature sensor, inputting the temperature field distribution data obtained by the scan into a pre-trained hot spot recognition neural network model to generate a hot spot probability distribution map; Step S330: integrating the physical structure information of the photovoltaic module cell, performing boundary optimization processing on the hot spot probability distribution map, and outputting the geometric center coordinates and physical boundary polygons of the hot spot.

[0013] Preferably, in step S400, the step of performing surface condition analysis on the confirmed hot spot area and generating an adaptive cleaning instruction based on the analysis result includes: Step S410: measuring the hot spot area through a surface analysis module to obtain surface dust distribution data; Step S420: Calculating a comprehensive dirtiness score based on the surface dust distribution data and the historical cleaning records of the hot spot area; Step S430: When the comprehensive score of the degree of dirtiness exceeds the dirtiness threshold, it is determined to be a hot spot caused by dirtiness, and the deep cleaning process is started; when the comprehensive score of the degree of dirtiness does not exceed the dirtiness threshold, a defect score is generated in combination with the temperature distribution data of the hot spot area. If the defect score exceeds the defect threshold, a component defect alarm instruction is generated.

[0014] Preferably, in step S430, the deep cleaning process includes the following steps: Step S431: Determine the initial cleaning intensity level and the maximum allowed number of rounds based on the comprehensive score of dirtiness; Step S432: Control the cleaning robot to perform a single-round cleaning operation; Step S433: Immediately after cleaning is completed, detect the current dust concentration and calculate the dust concentration change rate of this round; Step S434: when the dust concentration change rate is greater than the attenuation threshold, the cleaning intensity level is lowered; when the dust concentration change rate is less than the minimum effective threshold, the cleaning intensity level and the cleaning rounds are increased; Step S435: Determine whether the current dust concentration meets the standard. If so, terminate the process; determine whether the cumulative rounds exceed the maximum allowed rounds. If not, return to step S432 to perform a new round of cleaning. If so, mark the stubborn dirt and terminate the process.

[0015] A second aspect of the present invention provides a photovoltaic module hot spot diagnosis and adaptive cleaning system, comprising: Rapid temperature measurement module: used to obtain real-time temperature distribution data on the surface of photovoltaic modules during the cleaning process of the cleaning robot; A temperature anomaly detection module is configured to identify suspected hot spot areas with temperature anomalies based on the temperature distribution data. Hot spot identification module: used to control the cleaning robot to move to the suspected hot spot area, and perform high-precision temperature scanning through the hot spot diagnosis module to confirm the location and range of the hot spot; Adaptive cleaning module: performs surface condition analysis on the identified hot spot areas and generates adaptive cleaning instructions based on the analysis results.

[0016] The photovoltaic module hot spot diagnosis and adaptive cleaning method and system provided by the present invention establish a detection basis by synchronously acquiring high-density temperature distribution data during the cleaning process; accurately capture suspected hot spot areas based on a dynamic temperature difference recognition algorithm; automatically complete high-precision hot spot positioning re-inspection through the equipment's return path; intelligently determine the cause of hot spots by integrating surface dust accumulation and temperature gradient characteristics; dynamically optimize cleaning instruction execution decisions using a closed-loop feedback mechanism; realize integrated cleaning and diagnostic functions in a single device to eliminate manual secondary checks; and ultimately significantly improve operation and maintenance response time and reduce misjudgment rates.

[0017] Furthermore, the present invention also achieves precise temperature measurement at the cell level by matching the spatial distribution of the temperature sensor array with the photovoltaic module structure, avoids mechanical wear through a non-contact acquisition mechanism, ensures high-quality temperature data acquisition in conjunction with the active stay strategy of the cell area, and ensures overall system compatibility through parameter adaptive design; divides the grid units based on the physical structure of the cell and calculates the adjacent temperature differences by correlating the electrical characteristics, locates continuous abnormal areas through regional growth clustering, and combines the dual dynamic threshold judgment mechanism to improve the sensitivity and anti-interference ability of hot spot detection; corrects the threshold in real time through electrical parameters and environmental parameters, and dynamically optimizes the detection sensitivity based on the historical temperature database and environmental parameters, thereby improving the robustness of hot spot detection and reducing the risk of omission; adapts to the non-uniform temperature field characteristics through temperature feature extraction rules, and optimizes the adjacent joints in combination with the electrical topology. The system definition and maximum value screening mechanism are used to improve the ability to capture local abnormal temperature rise and the sensitivity of identifying strong hot spots; the differentiated analysis capability is improved through the multi-mode temperature feature extraction mechanism, among which the maximum value method enhances the sensitivity of capturing high hot spots, the arithmetic average method ensures the stability of conventional detection, and the position weighted method optimizes the local hot spot positioning accuracy; the sub-centimeter level hot spot positioning capability is improved through the synergistic effect of high-precision infrared scanning and neural network recognition, and the contour accuracy and structural matching are enhanced by the boundary optimization algorithm combined with the physical structure constraints of the battery cell; the accuracy of dirt scoring is improved through the dual-mode analysis mechanism of laser gray measurement and visible light images, combined with the fusion of historical data, and the ability to distinguish the causes of dirt and hot spot defects is improved; the efficiency and reliability of adaptive cleaning are improved through the dynamic two-way adjustment mechanism of intensity and rounds, combined with the upper limit constraint of rounds. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces 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 invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0019] Figure 1 A flow chart of a method for diagnosing and adaptively cleaning hot spots of photovoltaic modules according to an embodiment of the present invention; Figure 2 A flow chart of a method for real-time cleaning and rapid temperature measurement provided by one embodiment of the present invention; Figure 3 A flow chart of a method for identifying suspected hot spot areas provided by one embodiment of the present invention; Figure 4 A flow chart of a method for dynamically setting a threshold value provided by one embodiment of the present invention; Figure 5 A flow chart of a method for calculating the absolute value of temperature difference of a grid cell provided in one embodiment of the present invention; Figure 6 A flowchart of a high-precision scanning method for a hot spot diagnosis module provided by an embodiment of the present invention; Figure 7 A flow chart of a method for measuring hot spot areas using a surface analysis module according to an embodiment of the present invention; Figure 8 A flowchart of a deep cleaning method provided by one embodiment of the present invention; Figure 9 A schematic diagram showing the principle of a photovoltaic module hot spot diagnosis and adaptive cleaning system provided by one embodiment of the present invention; Figure 10 A schematic structural diagram of a photovoltaic module hot spot diagnosis and adaptive cleaning device provided in one embodiment of the present invention.

