A solar power generation optimization control system, method and photovoltaic module
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHONGSHAN JINYU NEW ENERGY TECH CO LTD
- Filing Date
- 2026-03-06
- Publication Date
- 2026-06-19
Smart Images
Figure CN122247322A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of photovoltaic power generation technology, and in particular to a solar power generation optimization control system, method, and photovoltaic module. Background Technology
[0002] Solar photovoltaic (PV) power generation systems are widely used in centralized power plants, distributed rooftops, and photovoltaic agriculture due to their clean energy attributes. During long-term outdoor operation, PV modules inevitably accumulate various contaminants such as dust, sand, bird droppings, oil, water stains, and salt spray crystals on their surfaces. This leads to decreased incident light transmittance, increased localized shading, and temperature variations in the modules, resulting in power output degradation and even reliability risks such as hot spots. To improve power generation efficiency and reduce operation and maintenance costs, the industry typically requires periodic or on-demand cleaning of PV modules, with careful consideration given to the appropriate timing of cleaning.
[0003] In existing technologies, the identification of when to clean photovoltaic modules typically relies on the following methods: First, based on threshold judgments of power generation or equivalent performance ratio, cleaning is triggered by comparing the deviation between actual and theoretical output; second, based on empirical rules triggered by external environmental conditions such as weather, sandstorms, or rainfall; third, using visible light cameras, drone inspections, etc., to collect images of the module surface during the day, and estimating the degree of contamination through image recognition or manual interpretation. While these methods have some effectiveness in engineering applications, they still have significant limitations.
[0004] First, the method of determining power generation deviation is significantly affected by factors such as module temperature, irradiance fluctuations, inverter efficiency, shading, and grid-connected power curtailment, making it difficult to effectively decouple power attenuation from the impact of contamination. This results in insufficient accuracy of cleaning triggering, easily leading to false or missed triggers. Second, experience-based triggering based on environmental conditions fails to reflect the actual differences in contamination distribution on the module surface, often only providing coarse-grained cleaning suggestions, making it difficult to further achieve fine control of cleaning intensity. Third, existing daytime image detection solutions are highly dependent on natural lighting conditions, affected by changes in solar altitude angle, cloud cover, glare / specular reflection, and shadow occlusion, resulting in insufficient image contrast and feature stability. Under strong reflective or weak lighting conditions, the distinction between contaminated and clean areas decreases, and different types of contamination show significant differences in visible light performance, easily leading to poor robustness in contamination identification. Especially when there is light, uniform dust, localized water film, or smooth oil stains on the module surface, the imaging information under single daytime lighting conditions is often insufficient to support a detailed assessment of the degree of contamination, making it difficult to reliably determine the timing and intensity of cleaning.
[0005] Furthermore, existing technologies often lack effective mechanisms for evaluating the reliability of contamination identification results. Some solutions output contamination levels based solely on image features under a single frame or illumination condition, failing to perform consistency verification and reliability quantification of the identification results. This results in uncertainties in the evaluation results being difficult to expose in a timely manner under complex lighting or contamination scenarios, thus affecting the stability of cleaning decisions. Summary of the Invention
[0006] To this end, the present invention provides a solar power generation optimization control system, method and photovoltaic module, which can actively construct a controllable lighting environment under low ambient light conditions at night, enhance the difference of dirt characteristics through imaging response under various lighting conditions, and establish a dirt level and reliability assessment mechanism on this basis, so as to further realize the solar power generation optimization control scheme for determining cleaning timing and controlling operation dosage, thereby improving the accuracy of dirt identification and the reliability of cleaning decisions.
[0007] To achieve the above objectives, in a first aspect, the present invention provides a solar power generation optimization control system, which includes an illuminance monitoring module, a structured lighting module, an imaging acquisition module, an evaluation control module, and a cleaning operation mechanism. The illuminance monitoring module is used to detect ambient illuminance and output a night detection enable signal when the ambient illuminance is below a threshold. The structured lighting module is arranged facing the test surface of the photovoltaic module and is configured to sequentially project multiple lighting conditions onto the test surface when the night detection enable signal is valid. The imaging acquisition module is used to acquire surface response images of the test surface under the multiple lighting conditions respectively. The evaluation control module includes a processor and a memory, the memory storing instructions to complete the following processes when executed by the processor: Constructing fouling characteristic responses based on the response images of each surface; Based on the aforementioned fouling characteristic response, a fouling level index and a confidence index for the fouling level index are determined. In response to the credibility index being qualified, the contamination level index is compared with the cleaning triggering criteria to determine the cleaning timing, and an operation control quantity is generated. The operation control quantity includes a start command and an operation dosage parameter, the operation dosage parameter being determined by the contamination level index. The cleaning operation mechanism is communicatively connected to the evaluation control module and is used to receive the operation control quantity and execute the cleaning operation. The soiling characteristic response at least characterizes: the distribution of brightness / reflection differences at the same spatial location under different lighting conditions, and the percentage of soiling coverage and the non-uniformity of soiling texture derived from the brightness / reflection difference distribution.
