Mountain photovoltaic power station monitoring system, method, device, equipment, medium and product

Abstract

The invention relates to the technical field of electronics, and discloses a mountain photovoltaic power station monitoring system, method, device, equipment, medium and product, the system comprises a data acquisition module, an inspection module and a data analysis and processing module; the data acquisition module is used for acquiring running state data and meteorological data of photovoltaic equipment in the running process of the mountain photovoltaic power station; the inspection module is used for controlling the unmanned aerial vehicle to collect appearance state information of the photovoltaic equipment according to a preset inspection route; the data analysis and processing module is connected with the data acquisition module and the inspection module, and is used for carrying out the fault monitoring of the mountain photovoltaic power station according to the meteorological data, the operation state data of the photovoltaic equipment and the appearance state data, and can timely recognize the abnormal operation state and potential faults of the photovoltaic power station. The problems of low efficiency, high cost and incapability of timely finding risks existing in the operation process of the mountain photovoltaic power station in manual inspection in related technologies are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronics, in particular to a mountain photovoltaic power station monitoring system, method, device, equipment, medium and product. BACKGROUND

[0002] At present, with the vigorous development of clean energy, the construction scale of mountain photovoltaic power stations is expanding due to the effective use of mountainous terrain and the advantage of occupying less land resources. However, the complex geographical environment of mountains brings many challenges to the operation and management of power stations.

[0003] In the related art, the operation state of a mountain photovoltaic power station is generally monitored by manual inspection. The complex terrain of mountains makes the traditional manual inspection extremely inefficient, costly and risky. At the same time, in the mountain environment, heavy rain, strong wind, snow and other severe weather, as well as complex geological conditions such as landslides and mudslides, are prone to damage photovoltaic equipment. The conventional inspection method cannot detect the damage in time, which leads to the failure to repair the equipment in time and further affects the power generation efficiency and economic benefits of the power station. SUMMARY

[0004] Therefore, the present application provides a mountain photovoltaic power station monitoring system, method, device, equipment, medium and product to solve the problem of low efficiency, high cost and inability to discover risks in the operation of a mountain photovoltaic power station in time in the related art.

[0005] In a first aspect, the present application provides a mountain photovoltaic power station monitoring system, which comprises a data acquisition module, an inspection module and a data analysis and processing module. The data acquisition module is used to acquire operation state data of photovoltaic equipment and meteorological data in the operation of a mountain photovoltaic power station. The inspection module is used to control a UAV to collect appearance state information of the photovoltaic equipment according to a preset inspection route. The data analysis and processing module is connected with the data acquisition module and the inspection module, and is used to monitor the fault of the mountain photovoltaic power station according to the meteorological data, the operation state data of the photovoltaic equipment and the appearance state data.

[0006] The mountain photovoltaic power station monitoring system provided by the application comprises a data acquisition module, an inspection module and a data analysis and processing module; the data acquisition module is used for acquiring operation state data of photovoltaic equipment and meteorological data in the operation process of the mountain photovoltaic power station; the inspection module is used for controlling the unmanned aerial vehicle to collect appearance state information of the photovoltaic equipment according to a preset inspection route; the data analysis and processing module is connected with the data acquisition module and the inspection module respectively, and is used for performing fault monitoring on the mountain photovoltaic power station according to the meteorological data, the operation state data of the photovoltaic equipment and the appearance state data, so that the abnormal operation state and potential fault of the photovoltaic power station can be identified in time, and the problem that the risk existing in the operation process of the mountain photovoltaic power station cannot be found in time due to low efficiency and high cost of manual inspection in the related art is solved.

[0007] In an optional embodiment, the system further comprises a power prediction module; the data analysis and processing module is further used for sending initial multi-source feature data of a first period generated in the fault monitoring process to the power prediction module, the initial multi-source feature data comprising initial meteorological feature data; the power prediction module is used for inputting terrain data of the mountain photovoltaic power station and the initial meteorological feature data of the first period into a pre-constructed meteorological correction model, so that the meteorological correction model outputs target meteorological feature data of the mountain photovoltaic power station in the first period; the power prediction module is further used for inputting target multi-source feature data of the mountain photovoltaic power station in the first period into a pre-constructed multi-source data fusion model, so that the multi-source data fusion model outputs power generation of the mountain photovoltaic power station in a second period, the target multi-source feature data being obtained by replacing the initial meteorological feature data in the initial multi-source feature data with the target meteorological feature data, the second period being later than the first period.

[0008] The method provided by the optional embodiment realizes accurate prediction of the power generation feature of the mountain photovoltaic power station by correcting the initial meteorological feature data output by the data analysis and processing module through the power prediction module, and predicting the power generation of the mountain photovoltaic power station in the second period based on the first power generation feature data of the mountain photovoltaic power station in the first period and the corrected target meteorological feature data.

[0009] In an optional embodiment, the meteorological correction model is obtained by the following steps: obtaining terrain data, a plurality of initial meteorological feature data and a plurality of target meteorological feature data corresponding to different photovoltaic power stations respectively; associating the terrain data of each photovoltaic power station with the corresponding plurality of initial meteorological feature data to obtain a plurality of first associated data; associating the plurality of first associated data of each photovoltaic power station with the plurality of target meteorological feature data to obtain an associated data set; and training a first preset model by using the associated data set until the model accuracy reaches a preset requirement, to obtain the meteorological correction model.

[0010] In an optional implementation, the multi-source data fusion model is constructed by the following steps: acquiring multi-source feature sequence data and power generation sequence data of the photovoltaic power station; dividing the multi-source feature sequence data by using a first preset length sliding window to obtain first training data; dividing the power generation sequence data by using a second preset length sliding window to obtain second training data; associating the first training data and the second training data according to a preset requirement to construct a data set; and training a second preset model according to the data set to obtain the multi-source data fusion model.

[0011] In an optional implementation, the preset inspection route is determined by the following steps: acquiring layout information of photovoltaic equipment in a region where the mountain photovoltaic power station is located; dividing the region where the mountain photovoltaic power station is located based on the layout information to obtain a plurality of sub-regions; determining a plurality of path node information of each sub-region; and planning an inspection route in the corresponding sub-region based on a preset path planning algorithm and the plurality of path node information of each sub-region to obtain the preset inspection route in the corresponding sub-region.