[0020] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] It should be noted that if the embodiments of the present invention involve directional indications, such as up, down, left, right, front, and back, the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0023] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme in which A and B are satisfied at the same time. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0024] Glossary: Hot spots: Solar panels are typically installed in open, sunny areas. Over long-term use, they are inevitably obstructed by objects such as birds, dust, and fallen leaves, casting shadows on the panels. Even in large arrays of solar panels with inappropriate row spacing, these can cast shadows on each other. Due to localized shadows, the current and voltage of certain cells in the solar panel change. This results in an increase in the product of the local current and voltage in the solar panel, causing a localized temperature rise in these cells. Defects in certain cells within the solar panel can also cause the panel to heat up locally during operation. This phenomenon is known as the "hot spot effect."

[0025] In view of this, the main purpose of the present invention is to propose a method and system for diagnosing and adaptively cleaning hot spots of photovoltaic modules, aiming to solve the technical problems of low accuracy and low operation and maintenance efficiency in the existing technology of hot spot diagnosis and adaptive cleaning of photovoltaic modules.

[0026] like Figures 1 to 8 As shown, the first aspect of the present invention provides a method for diagnosing and adaptively cleaning hot spots of photovoltaic modules, comprising: Step S100: During the cleaning process of the cleaning robot, the temperature distribution data on the surface of the photovoltaic module is obtained in real time through the rapid temperature measurement module; Step S200: identifying suspected hot spot areas with abnormal temperature differences based on the temperature distribution data; Step S300: Controlling the cleaning robot to move to the suspected hot spot area, and performing a high-precision temperature scan through the hot spot diagnosis module to confirm the location and range of the hot spot; Step S400: performing surface condition analysis on the identified hot spot area, and generating an adaptive cleaning instruction based on the analysis result.

[0027] For details, see Figure 1In one embodiment of the present invention, a flat-sweeping cleaning robot is used to implement a method for hot spot diagnosis and adaptive cleaning of photovoltaic modules. The robot comprises a walking mechanism straddling the photovoltaic module array, integrated with a front brush, a rapid temperature measurement module, a rear brush, and a movable hot spot diagnosis module. The front brush is wider than the rear brush to enhance pre-cleaning capabilities and provide the rapid temperature measurement module with a clean surface for the module. The rapid temperature measurement module, consisting of a linear array of closely spaced thermocouples, is fixedly mounted on a bracket between the front and rear brushes, slightly lower than the brushes to prevent direct friction with the module surface. The hot spot diagnosis module is linked to a drive motor via a connector, with its horizontal movement controlled by a top guide rail. It integrates a high-precision infrared temperature sensor and a laser dust sensor. Upon startup, the robot enters cleaning mode: it moves along the surface of the photovoltaic module to perform cleaning operations. Simultaneously, the rapid temperature measurement module continuously collects module surface temperature data at a preset frequency and transmits it to a processor in real time. The processor generates a temperature distribution map based on the sensor positions and robot displacement data. Using a dynamic threshold algorithm, the processor identifies and caches the coordinates of suspected hot spot areas with excessive temperature differences. After the cleaning task is completed, it switches to inspection mode: the robot returns to the center of the first suspected hot spot area, the driving motor moves the hot spot diagnostic module along the guide rail to the target position, and starts the infrared temperature sensor to perform millimeter-level precision scanning to calibrate the hot spot boundary; then the laser ash measurement sensor is enabled to analyze the surface dust accumulation status of the hot spot, and the command is triggered according to the detection results: if the dust accumulation concentration exceeds the threshold, the boost cleaning command is triggered, and the brush pressure and cleaning frequency are automatically adjusted to perform deep cleaning; if the dust accumulation is normal but the temperature is abnormal, a component defect report is generated and uploaded to the monitoring center; when all suspicious areas are inspected and there are no new commands, the robot returns to the starting standby point.

[0028] As can be understood, this embodiment significantly improves diagnostic accuracy by employing a dual detection mechanism: a rapid temperature scan is performed in cleaning mode to initially screen out abnormal areas; a secondary verification is then performed in inspection mode using high-precision infrared temperature measurement, effectively overcoming the problem of misjudgment caused by ambient temperature fluctuations during the morning and evening hours. Furthermore, this embodiment integrates surface dust distribution characteristics with temperature gradient data to automatically distinguish between hot spots caused by dirt and those caused by cell defects, thereby reducing the need for manual on-site inspections and lowering maintenance labor costs. For dirty hot spots, this embodiment intelligently adjusts the cleaning intensity and frequency based on the rate of change in dust concentration, avoiding the waste of resources caused by fixed cleaning cycles and improving cleaning efficiency. Furthermore, this embodiment integrates cleaning and diagnostic functions into a single device, and automatically re-inspects abnormal areas during the device's return process, completely eliminating the manual secondary inspection required in traditional solutions and improving maintenance response time. It should be noted that this embodiment is only a preferred option, and the robots used to implement the photovoltaic module hot spot diagnosis and adaptive cleaning method are not limited to flat-sweeping robots. Other types of robots or intelligent maintenance equipment, such as track-mounted, wheeled, or drone-mounted inspection platforms, may also be used. Based on the above technical solutions, those skilled in the art can make corresponding equivalent improvements according to the application scenarios, for example: replacing the rapid temperature measurement module with a technical solution based on a non-contact infrared temperature sensor array to achieve contactless rapid scanning; or using a flexible thin film temperature sensor array attached to the brush surface for follow-up detection, which is suitable for the surface of wavy components; or replacing the hot spot diagnosis module with a multispectral imaging module to synchronously invert the temperature distribution and dust accumulation level through spectral data from visible light to thermal infrared bands; and also deploying a composite diagnosis module based on ultrasonic / electromagnetic non-destructive testing to scan and verify the internal defects of the battery in combination with the hot spot position.

[0029] Preferably, in step S100, the step of obtaining temperature distribution data on the surface of the photovoltaic module in real time by using the rapid temperature measurement module includes: Step S110: When the cleaning robot moves along the surface of the photovoltaic module, the temperature data of multiple locations on the surface of the photovoltaic module are synchronously collected at a preset sampling frequency through the multi-temperature sensor array on board; Step S120: Calculating the spatial coordinates of each temperature sampling point on the surface of the photovoltaic module according to the position distribution of the multi-temperature sensor array and the real-time displacement data of the robot; Step S130: Integrate the temperature values ​​corresponding to the spatial coordinates to generate a real-time two-dimensional temperature distribution map of the photovoltaic module surface.

