Desert photovoltaic sand disaster monitoring method, device and equipment based on internet of things and medium

Abstract

The application relates to the technical field of equipment monitoring. By providing a desert photovoltaic sand damage monitoring method, device, equipment and medium based on the Internet of Things, the method comprises the following steps: dynamically detecting and processing the microorganism contamination characteristics of the surface of a photovoltaic module to generate microorganism contamination characteristic data; performing biological membrane identification processing through an AI classification model to generate contamination type labels and biological activity level data; performing corrosion risk assessment processing according to the contamination type labels and the biological activity level data to generate a corrosion risk index and a cleaning priority ranking result; performing directional cleaning and protection processing on the surface of the photovoltaic module to generate a cleaning completion signal; and performing cloud aggregation and trend prediction processing on the corrosion risk index and the cleaning effect data to generate a corrosion trend report and maintenance suggestions, so as to solve the problems of fragmented detection dimensions, static evaluation and lagging decision-making, and achieve the technical effects of improving biological membrane identification accuracy, dynamically quantifying microorganism corrosion risk and predicting the sand desert non-steady-state environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of device monitoring, in particular to a desert photovoltaic sand damage monitoring method, device and medium based on Internet of Things. BACKGROUND

[0002] With the large-scale construction of global desert photovoltaic power stations, photovoltaic modules are exposed to complex environments such as sandstorms, extreme temperature differences and microbial erosion for a long time, resulting in increasingly prominent problems of biological membrane pollution and chemical corrosion on the surface of the modules.

[0003] However, the related art has the following problems: single detection dimension, optical / electrochemical sensors working independently, unable to fuse multi-source data to accurately identify biological membranes; static corrosion risk assessment, ignoring spatial propagation and dynamic environment coupling effects, resulting in a deviation of the corrosion index from the actual situation; data-driven prediction capability lags behind, linear algorithms are difficult to adapt to the desert non-steady-state environment, and decision-making suggestions lag behind pollution evolution. SUMMARY

[0004] Therefore, it is necessary to provide a desert photovoltaic sand damage monitoring method, device and medium based on Internet of Things to solve the problems of fragmented detection dimension, static assessment and lagging decision-making, and to achieve the technical effects of improving biological membrane identification accuracy, dynamically quantifying microbial corrosion risk, and adapting to the prediction of the desert non-steady-state environment.

[0005] In a first aspect, the present application provides a desert photovoltaic sand damage monitoring method based on Internet of Things, which comprises:

[0006] dynamically detecting and processing the microbial pollution characteristics of the surface of the photovoltaic module to generate microbial pollution characteristic data;

[0007] based on the microbial pollution characteristic data, performing biological membrane identification processing through an AI classification model to generate pollution type labels and biological activity level data;

[0008] based on the pollution type labels and the biological activity level data, performing corrosion risk assessment processing to generate a corrosion risk index and a cleaning priority ranking result;

[0009] based on the cleaning priority ranking result, performing directional cleaning and protection processing on the surface of the photovoltaic module to generate a cleaning completion signal;

[0010] performing cloud aggregation and trend prediction processing on the corrosion risk index and the cleaning effect data to generate a corrosion trend report and maintenance suggestions.

[0011] Further, the corrosion risk index and the cleaning effect data are aggregated and trend prediction processing is performed on the cloud to generate a corrosion trend report and maintenance suggestions, including:

[0012] The corrosion risk index and cleaning effect data are subjected to noise filtering and missing value filling processing to generate cleaned corrosion time series data;

[0013] Based on the preset component number and timestamp, the cleaned corrosion time series data is subjected to multi-source alignment processing to generate a corrosion time series dataset associated with space and time;

[0014] The corrosion time series dataset is input into the trained long short-term memory neural network model to extract and process the periodic fluctuation characteristics of the component surface corrosion rate, generating corrosion trend prediction parameters;

[0015] Based on the corrosion trend prediction parameters, the collaborative maintenance time window of the multi-component area is dynamically planned to generate a corrosion trend report and maintenance suggestion including maintenance time, priority and resource allocation strategy.

[0016] Further, the corrosion time series dataset is input into the trained long short-term memory neural network model to extract and process the periodic fluctuation characteristics of the component surface corrosion rate, generating corrosion trend prediction parameters, including:

[0017] The corrosion time series dataset is subjected to time series segmentation processing, and based on the sandstorm occurrence period and microbial activity period, the time window is divided to generate multi-scale time series segments;

[0018] The multi-scale time series segments are input into the bidirectional long short-term memory neural network model to capture and process the forward and reverse time series dependency relationship, generating an initial time series feature vector;

[0019] Based on the attention mechanism, the initial time series feature vector is subjected to weight allocation processing to generate high-weight periodic fluctuation features;

[0020] The high-weight periodic fluctuation features and static environmental features are subjected to multi-scale fusion processing to generate corrosion trend prediction parameters.

[0021] Further, according to the pollution type label and biological activity level data, corrosion risk assessment processing is performed to generate corrosion risk index and cleaning priority ranking results, including:

[0022] The pollution type label and biological activity level data are subjected to multi-source data fusion processing to generate microbial pollution comprehensive evaluation data;

[0023] The microbial pollution comprehensive evaluation data is input into the trained corrosion risk assessment model to map the coupling relationship between the component surface corrosion rate and power attenuation, generating initial corrosion risk parameters;

[0024] Based on the spatial adjacency of the photovoltaic array and the environmental wind speed data, the initial corrosion risk parameters are subjected to propagation path analysis processing to generate dynamically adjusted corrosion risk index.

[0025] According to the corrosion risk index adjusted by the dynamic weight, a multi-objective optimization sorting process is performed on the contaminated area to generate a cleaning priority sorting result considering the cleaning efficiency and corrosion inhibition.

