New Energy Power Station Intelligent Management System and Method Based on 5G Communication

Abstract

The present invention discloses an intelligent management system and method for new energy stations based on 5G communication, which belongs to the field of blockchain technology. The system includes: a first area inspection module, a second area inspection module, a photovoltaic component inspection module and a new energy smart supervision platform. The first area inspection of the present invention uses a trackless walking robot, the second area inspection uses AI cameras and infrared thermal imaging technology, and the photovoltaic component inspection is completed by drones. All data is transmitted to the smart supervision platform via 5G. The platform calculates the safety coverage, closed-loop tracking and defect recognition coefficients, and transmits them to the blockchain for storage, so that data can be obtained in bad weather and in difficult-to-reach locations, thereby improving the work quality of new energy station inspections, making up for the blind spots of manual inspections, improving work quality and operation and maintenance efficiency, and solving the problem of difficulty in ensuring work quality in new energy station inspections in the existing technology.

Description

Technical Field

[0001] The present invention relates to the field of blockchain technology, and in particular to a new energy station intelligent management system and method based on 5G communication. Background Art

[0002] 5G communication technology, the fifth generation of mobile communication technology, boasts scalability, reliability, and timeliness. New energy sites, such as power plants, solar cell plants, and wind farms, are primarily located in complex geographical environments, including plains, hills, and mountains. New energy industries include solar energy, nuclear energy, wind energy, biomass energy, geothermal energy, hydrogen energy, and tidal energy. Solar energy resources are vast, widely distributed, environmentally friendly, and inexhaustible, offering the potential to meet growing electricity demand. Because 5G communication technology offers excellent penetration and is virtually unaffected by external factors, it can provide a reliable spectrum. Therefore, 5G mobile communication technology can be used to promote the development of distributed new energy.

[0003] As economic development increases the demand for power reliability, photovoltaic power generation, as a new energy source, has seen a rapid increase in the number and volume of power generation equipment, more complex operation conditions, and diversified equipment inspections with short cycles. The operation and maintenance frequency of some equipment requires twice a month, and in special sections it is even increased to once a day. Currently, inspection work still relies mainly on manpower.

[0004] For example, the invention patent announcement number CN116308306B discloses a 5G-based smart management system and method for new energy stations, which includes: determining multiple evaluation intervals based on the operating cycle of the distribution equipment, and then calculating the changing trend value of the distribution equipment operation based on the historical operating parameters of each evaluation interval, so that the calculation result of the changing trend value of the distribution equipment is more accurate, and the changing trend value of the distribution equipment operation can also be verified to screen out old historical operating parameters.

[0005] For example, the patent application with publication number CN117196574A discloses a photovoltaic intelligent diagnosis and evaluation method, which includes: S1: building a computer system architecture; S2: building an online monitoring and diagnosis algorithm model; and S3: conducting a comprehensive energy efficiency evaluation and analysis and cross-validating the overall power plant model.

[0006] However, in the process of implementing the technical solutions of the embodiments of the present application, the present application discovered that the above technology has at least the following technical problems:

[0007] Currently, faced with the arduous inspection tasks, the quality of manual inspections depends largely on the skill level of the operation and maintenance personnel. In bad weather or special locations that are difficult for personnel to reach easily, there are blind spots in the inspection, which makes it difficult to ensure the quality of work and increases the pressure on operation and maintenance.

[0008] In summary, for photovoltaic power generation scenarios, the existing technology has the problem that it is difficult to ensure the quality of inspection work at new energy stations. Summary of the Invention

[0009] The embodiments of the present application solve the problem in the prior art that it is difficult to ensure the quality of inspection work at new energy stations by providing an intelligent management system and method for new energy stations based on 5G communication, thereby improving the quality of inspection work at new energy stations.

[0010] The embodiment of the present application provides an intelligent management system for new energy stations based on 5G communication, including: a first area inspection module, a second area inspection module, a photovoltaic component inspection module and a new energy smart supervision platform; wherein, the first area inspection module is used to inspect the first area of the new energy station according to the inspection path through a trackless walking robot, obtain first inspection data, and transmit the first inspection data to the new energy smart supervision platform through 5G communication technology; the second area inspection module is used to inspect the second area of the new energy station through an AI camera and infrared thermal imaging technology, obtain second inspection data, and transmit the second inspection data to the new energy smart supervision platform through 5G communication technology. Supervision platform; the photovoltaic component inspection module is used to inspect photovoltaic components through drones, identify photovoltaic component defects, and transmit component inspection data to the new energy smart supervision platform through 5G communication technology; the new energy smart supervision platform is used to derive a safety coverage coefficient based on the first inspection data, derive a closed-loop tracking and monitoring coefficient based on the second inspection data, and derive a defect identification coefficient based on the component inspection data. The inspection coverage coefficient, closed-loop tracking and monitoring coefficient, and defect identification coefficient are used to visualize the operating status of the new energy station, and the first inspection data, the second inspection data, the component inspection data, the safety coverage coefficient, the closed-loop tracking and monitoring coefficient, and the defect identification coefficient are transmitted to the blockchain for storage.