[0008] As a preferred technical solution for the solar power generation optimization control system, each lighting condition in the structured lighting module includes spectral parameters and incident direction parameters. The spectral parameters are used to define the emission band and / or correlated color temperature of the structured lighting module, and the multiple lighting conditions include at least two non-overlapping visible light emission bands and at least two different incident directions in combination.
[0009] As a preferred technical solution for the solar power generation optimization control system, the evaluation control module constructs a fouling feature response based on each surface response image, including: generating a difference map based on the surface response images under different lighting conditions; extracting a fouling mask based on the difference map; calculating the fouling coverage ratio based on the fouling mask; and calculating the fouling texture non-uniformity based on the grayscale dispersion within the fouling mask.
[0010] As a preferred technical solution for the solar power generation optimization control system, the reliability index is determined by the consistency between the contamination masks obtained under different lighting conditions, and the consistency includes at least the overlap coefficient and boundary offset of the contamination masks.
[0011] As a preferred technical solution for the solar power generation optimization control system, the evaluation control module is also configured to record lighting conditions that meet the reliability standards and generate suggestions for daytime pollution collection periods based on the lighting conditions.
[0012] As a preferred technical solution for the solar power generation optimization control system, the evaluation control module further includes the following steps before the reliability index is qualified: when the reliability index is unqualified, controlling the structured lighting module to adjust the irradiance parameters and / or incident direction parameters in the various lighting conditions, and controlling the imaging acquisition module to re-acquire the surface response image of the surface to be tested.
[0013] As a preferred technical solution for the solar power generation optimization control system, the operating dosage parameters include at least one of cleaning times, operating time, operating speed, spray supply, and scrubbing pressure, and the operating dosage parameters are determined by the mapping relationship between the dirt level index and the preset dosage.
[0014] As a preferred technical solution for the solar power generation optimization control system, the cleaning triggering criteria include a first triggering threshold and a second triggering threshold; when the dirt level index is not lower than the first triggering threshold, the cleaning timing is determined to be immediate cleaning; when the dirt level index is lower than the first triggering threshold and not lower than the second triggering threshold, the cleaning timing is determined to be scheduled cleaning within the effective period of the nighttime detection enable signal.
[0015] Secondly, the present invention provides a solar power generation optimization control method, applied to the solar power generation optimization control system described in any of the above-mentioned schemes, comprising: Detect ambient illuminance and output a night detection enable signal when ambient illuminance is below a threshold; In response to the night detection enable signal being valid, various lighting conditions are sequentially projected onto the test surface of the photovoltaic module; Surface response images of the surface under test were acquired under the various lighting conditions. Construct a dirt feature response based on the surface response images described above; Based on the aforementioned fouling characteristic response, a fouling level index and a confidence index for the fouling level index are determined. In response to the credibility index being qualified, the contamination level index is compared with the cleaning triggering criteria to determine the cleaning timing, and an operation control quantity is generated. The operation control quantity includes a start command and an operation dosage parameter, and the operation dosage parameter is determined by the contamination level index. The operation control quantity is sent to the cleaning operation organization so that the cleaning operation organization receives the operation control quantity and performs the cleaning operation; The aforementioned dirt feature response at least characterizes: the distribution of brightness / reflection differences at the same spatial location under different lighting conditions, and the proportion of dirt coverage and the non-uniformity of dirt texture derived from the brightness / reflection difference distribution.
[0016] Thirdly, the present invention also provides a photovoltaic module applied to the solar power generation optimization control system described in any of the above-mentioned schemes.