[0030] For details, see Figure 2In one specific embodiment of the present invention, a multi-temperature sensor array is configured to suit the physical structure of the photovoltaic module. For example, for a standard 60-cell photovoltaic module (6x10 array, 1.65m x 1m in size), the multi-temperature sensor is configured as 18 closely spaced thermocouples arranged in a single horizontal row, fixed to the centerline of the bracket between the front and rear brushes. The array layout satisfies the following requirements: 18 thermocouples are evenly spaced in a single row across the width of the photovoltaic module; the lateral width of each cell corresponds to the monitoring area of ​​three consecutive thermocouples; the thermocouples are installed slightly below the brush working plane to minimize contact, and surface temperature information is indirectly obtained by measuring the air layer temperature at a slight distance above the module surface. As the robot moves, the displacement sensor records position information in real time, and each temperature acquisition point is mapped to the module's global coordinate system using a fixed offset. Furthermore, when the cleaning robot moves horizontally along the length of the component and enters a new cell area, it automatically slows down and stops. During the stop, temperature acquisition is performed synchronously through the three thermocouples that cover the cell horizontally. Three independent temperature samples are completed for a single cell area, and each sample contains three thermocouple data. At the same time, the displacement sensor records the position information in real time, and each temperature acquisition point is mapped to the component global coordinate system through a fixed offset. The representative temperature values ​​of 60 cells form a two-dimensional temperature distribution matrix on the component surface. It should be noted that the temperature acquisition frequency, the number of thermocouples, and the layout position of this embodiment can be adjusted according to the actual application scenario. For example, the number of sensors can be increased for large components, the sampling frequency can be increased in high wind speed scenarios, the thermocouple suspension height can be optimized for uneven installation surfaces to adapt to surface undulations, and special component layouts can be matched to the cell distribution characteristics by adjusting the lateral spacing.

[0031] It can be understood that this embodiment ensures that the spatial distribution of temperature sampling points corresponds to the physical position of the battery cell through the matching design of the temperature sensor array layout and the alignment of the component structure; and the non-contact mechanism based on air layer temperature measurement can effectively avoid mechanical wear on the sensor and the component surface, thereby extending the service life of the equipment; combined with the acquisition strategy of displacement synchronization mapping and active stay in the battery cell area, it is possible to obtain accurately positioned, low-interference temperature data sets during dynamic movement; at the same time, the temperature distribution matrix construction process is closely related to the battery cell structural unit, providing an accurate and reliable data basis for subsequent temperature difference analysis; through the flexible design of adaptively adjustable number of thermocouples and sampling frequency, the solution can adapt to the changing needs of components of different sizes, installation environments and operating conditions, thereby enhancing the overall adaptability of the system.

[0032] Preferably, in step S200, the step of identifying suspected hot spot areas with temperature abnormalities based on the temperature distribution data includes: Step S210: Based on the real-time two-dimensional temperature distribution map, the photovoltaic module cells are divided into grid units according to their physical structure, and each grid unit includes at least one temperature sampling point; Step S220: Calculate the absolute value of the temperature difference between each grid cell and its adjacent grid cells. If the difference exceeds a first threshold, mark the grid cell as a suspected abnormal cell. Step S230: spatially cluster adjacent suspected abnormal units to form a continuous cluster area; if the cluster area meets any of the following conditions, it is determined to be a suspected hot spot area: the absolute value of the maximum temperature difference in the area exceeds the second threshold, or the absolute value of the highest temperature in the area exceeds the safety threshold.

[0033] For details, see Figure 3 In a specific embodiment of the present invention, the grid units are divided according to the physical cell boundaries of the photovoltaic module, and a single grid unit corresponds to a cell area and its average temperature is used as the representative value; when calculating the temperature difference, the cell temperature values ​​of adjacent cells in the same row or column in the same cell string are preferentially compared. If the temperature difference with any adjacent cell exceeds a first threshold, it is marked as a suspected abnormal cell; when spatially clustering the marked cells, a regional growing algorithm is used to automatically merge directly adjacent abnormal cells starting from the first abnormal cell to form a temperature abnormality clustering area; when the absolute difference between the highest and lowest temperatures in the area exceeds a second threshold or the highest temperature of the area exceeds a preset safety threshold, it is determined to be a suspected hot spot area and its spatial boundary coordinates are recorded. It should be noted that the first threshold is typically 10°C, the second threshold is typically 20°C, and the safety threshold is typically 100°C, all of which can be dynamically adjusted based on real-time environmental parameters. Grid division can also employ an evenly spaced grid approach beyond cell boundaries, for example, subdividing each cell region into 2×2 or 3×3 subgrids to improve the accuracy of small-scale hot spot detection, or customizing a non-uniform grid based on the actual statistical characteristics of module failure distribution. In addition to using direct neighbor relationships, the regional clustering strategy can also optimize the definition of neighboring cells based on the series and parallel topology of the modules. All algorithms can be executed in real time on an embedded processor. The following example illustrates this: The embedded processor collects current irradiance, ambient temperature, and module operating current. When the irradiance falls below 500W / m², the first threshold is automatically lowered to 8°C and the second threshold to 15°C. When the ambient temperature exceeds 40°C, the threshold temperature rise compensation mechanism is activated. The regional clustering strategy optimizes the definition of neighbor relationships based on the module topology. For example, for series strings, the comparison prioritizes neighboring cells within the same string, while for parallel structures, both horizontal and vertical neighbors are compared.

[0034] It can be understood that this embodiment uses the physical structure alignment design of the cell-level grid units to closely link the temperature difference analysis with the electrical transmission characteristics of the photovoltaic modules; uses the regional growth clustering algorithm to efficiently locate continuous abnormal areas and avoid misjudgment of discrete points; the dual judgment mechanism combines the absolute temperature difference and the safe temperature rise threshold to significantly improve the sensitivity and reliability of hot spot identification; the dynamic threshold adjustment function adapts to the needs of complex environmental changes and ensures the robustness of detection under different working conditions; at the same time, the embedded real-time processing capability meets the requirements of online analysis of the equipment, providing effective target positioning for subsequent precise re-inspection.