[0026] Further, based on the spatial adjacency of the photovoltaic array and the environmental wind speed data, an initial corrosion risk parameter is subjected to a propagation path analysis process to generate a corrosion risk index adjusted by a dynamic weight, including:

[0027] Based on the spatial layout topology relationship of the photovoltaic array and the component spacing data, a pollution propagation path topology network model is constructed to generate a pollution diffusion correlation degree parameter between components;

[0028] Combined with the environmental wind speed data, the pollution diffusion correlation degree parameter is subjected to a wind direction correction process to generate a wind speed weighted propagation probability matrix;

[0029] The initial corrosion risk parameter is input into the risk weighted propagation probability matrix, and the risk superposition effect of adjacent components is subjected to an iterative calculation process to generate a dynamic propagation risk weight;

[0030] Based on the dynamic propagation risk weight, the initial corrosion risk parameter is subjected to a multi-factor fusion process to generate a corrosion risk index adjusted by a dynamic weight.

[0031] Further, based on the cleaning priority sorting result, the surface of the photovoltaic component is subjected to directional cleaning and protection processing to generate a cleaning completion signal, including:

[0032] Based on the cleaning priority sorting result, the surface of the photovoltaic component in the high priority area is subjected to pre-wetting processing to generate a surface humidity compliance signal;

[0033] According to the surface humidity compliance signal, the directional cleaning device is started to perform high-pressure water mist gradient spraying processing on the target area to generate a preliminary cleaning signal;

[0034] Based on the preliminary cleaning signal, the surface of the cleaned component is subjected to a microbial inhibitor self-adaptive spraying process to generate a protection layer thickness parameter;

[0035] According to the protection layer thickness parameter, the uniformity of the inhibitor coverage is subjected to optical detection processing to generate a protection layer formation signal;

[0036] The preliminary cleaning signal and the protection layer formation signal are subjected to logical AND processing to generate a cleaning completion signal.

[0037] Further, the preliminary cleaning signal and the protection layer formation signal are subjected to logical AND processing to generate a cleaning completion signal, including:

[0038] The preliminary cleaning signal is subjected to a cleaning effect verification process, and a comparison analysis is performed based on the multispectral reflection data and a preset cleaning threshold to generate a cleaning standard compliance flag;

[0039] The protective layer formation signal is subjected to thickness and coverage abnormality detection processing to generate a protective layer qualification flag;

[0040] Based on the current environmental wind speed and sand concentration data, the cleaning standard compliance flag and the protective layer qualification flag are subjected to dynamic weight distribution processing to generate a weighted logic and condition parameter;

[0041] According to the weighted logic and condition parameter, the preliminary cleaning signal and the protective layer formation signal are subjected to multi-modal fusion judgment processing to generate a cleaning completion signal.

[0042] In a second aspect, the present application also provides a desert photovoltaic sand damage monitoring device based on the Internet of Things, which comprises:

[0043] A pollution dynamic detection module is configured to perform dynamic detection processing on the microbial pollution characteristics of the surface of the photovoltaic module to generate microbial pollution characteristic data;

[0044] An intelligent biofilm identification module is configured to perform biofilm identification processing on the microbial pollution characteristic data through an AI classification model to generate pollution type labels and bioactivity level data;

[0045] An erosion risk assessment module is configured to perform erosion risk assessment processing according to the pollution type labels and bioactivity level data to generate an erosion risk index and a cleaning priority ranking result;

[0046] An intelligent cleaning and protection module is configured to perform directional cleaning and protection processing on the surface of the photovoltaic module based on the cleaning priority ranking result to generate a cleaning completion signal;

[0047] A cloud prediction and optimization module is configured to perform cloud aggregation and trend prediction processing on the erosion risk index and cleaning effect data to generate an erosion trend report and maintenance recommendations.

[0048] In a third aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of any method of the first aspect of the present application when executing the computer program.

[0049] In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of any method of the first aspect of the present application.

[0050] The technical scheme provided by the application comprises the following technical effects: by providing a desert photovoltaic sand damage monitoring method, device, equipment and medium based on the Internet of Things, the method comprises: performing dynamic detection processing on the microorganism pollution characteristic of the surface of the photovoltaic module to generate microorganism pollution characteristic data; performing biological membrane identification processing on the microorganism pollution characteristic data based on the AI classification model to generate pollution type label and biological activity level data; performing corrosion risk assessment processing according to the pollution type label and the biological activity level data to generate a corrosion risk index and a cleaning priority ranking result; performing directional cleaning and protection processing on the surface of the photovoltaic module based on the cleaning priority ranking result to generate a cleaning completion signal; and performing cloud aggregation and trend prediction processing on the corrosion risk index and the cleaning effect data to generate a corrosion trend report and maintenance suggestions, so as to solve the problems of fragmented detection dimension, static evaluation and decision lag, and achieve the technical effects of improving biological membrane identification accuracy, dynamically quantifying microorganism corrosion risk, and predicting the non-steady-state environment of the desert. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0052] Figure 1 The flow chart of the desert photovoltaic sand damage monitoring method based on the Internet of Things in an embodiment of the application;

[0053] Figure 2 The structural diagram of the desert photovoltaic sand damage monitoring device based on the Internet of Things in an embodiment of the application. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the specific implementation modes of the application will be described in detail below with reference to the drawings. In the following description, many specific details are set forth in order to provide a thorough understanding of the application. However, the application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the spirit of the application, so the application is not limited by the specific embodiments disclosed below.

[0055] As Figure 1 shown, the application provides a desert photovoltaic sand damage monitoring method based on the Internet of Things, which comprises:

[0056] S101: performing dynamic detection processing on the microorganism pollution characteristic of the surface of the photovoltaic module to generate microorganism pollution characteristic data.

[0057] Specifically, real-time or periodic collection of microorganism contamination features on the surface of photovoltaic modules is performed using optical sensors (such as multispectral or hyperspectral imagers) and chemical sensors (such as pH sensors, organic acid detection probes), obtaining raw data such as spectral reflectance, chemical activity signals, etc. The collected raw data is processed for noise filtering and missing value filling to ensure data integrity and accuracy. At the same time, the data is normalized for subsequent analysis. Through feature extraction algorithms (such as principal component analysis PCA or deep learning feature extraction models), features related to microorganism contamination are extracted from the preprocessed data, including spectral features, chemical activity features (such as organic acid concentration), microbial metabolite features, etc. The extracted multi-source features are fused to generate comprehensive microorganism contamination feature data. For example, combining spectral features and chemical activity features, a comprehensive feature vector is generated that can represent the degree and type of microorganism contamination. The fused feature data is stored as a structured microorganism contamination feature dataset for subsequent biofilm identification and corrosion risk assessment. Through the above steps, dynamic detection of microorganism contamination features on the surface of photovoltaic modules and generation of feature data are achieved, providing a basis for subsequent biofilm identification and corrosion risk assessment.