[0017] Compared with existing technologies, the advantages of this invention lie in the fact that by outputting a nighttime detection enable signal when the ambient illuminance is below a threshold, the structured lighting module is driven to sequentially project various lighting conditions onto the photovoltaic module's test surface, and the imaging acquisition module acquires the corresponding surface response images. The evaluation and control module constructs a fouling characteristic response based on the brightness / reflection difference distribution at the same spatial location under different lighting conditions, further obtaining fouling level indicators and reliability indicators. When the reliability indicator is qualified, the cleaning timing is determined, and an operational control quantity containing start-up instructions and operational dosage parameters is generated, thereby achieving closed-loop control at night. This significantly improves the discriminative power and stability of fouling identification, reduces misjudgments and missed judgments caused by daytime natural light fluctuations, glare, and shadows, makes cleaning decisions more reliable, and thus improves power generation efficiency and reduces resource consumption caused by unnecessary cleaning.
[0018] Furthermore, by introducing spectral parameters of emission band and / or correlated color temperature into various lighting conditions and combining them with different incident directions, different types of contamination can form differentiated surface responses under various conditions. This improves the robustness of contamination mask extraction, contamination coverage ratio, and contamination texture non-uniformity calculation, thereby making the contamination level index more detailed and applicable to a wider range of conditions.
[0019] Furthermore, by determining the reliability index based on the consistency of the contaminated mask under different lighting conditions, and adjusting the lighting conditions and re-acquiring images when the reliability is unqualified, the evaluation uncertainty caused by abnormal imaging conditions or local reflection interference can be actively avoided. At the same time, the contamination level index is bound to the preset dose mapping relationship to generate the operation dose parameter, so that the cleaning operation is changed from a fixed intensity to adaptive control according to the degree of contamination, taking into account both cleaning effect and operation cost.
[0020] Furthermore, the evaluation control module of the present invention is configured to record lighting conditions that meet the reliability standards, and generate suggestions for daytime pollution collection periods based on the lighting conditions, which can improve the accuracy of daytime pollution identification and effectively utilize... Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description
[0021] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.
[0022] Figure 1 This is a structural block diagram of the solar power generation optimization control system according to an embodiment of the present invention; Figure 2 This is a flowchart of the solar power generation optimization control method according to an embodiment of the present invention. Detailed Implementation
[0023] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.
[0024] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.
[0025] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0026] Please see Figure 1 As shown, this embodiment provides a solar power generation optimization control system, including an illuminance monitoring module, a structured lighting module, an imaging acquisition module, an evaluation control module, and a cleaning operation mechanism. The illuminance monitoring module is used to detect the ambient illuminance and output a night detection enable signal when the ambient illuminance is lower than a threshold. In this embodiment, the threshold is set to 50 lx. When the light intensity is lower than this value, the system will trigger the night detection mode. The threshold setting can be adjusted according to the actual application scenario. For example, for a photovoltaic power generation system in a cloudy or rainy urban environment, the threshold may be set to 40 lx or 60 lx. The structured lighting module is arranged facing the test surface of the photovoltaic module and is configured to sequentially project multiple lighting conditions onto the test surface when the night detection enable signal is valid. The imaging acquisition module is used to acquire surface response images of the test surface under the multiple lighting conditions respectively. The evaluation control module includes a processor and memory. The memory stores instructions to complete the following processes when executed by the processor: Constructing fouling characteristic responses based on the response images of each surface; Based on the response characteristics of fouling, determine the fouling level index and the reliability index of the fouling level index; In response to the credibility index being qualified, the contamination level index is compared with the cleaning triggering criteria to determine the cleaning timing and generate the operation control quantity. The operation control quantity includes the start command and the operation dosage parameter, which is determined by the contamination level index. The cleaning operation mechanism is connected to the assessment control module to receive the operation control quantity and execute the cleaning operation. The staining characteristic response at least characterizes: the distribution of brightness / reflection differences at the same spatial location under different lighting conditions, and the staining coverage ratio and staining texture non-uniformity derived from the brightness / reflection difference distribution.
[0027] Specifically, each of the various lighting conditions in a structured lighting module includes spectral parameters and incident direction parameters. The spectral parameters define the emission band and / or correlated color temperature of the structured lighting module, and the various lighting conditions include at least two non-overlapping visible light emission bands and at least two different combinations of incident directions. For ease of engineering implementation, without limiting the scope of protection, a set of example values can be provided for illustration: Band A: Green light band, main emission range 500–560nm; Band B: Red light band, main emission range 620–680nm; Direction 1: Angle of incidence approximately 25° (relative to the surface normal); Direction 2: Angle of incidence approximately 55° (relative to the surface normal); If an implementation path with relevant color temperature constraints is used, then: Color temperature 1: Approximately 3000K; Color temperature 2: Approximately 6500K; Furthermore, by combining different incident directions, variations can be achieved; the main emission zones can be ensured not to overlap through filtering / narrowband light sources with different emission channels. On the same test surface, different types of contamination exhibit different reflection and scattering behaviors under different wavelengths of illumination; simultaneously, different incident directions alter the relative proportions of specular and diffuse reflection components, thus making the brightness / reflection difference distribution between contaminated and clean areas more stable and separable. Therefore, by combining variations of at least two non-overlapping wavelengths and at least two incident directions, multi-dimensional surface responses can be obtained under active nighttime illumination conditions, which is beneficial for subsequent construction of contamination characteristic responses and improving the reliability of consistency evaluation.