[0012] In a second aspect, the present application provides a mountain photovoltaic power station monitoring method applied to the mountain photovoltaic power station monitoring system of the first aspect or any of the corresponding embodiments thereof. The method comprises the following steps: acquiring meteorological data of the mountain photovoltaic power station, operation state data and appearance state data of photovoltaic equipment in the mountain photovoltaic power station; integrating and cleaning the meteorological data, the operation state data and the appearance state data respectively to obtain processed target meteorological feature data, target operation state data and target appearance state data; extracting features from the target meteorological feature data, the target operation state data and the target appearance state data respectively to obtain first feature data of the target meteorological feature data, second feature data of the target operation state data and third feature data of the target appearance state data; and performing fault monitoring on the mountain photovoltaic power station based on the first feature data, the second feature data and the third feature data.

[0013] The mountain photovoltaic power station monitoring method provided by the present application integrates and cleans the meteorological data, the operation state data and the appearance state data respectively to obtain processed target meteorological feature data, target operation state data and target appearance state data; extracts features from the target meteorological feature data, the target operation state data and the target appearance state data respectively to obtain first feature data of the target meteorological feature data, second feature data of the target operation state data and third feature data of the target appearance state data; and performs fault monitoring on the mountain photovoltaic power station based on the first feature data, the second feature data and the third feature data, which can timely identify abnormal operation state and potential faults of the photovoltaic power station, and solves the problems of low efficiency, high cost and inability to timely discover risks in the operation process of the mountain photovoltaic power station existing in the related art through manual inspection.

[0014] In a third aspect, the present application provides a mountain photovoltaic power station monitoring device, which comprises: an acquisition module, configured to acquire meteorological data of the mountain photovoltaic power station, operation state data of photovoltaic equipment in the mountain photovoltaic power station, and appearance state data; a processing module, configured to integrate and clean the meteorological data, the operation state data, and the appearance state data respectively to obtain target meteorological feature data, target operation state data, and target appearance state data; a feature extraction module, configured to extract features from the target meteorological feature data, the target operation state data, and the target appearance state data respectively to obtain first feature data of the target meteorological feature data, second feature data of the target operation state data, and third feature data of the target appearance state data; and a detection module, configured to perform fault monitoring on the mountain photovoltaic power station based on the first feature data, the second feature data, and the third feature data.

[0015] In a fourth aspect, the present application provides a computer device, which comprises a memory and a processor, the memory and the processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the mountain photovoltaic power station monitoring method of the first aspect.

[0016] In a fifth aspect, the present application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the mountain photovoltaic power station monitoring method of the first aspect or any of the corresponding embodiments.

[0017] In a sixth aspect, the present application provides a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the mountain photovoltaic power station monitoring method of the first aspect or any of the corresponding embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed in the specific embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a flowchart of a mountain photovoltaic power station monitoring system according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of another mountain photovoltaic power station monitoring method according to an embodiment of the present application;

[0021] Figure 3is a flowchart diagram according to an embodiment of the mountain photovoltaic power station monitoring method of the present application;

[0022] Figure 4 is a structural block diagram of a mountain photovoltaic power station monitoring device according to an embodiment of the present application;

[0023] Figure 5 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0025] In the related art, the running state of the mountain photovoltaic power station is generally monitored by manual inspection. The complex terrain of the mountain makes the traditional manual inspection extremely inefficient, costly and risky. At the same time, in the mountain environment, heavy rain, strong wind, snow and other bad weather, as well as complex geological conditions such as landslides and mudslides, are easy to damage photovoltaic equipment, and the conventional inspection method is difficult to detect in time, resulting in that the equipment failure cannot be repaired in time, and thus affecting the power generation efficiency and economic benefit of the power station.

[0026] Therefore, the present application provides a mountain photovoltaic power station monitoring system, which collects the running state data of the photovoltaic equipment and the meteorological data during the operation of the mountain photovoltaic power station by using a data acquisition module; collects the appearance state information of the photovoltaic equipment by using an inspection module; and performs fault monitoring on the mountain photovoltaic power station according to the meteorological data, the running state data of the photovoltaic equipment and the appearance state data by using a data analysis and processing module, so as to identify the abnormal running state and potential failure of the photovoltaic power station in time, and solve the problems of low efficiency, high cost and inability to discover the risks existing in the operation of the mountain photovoltaic power station in time in the related art.

[0027] According to the embodiments of the present application, a mountain photovoltaic power station monitoring system is provided, as shown in Figure 1 The system includes a data acquisition module 101, an inspection module 102 and a data analysis and processing module 103.

[0028] The data acquisition module is configured to collect the operation state data of the photovoltaic device and the meteorological data during the operation of the mountain photovoltaic power station. For example, the data acquisition module can include, but is not limited to, a current sensor, a voltage sensor, a power sensor, a temperature sensor, an irradiance sensor, a light sensor, a temperature sensor, a wind speed and direction sensor, a humidity sensor, an inverter sensor, a box transformer sensor, and a current combiner sensor. The operation state data of the photovoltaic device can include, but is not limited to, the output current, voltage and power of the photovoltaic device, the light intensity, the temperature of the photovoltaic device, the input and output voltage, current and power of the inverter, the load rate of the box transformer, the winding temperature, the cooling system state, and the current and voltage of each branch. The meteorological data can include, but is not limited to, the light intensity, the ambient temperature and humidity, the wind speed and direction information.

[0029] The inspection module is configured to control the unmanned aerial vehicle to collect the appearance state information of the photovoltaic device according to a preset inspection route. For example, the preset inspection route can be an optimal inspection path planned in advance based on the inspection requirements by a path planning algorithm, and the specific content of the preset inspection route is not limited in the embodiments of the present application, which can be determined by a person skilled in the art according to the requirements. The appearance state information of the photovoltaic device can include, but is not limited to, the image data of the appearance of the photovoltaic device.