[0058] S102: Based on the microorganism contamination feature data, biofilm identification is performed through an AI classification model to generate contamination type labels and bioactivity level data.

[0059] Specifically, the collected microbial contamination feature data is cleaned, including noise removal and missing value filling, to ensure the integrity and accuracy of the data. At the same time, the data is normalized for subsequent analysis. From the preprocessed data, features related to biofilm identification are extracted, including spectral features, chemical activity features (such as organic acid concentration), microbial metabolite features, etc. Principal component analysis (PCA) or deep learning feature extraction models are used to extract key features. The extracted multi-source features are fused to generate comprehensive microbial contamination feature data. For example, combining spectral features and chemical activity features, a comprehensive feature vector is generated that can represent the degree and type of microbial contamination. The fused feature data is classified using a trained AI classification model (such as convolutional neural network CNN, support vector machine SVM, etc.). The model needs to be trained in advance with a large amount of labeled data to ensure the accuracy and robustness of the classification. The fused feature data is input into the trained AI classification model, which outputs the contamination type label (such as lichen, blue-green algae, etc.) and the biological activity level data (such as low, medium, high activity). According to the output of the AI classification model, the contamination type label and the biological activity level data are generated, which are used for subsequent corrosion risk assessment and cleaning strategy development. Through the above steps, biofilm identification processing based on microbial contamination feature data is realized, providing a basis for subsequent corrosion risk assessment and cleaning strategy.

[0060] S103: According to the contamination type label and the biological activity level data, corrosion risk assessment processing is performed to generate corrosion risk index and cleaning priority ranking results.

[0061] Specifically, the pollution type labels and bioactivity level data are fused to generate a comprehensive microorganism pollution feature dataset. This step ensures that data from different sources can work together to provide a comprehensive information base for subsequent corrosion risk assessment. The fused microorganism pollution feature data is input into the trained corrosion risk assessment model. This model can be a risk assessment-based model, a mass transfer process control-based model, or a comprehensive model based on electrochemical corrosion mechanism. The model predicts the likelihood and severity of corrosion by analyzing the relationship between microorganism pollution features and corrosion rate. Considering the spatial adjacency of photovoltaic arrays and environmental wind speed data, the initial corrosion risk parameters are processed for propagation path analysis. By constructing a pollution propagation path topology network model and combining wind speed data to correct the pollution diffusion correlation parameters, a dynamic weight-adjusted corrosion risk index is generated. This step can more accurately reflect the corrosion risk distribution in the actual environment. According to the dynamic weight-adjusted corrosion risk index, the pollution area is processed for multi-objective optimization sorting. Through optimization algorithm, the cleaning priority sorting result considering cleaning efficiency and corrosion inhibition is generated, ensuring the optimality of the cleaning strategy. Then the corrosion risk index and cleaning priority sorting result are generated to provide a scientific basis for subsequent cleaning and maintenance strategies. Through the above steps, the precise evaluation of photovoltaic module surface corrosion risk and the optimization of cleaning strategy are realized, effectively solving the evaluation static and decision lag problems in traditional methods.

[0062] S104: Based on the cleaning priority sorting result, the photovoltaic module surface is cleaned and protected, and a cleaning completion signal is generated.

[0063] Specifically, according to the pollution degree and corrosion risk, the photovoltaic module is sorted by cleaning priority. According to the cleaning priority sorting result, the corresponding cleaning equipment is started. The surface of the photovoltaic module with high priority area is pre-wetted to reduce static electricity and dust flying during cleaning, and to prepare for the subsequent cleaning steps. High-pressure water mist gradient spraying technology is used to clean the surface of the photovoltaic module. This technology can effectively remove dust and biofilm on the surface, while reducing water consumption. After cleaning, the photovoltaic module surface is treated with adaptive spraying of microbial inhibitor. This step aims to prevent the reformation of biofilm and prolong the duration of cleaning effect. The uniformity of the inhibitor coverage and the thickness of the protective layer are verified by optical detection means to ensure that the protective layer can effectively inhibit microbial growth. When the above cleaning and protection steps are completed, a cleaning completion signal is generated. This signal can be a simple status indication or a report containing detailed cleaning effect data for subsequent maintenance and management decisions. Through the above steps, the photovoltaic module surface can be effectively cleaned and protected, thereby improving its power generation efficiency and service life.

[0064] S105: Perform cloud aggregation and trend prediction processing on the corrosion risk index and cleaning effect data to generate a corrosion trend report and maintenance recommendations.

[0065] Specifically, the corrosion risk index and cleaning effect data from different components are aggregated in the cloud. This step ensures centralized management of the data and provides a unified data basis for subsequent analysis. Noise filtering and missing value filling are performed on the aggregated data to generate cleaned corrosion time series data. This step improves the quality of the data and provides reliable data support for subsequent analysis. Kernel Principal Component Analysis (KPCA) algorithm is used to extract features from the cleaned data, reduce feature dimension, reduce noise interference, and extract key features. This step can improve the prediction performance of the model. The extracted feature data is input into the trained Long Short-Term Memory (LSTM) neural network model to extract the periodic fluctuation characteristics of the component surface corrosion rate, generating corrosion trend prediction parameters. This step can capture the nonlinear relationship between the periodicity of sandstorms, the fluctuation of microbial activity, and the corrosion rate in the desert environment.

[0066] Based on the corrosion trend prediction parameters, the dynamic planning of the cooperative maintenance time window of multiple component regions is performed to generate a corrosion trend report and maintenance recommendations including maintenance time, priority, and resource allocation strategy. This step ensures the optimality of the maintenance strategy and reduces the operation and maintenance cost. The corrosion trend prediction results and maintenance recommendations are integrated into a detailed corrosion trend report to provide a scientific basis for subsequent maintenance decisions. Through the above steps, cloud aggregation and trend prediction processing of corrosion risk index and cleaning effect data are realized, providing precise decision support for the maintenance of desert photovoltaic power stations.