[0028] Specifically, the evaluation control module constructs a dirt feature response based on each surface response image, including: generating a difference map based on the surface response images under different lighting conditions; extracting a dirt mask based on the difference map; calculating the dirt coverage ratio based on the dirt mask; and calculating the dirt texture non-uniformity based on the gray-level dispersion within the dirt mask. In one embodiment of the present invention, after the imaging acquisition module obtains surface response images under different lighting conditions, the evaluation control module constructs the dirt feature response according to the following steps.
[0029] The evaluation control module selects at least two surface response images from different lighting conditions, and calculates the difference map by subtracting the corresponding pixels to highlight the brightness / reflection differences of the same location under different lighting conditions.
[0030] In one example, the difference map is the absolute difference between the grayscale values of two images; that is, the absolute value of the grayscale difference between the two images is calculated for each pixel. The evaluation control module performs thresholding on the difference map, marking pixels with a difference value greater than or equal to the threshold as smudged pixels and the remaining pixels as unsmudged pixels, thus obtaining a smudge mask. In one example, the threshold can be set to 1.2 times the average value of the difference map; it can also be set to a pre-calibrated fixed value.
[0031] The evaluation control module counts the number of contaminated pixels in the contaminated mask and divides this number by the total number of valid pixels on the surface under test to obtain the contaminated coverage percentage. Contaminated coverage percentage = Number of contaminated pixels / Total number of valid pixels.
[0032] The evaluation control module extracts the corresponding set of gray values within the area marked as contaminated by the contamination mask, and calculates the dispersion of this set of gray values as the non-uniformity of the contamination texture. In one example, the dispersion is represented by the gray standard deviation; the larger the standard deviation, the more obvious the gray-level changes within the contaminated area, and the more non-uniform the texture.
[0033] Specifically, the reliability index is determined by the consistency between contaminated masks obtained under different lighting conditions. Consistency includes at least the overlap coefficient and boundary offset of the contaminated masks. Specifically, the evaluation control module selects at least two contaminated masks from different lighting conditions and calculates their overlap coefficient as part of the consistency. A higher overlap coefficient indicates more consistent contaminated areas under different conditions and more reliable results. In a simplified example, the overlap coefficient is the ratio of the intersection area to the union area of two contaminated masks; when there are more than two lighting conditions, the overlap coefficient can be calculated for multiple pairs of contaminated masks separately, and the average value can be taken as the overall overlap consistency result.
[0034] Meanwhile, the evaluation control module calculates boundary offsets as another part of the consistency assessment. Boundary offsets represent the magnitude of the positional deviation of the boundary of the contaminated area corresponding to different contaminated masks; a smaller offset indicates a more stable contaminated profile under different operating conditions. In a simplified example, the evaluation control module extracts the boundary of the contaminated area for each contaminated mask and calculates the average distance between the boundaries of two masks as the boundary offset. When there are more than two lighting conditions, the boundary offsets of multiple pairs of masks can also be averaged to obtain the overall boundary stability result.
[0035] In this embodiment, the evaluation control module combines the overlap coefficient and the boundary offset to generate a credibility index. For example, when the overlap coefficient is higher than the corresponding set value (0.50 to 0.70 in this embodiment) and the boundary offset is lower than the corresponding set value (5 to 12 pixels in this embodiment), the credibility index is deemed qualified; otherwise, the credibility index is deemed unqualified.