[0030] The data analysis and processing module is connected with the data acquisition module and the inspection module, and is configured to perform fault monitoring on the mountain photovoltaic power station according to the meteorological data, the operation state data of the photovoltaic device and the appearance state data. For example, in the embodiments of the present application, the data analysis and processing module acquires the meteorological data, the operation state data of the photovoltaic device and the appearance state data collected by the data acquisition module and the inspection module. The data analysis and processing module first removes the noise, error values and repeated data in the meteorological data, the operation state data of the photovoltaic device and the appearance state data, removes the data beyond the normal range such as the data with negative light intensity by setting a reasonable data threshold, smoothes the data with large fluctuations by using a filtering algorithm, removes the noise caused by interference, and directly deletes the repeated data. The integrated and cleaned meteorological data, the operation state data of the photovoltaic device and the appearance state data are formed into a unified data table, and the integrated and cleaned meteorological data, the operation state data of the photovoltaic device and the appearance state data are subjected to feature extraction to obtain the first feature of the meteorological data, the second feature of the operation state data and the third feature of the appearance state data. The first feature, the second feature and the third feature are subjected to feature fusion to obtain source feature data, the extracted multi-source features are subjected to abnormality detection by using statistical analysis methods and machine learning algorithms, and the abnormal features are deleted. The normal operation data model is established, the real-time data is compared, and when the data deviates from the normal model to a certain extent, it is determined to be abnormal.

[0031] Specifically, taking feature extraction of photovoltaic device operation data as an example, the photovoltaic device operation data (peak power, open circuit voltage, short circuit current, maximum power point, etc.) is normalized, and the formula is:

[0032]

[0033] Where STC is the standard test condition, MPPT is the maximum power point tracking value, I norm represents the measured current value, I actual represents the actual current, I MPPT represents the maximum power point current, I STC represents the current under standard test conditions, G STC represents the irradiance under standard test conditions, G actual represents the actual irradiance.

[0034] The Haversine distance calculated from the latitude and longitude and the data collection time difference are used to construct a spatio-temporal correlation matrix, and the formula is:

[0035]

[0036] Where i and j represent two time points on the time axis; Δt ij is the data collection time difference, d geo is the Haversine distance calculated from the latitude and longitude; σ d = 100 m, is a adjustable parameter.

[0037] The physical constraint feature is generated, and the formula is:

[0038] F phy = ReLU (W p · [P pred || P ideal ])

[0039] P ideal = η·S·G·(1-0.0045(T-25))

[0040] Where F phy represents the physical constraint feature vector, ReLU represents the linear rectifier function, η represents the nominal efficiency of the component, S represents the effective light receiving area of the component, G represents the effective irradiance of the component, T represents the temperature of the component back plate, W p represents the trainable weight matrix, P pred represents the predicted power, P ideal represents the theoretical ideal power.

[0041] The valuable features are obtained by feature fusion, and the formula is:

[0042] F final = α·Fphy +(1-alpha) GCN(M, F raw )

[0043] In the formula, F final represents normalized data, alpha represents a normalization coefficient, GCN represents a graph convolutional neural network, M represents a model feature value, F raw represents an original data set.

[0044] And calculate its power generation efficiency, power fluctuation coefficient, etc. ; for environmental data, extract the change trend of light intensity, the daily variation amplitude of temperature, etc.

[0045] The extracted features are detected for abnormalities by using statistical analysis methods and machine learning algorithms, and abnormal features are deleted, a model of normal operation data is established, real-time data is compared, when the data deviates from the normal model to a certain extent, it is determined to be abnormal, and then the detected features are sent to the power prediction module as input data for model prediction.

[0046] The mountain photovoltaic power station monitoring system provided by the application collects the running state data of photovoltaic equipment and meteorological data during the operation of the mountain photovoltaic power station by using the data acquisition module; the appearance state information of the photovoltaic equipment is collected by using the inspection module; the data analysis and processing module is used to monitor the fault of the mountain photovoltaic power station according to the meteorological data, the running state data of the photovoltaic equipment and the appearance state data, which can timely identify the abnormal operation state and potential fault of the photovoltaic power station, and solve the problems of low efficiency, high cost and inability to timely discover the risks existing in the operation of the mountain photovoltaic power station in the related art.

[0047] In some optional embodiments, the system further comprises a power prediction module.

[0048] The data analysis and processing module is further configured to send initial multi-source feature data of the first period generated in the fault monitoring process to the power prediction module, and the initial multi-source feature data comprises initial meteorological feature data.

[0049] Exemplarily, in the embodiments of the application, the first period can be any period, the data analysis and processing module extracts features from the meteorological data, the running state data of the photovoltaic equipment and the appearance state data of the first period to obtain multi-source feature data of the first period, and the multi-source feature data refers to meteorological feature data valuable for power prediction, and in the embodiments of the application, the initial multi-source feature data can include but is not limited to the change trend of light intensity, the daily variation amplitude of temperature, power generation efficiency, power fluctuation coefficient, etc.

[0050] The power prediction module is configured to input the terrain data of the mountain photovoltaic power station and the initial meteorological feature data in a first time period into a pre-constructed meteorological correction model, so that the meteorological correction model outputs target meteorological feature data of the mountain photovoltaic power station in the first time period.

[0051] Exemplarily, the terrain data of the mountain photovoltaic power station can include, but is not limited to, terrain parameters of a geographical area where the mountain photovoltaic power station is located. In the embodiment of the present application, a digital elevation model is generated by acquiring terrain data of the area where the mountain photovoltaic power station is located through satellite remote sensing and a geographic information system, and terrain parameters such as slope, slope direction and terrain shading factor are calculated based on the digital elevation model. Specifically, the meteorological correction model considers the influence of terrain on meteorology and corrects the light intensity data input into the multi-source data fusion model. For example, the light intensity originally monitored by the meteorological station is 800 W / m 2 , and after correction, it becomes 750 W / m 2 . The corrected meteorological data is input into the multi-source data fusion model, which facilitates the multi-source data fusion model to predict the power generation based on more accurate data.

[0052] The power prediction module is further configured to input the target multi-source feature data of the mountain photovoltaic power station in the first time period into a pre-constructed multi-source data fusion model, so that the multi-source data fusion model outputs power generation of the mountain photovoltaic power station in a second time period, the target multi-source feature data being obtained by replacing the initial meteorological feature data in the initial multi-source feature data with the target meteorological feature data, and the second time period being later than the first time period.