[0035] Based on the above technical solutions, those skilled in the art can make corresponding equivalent improvements according to the application scenarios, for example: adjusting the grid unit division method to non-uniform partitioning, dynamically generating differentiated grid density according to the historical hot spot distribution probability of the component, and automatically encrypting the grid points in high-risk areas; or expanding the temperature field spatial clustering algorithm, using the maximum connected domain identification algorithm based on graph theory instead of the region growing method, and realizing cross-regional abnormality correlation analysis by constructing a temperature difference topology map of the battery cell; or introducing a lightweight convolutional neural network model, performing end-to-end hot spot area semantic segmentation on the real-time two-dimensional temperature distribution map, and directly outputting the abnormal area boundary and confidence score; for large-scale photovoltaic power station scenarios, the initial screening clustering algorithm can be run on the edge computing unit to identify suspected hot spot areas, and the temperature distribution data can be simultaneously uploaded to the cloud to perform complex model review and verification; in micro-component or mobile detection platform scenarios, the grid unit definition can be simplified, and the adjacent temperature difference comparison can be performed directly with a single battery cell as the minimum analysis unit, thereby improving the processing efficiency of the embedded system.

[0036] Preferably, the first threshold and the second threshold are dynamically set by the following steps: Step S231: collecting operating electrical parameters and environmental parameters of the target photovoltaic module in real time, wherein the operating electrical parameters include operating current and operating voltage, and the environmental parameters include irradiance and ambient temperature; Step S232: generating an electrical parameter correction coefficient according to the deviation between the operating electrical parameter and the rated electrical parameter; Step S233: determining a temperature reference value based on the matching result between the ambient temperature and the historical temperature database, and generating an environmental correction coefficient in combination with the real-time irradiance; Step S234: matching a reference threshold from a preset database according to the target PV module model, and dynamically adjusting the electrical parameter correction coefficient and the environmental correction coefficient to generate a first threshold; Step S235: Based on the first threshold and the preset level difference ratio, generate a second threshold that is greater than the first threshold.

[0037] For details, see Figure 4In a specific embodiment of the present invention, the system monitors the output current and voltage of photovoltaic modules in real time and simultaneously reads the values ​​of the ambient irradiance sensor and the atmospheric temperature sensor. When the operating current falls below 15% of the rated value, an electrical parameter correction coefficient K1 = 1.2 is generated; when the voltage fluctuation exceeds ±5%, K1 = 1.1 is generated. Based on the current ambient temperature, a historical database for the same season is searched to match similar operating temperature benchmarks. When the real-time irradiance falls below 800W / m², an environmental correction coefficient K2 = 0.8 is generated. The first threshold, based on the module model matching benchmark, is 10°C. After correction calculation, the first threshold is adjusted to 10 × K1 × K2 = 8.4°C. The second threshold is calculated based on a preset 1.8 times differential ratio and adjusted to 8.4 × 1.8 = 15°C. The safety threshold is fixed at 100°C. It should be noted that the dynamic threshold setting process is automatically executed by an embedded processor. The database supports real-time expansion and updating. The differential ratio can be adaptively adjusted based on the module degradation level. The baseline threshold can be optimized and iterated based on actual power plant operating data.

[0038] It can be understood that this embodiment corrects the threshold through multi-dimensional parameter fusion to overcome the detection blind spots of fixed thresholds that cannot adapt to low-irradiation and aging components; the ambient temperature benchmark matching based on the historical database can improve the detection robustness during the dawn and dusk periods; through the dynamic correction mechanism of electrical parameters, abnormal operating conditions of components can be effectively identified to avoid misjudgment of temperature differences caused by sudden current drops; the differential ratio can be adapted according to the life attenuation characteristics of the components, and global protection can be performed through safety thresholds to ensure zero omissions of high-risk hot spots.

[0039] Based on the above technical solution, those skilled in the art can make corresponding equivalent improvements according to the application scenario, for example: changing the linear superposition calculation of the electrical parameter correction coefficient and the environmental correction coefficient to a nonlinear combination algorithm, and generating a comprehensive correction factor by fusing the current attenuation trend and the irradiance change rate through a polynomial fitting model; or using an end-to-end deep neural network model to replace the traditional calculation steps, inputting real-time current, voltage, irradiance, ambient temperature and historical database characteristics, and directly outputting the dynamically adjusted first threshold and second threshold; in newly built power stations that lack a historical database, the standard deviation of the temperatures of adjacent components can be used as an alternative calculation basis for the temperature reference value; in scenarios where the temperature gradient distribution of components is obvious, the step ratio can be set as a function of the median of the regional temperature difference to achieve adaptive adjustment.

[0040] Preferably, in step S220, the step of calculating the absolute value of the temperature difference between each grid unit and the adjacent grid units includes: Step S221: determining a set of adjacent grid cells of the current grid cell according to the physical structure of the target photovoltaic module cell; Step S222: generating a representative temperature value of the current grid cell based on a preset temperature feature extraction rule; Step S223: Calculate the absolute value of the difference between the current grid cell representative temperature value and the representative temperature value of each adjacent grid cell; Step S224: selecting the maximum value among the absolute values ​​of the differences as the absolute value of the temperature difference between the current grid unit and the adjacent grid unit.

[0041] For details, see Figure 5 In a specific embodiment of the present invention, the temperature difference calculation process is illustrated using the aforementioned standard 60-cell photovoltaic module and a single-row configuration of 18 thermocouples. Grid cells are divided based on individual cells, and the representative temperature value of the current cell is the arithmetic mean of nine temperature points, obtained from three independent samplings of data from the three thermocouples covering that cell during their dwell period. The set of adjacent grid cells is defined, based on the module's electrical topology, as cells directly electrically connected to the current cell, including the previous and next cells in the same column of the same cell string, as well as the previous and next cells in adjacent cell strings in the same row. The calculation first determines the representative temperature values ​​of all adjacent cells to the current cell, then calculates the absolute value of the difference between the current cell temperature and each adjacent cell temperature, selecting the maximum value as the final absolute temperature difference value. For example, the adjacent cells of the cell in row 3, column 2 are defined as the cells in row 2, column 2, row 4, column 2, row 3, column 1, and row 3, column 3. The temperature difference calculation takes the maximum value of the difference between the current cell temperature and these four adjacent cells. It should be noted that the definition of adjacent relationships can be extended to diagonal cells and other cells that have direct electrical connections or spatial heat conduction associations with the current cell.