[0067] An embodiment of the present application provides a desert photovoltaic sand damage monitoring method based on Internet of Things, which includes: performing dynamic detection processing on the microbial contamination characteristics of the surface of the photovoltaic component to generate microbial contamination characteristic data; performing biological membrane recognition processing on the microbial contamination characteristic data through an AI classification model to generate contamination type labels and biological activity level data; performing corrosion risk assessment processing according to the contamination type labels and biological activity level data to generate a corrosion risk index and a cleaning priority ranking result; performing directional cleaning and protection processing on the surface of the photovoltaic component based on the cleaning priority ranking result to generate a cleaning completion signal; and performing cloud aggregation and trend prediction processing on the corrosion risk index and cleaning effect data to generate a corrosion trend report and maintenance recommendations, thereby solving the problems of fragmented detection dimension, static evaluation, and lagging decision-making, and achieving the technical effects of improving biological membrane recognition accuracy, dynamically quantifying microbial corrosion risk, and adapting to the prediction of non-steady-state environments in the desert.

[0068] Further, the corrosion risk index and cleaning effect data are cloud aggregated and trend prediction processed to generate corrosion trend report and maintenance suggestions, including:

[0069] (1) Noise filtering and missing value filling processing are performed on the corrosion risk index and cleaning effect data to generate cleaned corrosion time series data;

[0070] (2) Based on the preset component number and timestamp, multi-source alignment processing is performed on the cleaned corrosion time series data to generate spatiotemporally correlated corrosion time series data set;

[0071] (3) The corrosion time series data set is input into the trained long short-term memory neural network model to extract the periodic fluctuation characteristics of the component surface corrosion rate and generate corrosion trend prediction parameters;

[0072] (4) Based on the corrosion trend prediction parameters, dynamic programming is performed on the cooperative maintenance time window of multiple component regions to generate corrosion trend report and maintenance suggestions including maintenance time, priority and resource allocation strategy.

[0073] Specifically, the corrosion risk index and cleaning effect data from different components are cloud aggregated. Noise filtering and missing value filling processing are performed on the aggregated data to generate cleaned corrosion time series data. This step ensures the integrity and quality of the data, providing reliable data support for subsequent analysis. Based on the preset component number and timestamp, multi-source alignment processing is performed on the cleaned corrosion time series data to generate spatiotemporally correlated corrosion time series data set. This step ensures that data from different sources can be accurately matched in time and space, providing a basis for subsequent trend prediction. Kernel Principal Component Analysis (KPCA) algorithm is used to extract and reduce the dimension of the cleaned data, reducing noise interference and extracting key features. This step can improve the prediction performance of the model. The extracted feature data is input into the trained Long Short-Term Memory (LSTM) neural network model to extract the periodic fluctuation characteristics of the component surface corrosion rate and generate corrosion trend prediction parameters. The LSTM model can capture the long-term dependence of data through memory cells and gating mechanisms, making up for the shortcomings of traditional models in processing time series data. Based on the corrosion trend prediction parameters, dynamic programming is performed on the cooperative maintenance time window of multiple component regions to generate corrosion trend report and maintenance suggestions including maintenance time, priority and resource allocation strategy. This step ensures the optimality of the maintenance strategy and reduces the operation and maintenance cost. The corrosion trend prediction results and maintenance suggestions are integrated into a detailed corrosion trend report to provide scientific basis for subsequent maintenance decisions.

[0074] Further, the corrosion time series dataset is input into the trained long short-term memory neural network model to extract the periodic fluctuation characteristics of the component surface corrosion rate, generate corrosion trend prediction parameters, including:

[0075] (1) Time series segmentation processing is performed on the corrosion time series dataset, time windows are divided based on the sandstorm occurrence period and microbial activity period, and multi-scale time series segments are generated;

[0076] (2) The multi-scale time series segments are input into the bidirectional long short-term memory neural network model to capture and process the forward and reverse time series dependency relationships, and generate an initial time series feature vector;

[0077] (3) The initial time series feature vector is processed by weight allocation based on the attention mechanism to generate high-weight periodic fluctuation features;

[0078] (4) The high-weight periodic fluctuation features and static environmental features are processed by multi-scale fusion to generate corrosion trend prediction parameters.

[0079] Specifically, time series segmentation processing is performed on the corrosion time series dataset, time windows are divided based on the sandstorm occurrence period and microbial activity period, and multi-scale time series segments are generated. This step can capture corrosion features at different time scales, providing a basis for subsequent feature extraction. The multi-scale time series segments are input into the bidirectional long short-term memory (BiLSTM) neural network model. BiLSTM can simultaneously process the forward and reverse parts of the input sequence, thereby better capturing the context relationship in the sequence data. The BiLSTM model captures and processes the forward and reverse time series dependency relationships through its internal two LSTM layers, generating an initial time series feature vector. This step can fully utilize the historical and future information in the sequence data, improving the prediction ability of the model. The initial time series feature vector is processed by weight allocation using the attention mechanism to generate high-weight periodic fluctuation features. The attention mechanism can highlight important features and ignore unimportant features, thereby improving the prediction accuracy of the model. The high-weight periodic fluctuation features and static environmental features are processed by multi-scale fusion to generate corrosion trend prediction parameters. This step can consider both dynamic and static factors to further improve the accuracy of the prediction.

[0080] Further, according to the pollution type label and biological activity level data, corrosion risk assessment processing is performed to generate corrosion risk index and cleaning priority ranking results, including:

[0081] (1) Multi-source data fusion processing is performed on the pollution type label and biological activity level data to generate microbial pollution comprehensive evaluation data;

[0082] (2) input the comprehensive evaluation data of microbial contamination into the trained corrosion risk assessment model, map the coupling relationship between the corrosion rate of the component surface and the power attenuation, and generate initial corrosion risk parameters;

[0083] (3) based on the spatial adjacency of the photovoltaic array and the environmental wind speed data, perform propagation path analysis processing on the initial corrosion risk parameters to generate a corrosion risk index adjusted by dynamic weight;

[0084] (4) according to the corrosion risk index adjusted by dynamic weight, perform multi-objective optimization sorting processing on the contaminated area to generate a cleaning priority sorting result considering cleaning efficiency and corrosion inhibition.