[0053] Exemplarily, the second time period is later than the first time period, the initial meteorological feature data in the initial multi-source feature data is replaced with the corrected target meteorological feature data to obtain the target multi-source feature data. Specifically, when the power generation at 10 o'clock in the morning of the next day needs to be predicted, the multi-source feature data in the time period before 9 o'clock in the morning of the same day is input into the multi-source data fusion model, and the multi-source data fusion model preliminarily predicts the power generation at 10 o'clock in the morning according to the learned relationship between different data. For example, the model finds that when the light intensity increases by 100 W / m 2 , the power generation will increase by a certain value under the condition that other conditions remain unchanged, and the power generation prediction value is given in combination with the temperature, component electrical parameters and other data at that time.

[0054] In some optional embodiments, the meteorological correction model is constructed by the following steps:

[0055] Step a1, acquiring terrain data, a plurality of initial meteorological feature data and a plurality of target meteorological feature data corresponding to different photovoltaic power stations respectively.

[0056] Exemplarily, the terrain data includes, but is not limited to, terrain parameters such as slope, slope direction and terrain shading factor of the photovoltaic power station, and geographic location information, which can be obtained by a pre-set geographic information acquisition sensor in the data acquisition module in the embodiment of the present application. The target meteorological feature data is obtained by feature extraction from actual meteorological data of the photovoltaic power station.

[0057] Step a2, associating the terrain data of each photovoltaic power station with the corresponding plurality of initial meteorological feature data to obtain a plurality of first associated data. Exemplarily, the association manner is not limited in the embodiment of the present application, as long as it is reasonable.

[0058] Step a3, associating the plurality of first associated data of each photovoltaic power station with the plurality of target meteorological feature data to obtain an associated data set. Exemplarily, the first associated data is associated with the corresponding target meteorological feature data to obtain the associated data set.

[0059] Step a4, training the first preset model by using the associated data set until the model accuracy reaches the preset requirement to obtain a meteorological correction model.

[0060] Exemplarily, in the embodiment of the present application, the first associated data is used as the output of the first preset model, the first preset model is trained until the model accuracy reaches the preset requirement to obtain the meteorological correction model, and the preset requirement can be determined based on the actual demand, which is not limited in the embodiment of the present application. The first preset model can include, but is not limited to, a machine learning model.

[0061] In some optional embodiments, the multi-source data fusion model is obtained by the following steps:

[0062] Step b1, obtaining the multi-source feature sequence data and the power generation sequence data of the photovoltaic power station.

[0063] Exemplarily, the multi-source feature sequence data is used to represent the multi-source feature data corresponding to different time nodes in a preset time period. The power generation sequence data can be obtained by historical power generation data of the photovoltaic power station, and the power generation sequence data is used for power generation corresponding to different time nodes in a preset time period. Specifically, historical meteorological data, geographic information data, photovoltaic equipment electrical parameters and historical power generation data of the mountain photovoltaic power station are collected, including light intensity, temperature, humidity, wind speed, wind direction, etc., geographic information data such as terrain, topography, altitude, photovoltaic equipment electrical parameters such as voltage, current, power, and integration is performed. The collected data is cleaned to remove outliers, such as power data that deviates significantly from the normal range, missing values are filled, a small amount of missing meteorological data can be supplemented by interpolation method, and normalization processing is performed to convert data of different ranges and dimensions to the same scale, such as normalizing light intensity and temperature data to the [0, 1] interval. Key features are extracted from the processed data to obtain multi-source feature sequence data, for example, fill factor, maximum power point tracking efficiency, etc. are calculated from electrical parameters, and light accumulation, average wind speed, etc. in different time periods are extracted from meteorological data. Derivative features can also be constructed, such as temperature and light ratio obtained by combining light intensity and temperature.

[0064] Step b2, the multi-source feature sequence data is divided by using a first preset length sliding window to obtain first training data.

[0065] Exemplarily, the first preset length can be determined based on requirements, and the multi-source feature sequence data is divided by using a first preset length sliding window to divide the multi-source feature sequence data into a plurality of first sub-sequences, and the plurality of first sub-sequences are used as first training data.

[0066] Step b2, the power generation sequence data is divided by using a second preset length sliding window to obtain second training data.

[0067] Exemplarily, the second preset length can be determined based on requirements, and the power generation sequence data is divided by using a first preset length sliding window to divide the power generation sequence data into a plurality of second sub-sequences, and the plurality of second sub-sequences are used as second training data.

[0068] Step b3, the first training data and the second training data are associated according to a preset requirement to construct a data set.

[0069] Exemplarily, the embodiments of the present application do not limit the preset requirement, and a person skilled in the art can determine according to requirements. Specifically, the first sub-sequence of the first time period and the second sub-sequence of the second time period can be associated, and the first time period can be the previous time period adjacent to the second time period.

[0070] Step b4, training the second preset model according to the data set to obtain a multi-source data fusion model.

[0071] Exemplarily, in the embodiments of the present application, the second preset model can be a deep learning framework such as TensorFlow or PyTorch, and a model containing an input layer, a hidden layer and an output layer is built, the input layer receives the processed data, the hidden layer processes the data dependency relationship, and the output layer outputs the predicted value. The correlation data set is divided into a training set, a validation set and a test set, the training parameters are set, the loss function and the optimizer are selected to train the model, the performance is monitored by using the validation set during training, the multi-source data fusion model is evaluated by using the test set, and the structure or parameters of the multi-source data fusion model are adjusted according to the evaluation result for optimization.

[0072] In some optional embodiments, the preset inspection route is determined by the following steps:

[0073] Step c1, obtaining layout information of photovoltaic equipment in a region where the mountain photovoltaic power station is located.