[0042] It can be understood that this embodiment can effectively capture the characteristics of local abnormal temperature rise through focused analysis of representative temperature values ​​at the cell level; avoid the influence of weak interference in the neighborhood through the maximum temperature difference screening mechanism, and improve the sensitivity of strong hot spot identification; adapt to non-uniform temperature field scenarios through representative value extraction rules to improve scalability; and be compatible with multi-scale spatial correlation analysis requirements through adjacent relationship definitions. Based on the above technical solutions, those skilled in the art can make corresponding equivalent improvements according to the application scenarios, for example: adjust the definition of adjacent units to a composite relationship based on the electrical path and the heat conduction path, and generate a dynamic adjacent weight coefficient matrix through a finite element analysis model; or introduce a transfer learning mechanism to train the temperature propagation feature model based on historical hot spot data to generate customized adjacent unit sets for cells in different positions; simplify to the spatial distance priority principle in the micro-component scenario, and only calculate the spatially adjacent cells in the same row and column; for photovoltaic building integrated components with serious backplane heat accumulation, expand to diagonal units and assign higher weights; for special scenarios with abnormally uniform thermal field distribution, skip the adjacent temperature difference calculation and directly detect the absolute temperature exceeding the threshold area; and use graph neural networks to model the temperature correlation of cell cells, and automatically learn the optimal adjacent relationship judgment rules through node embedding features.

[0043] Preferably, in step S222, the temperature feature extraction rule is set to extract a representative temperature value from the grid unit temperature data, and its implementation method includes extracting the highest temperature value of all temperature sampling points, or calculating the arithmetic average temperature value of all temperature sampling points, or calculating the weighted average temperature value based on the position weight.

[0044] Specifically, in a specific embodiment of the present invention, taking the above-mentioned standard 60-cell photovoltaic module and the configuration of 18 thermocouples in a single row as an example, three representative temperature value calculation methods are respectively described. For the cell unit in the 3rd row and 2nd column, 9 temperature sampling points are obtained, which are 32.1°C, 31.8°C, 32.3°C, 33.5°C, 33.9°C, 33.2°C, 32.7°C, 34.1°C, and 33.6°C. When the highest temperature value rule is adopted, the maximum value of 34.1°C among the sampling points is directly extracted as the representative value; when the arithmetic average rule is adopted, the sum of the 9 temperature values ​​287.2°C is divided by 9 to obtain the average value of 31.91°C, and 31.9°C is rounded off as the representative temperature value; under the weighted average temperature value calculation method based on position weight, the system assigns a weight of 1.2 to the three sampling points of 33.5°C, 33.9°C, and 34.1°C in the center area, and the remaining edge points are assigned a weight of 1.2. The six sampling points in the edge region are assigned a weight of 0.8. The calculation process is (33.5 × 1.2 + 33.9 × 1.2 + 34.1 × 1.2) + (32.1 × 0.8 + 31.8 × 0.8 + 32.3 × 0.8 + 33.2 × 0.8 + 32.7 × 0.8 + 33.6 × 0.8) = 278.36. Dividing this by the total weight (3 × 1.2 + 6 × 0.8 = 8.4) yields 33.14°C as the final representative temperature. It should be noted that the system can automatically switch or combine the above temperature extraction rules based on component status. The maximum temperature extraction method is suitable for inspecting old components with localized strong hot spots on the surface. The arithmetic average temperature extraction method is suitable for routine inspection of new components with uniform temperature distribution. The location-weighted weighted average temperature extraction method is suitable for inspecting specific components with uneven temperature distribution.

[0045] It can be understood that this embodiment provides differentiated analysis strategies for different types of components through a multi-mode temperature feature extraction mechanism; maximum value extraction ensures sensitive capture of strong hotspots; arithmetic averaging ensures the stability of conventional detection; position weighting method optimizes the accuracy of local hotspot identification; the adaptive switching mechanism significantly improves the system's compatibility with different working conditions; the weight allocation rules can be dynamically adjusted according to the component attenuation characteristics to continuously optimize the detection effectiveness.

[0046] Based on the above technical solution, those skilled in the art can make corresponding equivalent improvements according to the application scenario, for example: adding a backplane temperature weighting algorithm for bifacial power generation components and optimizing the weight distribution rules; or introducing a Gaussian mixture model to automatically identify the center point of the temperature distribution feature cluster; or defining the position weight as an inverse proportional function of the distance from the center of the battery cell; or using a convolutional neural network to directly extract feature vectors from the temperature distribution map instead of manual rules.

[0047] Preferably, in step S300, the step of performing a high-precision temperature scan by the hot spot diagnosis module to confirm the location and range of the hot spot includes: Step S310: Controlling the cleaning robot to move to the suspected hot spot area, wherein the hot spot diagnosis module includes an infrared temperature sensor; Step S320: performing a high-precision temperature scan using the infrared temperature sensor, inputting the temperature field distribution data obtained by the scan into a pre-trained hot spot recognition neural network model to generate a hot spot probability distribution map; Step S330: integrating the physical structure information of the photovoltaic module cell, performing boundary optimization processing on the hot spot probability distribution map, and outputting the geometric center coordinates and physical boundary polygons of the hot spot.

[0048] For details, see Figure 6 In a specific embodiment of the present invention, after the cleaning robot returns to the center point of the suspected hot spot area, the driving motor controls the hot spot diagnosis module to move along the guide rail to the target position; the high-precision infrared temperature sensor is started to scan the target area with millimeter-level resolution to obtain temperature field distribution data; the scanning process performs high-density dot matrix temperature measurement along the horizontal and vertical directions of the component surface, and the collected temperature field distribution data is input into the hot spot recognition neural network model preloaded in the embedded processor; the model adopts a lightweight convolutional neural network architecture, with the original temperature matrix as input and the hot spot probability distribution map of the same resolution as the output; the processor then loads the physical structure parameters of the component battery cell and performs morphological boundary optimization on the hot spot probability distribution map according to the boundary position of the battery cell: first, the corrosion algorithm is applied to eliminate discrete noise points, and then the adjacent hot spot areas are connected by the expansion algorithm, and finally the hot spot boundary polygon is corrected along the edge of the battery cell; the output result is the coordinates of the geometric center point of the hot spot area and the minimum circumscribed polygon composed of a multi-vertex coordinate chain; the polygon is strictly aligned with the physical boundary of the battery cell to ensure that subsequent diagnostic operations accurately locate the target area. It should be noted that the neural network model is trained based on historical hot spot temperature field data and supports receiving cloud-based model updates through the system message center; the boundary optimization process can match battery cell structure templates of different sizes based on component models.