[0085] Specifically, the multi-source data fusion processing is performed on the pollution type label and biological activity level data to generate comprehensive evaluation data of microbial contamination. This step ensures that data from different sources can work together to provide a comprehensive information base for subsequent corrosion risk assessment. The comprehensive evaluation data of microbial contamination is input into the trained corrosion risk assessment model. The model analyzes the relationship between microbial contamination characteristics and corrosion rate to predict the possibility and severity of corrosion, and generates initial corrosion risk parameters. Based on the spatial adjacency of the photovoltaic array and the environmental wind speed data, the initial corrosion risk parameters are subjected to propagation path analysis processing. By constructing a pollution propagation path topology network model, the pollution diffusion correlation parameters are corrected in combination with wind speed data to generate a corrosion risk index adjusted by dynamic weight. According to the corrosion risk index adjusted by dynamic weight, the contaminated area is subjected to multi-objective optimization sorting processing. Through optimization algorithm, a cleaning priority sorting result considering cleaning efficiency and corrosion inhibition is generated to ensure the optimality of the cleaning strategy.

[0086] Further, based on the spatial adjacency of the photovoltaic array and the environmental wind speed data, the initial corrosion risk parameters are subjected to propagation path analysis processing to generate a corrosion risk index adjusted by dynamic weight, including:

[0087] (1) based on the spatial layout topology relationship of the photovoltaic array and the component spacing data, construct a pollution propagation path topology network model to generate pollution diffusion correlation parameters between components;

[0088] (2) in combination with environmental wind speed data, perform wind direction correction processing on the pollution diffusion correlation parameters to generate a wind speed weighted propagation probability matrix;

[0089] (3) input the initial corrosion risk parameters into the risk weighted propagation probability matrix to perform iterative calculation processing on the risk superposition effect of adjacent components to generate dynamic propagation risk weight;

[0090] (4) Based on the dynamic propagation risk weight, the initial corrosion risk parameter is subjected to multi-factor fusion processing to generate a dynamic weight-adjusted corrosion risk index.

[0091] Specifically, based on the spatial layout topology relationship of the photovoltaic array and the component spacing data, a pollution propagation path topology network model is constructed to generate a component-to-component pollution diffusion correlation degree parameter. This step determines the pollution propagation path between components by analyzing the physical layout of the photovoltaic array and the component spacing. In combination with the environmental wind speed data, the pollution diffusion correlation degree parameter is subjected to wind direction correction processing to generate a wind speed-weighted propagation probability matrix. Wind speed and wind direction have a significant impact on pollution diffusion. By dynamically adjusting the propagation probability matrix, the actual pollution propagation situation can be more accurately reflected. The initial corrosion risk parameter is input into the wind speed-weighted propagation probability matrix, and the risk superposition effect of adjacent components is subjected to iterative calculation processing to generate a dynamic propagation risk weight. This step simulates the diffusion effect of pollution between components through iterative calculation to dynamically adjust the risk weight. Based on the dynamic propagation risk weight, the initial corrosion risk parameter is subjected to multi-factor fusion processing to generate a dynamic weight-adjusted corrosion risk index. Through an optimization algorithm, the pollution propagation between components and environmental factors are comprehensively considered to generate a more accurate corrosion risk index.

[0092] Further, based on the cleaning priority ranking result, the surface of the photovoltaic component is subjected to directional cleaning and protection processing to generate a cleaning completion signal, including:

[0093] (1) Based on the cleaning priority ranking result, the surface of the photovoltaic component in the high-priority area is subjected to pre-wetting processing to generate a surface humidity compliance signal;

[0094] (2) According to the surface humidity compliance signal, a directional cleaning device is started to perform high-pressure water mist gradient spraying processing on the target area to generate a preliminary cleaning signal;

[0095] (3) Based on the preliminary cleaning signal, the surface of the cleaned component is subjected to adaptive spraying processing of a microbial inhibitor to generate a protection layer thickness parameter;

[0096] (4) According to the protection layer thickness parameter, the uniformity of the inhibitor coverage is subjected to optical detection processing to generate a protection layer formation signal;

[0097] (5) The preliminary cleaning signal and the protection layer formation signal are subjected to logical AND processing to generate a cleaning completion signal.

[0098] Specifically, according to the cleaning priority ranking result, the photovoltaic module surface of the high-priority area is pre-wetted to reduce static electricity and dust flying during the cleaning process, and to prepare for the subsequent cleaning steps. When the surface humidity reaches the preset standard, a surface humidity qualified signal is generated. After receiving the surface humidity qualified signal, a directional cleaning device is started to perform high-pressure water mist gradient spraying treatment on the target area to effectively remove dust and biological membrane on the surface of the module. After the treatment is completed, a preliminary cleaning signal is generated. Based on the preliminary cleaning signal, a microbial inhibitor adaptive spraying system is started to spray the cleaned module surface to form a protective layer to inhibit microbial growth. At the same time, a protective layer thickness parameter is generated for subsequent detection. According to the protective layer thickness parameter, an optical detection technology is used to verify the uniformity of the inhibitor coverage and the thickness of the protective layer to ensure that the protective layer can effectively inhibit microbial growth. After the detection is qualified, a protective layer formation signal is generated. The preliminary cleaning signal and the protective layer formation signal are logically AND processed. Only when both signals indicate that the cleaning and protection steps are successfully completed, a cleaning completion signal is generated, indicating the end of the entire cleaning and protection process.