[0074] Exemplarily, in the embodiments of the present application, the topographic data of the mountain photovoltaic power station and the surrounding region is obtained by using satellite remote sensing images and three-dimensional laser scanning technology, and a digital elevation model is constructed, which needs to present the terrain features of the mountain such as undulation, slope, valley and ridge. At the same time, the geographic coordinate information of the power station is collected to determine its accurate position on the map. Through field survey combined with the design drawings of the power station, the information of the row spacing, arrangement angle and partition of the photovoltaic equipment is mastered, and the positions and sizes of the obstacles such as buildings, trees, high-voltage cables and towers in the power station region are recorded and measured in detail. The total station instrument, laser range finder and other equipment can be used for measurement, so as to determine the layout information of the photovoltaic equipment and the topographic information of the mountain photovoltaic power station.

[0075] Step c2, dividing the region where the mountain photovoltaic power station is located based on the layout information to obtain a plurality of sub-regions.

[0076] Exemplarily, in the embodiments of the present application, according to the layout of the photovoltaic modules and the terrain features, the mountain photovoltaic power station is divided into a plurality of relatively independent rectangular or polygonal regions (sub-regions). When dividing, the layout of the photovoltaic modules in each region should be as uniform as possible, and at the same time, the size of the region is controlled according to the endurance and flight speed of the unmanned aerial vehicle. For the region with complex terrain, the range of the region can be reduced.

[0077] Step c3, determining a plurality of path node information of each sub-region.

[0078] Exemplarily, in the embodiments of the present application, in each sub-region, the key points of the rows and columns of photovoltaic modules, the turning points of the region boundaries, and the safety points around the obstacles are selected as the path nodes, for example, the nodes are set at the starting point, the intermediate point and the end point of the rows and columns of photovoltaic modules, and the nodes are set near the devices that are likely to malfunction.

[0079] In step c4, the inspection route in the corresponding sub-region is planned based on a preset path planning algorithm and the path node information of each sub-region, and a preset inspection route in the corresponding sub-region is obtained.

[0080] Exemplarily, in the embodiments of the present application, according to actual requirements and data characteristics, a corresponding path planning algorithm is selected, such as Dijkstra algorithm or A algorithm, the starting point and the path nodes of each region are input into the selected algorithm, the shortest or optimal path to each node is calculated with the starting point as the base point, in the calculation process, the distance between nodes and terrain factors need to be considered, for each node, the distance to the starting point and other related costs are calculated, through iterative calculation of the algorithm, the best path from the starting point to each node is gradually found, and thus a preliminary inspection route is generated. According to the performance parameters of the unmanned aerial vehicle, the preliminary inspection route is optimized, and at the same time, the collected meteorological data are combined to adjust the path, so that the final inspection route is generated, and it is ensured that the total length of the path does not exceed the endurance mileage of the unmanned aerial vehicle. The terrain complexity level (flat area / slope area / steep cliff area) is divided based on the DEM digital elevation model: the flat area adopts the spiral coverage path (Spiral Coverage) to maximize the straight flight segment; the gentle slope area adopts the improved plow type path (Boustrophedon) to cooperate with the slope adaptive height adjustment; the steep cliff area adopts the three-dimensional Z-type scanning (3D Zigzag Scanning) combined with the obstacle pre-avoidance algorithm; the transition section between different regions adopts the minimum energy consumption path (MECP) algorithm, and the downward flight is preferentially selected. The final inspection route is stored in the flight control system of the unmanned aerial vehicle.

[0081] Further, the system provided by the present application further comprises a monitoring and management platform for visually displaying the operation state of the photovoltaic power station, the inspection result and the power prediction data. The visualization of the monitoring and management platform comprises the following steps:

[0082] In step d1, the corresponding data is obtained from the data acquisition module, the inspection module, the data analysis and processing module and the power prediction module, the data format is unified, and the data is stored in categories;

[0083] Step d2, according to different data characteristics and display requirements, select the appropriate visualization chart type, for running state data, use line chart to show the trend of photovoltaic module power with time, facilitate observation of power fluctuation; use column chart to compare the power generation efficiency of photovoltaic modules in different regions, quickly find out the efficiency difference, the patrol result data can be presented in the form of table, list the patrol time, place, found problem and treatment in detail, for the area with fault, mark with different color on the power station map, intuitive display of fault distribution, power prediction data uses area chart to show the change range of predicted power in a period of time in the future, so that the operation and maintenance personnel have overall cognition of the future power generation of the power station;

[0084] Step d3, send the visualization chart to the display screen.

[0085] According to the embodiment of the present application, a mountain photovoltaic power station monitoring method is also provided. It should be noted that the steps shown in the flowchart of the drawing can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0086] In the present embodiment, a mountain photovoltaic power station monitoring method is provided, which can be used in the above-mentioned mountain photovoltaic power station monitoring system, Figure 2 The flowchart of the mountain photovoltaic power station monitoring method according to the embodiment of the present application is shown in Figure 2 The flowchart includes the following steps:

[0087] Step S201, obtain the meteorological data of the mountain photovoltaic power station, the running state data and the appearance state data of the photovoltaic equipment in the mountain photovoltaic power station. For example, refer to the description of the related content in the above embodiment for details, which will not be repeated here.

[0088] Step S202, respectively integrate and clean the meteorological data, the running state data and the appearance state data, to obtain the target meteorological feature data, the target running state data and the target appearance state data after processing. For example, refer to the description of the related content in the above embodiment for details, which will not be repeated here.

[0089] Step S203, respectively extract features from the target meteorological feature data, the target running state data and the target appearance state data, to obtain the first feature data of the target meteorological feature data, the second feature data of the target running state data and the third feature data of the target appearance state data.

[0090] Step S204, based on the first feature data, the second feature data and the third feature data, perform fault monitoring on the mountain photovoltaic power station.

[0091] Exemplarily, in the embodiments of the present application, the first feature data, the second feature data and the third feature data are fused to obtain multi-source fusion feature data, and the multi-source fusion feature data is used for fault monitoring of the mountain photovoltaic power station.

[0092] The mountain photovoltaic power station monitoring method provided in the embodiments integrates and cleans the meteorological data, the operation state data and the appearance state data to obtain processed target meteorological feature data, target operation state data and target appearance state data; the target meteorological feature data, the target operation state data and the target appearance state data are subjected to feature extraction to obtain first feature data of the target meteorological feature data, second feature data of the target operation state data and third feature data of the target appearance state data; and the mountain photovoltaic power station is subjected to fault monitoring based on the first feature data, the second feature data and the third feature data, which can identify abnormal operation state and potential fault of the photovoltaic power station in time, and solves the problems of low efficiency, high cost and inability to find risks existing in the operation of the mountain photovoltaic power station in time in the related art through manual inspection.