[0036] Specifically, the evaluation control module is also configured to record lighting conditions that meet the reliability standards and generate daytime pollution collection period suggestions based on these lighting conditions. In one embodiment, the evaluation control module evaluates natural light conditions during daytime periods. The evaluation includes at least: calculating the solar incidence direction based on time, site geographic information, and component installation tilt angle, and matching the calculated solar incidence direction with the incidence direction parameters of the reference lighting conditions; simultaneously, the evaluation control module performs an approximate matching of the spectral characteristics of natural light, characterized by correlated color temperature or equivalent spectral category, and judges consistency with the spectral parameters of the reference lighting conditions. When the incidence direction matching degree meets preset conditions and the spectral matching degree meets preset conditions, the evaluation control module outputs the corresponding time period as a daytime pollution collection period suggestion.
[0037] For example, when the incident direction parameter corresponding to the nighttime reliable lighting condition is "an incident direction of approximately 25° relative to the component normal" and the spectral parameter corresponds to "warmer color temperature lighting", the evaluation control module can recommend the time period during the daytime solar altitude angle and azimuth angle that makes the equivalent incident direction of sunlight on the component surface close to that incident direction, and prioritize the time window when the natural light color temperature is close to the warmer color temperature; thereby making the surface response image collected during the daytime closer to the imaging conditions under the nighttime reliable condition in terms of incident geometry and spectral distribution, reducing the fluctuations introduced by changes in the daytime incident angle, glare and reflection differences, and improving the consistency between the daytime dirt collection results and the nighttime evaluation results.
[0038] Specifically, the evaluation control module response before the credibility index is qualified also includes: when the credibility index is unqualified, controlling the structured lighting module to adjust the irradiance parameters and / or incident direction parameters in various lighting conditions, and controlling the imaging acquisition module to re-acquire the surface response image of the surface under test.
[0039] Specifically, the operational dosage parameters include at least one of the following: cleaning frequency, operation duration, operation speed, spray supply, and scrubbing pressure. These operational dosage parameters are determined through a mapping relationship between a soiling level index and a preset dosage. For example, in this embodiment, the operational dosage parameters are scrubbing pressure and operation duration. A mapping relationship is established between the percentage of soiled area and the operation duration, as well as a mapping relationship between scrubbing pressure and the unevenness of soiled texture. Both mapping relationships are positively correlated, and the appropriate parameters can be configured based on actual working conditions.
[0040] Specifically, the cleaning triggering criteria include a first trigger threshold and a second trigger threshold. When the soiling level index is not lower than the first trigger threshold, the cleaning timing is determined to be immediate cleaning. When the soiling level index is lower than the first trigger threshold but not lower than the second trigger threshold, the cleaning timing is determined to be scheduled cleaning during the effective period of the nighttime detection enable signal. It should be understood that the first trigger threshold is greater than the second trigger threshold (in this embodiment, both are thresholds for the percentage of soiled area in the soiling level index). The two can be determined by calibration based on the actual scenario. In this embodiment, the calibrated thresholds satisfy the following conditions: when the percentage of soiled area is greater than the first trigger threshold, the cleaning duration is greater than 1 hour; when it is lower than the first trigger threshold but not lower than the second trigger threshold, the cleaning duration is less than or equal to 1 hour. The first trigger threshold is 0.12, and the second trigger threshold is 0.03. Cleaning is not performed when the percentage of soiled area is lower than the second trigger threshold. The above settings facilitate the planning of cleaning paths and optimize cleaning allocation.
[0041] See Figure 2 As shown, this embodiment provides a solar power generation optimization control method, applied to any of the above-mentioned solar power generation optimization control systems, including: Step S1: Detect ambient illuminance and output a night detection enable signal when the ambient illuminance is below a threshold. Step S2: In response to the night detection enable signal being valid, various lighting conditions are sequentially projected onto the test surface of the photovoltaic module; Step S3: Acquire surface response images of the surface to be tested under various lighting conditions; Step S4: Construct the dirt feature response based on the response images of each surface; Step S5: Determine the fouling level index and the credibility index of the fouling level index based on the fouling characteristic response. Step S6: In response to the credibility index being qualified, the contamination level index is compared with the cleaning triggering criteria to determine the cleaning timing, and an operation control quantity is generated. The operation control quantity includes the start command and the operation dosage parameter, and the operation dosage parameter is determined by the contamination level index. Step S7: Send the work control quantity to the cleaning operation organization so that the cleaning operation organization receives the work control quantity and performs the cleaning operation; The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.