[0099] Further, the preliminary cleaning signal and the protective layer formation signal are logically AND processed to generate a cleaning completion signal, including:

[0100] (1) The preliminary cleaning signal is subjected to cleaning effect verification processing, based on comparison and analysis of multispectral reflection data and a preset cleaning threshold, a cleaning qualified flag is generated;

[0101] (2) The protective layer formation signal is subjected to thickness and coverage abnormality detection processing, a protective layer qualified flag is generated;

[0102] (3) Based on the current environmental wind speed and dust concentration data, the cleaning qualified flag and the protective layer qualified flag are subjected to dynamic weight allocation processing, a weighted logical AND condition parameter is generated;

[0103] (4) According to the weighted logical AND condition parameter, the preliminary cleaning signal and the protective layer formation signal are subjected to multi-modal fusion judgment processing, a cleaning completion signal is generated.

[0104] Specifically, the preliminary cleaning signal is subjected to a cleaning effect verification process, and a cleaning standard compliance flag is generated by comparing and analyzing the multispectral reflection data with a preset cleaning threshold. This step ensures that the cleaning effect meets the expected standard. The protective layer formation signal is subjected to thickness and coverage abnormality detection processing, and a protective layer qualification flag is generated. The uniformity of the inhibitor coverage and the thickness of the protective layer are verified by optical detection technology to ensure that the protective layer can effectively inhibit microbial growth. Based on the current environmental wind speed and sand concentration data, the cleaning standard compliance flag and the protective layer qualification flag are subjected to dynamic weight allocation processing, and a weighted logic and condition parameter is generated. This step considers the influence of environmental factors on cleaning and protection effect, ensuring the rationality of weight allocation. According to the weighted logic and condition parameter, the preliminary cleaning signal and the protective layer formation signal are subjected to multi-modal fusion judgment processing, and a cleaning completion signal is generated. Multi-modal fusion technology can comprehensively consider the data of different modalities to improve the accuracy and reliability of the judgment. Through the above steps, the comprehensive judgment of the preliminary cleaning signal and the protective layer formation signal is realized, and the cleaning completion signal is generated, ensuring the integrity and effectiveness of the surface cleaning and protection of the photovoltaic module.

[0105] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0106] In an embodiment, as shown in Figure 2 The present application also provides a desert photovoltaic sand damage monitoring device 200 based on the Internet of Things, which comprises:

[0107] The pollution dynamic detection module 201 is configured to perform dynamic detection processing on the microbial pollution characteristics of the surface of the photovoltaic module to generate microbial pollution characteristic data.

[0108] The intelligent biofilm recognition module 202 is configured to perform biofilm recognition processing on the microbial pollution characteristic data based on an AI classification model to generate pollution type labels and bioactivity level data.

[0109] The corrosion risk assessment module 203 is configured to perform corrosion risk assessment processing according to the pollution type label and the biological activity level data, and generate a corrosion risk index and a cleaning priority ranking result.

[0110] The intelligent cleaning protection module 204 is configured to perform directional cleaning and protection processing on the surface of the photovoltaic module based on the cleaning priority ranking result, and generate a cleaning completion signal.

[0111] The cloud prediction optimization module 205 is configured to perform cloud aggregation and trend prediction processing on the corrosion risk index and the cleaning effect data, and generate a corrosion trend report and a maintenance suggestion.

[0112] Specifically, the pollution dynamic detection module 201 is configured to perform dynamic detection on the microbial pollution characteristics of the surface of the photovoltaic module, collect spectrum reflectivity, chemical activity signal and other data through optical sensors and chemical sensors, and generate microbial pollution characteristic data. The above data provides a basis for subsequent biofilm identification and corrosion risk assessment. The intelligent biofilm identification module 202 is configured to identify the biofilm based on the microbial pollution characteristic data by using an AI classification model, and generate a pollution type label (such as lichen, blue-green algae, etc.) and biological activity level data (such as low, medium and high activity). This step improves the accuracy of biofilm identification through multi-source data fusion and feature extraction. The corrosion risk assessment module 203 is configured to evaluate the corrosion risk of the surface of the photovoltaic module in combination with the pollution type label and the biological activity level data, and generate a corrosion risk index and a cleaning priority ranking result. This module ensures the optimality of the cleaning strategy through dynamic weight adjustment and multi-objective optimization sorting. The intelligent cleaning protection module 204 is configured to perform directional cleaning and protection processing on the surface of the photovoltaic module according to the cleaning priority ranking result. This module includes pre-wetting processing, high-pressure water mist gradient spraying, microbial inhibitor spraying and optical detection, and then generates a cleaning completion signal to ensure the reliability of the cleaning and protection effect. The cloud prediction optimization module 205 is configured to aggregate the corrosion risk index and the cleaning effect data in the cloud, perform trend prediction through a long short-term memory neural network model, and generate a corrosion trend report and a maintenance suggestion. This module provides a scientific basis for long-term maintenance of the desert photovoltaic power station through dynamic planning of a maintenance time window and a resource allocation strategy. Through the cooperative work of the above modules, the device 200 realizes full-process automation from pollution detection to cleaning and protection, effectively improves the operation efficiency and service life of the photovoltaic module.

[0113] The cloud prediction optimization module 205 is further configured to:

[0114] perform noise filtering and missing value filling processing on the corrosion risk index and the cleaning effect data to generate cleaned corrosion time series data;

[0115] The corrosion time series data after cleaning is subjected to multi-source alignment processing based on the preset component number and timestamp, to generate a corrosion time series dataset with spatiotemporal correlation;

[0116] The corrosion time series dataset is input into the trained long short-term memory neural network model to extract and process the periodic fluctuation characteristics of the component surface corrosion rate, to generate corrosion trend prediction parameters;

[0117] Based on the corrosion trend prediction parameters, the dynamic programming processing is performed on the collaborative maintenance time window of the multi-component region, to generate a corrosion trend report and maintenance suggestion including maintenance time, priority and resource allocation strategy.

[0118] The cloud prediction optimization module 205 is also used for:

[0119] The corrosion time series dataset is subjected to time series segmentation processing, and the time window is divided based on the sandstorm occurrence period and the microbial activity period, to generate multi-scale time series segments;

[0120] The multi-scale time series segments are input into the bidirectional long short-term memory neural network model to capture and process the forward and reverse time series dependency relationship, to generate an initial time series feature vector;

[0121] The initial time series feature vector is subjected to weight allocation processing based on the attention mechanism, to generate high-weight periodic fluctuation characteristics;

[0122] The high-weight periodic fluctuation characteristics and static environmental characteristics are subjected to multi-scale fusion processing, to generate corrosion trend prediction parameters.