[0093] The mountain photovoltaic power station monitoring method and system provided by the present application will be specifically described below through specific embodiments.

[0094] Embodiment 1

[0095] Please refer to Figure 3 , the mountain photovoltaic power station monitoring method specifically comprises the following steps:

[0096] Step 1: Install and debug the system hardware devices, ensure that all kinds of sensors of the data acquisition module are correctly installed in the photovoltaic components, equipment and surrounding environment, stably run and normally transmit data. At the same time, check the unmanned aerial vehicle to ensure that the camera, infrared thermal imager and flight control system carried by the unmanned aerial vehicle are in good condition. In terms of software, start the system software such as data analysis and processing module, monitoring and management platform, etc. to ensure smooth communication between modules, collect the basic data of the mountain photovoltaic power station, such as using satellite remote sensing image, three-dimensional laser scanning technology to obtain terrain data to construct digital elevation model, combining field survey and power station design drawings to master photovoltaic component layout, obstacle information, collect local meteorological data, etc. to prepare for subsequent work;

[0097] Step two: According to the collected data, the final inspection route is generated by using relevant algorithms according to the inspection route planning step and stored in the unmanned aerial vehicle flight control system. The unmanned aerial vehicle takes off according to the planned route. The camera and infrared thermal imager carried by the unmanned aerial vehicle collect the appearance state information of the photovoltaic equipment. The image and data are transmitted to the data analysis and processing module in real time through wireless communication. During the inspection process, the inspection route can be manually adjusted on the monitoring and management platform according to the actual situation to ensure that the inspection work is completed comprehensively and efficiently.

[0098] Step three: The data acquisition module continuously collects photovoltaic module electrical parameters, meteorological data, geographic information data and equipment state data, and transmits them to the data analysis and processing module in real time through wired or wireless communication. During data transmission, the communication link state is checked regularly. If data transmission is interrupted or abnormal, the fault is checked in time to ensure the continuity and integrity of the data.

[0099] Step four: The data analysis and processing module receives the collected and inspection data, and sequentially removes noise, error values and duplicate data, integrates different source data, extracts valuable features for photovoltaic power plant operation analysis and power prediction, and performs preprocessing operations such as anomaly detection and deletion of abnormal features using statistical analysis methods and machine learning algorithms. The preprocessed feature data is automatically sent to the power prediction module, and the abnormal data and potential fault information are displayed in real time on the monitoring and management platform for timely processing by the operation and maintenance personnel.

[0100] Step five: The power prediction module receives the preprocessed data, predicts the future power generation of the mountain photovoltaic power station based on the multi-source data fusion model and the weather correction model, and adjusts the model parameters according to the actual needs during the prediction process to improve the prediction accuracy. The prediction results are transmitted to the monitoring and management platform in real time.

[0101] Step six: The monitoring and management platform obtains data from each module, stores them in a unified format and classifies them, selects appropriate visualization charts according to the characteristics of the data, and displays the visualization charts on the display screen. The operation and maintenance personnel can view the operation state of the photovoltaic power station, the inspection results and the power prediction data in real time through the monitoring and management platform, arrange maintenance personnel to handle faults in time according to the abnormal prompt, and arrange power dispatching and equipment maintenance plan reasonably according to the power prediction results.

[0102] Example 2

[0103] Specifically, assume that a photovoltaic power station is built in a mountainous area. The power station covers a large area and has a complex terrain, including a large number of photovoltaic modules, inverters, transformers, combiner boxes and other equipment. Based on this photovoltaic power station, the system provided by the present application is described in detail.

[0104] Sensors of data acquisition modules are installed at key positions of the photovoltaic power station, such as current sensors, voltage sensors, power sensors, temperature sensors and irradiance sensors installed on photovoltaic modules to monitor electrical parameters and temperature, light and other environmental parameters of the modules; wind speed and direction sensors, humidity sensors are installed around the power station to obtain meteorological data; corresponding sensors are installed on inverters, transformers and combiner boxes to monitor the operating status of the equipment; geographic information acquisition sensors are used to obtain geographic information of the power station, and the unmanned aerial vehicle is checked and debugged to ensure that the camera and infrared thermal imager carried by the unmanned aerial vehicle work normally and the flight control system is stable and reliable.

[0105] Further, system software such as data analysis and processing module, monitoring and management platform is started, and communication between modules is ensured to be normal, satellite remote sensing images and three-dimensional laser scanning technology are used to obtain topographic data of the mountain photovoltaic power station and its surrounding area, a digital elevation model is constructed, and through field survey combined with power station design drawings, information such as row spacing, arrangement angle and partition of photovoltaic modules is mastered, and obstacles such as buildings, trees, high-voltage cables and towers in the power station area are recorded in detail in terms of position and size, and meteorological data including dominant wind direction, wind speed, precipitation, temperature and other information are collected from local meteorological stations or meteorological monitoring equipment of the power station to prepare for subsequent work.

[0106] According to the collected data, a related algorithm is used to plan the inspection route, first, the mountain photovoltaic power station is divided into multiple relatively independent rectangular regions, according to the layout of the photovoltaic modules and the terrain characteristics, the starting point, the middle point and the end point of the photovoltaic module rows and columns in each region, as well as the boundary turning points of the region and the safety points around the obstacles are selected as path nodes, the Dijkstra algorithm is selected, the starting point and the path nodes of each region are input into the algorithm, the shortest path to each node is calculated, and a preliminary inspection route is generated, then according to the endurance mileage, flight speed and other performance parameters of the unmanned aerial vehicle, combined with the collected meteorological data, the preliminary inspection route is optimized and adjusted to ensure that the total length of the path does not exceed the endurance capability of the unmanned aerial vehicle, and can avoid areas with severe weather conditions, finally an inspection route suitable for the unmanned aerial vehicle to fly is generated, and stored in the flight control system of the unmanned aerial vehicle.