[0049] It can be understood that this embodiment achieves high-precision hot spot positioning through the collaboration of high-resolution infrared scanning and lightweight neural network; the sensor noise interference can be eliminated through the boundary optimization algorithm based on the cell structure; the boundary polygon output with strong physical structure constraints ensures that the hot spot contour conforms to the electrical structure characteristics of the component, thereby improving the accuracy of subsequent operations; the embedded processing architecture meets the needs of on-site real-time analysis, and provides a reliable spatial reference for subsequent dirt detection and defect determination. Based on the above technical solutions, those skilled in the art can make corresponding equivalent improvements according to the application scenario, for example: replacing the neural network model with a support vector machine decision model to improve the adaptability of small sample scenarios; or using a random forest algorithm to fuse visible light images and temperature features to generate a composite hot spot probability map; or adding a curved surface projection coordinate conversion module for curved surface components; or simplifying to fixed threshold segmentation instead of neural network reasoning in microprocessor scenarios; or optimizing the constraints of the hot spot boundary diffusion path based on the series and parallel relationship of components; or adapting the hot spot pattern recognition of new components through transfer learning technology; or introducing an attention mechanism to enhance the neural network's ability to capture tiny hot spots; or integrating a hot spot diffusion trend prediction model into boundary optimization.

[0050] Preferably, in step S400, the step of performing surface condition analysis on the confirmed hot spot area and generating an adaptive cleaning instruction based on the analysis result includes: Step S410: measuring the hot spot area through a surface analysis module to obtain surface dust distribution data; Step S420: Calculating a comprehensive dirtiness score based on the surface dust distribution data and the historical cleaning records of the hot spot area; Step S430: When the comprehensive score of the degree of dirtiness exceeds the dirtiness threshold, it is determined to be a hot spot caused by dirtiness, and the deep cleaning process is started; when the comprehensive score of the degree of dirtiness does not exceed the dirtiness threshold, a defect score is generated in combination with the temperature distribution data of the hot spot area. If the defect score exceeds the defect threshold, a component defect alarm instruction is generated.

[0051] For details, see Figure 7In a specific embodiment of the present invention, the surface analysis module adopts two implementation methods: a laser dust measurement sensor or a visible light image analysis system: the first method uses a laser dust measurement sensor to emit a near-infrared beam to the hot spot area, calculates the micron-level dust coverage density based on the reflection intensity and scattering characteristics, and generates a surface dust concentration distribution cloud map; the second method uses an ordinary visible light camera to capture a high-definition image of the hot spot area, analyzes the image grayscale distribution and texture characteristics based on a pre-trained dust accumulation recognition model, and outputs the proportion of dirt coverage area and the dust thickness level; the system integrates the real-time measured dust accumulation data and the dirt residue trend parameters of the area in the historical cleaning records, and calculates the comprehensive dirtiness score according to a weighted formula; when the score exceeds the dynamic dirtiness threshold, a boost cleaning instruction is triggered, and the brush pressure and cleaning frequency are automatically increased to perform deep cleaning; if the score does not exceed the threshold but the temperature of the area continues to be abnormal, a defect score is generated in combination with the temperature difference gradient of the adjacent grids, and a component defect alarm is uploaded for the area exceeding the defect threshold. It should be noted that the dirt threshold is set to a default value according to the component installation environment and can be adaptively optimized. The selection of the surface analysis module type does not affect the subsequent cleaning decision-making process, and the visible light image analysis solution can achieve real-time processing by deploying a lightweight model through the edge computing unit.

[0052] It can be understood that this embodiment adapts to different cost and accuracy requirements through a dual-mode surface state analysis mechanism. The laser gray measurement solution provides micron-level precision detection, and the visible light imaging solution uses existing hardware to reduce system costs. The dirt scoring model fused with historical data can dynamically optimize the cleaning decision threshold and improve system adaptability. The defect scoring mechanism effectively isolates the causes of dirt-type and defect-type hot spots, improving accuracy. Adaptive cleaning parameter adjustment achieves precise resource allocation, avoiding the waste of resources in traditional fixed-round cleaning. The modular design supports seamless switching of multiple detection technologies, improving system deployment flexibility. Based on the above technical solutions, those skilled in the art can make corresponding equivalent improvements according to the application scenario, for example: using multispectral imaging technology to simultaneously acquire reflectivity and thermal radiation data to generate a composite dirt score; or deploying the image analysis module on a cloud server for asynchronous processing in drone inspection scenarios; or combining acoustic wave resonance detection technology to quantify the degree of surface adhesion dirt; or introducing a cleaning decision model based on reinforcement learning to replace the fixed scoring rule; or adapting differentiated cleaning strategies through the dirt type recognition function; and adding a humidity compensation coefficient to correct the dirt score calculation model for high humidity environments.

[0053] Preferably, in step S430, the deep cleaning process includes the following steps: Step S431: Determine the initial cleaning intensity level and the maximum allowed number of rounds based on the comprehensive score of dirtiness; Step S432: Control the cleaning robot to perform a single-round cleaning operation; Step S433: Immediately after cleaning is completed, detect the current dust concentration and calculate the dust concentration change rate of this round; Step S434: when the dust concentration change rate is greater than the attenuation threshold, the cleaning intensity level is lowered; when the dust concentration change rate is less than the minimum effective threshold, the cleaning intensity level and the cleaning rounds are increased; Step S435: Determine whether the current dust concentration meets the standard. If so, terminate the process; determine whether the cumulative rounds exceed the maximum allowed rounds. If not, return to step S432 to perform a new round of cleaning. If so, mark the stubborn dirt and terminate the process.

[0054] For details, see Figure 8 In one embodiment of the present invention, the system sets initial cleaning parameters based on a comprehensive score of dirtiness. The following is an example setting: When the score is 75, the initial cleaning intensity is set to 130% of the standard pressure, and the maximum allowable rounds are set to 4. After the first round of cleaning, the dust concentration change rate is detected to be 40%, which is greater than the preset attenuation threshold of 30%, so the cleaning intensity level is reduced to 120%. After the second round of cleaning, the change rate is 18%, which is lower than the minimum effective threshold of 25%. At this time, the cleaning intensity is increased to 125% and the upper limit of the cleaning rounds is increased to 5. After the third round of cleaning, the concentration still does not meet the standard, but the cumulative number of rounds is less than the upper limit of 5 for 3 rounds, and the system returns to the fourth round of cleaning. After the fourth round, the concentration is retested and meets the standard, and the cleaning process is terminated. If the standard is still not met after the fifth round, because the upper limit of cleaning rounds has been reached after 5 cumulative rounds, the system will mark the current hot spot as stubborn dirt and upload an alarm message. It should be noted that the number of cleaning rounds does not increase indefinitely. Generally, an upper limit is set according to the actual working conditions of the photovoltaic modules. In this embodiment, after comprehensively considering the mechanical fatigue of the equipment and the operation and maintenance efficiency, the upper limit is set to 5 rounds.