[0123] The corrosion risk assessment module 203 is also used for:

[0124] The multi-source data fusion processing is performed on the pollution type label and biological activity level data, to generate microbial pollution comprehensive evaluation data;

[0125] The microbial pollution comprehensive evaluation data is input into the trained corrosion risk assessment model to map the coupling relationship between the component surface corrosion rate and the power attenuation, to generate initial corrosion risk parameters;

[0126] Based on the spatial adjacency of the photovoltaic array and the environmental wind speed data, the initial corrosion risk parameters are subjected to propagation path analysis processing, to generate a corrosion risk index with dynamic weight adjustment;

[0127] According to the corrosion risk index with dynamic weight adjustment, the multi-objective optimization sorting processing is performed on the contaminated area, to generate a cleaning priority sorting result taking into account the cleaning efficiency and corrosion inhibition.

[0128] The corrosion risk assessment module 203 is also used for:

[0129] Based on the spatial layout topology relationship of the photovoltaic array and the component spacing data, a pollution propagation path topology network model is constructed, and a component-to-component pollution diffusion correlation degree parameter is generated;

[0130] Combined with the environmental wind speed data, the pollution diffusion correlation degree parameter is processed for wind direction correction, and a wind speed weighted propagation probability matrix is generated;

[0131] The initial corrosion risk parameter is input into the risk weighted propagation probability matrix, and the risk superposition effect of adjacent components is iteratively calculated and processed to generate a dynamic propagation risk weight;

[0132] Based on the dynamic propagation risk weight, the initial corrosion risk parameter is processed for multi-factor fusion to generate a corrosion risk index after dynamic weight adjustment.

[0133] The intelligent cleaning protection module 204 is also used for:

[0134] Based on the cleaning priority ranking result, the surface of the photovoltaic component in the high priority area is pre-wetted to generate a surface humidity compliance signal;

[0135] According to the surface humidity compliance signal, the directional cleaning device is started to perform gradient spraying treatment on the target area, and a preliminary cleaning signal is generated;

[0136] Based on the preliminary cleaning signal, the component surface after cleaning is subjected to adaptive spraying treatment of the microbial inhibitor to generate a protection layer thickness parameter;

[0137] According to the protection layer thickness parameter, the optical detection treatment is performed on the uniformity of the inhibitor coverage to generate a protection layer formation signal;

[0138] The preliminary cleaning signal and the protection layer formation signal are subjected to logical AND processing to generate a cleaning completion signal.

[0139] The intelligent cleaning protection module 204 is also used for:

[0140] The preliminary cleaning signal is subjected to cleaning effect verification processing, and the multispectral reflection data are compared and analyzed based on the preset cleaning threshold to generate a cleaning compliance flag;

[0141] The protection layer formation signal is subjected to thickness and coverage abnormality detection processing to generate a protection layer qualification flag;

[0142] Based on the current environmental wind speed and dust concentration data, the cleaning compliance flag and the protection layer qualification flag are subjected to dynamic weight distribution processing to generate a weighted logical and condition parameter;

[0143] According to the weighted logical and condition parameter, the preliminary cleaning signal and the protection layer formation signal are subjected to multi-modal fusion judgment processing to generate a cleaning completion signal.

[0144] In one embodiment, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0145] In one embodiment, the present application also provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps in the above method embodiments.

[0146] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts are described in the method embodiments. The above described device embodiments are only schematic and the components illustrated as separate components can or can not be physically separate, and the components illustrated as a unit can or can not be physical units, i.e. can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present disclosure according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0147] The above described embodiments only express several implementation manners of the present application, the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which are all within the protection scope of the present application.

Claims

1. A desert photovoltaic sand damage monitoring method based on the Internet of Things, characterized in that, The method includes: Dynamic detection and processing of microbial contamination characteristics on the surface of photovoltaic modules are performed to generate microbial contamination characteristic data. Based on the microbial contamination characteristic data, a biofilm identification process is performed using an AI classification model to generate contamination type labels and biological activity level data; the microbial contamination characteristic data includes spectral characteristics, chemical activity characteristics, and microbial metabolite characteristics. Based on the pollution type labels and bioactivity level data, a corrosion risk assessment is performed to generate a corrosion risk index and a cleaning priority ranking. The pollution type labels include lichens and cyanobacteria; the bioactivity level data includes low activity, medium activity, and high activity. Based on the cleaning priority ranking result, the photovoltaic module surface is subjected to targeted cleaning and protection treatment, and a cleaning completion signal is generated. The corrosion risk index and cleaning effect data are aggregated and trend predicted in the cloud to generate a corrosion trend report and maintenance recommendations. The process of cloud-based aggregation and trend prediction of the corrosion risk index and cleaning effect data to generate a corrosion trend report and maintenance recommendations includes: performing noise filtering and missing value imputation on the corrosion risk index and cleaning effect data to generate post-cleaning corrosion time-series data; performing multi-source alignment processing on the post-cleaning corrosion time-series data based on preset component numbers and timestamps to generate a spatiotemporally correlated corrosion time-series dataset; inputting the corrosion time-series dataset into a trained long short-term memory neural network model to extract the periodic fluctuation characteristics of the corrosion rate on the component surface and generate corrosion trend prediction parameters; and performing dynamic planning processing on the collaborative maintenance time window of multiple component areas based on the corrosion trend prediction parameters to generate the corrosion trend report and maintenance recommendations including maintenance time, priority, and resource allocation strategies.

2. The desert photovoltaic sand damage monitoring method based on the Internet of Things according to claim 1, characterized in that, The step of inputting the corrosion time-series dataset into a trained long short-term memory neural network model to extract the periodic fluctuation characteristics of the corrosion rate on the component surface and generate corrosion trend prediction parameters includes: The corrosion time series dataset is processed by time series segmentation, and time windows are divided based on the sandstorm occurrence cycle and microbial activity cycle to generate multi-scale time series segments. The multi-scale time series segments are input into a bidirectional long short-term memory neural network model to capture and process the forward and reverse time series dependencies, and generate an initial time series feature vector. The initial temporal feature vector is weighted based on an attention mechanism to generate high-weight periodic fluctuation features. The high-weight periodic fluctuation features and static environmental features are fused at multiple scales to generate the corrosion trend prediction parameters.