[0107] The unmanned aerial vehicle is operated to take off and inspect according to the planned inspection route, and in the inspection process, the camera and infrared thermal imager carried by the unmanned aerial vehicle take pictures and thermal imaging detection of the photovoltaic equipment to obtain appearance state information of the photovoltaic equipment, such as whether the module is damaged, thermal spot and other abnormal conditions, and the unmanned aerial vehicle transmits the collected images and data to the data analysis and processing module in real time through wireless communication to discover equipment problems in time.

[0108] The various sensors of the data acquisition module continuously collect photovoltaic module electrical parameters, meteorological data, geographic information data, and equipment status data. For example, a current sensor monitors the output current of the photovoltaic module in real time, and a wind speed and direction sensor continuously collects current wind speed and direction information.

[0109] Further, the sensors transmit the collected data to the data analysis and processing module through wired or wireless communication. During data transmission, the communication link status is regularly checked. If data transmission is interrupted or abnormal, the fault is promptly investigated to ensure that data can be continuously and completely transmitted, providing reliable data support for subsequent data analysis and processing.

[0110] Further, after receiving the data sent by the data acquisition module and the inspection module, the data analysis and processing module first performs data preprocessing, sets reasonable data thresholds, removes data outside the normal range such as negative light intensity, uses filtering algorithms to smooth data with large fluctuations to remove noise, and deletes duplicate data. Then, the photovoltaic module performance data, environmental monitoring data, and equipment operating status data are associated and integrated according to time and geographic location to form a unified data table.

[0111] Further, valuable features for photovoltaic power plant operation analysis and power prediction are extracted from the integrated data. For photovoltaic module performance data, power generation efficiency and power fluctuation coefficient are calculated. For environmental data, the change trend of light intensity and the daily variation amplitude of temperature are extracted. Statistical analysis methods and machine learning algorithms are used to detect anomalies in the extracted features. By establishing a model of normal operation data, real-time data is compared. When the data deviates from the normal model to a certain extent, it is determined to be abnormal, and the abnormal features are deleted. The processed feature data is automatically sent to the power prediction module. At the same time, abnormal data and potential fault information are displayed in real time on the monitoring and management platform to remind the operation and maintenance personnel to handle it in a timely manner.

[0112] Further, a multi-source data fusion model and a weather correction model are constructed, historical weather data, geographic information data, photovoltaic component electrical parameters and historical power generation data of the mountain photovoltaic power station are collected and integrated, cleaned, normalized and the like, key features such as the fill factor, the maximum power point tracking efficiency, the light accumulation amount in different time periods and the like are extracted from the processed data, derived features such as the temperature-light ratio are constructed, the TensorFlow deep learning framework is selected to build a multi-source data fusion model including an input layer, a hidden layer and an output layer, the key features and the derived features are divided into a training set, a validation set and a test set, training parameters are set, a suitable loss function and an optimizer are selected to train the model, the validation set is used to monitor the performance during training, the test set is used to evaluate the model, and the model structure or parameters are adjusted and optimized according to the evaluation results, terrain data is obtained through satellite remote sensing and geographic information system to generate a digital elevation model, terrain parameters such as slope, aspect and terrain shading factor are calculated based on the digital elevation model, weather data of weather stations around the mountain photovoltaic power station is collected, and weather information of the power station area is obtained by using a spatial interpolation method, and a weather correction model is established by statistical analysis, such as a regression equation of the light intensity and the slope and aspect.

[0113] Further, when the power generation at 10 o'clock in the morning of the next day needs to be predicted, the multi-source data of a period of time before 9 o'clock in the morning of the current day is input into the multi-source data fusion model, and the model preliminarily predicts the power generation at 10 o'clock in the morning according to the learned relationship between different data. For example, the model finds that when the light intensity increases by 100 W / m 2 , the power generation will increase by a certain value under other conditions unchanged, combined with the temperature, component electrical parameters and the like at that time, a preliminary prediction value is given, at the same time, weather data is obtained from the mountain photovoltaic power station and its surrounding environment, and is input into the weather correction model to calculate the corrected weather parameters, such as the light intensity of 800 W / m 2 , which is corrected to 750 W / m 2 , the corrected weather data is re-input into the multi-source data fusion model to adjust the preliminary prediction of the power generation, so that the prediction result is more in line with the power generation under the actual environment of the mountain, and the prediction result is transmitted to the monitoring and management platform in real time.

[0114] The monitoring and management platform obtains corresponding data from the data acquisition module, the inspection module, the data analysis and processing module and the power prediction module, unifies the data format, and stores them in categories.

[0115] A mountain photovoltaic power station monitoring device is also provided in the embodiment, which is used to implement the above-mentioned embodiments and preferred embodiments, and has been described above and will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, implementation of hardware, or a combination of software and hardware, is also possible and contemplated.

[0116] The embodiment provides a mountain photovoltaic power station monitoring device, which comprises: Figure 4

[0117] The acquisition module 401 is configured to acquire meteorological data of the mountain photovoltaic power station, operation state data of photovoltaic equipment in the mountain photovoltaic power station, and appearance state data.

[0118] The processing module 402 is configured to integrate and clean the meteorological data, the operation state data, and the appearance state data respectively to obtain target meteorological feature data, target operation state data, and target appearance state data.

[0119] The feature extraction module 403 is configured to perform feature extraction on the target meteorological feature data, the target operation state data, and the target appearance state data respectively to obtain first feature data of the target meteorological feature data, second feature data of the target operation state data, and third feature data of the target appearance state data.

[0120] The detection module 404 is configured to perform fault monitoring on the mountain photovoltaic power station based on the first feature data, the second feature data, and the third feature data.

[0121] Further function descriptions of the above-mentioned modules and units are the same as those of the corresponding embodiments, and will not be repeated here.