[0055] It can be understood that this embodiment significantly improves the efficiency of deep cleaning while ensuring the safety of components through the dual adjustment mechanism of reducing intensity to prevent damage and increasing intensity to break stubborn stains; meets the needs of tackling different stains through the elastic expansion design of rounds; effectively prevents equipment from overload operation through the hard round upper limit constraint; optimizes cleaning parameters in real time through feedback to achieve a dynamic balance between energy consumption, timeliness and cleanliness, and ultimately achieves the goal of minimizing operation and maintenance costs. Based on the above technical solutions, those skilled in the art can make corresponding equivalent improvements according to the application scenario, for example: setting the round upper limit as a function of the working life of the battery cell, and dynamically relaxing the restriction range according to the aging degree of the component; or using a deep reinforcement learning model to dynamically generate a cleaning parameter combination instead of the empirical formula setting; or adding a motor temperature rise compensation algorithm to adjust the round upper limit in real time in a low-oxygen environment on the plateau.

[0056] See also Figure 9 The second aspect of the present invention provides a photovoltaic module hot spot diagnosis and adaptive cleaning system, comprising: Rapid temperature measurement module: used to obtain real-time temperature distribution data on the surface of photovoltaic modules during the cleaning process of the cleaning robot; A temperature anomaly detection module is configured to identify suspected hot spot areas with temperature anomalies based on the temperature distribution data. Hot spot identification module: used to control the cleaning robot to move to the suspected hot spot area, and perform high-precision temperature scanning through the hot spot diagnosis module to confirm the location and range of the hot spot; Adaptive cleaning module: performs surface condition analysis on the identified hot spot areas and generates adaptive cleaning instructions based on the analysis results.

[0057] The third aspect of the present invention also provides a storage medium, which stores a photovoltaic component hot spot diagnosis and adaptive cleaning processing program. When the photovoltaic component hot spot diagnosis and adaptive cleaning program is executed by a processor, the photovoltaic component hot spot diagnosis and adaptive cleaning steps as described in any of the above embodiments are implemented.

[0058] See also Figure 10 The fourth aspect of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the photovoltaic module hot spot diagnosis and adaptive cleaning method as described in any embodiment of the first aspect when executing the computer program.

[0059] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor serves as the control center for the photovoltaic module hot spot diagnosis and adaptive cleaning system, and utilizes various interfaces and lines to connect the various parts of the processing and operational devices of the entire photovoltaic module hot spot diagnosis and adaptive cleaning system.

[0060] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the photovoltaic module hot spot diagnosis and adaptive cleaning system by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0061] Compared with the prior art, the beneficial effects of the present invention include at least: The photovoltaic module hot spot diagnosis and adaptive cleaning method and system provided by the present invention establish a detection basis by synchronously acquiring high-density temperature distribution data during the cleaning process; accurately capture suspected hot spot areas based on a dynamic temperature difference recognition algorithm; automatically complete high-precision hot spot positioning re-inspection through the equipment's return path; intelligently determine the cause of hot spots by integrating surface dust accumulation and temperature gradient characteristics; dynamically optimize cleaning instruction execution decisions using a closed-loop feedback mechanism; realize integrated cleaning and diagnostic functions in a single device to eliminate manual secondary checks; and ultimately significantly improve operation and maintenance response time and reduce misjudgment rates.

[0062] Furthermore, the present invention also achieves precise temperature measurement at the cell level by matching the spatial distribution of the temperature sensor array with the photovoltaic module structure, avoids mechanical wear through a non-contact acquisition mechanism, ensures high-quality temperature data acquisition in conjunction with the active stay strategy of the cell area, and ensures overall system compatibility through parameter adaptive design; divides the grid units based on the physical structure of the cell and calculates the adjacent temperature differences by correlating the electrical characteristics, locates continuous abnormal areas through regional growth clustering, and combines the dual dynamic threshold judgment mechanism to improve the sensitivity and anti-interference ability of hot spot detection; corrects the threshold in real time through electrical parameters and environmental parameters, and dynamically optimizes the detection sensitivity based on the historical temperature database and environmental parameters, thereby improving the robustness of hot spot detection and reducing the risk of omission; adapts to the non-uniform temperature field characteristics through temperature feature extraction rules, and optimizes the adjacent joints in combination with the electrical topology. The system definition and maximum value screening mechanism are used to improve the ability to capture local abnormal temperature rise and the sensitivity of identifying strong hot spots; the differentiated analysis capability is improved through the multi-mode temperature feature extraction mechanism, among which the maximum value method enhances the sensitivity of capturing high hot spots, the arithmetic average method ensures the stability of conventional detection, and the position weighted method optimizes the local hot spot positioning accuracy; the sub-centimeter level hot spot positioning capability is improved through the synergistic effect of high-precision infrared scanning and neural network recognition, and the contour accuracy and structural matching are enhanced by the boundary optimization algorithm combined with the physical structure constraints of the battery cell; the accuracy of dirt scoring is improved through the dual-mode analysis mechanism of laser gray measurement and visible light images, combined with the fusion of historical data, and the ability to distinguish the causes of dirt and hot spot defects is improved; the efficiency and reliability of adaptive cleaning are improved through the dynamic two-way adjustment mechanism of intensity and rounds, combined with the upper limit constraint of rounds.

[0063] The above-described embodiments merely represent several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that, for those skilled in the art, without departing from the concept of the present invention, several variations and improvements can be made, and equivalent structural transformations made using the contents of the present invention's description and drawings, or direct / indirect application in other related technical fields are all included within the scope of the present invention's patent protection. Therefore, the scope of protection of the present invention's patent shall be based on the appended claims.

[0064] It should be noted that, in the present invention, the embodiments implemented by the photovoltaic module hot spot diagnosis and adaptive cleaning system can be cross-referenced with the embodiments implemented by the photovoltaic module hot spot diagnosis and adaptive cleaning method, and the present invention will not elaborate on them one by one.

[0065] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for diagnosing and adaptively cleaning hot spots of photovoltaic modules, characterized in that: include: Step S100: During the cleaning process of the cleaning robot, the temperature distribution data on the surface of the photovoltaic module is obtained in real time through the rapid temperature measurement module; Step S200: identifying suspected hot spot areas with abnormal temperature differences based on the temperature distribution data; Step S300: Controlling the cleaning robot to move to the suspected hot spot area, and performing a high-precision temperature scan through the hot spot diagnosis module to confirm the location and range of the hot spot; Step S400: performing surface condition analysis on the identified hot spot area, and generating an adaptive cleaning instruction based on the analysis result.

2. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to claim 1, characterized in that: In step S100, the step of obtaining temperature distribution data on the surface of the photovoltaic module in real time by using the rapid temperature measurement module includes: Step S110: When the cleaning robot moves along the surface of the photovoltaic module, the temperature data of multiple locations on the surface of the photovoltaic module are synchronously collected at a preset sampling frequency through the multi-temperature sensor array on board; Step S120: Calculating the spatial coordinates of each temperature sampling point on the surface of the photovoltaic module according to the position distribution of the multi-temperature sensor array and the real-time displacement data of the robot; Step S130: Integrate the temperature values ​​corresponding to the spatial coordinates to generate a real-time two-dimensional temperature distribution map of the photovoltaic module surface.

3. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to claim 2, characterized in that: In step S200, the step of identifying suspected hot spot areas with temperature abnormalities based on the temperature distribution data includes: Step S210: Based on the real-time two-dimensional temperature distribution map, the photovoltaic module cells are divided into grid units according to their physical structure, and each grid unit includes at least one temperature sampling point; Step S220: Calculate the absolute value of the temperature difference between each grid cell and its adjacent grid cells. If the difference exceeds a first threshold, mark the grid cell as a suspected abnormal cell. Step S230: spatially cluster adjacent suspected abnormal units to form a continuous cluster area; if the cluster area meets any of the following conditions, it is determined to be a suspected hot spot area: the absolute value of the maximum temperature difference in the area exceeds the second threshold, or the absolute value of the highest temperature in the area exceeds the safety threshold.

4. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to claim 3, characterized in that: The first threshold and the second threshold are dynamically set by the following steps: Step S231: collecting operating electrical parameters and environmental parameters of the target photovoltaic module in real time, wherein the operating electrical parameters include operating current and operating voltage, and the environmental parameters include irradiance and ambient temperature; Step S232: generating an electrical parameter correction coefficient according to the deviation between the operating electrical parameter and the rated electrical parameter; Step S233: determining a temperature reference value based on the matching result between the ambient temperature and the historical temperature database, and generating an environmental correction coefficient in combination with the real-time irradiance; Step S234: matching a reference threshold from a preset database according to the target PV module model, and dynamically adjusting the electrical parameter correction coefficient and the environmental correction coefficient to generate a first threshold; Step S235: Based on the first threshold and the preset level difference ratio, generate a second threshold that is greater than the first threshold.

5. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to claim 3, characterized in that: In step S220, the step of calculating the absolute value of the temperature difference between each grid unit and the adjacent grid units includes: Step S221: determining a set of adjacent grid cells of the current grid cell according to the physical structure of the target photovoltaic module cell; Step S222: generating a representative temperature value of the current grid cell based on a preset temperature feature extraction rule; Step S223: Calculate the absolute value of the difference between the current grid cell representative temperature value and the representative temperature value of each adjacent grid cell; Step S224: selecting the maximum value among the absolute values ​​of the differences as the absolute value of the temperature difference between the current grid unit and the adjacent grid unit.

6. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to claim 5, characterized in that: In step S222, the temperature feature extraction rule is set to extract a representative temperature value from the grid unit temperature data, and its implementation method includes extracting the highest temperature value of all temperature sampling points, or calculating the arithmetic average temperature value of all temperature sampling points, or calculating the weighted average temperature value based on the position weight.

7. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to any one of claims 1 to 6, characterized in that: In step S300, the step of performing a high-precision temperature scan by the hot spot diagnosis module to confirm the location and range of the hot spot includes: Step S310: Controlling the cleaning robot to move to the suspected hot spot area, wherein the hot spot diagnosis module includes an infrared temperature sensor; Step S320: performing a high-precision temperature scan using the infrared temperature sensor, inputting the temperature field distribution data obtained by the scan into a pre-trained hot spot recognition neural network model to generate a hot spot probability distribution map; Step S330: integrating the physical structure information of the photovoltaic module cell, performing boundary optimization processing on the hot spot probability distribution map, and outputting the geometric center coordinates and physical boundary polygons of the hot spot.

8. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to any one of claims 1 to 6, characterized in that: In step S400, the step of performing surface condition analysis on the identified hot spot area and generating an adaptive cleaning instruction based on the analysis result includes: Step S410: measuring the hot spot area through a surface analysis module to obtain surface dust distribution data; Step S420: Calculating a comprehensive dirtiness score based on the surface dust distribution data and the historical cleaning records of the hot spot area; Step S430: When the comprehensive score of the degree of dirtiness exceeds the dirtiness threshold, it is determined to be a hot spot caused by dirtiness, and the deep cleaning process is started; when the comprehensive score of the degree of dirtiness does not exceed the dirtiness threshold, a defect score is generated in combination with the temperature distribution data of the hot spot area. If the defect score exceeds the defect threshold, a component defect alarm instruction is generated.

9. The photovoltaic module hot spot diagnosis and adaptive cleaning method according to claim 8, characterized in that: In step S430, the deep cleaning process includes the following steps: Step S431: Determine the initial cleaning intensity level and the maximum allowed number of rounds based on the comprehensive score of dirtiness; Step S432: Control the cleaning robot to perform a single-round cleaning operation; Step S433: Immediately after cleaning is completed, detect the current dust concentration and calculate the dust concentration change rate of this round; Step S434: when the dust concentration change rate is greater than the attenuation threshold, the cleaning intensity level is lowered; when the dust concentration change rate is less than the minimum effective threshold, the cleaning intensity level and the cleaning rounds are increased; Step S435: Determine whether the current dust concentration meets the standard. If so, terminate the process; determine whether the cumulative rounds exceed the maximum allowed rounds. If not, return to step S432 to perform a new round of cleaning. If so, mark the stubborn dirt and terminate the process.

10. A photovoltaic module hot spot diagnosis and adaptive cleaning system, characterized in that: include: Rapid temperature measurement module: used to obtain real-time temperature distribution data on the surface of photovoltaic modules during the cleaning process of the cleaning robot; A temperature anomaly detection module is configured to identify suspected hot spot areas with temperature anomalies based on the temperature distribution data. Hot spot identification module: used to control the cleaning robot to move to the suspected hot spot area, and perform high-precision temperature scanning through the hot spot diagnosis module to confirm the location and range of the hot spot; Adaptive cleaning module: performs surface condition analysis on the identified hot spot areas and generates adaptive cleaning instructions based on the analysis results.

Images