3. The desert photovoltaic sand damage monitoring method based on the Internet of Things according to claim 1, characterized in that, The process involves conducting a corrosion risk assessment based on the pollution type label and bioactivity level data, generating a corrosion risk index and cleaning priority ranking results, including: The pollution type labels and bioactivity level data are subjected to multi-source data fusion processing to generate comprehensive microbial pollution assessment data; The comprehensive assessment data of microbial contamination is input into the trained corrosion risk assessment model to map the coupling relationship between component surface corrosion rate and power attenuation, and generate initial corrosion risk parameters. Based on the spatial adjacency of the photovoltaic array and environmental wind speed data, the initial corrosion risk parameters are analyzed for propagation paths to generate the corrosion risk index after dynamic weight adjustment. Based on the corrosion risk index adjusted by the dynamic weight, the contaminated areas are subjected to multi-objective optimization and ranking to generate a cleaning priority ranking result that takes into account both cleaning efficiency and corrosion inhibition.

4. The desert photovoltaic sand damage monitoring method based on the Internet of Things according to claim 3, characterized in that, Based on the spatial adjacency of the photovoltaic array and environmental wind speed data, the initial corrosion risk parameters are analyzed for propagation paths to generate the corrosion risk index after dynamic weight adjustment, including: Based on the spatial layout topology of photovoltaic arrays and component spacing data, a topological network model of pollution propagation paths is constructed to generate pollution diffusion correlation parameters between components. Based on the environmental wind speed data, the pollution diffusion correlation parameter is corrected for wind direction to generate a wind speed-weighted propagation probability matrix; The initial corrosion risk parameters are input into the wind speed weighted propagation probability matrix, and the risk superposition effect of adjacent components is iteratively calculated to generate dynamic propagation risk weights. Based on the dynamic propagation risk weights, the initial corrosion risk parameters are subjected to multi-factor fusion processing to generate the corrosion risk index after dynamic weight adjustment.

5. The desert photovoltaic sand damage monitoring method based on the Internet of Things according to claim 1, characterized in that, Based on the cleaning priority ranking result, the photovoltaic module surface is subjected to targeted cleaning and protective treatment, and a cleaning completion signal is generated, including: Based on the cleaning priority ranking result, the photovoltaic module surface in the high priority area is pre-wetted to generate a surface humidity compliance signal. Based on the surface humidity compliance signal, the directional cleaning device is activated to perform high-pressure water mist gradient spraying on the target area to generate a preliminary cleaning signal. Based on the initial cleaning signal, the cleaned component surface is subjected to adaptive spraying of microbial inhibitors to generate protective layer thickness parameters. Based on the protective layer thickness parameters, optical detection processing is performed on the inhibitor coverage uniformity to generate a protective layer formation signal; The initial cleaning signal and the protective layer formation signal are subjected to a logical AND operation to generate the cleaning completion signal.

6. The desert photovoltaic sand damage monitoring method based on the Internet of Things according to claim 5, characterized in that, The step of performing a logical AND operation on the preliminary cleaning signal and the protective layer formation signal to generate the cleaning completion signal includes: The initial cleaning signal is processed to verify the cleaning effect. Based on the multispectral reflectance data, it is compared and analyzed with the preset cleaning threshold to generate a cleaning compliance mark. The signal forming the protective layer is processed for thickness and coverage anomaly detection to generate a protective layer qualification mark; Based on the current environmental wind speed and dust concentration data, the cleanliness compliance mark and the protective layer qualification mark are dynamically weighted and processed to generate weighted logic and conditional parameters. Based on the weighted logic and condition parameters, the preliminary cleaning signal and the protective layer formation signal are subjected to multimodal fusion judgment processing to generate the cleaning completion signal.

7. A desert photovoltaic sand damage monitoring device based on the Internet of Things, characterized in that, The device includes: The pollution dynamic detection module is used to dynamically detect and process the microbial pollution characteristics on the surface of photovoltaic modules and generate microbial pollution characteristic data. The intelligent biofilm identification module is used to identify biofilms based on the microbial contamination feature data using an AI classification model, and generate contamination type labels and biological activity level data; the microbial contamination feature data includes spectral features, chemical activity features, and microbial metabolite features. The corrosion risk assessment module is used to perform corrosion risk assessment processing based on the pollution type labels and biological activity level data, and generate corrosion risk index and cleaning priority ranking results; the pollution type labels include lichens and cyanobacteria; the biological activity level data includes low activity, medium activity and high activity; The intelligent cleaning and protection module is used to perform targeted cleaning and protection treatment on the surface of the photovoltaic module based on the cleaning priority ranking result, and generate a cleaning completion signal. The cloud-based prediction and optimization module is used to aggregate and predict the corrosion risk index and cleaning effect data in the cloud, and generate a corrosion trend report and maintenance suggestions. The process of cloud-based aggregation and trend prediction of the corrosion risk index and cleaning effect data to generate a corrosion trend report and maintenance recommendations includes: performing noise filtering and missing value imputation on the corrosion risk index and cleaning effect data to generate post-cleaning corrosion time-series data; performing multi-source alignment processing on the post-cleaning corrosion time-series data based on preset component numbers and timestamps to generate a spatiotemporally correlated corrosion time-series dataset; inputting the corrosion time-series dataset into a trained long short-term memory neural network model to extract the periodic fluctuation characteristics of the corrosion rate on the component surface and generate corrosion trend prediction parameters; and performing dynamic planning processing on the collaborative maintenance time window of multiple component areas based on the corrosion trend prediction parameters to generate the corrosion trend report and maintenance recommendations including maintenance time, priority, and resource allocation strategies.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the desert photovoltaic sand damage monitoring method based on the Internet of Things as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the desert photovoltaic sand damage monitoring method based on the Internet of Things as described in any one of claims 1 to 6.

Images