[0122] The mountain photovoltaic power station monitoring device in the embodiment is presented in the form of a functional unit, and the unit herein refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0123] The embodiment of the present application also provides a computer device with the mountain photovoltaic power station monitoring device shown in the above. Figure 4

[0124] Please refer to Figure 5 , Figure 5 is a structural schematic diagram of a computer device provided in an optional embodiment of the present application, as shown in Figure 5 ​​As shown, the computer device includes one or more processors 10, memory 20, and interfaces 30 for external devices such as a keyboard and a mouse and peripheral devices such as disk devices or other storage devices. One or more busses 10 can be used to implement the interface between the various internal and external components and can be implemented using any one or more of a variety of bus technologies including a System bus, PCI, SCSI, AGP, Super- I / O bus, etc. Furthermore, various buses can be used in front side buses, back side buses, and other bus configurations based on any bus or messaging technology known to those skilled in the art. Figure 5 The processor 10 is used in the embodiments below as an example.

[0125] The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0126] The memory 20 stores instructions that can be executed by the at least one processor 10, so that the at least one processor 10 implements the method shown in the above embodiments.

[0127] The memory 20 can include a program region and a data region. The program region can store an operating system and application programs required by at least one function. The data region can store data created according to the use of the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some alternative embodiments, the memory 20 can optionally include a memory disposed remotely with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0128] The memory 20 can include a volatile memory such as a random access memory, and can also include a non-volatile memory such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned kinds of memories.

[0129] The computer device further includes a communication interface 30 for communication with other devices or communication networks.

[0130] The embodiments of the present application further provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0131] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, the method and / or technical solutions according to the present application can be called or provided. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source file, executable file, installation package file, etc. Correspondingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0132] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A monitoring system for a mountain photovoltaic power station, characterized in that, The system includes: a data acquisition module, an inspection module, and a data analysis and processing module; The data acquisition module is used to collect operating status data of photovoltaic equipment and meteorological data during the operation of the mountain photovoltaic power station. The inspection module is used to control the drone to collect the appearance status information of the photovoltaic equipment according to the preset inspection route; The data analysis and processing module is connected to the data acquisition module and the inspection module respectively, and is used to monitor the mountain photovoltaic power station for faults based on the meteorological data, the operating status data of the photovoltaic equipment and the appearance status data.

2. The system according to claim 1, characterized in that, The system also includes: a power prediction module; The data analysis and processing module is also used to send the initial multi-source feature data of the first time period generated during the fault monitoring process to the power prediction module. The initial multi-source feature data includes initial meteorological feature data. The power prediction module is used to input the terrain data of the mountain photovoltaic power station and the initial meteorological characteristic data of the first time period into the pre-built meteorological correction model, so that the meteorological correction model outputs the target meteorological characteristic data of the mountain photovoltaic power station in the first time period. The power prediction module is also used to input the target multi-source feature data of the mountain photovoltaic power station in the first time period into the pre-constructed multi-source data fusion model, so that the multi-source data fusion model outputs the power generation of the mountain photovoltaic power station in the second time period. The target multi-source feature data is obtained by replacing the initial meteorological feature data in the initial multi-source feature data with the target meteorological feature data. The second time period is later than the first time period.

3. The system according to claim 2, characterized in that, The meteorological correction model is constructed through the following steps: Acquire terrain data, multiple initial meteorological feature data, and multiple target meteorological feature data corresponding to different photovoltaic power stations; The terrain data of each photovoltaic power station is correlated with multiple corresponding initial meteorological feature data to obtain multiple first correlation data; Multiple first-association data from each photovoltaic power station are associated with the multiple target meteorological feature data to obtain an associated dataset; The first preset model is trained using the associated dataset until the model accuracy reaches the preset requirement, thus obtaining the meteorological correction model.

4. The system according to claim 2 or 3, characterized in that, The multi-source data fusion model is constructed through the following steps: Acquire multi-source feature sequence data and power generation sequence data of photovoltaic power plants; The multi-source feature sequence data is divided using a sliding window of a first preset length to obtain the first training data; The power generation sequence data is divided using a sliding window of a second preset length to obtain the second training data; The first training data and the second training data are associated according to preset requirements to construct a dataset; The second preset model is trained based on the dataset to obtain a multi-source data fusion model.

5. The system according to any one of claims 1 to 3, characterized in that, The preset inspection route is determined through the following steps: Obtain the layout information of photovoltaic equipment in the area where the mountain photovoltaic power station is located; Based on the aforementioned layout information, the area where the mountain photovoltaic power station is located is divided into multiple sub-regions; Determine the path node information for each sub-region; Based on the preset path planning algorithm and the information of multiple path nodes in each sub-region, the inspection route in the corresponding sub-region is planned, and the preset inspection route in the corresponding sub-region is obtained.

6. A monitoring method for a mountain photovoltaic power station, characterized in that, The method, applied to the mountain photovoltaic power station monitoring system according to any one of claims 1 to 5, comprises: Acquire meteorological data, operational status data, and appearance data of photovoltaic equipment in mountain photovoltaic power stations; The meteorological data, the operational status data, and the appearance status data are integrated and cleaned respectively to obtain the processed target meteorological characteristic data, target operational status data, and target appearance status data. Feature extraction is performed on the target meteorological feature data, the target operational status data, and the target appearance status data respectively to obtain the first feature data of the target meteorological feature data, the second feature data of the target operational status data, and the third feature data of the target appearance status data; Fault monitoring is performed on the mountain photovoltaic power station based on the first feature data, the second feature data, and the third feature data.

7. A monitoring device for a mountain photovoltaic power station, characterized in that, The device includes: The acquisition module is used to acquire meteorological data, operational status data of photovoltaic equipment in mountain photovoltaic power stations, and appearance status data. The processing module is used to integrate and clean the meteorological data, the operational status data and the appearance status data respectively to obtain the processed target meteorological feature data, target operational status data and target appearance status data. The feature extraction module extracts features from the target meteorological feature data, the target operating status data, and the target appearance status data respectively, to obtain the first feature data of the target meteorological feature data, the second feature data of the target operating status data, and the third feature data of the target appearance status data. The detection module is used to perform fault monitoring on the mountain photovoltaic power station based on the first feature data, the second feature data, and the third feature data.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the mountain photovoltaic power station monitoring method of claim 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the mountain photovoltaic power station monitoring method of claim 6.

10. A computer program product, characterized in that, It includes computer instructions, which are used to cause the computer to execute the mountain photovoltaic power station monitoring method of claim 6.

Images