[0042] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention; various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A solar power generation optimization control system, characterized by, include: The illuminance monitoring module is used to detect ambient illuminance and output a night detection enable signal when the ambient illuminance is below a threshold. A structured lighting module is arranged to face the test surface of the photovoltaic module and is configured to sequentially project multiple lighting conditions onto the test surface when the night detection enable signal is valid; The imaging acquisition module is used to acquire surface response images of the surface to be tested under the various lighting conditions. The evaluation control module includes a processor and a memory, the memory storing instructions to complete the following processes when executed by the processor: Constructing fouling characteristic responses based on the response images of each surface; Based on the aforementioned fouling characteristic response, a fouling level index and a confidence index for the fouling level index are determined. In response to the credibility index being qualified, the contamination level index is compared with the cleaning triggering criteria to determine the cleaning timing and to generate a work control quantity, which includes a start command and a work dosage parameter, the work dosage parameter being determined by the contamination level index; The cleaning operation mechanism is communicatively connected to the evaluation and control module, and is used to receive the operation control quantity and perform cleaning operations; The soiling characteristic response at least characterizes: the distribution of brightness / reflection differences at the same spatial location under different lighting conditions, and the percentage of soiling coverage and the non-uniformity of soiling texture derived from the brightness / reflection difference distribution.
2. The solar power optimization control system of claim 1, wherein, Each of the multiple lighting conditions of the structured lighting module includes spectral parameters and incident direction parameters. The spectral parameters are used to define the emission band and / or correlated color temperature of the structured lighting module, and the multiple lighting conditions include at least two non-overlapping visible light emission bands and at least two different incident directions in combination.
3. The solar power generation optimization control system according to claim 1, characterized in that, The evaluation control module constructs a dirt feature response based on each surface response image, including: generating a difference map based on the surface response images under different lighting conditions; extracting a dirt mask based on the difference map; calculating the dirt coverage ratio based on the dirt mask; and calculating the dirt texture non-uniformity based on the grayscale dispersion within the dirt mask.
4. The solar power generation optimization control system according to claim 3, characterized in that, The reliability index is determined by the consistency between the contaminated masks obtained under different lighting conditions, and the consistency includes at least the overlap coefficient and boundary offset of the contaminated masks.
5. The solar power generation optimization control system according to claim 4, characterized in that, The assessment control module is also configured to record lighting conditions that meet the reliability standards and generate suggestions for daytime pollution collection periods based on the lighting conditions.
6. The solar power generation optimization control system according to claim 1, characterized in that, The evaluation control module further includes the following steps before the credibility index is qualified: when the credibility index is unqualified, controlling the structured lighting module to adjust the irradiance parameters and / or incident direction parameters in the various lighting conditions, and controlling the imaging acquisition module to re-acquire the surface response image of the surface to be tested.
7. The solar power generation optimization control system according to claim 6, characterized in that, The operational dosage parameters include at least one of the following: cleaning frequency, operation duration, operation speed, spray supply, and scrubbing pressure, and the operational dosage parameters are determined through the mapping relationship between the soiling level index and the preset dosage.
8. The solar power generation optimization control system according to claim 7, characterized in that, The cleaning triggering criteria include a first triggering threshold and a second triggering threshold; when the soiling level index is not lower than the first triggering threshold, the cleaning timing is determined to be immediate cleaning; When the soiling level index is lower than the first trigger threshold and not lower than the second trigger threshold, the cleaning time is determined to be the scheduled cleaning during the effective period of the night detection enable signal.
9. A method for optimizing control of solar power generation, characterized in that, The solar power generation optimization control system according to any one of claims 1-8 comprises: Detect ambient illuminance and output a night detection enable signal when ambient illuminance is below a threshold; In response to the night detection enable signal being valid, various lighting conditions are sequentially projected onto the test surface of the photovoltaic module; Surface response images of the surface under test were acquired under the various lighting conditions. Construct a dirt feature response based on the surface response images described above; Based on the aforementioned fouling characteristic response, a fouling level index and a confidence index for the fouling level index are determined. In response to the credibility index being qualified, the contamination level index is compared with the cleaning triggering criteria to determine the cleaning timing, and an operation control quantity is generated. The operation control quantity includes a start command and an operation dosage parameter, and the operation dosage parameter is determined by the contamination level index. The operation control quantity is sent to the cleaning operation organization so that the cleaning operation organization receives the operation control quantity and performs the cleaning operation; The aforementioned dirt feature response at least characterizes: the distribution of brightness / reflection differences at the same spatial location under different lighting conditions, and the proportion of dirt coverage and the non-uniformity of dirt texture derived from the brightness / reflection difference distribution.
10. A photovoltaic module, characterized in that, It is applied to the solar power generation optimization control system according to any one of claims 1-8.