[0011] Furthermore, the first area inspection module includes an area division unit, a mobile inspection unit and a 5G transmission unit; the area division unit is used to obtain an inspection area map A of the first area of the new energy station from the blockchain, divide the first area into a first inspection sub-area according to the inspection area map A, and number the first inspection sub-area, and obtain the inspection path according to the full coverage path planning algorithm; the mobile inspection unit is used to inspect the first inspection sub-area in the first area in sequence based on the inspection path by a trackless walking robot, and obtain the first inspection data corresponding to the first area; the 5G transmission unit is used to transmit the first inspection data to the new energy smart supervision platform through 5G communication technology.

[0012] Furthermore, the process of deriving the safety coverage coefficient based on the first inspection data is: preprocessing the first inspection data, the first inspection data including: switch status information, indicator light status information, equipment temperature value, harmful gas detection value; constructing a safety coverage coefficient model based on the preprocessed first inspection data; deriving the safety coverage coefficient of each first inspection sub-area in the first area based on the safety coverage coefficient model, and the safety coverage coefficient is used to reflect the safety level of the first inspection sub-area.

[0013] Furthermore, the trackless walking robot includes a first patrol data acquisition unit, a real-time interaction unit and a photoelectric obstacle stop navigation system; the first patrol data acquisition unit is used to acquire first patrol data; the real-time interaction unit is used to transmit the first patrol data to the first area patrol module; the photoelectric obstacle stop navigation system is used to immediately stop the trackless walking robot from moving when an obstacle is detected in front, and is also used to obtain three-dimensional data of the robot's surrounding environment through a 3D laser radar device, and match the surrounding environment in the form of a three-dimensional point cloud map.

[0014] Furthermore, the second area inspection module includes a second inspection data acquisition unit, a 5G communication unit and a closed-loop tracking and monitoring unit; the second inspection data acquisition unit is used to acquire second inspection data, and the second inspection data includes visible light images of the second area, equipment temperature of the second area and abnormal status of equipment in the second area; the 5G communication unit is used to transmit the second inspection data to the new energy smart supervision platform through 5G communication technology; the closed-loop tracking and monitoring unit is used to derive a closed-loop tracking and monitoring coefficient based on the second inspection data.

[0015] Furthermore, the closed-loop tracking and monitoring unit includes a data processing unit, a closed-loop demand monitoring unit, a trend analysis unit and a closed-loop control unit; the data processing unit is used to receive, store and pre-process the second inspection data; the closed-loop demand monitoring unit constructs a closed-loop tracking and monitoring model based on the pre-processed second inspection data, and obtains a closed-loop tracking and monitoring coefficient through the closed-loop tracking and monitoring model, and the closed-loop tracking and monitoring coefficient is used to reflect the degree of demand for re-inspection of the second inspection area; the closed-loop control unit is used to issue an alarm to notify the user to re-inspect the second inspection data using a remote adjustment device according to the closed-loop tracking and monitoring coefficient when the closed-loop tracking and monitoring coefficient exceeds threshold A, and no notification is given when the closed-loop tracking and monitoring coefficient does not exceed threshold A.

[0016] Furthermore, the analysis method of the closed-loop tracking monitoring coefficient is: obtaining the second inspection data for preprocessing and extracting the inspection feature data, including the visible light image feature value of the second area, the temperature feature value of the equipment in the second area and the abnormal state value of the equipment in the second area, obtaining the historical re-inspection data and extracting the cause feature data of the re-inspection; normalizing the inspection feature data and the cause feature data; finding the mapping relationship between the inspection feature data and the cause feature data through the support vector machine algorithm; finding the maximum value of the inspection feature data corresponding to the cause feature data according to the mapping relationship; obtaining the maximum visible light image feature value of the second area, and comparing the visible light image feature value of the second area with the maximum visible light image feature value of the second area , obtain the characteristic value of the visible light image ratio in the second area; obtain the temperature characteristic value of the equipment in the second area, compare the temperature characteristic value of the equipment in the second area with the maximum temperature characteristic value of the equipment in the second area, and obtain the temperature danger characteristic value of the equipment in the second area; the abnormal state value of the equipment in the second area includes 0 and 1, when the abnormal state value of the equipment in the second area is 0, it means that there is no abnormality in the equipment in the second area, and when the abnormal state value of the equipment in the second area is 1, it means that there is an abnormality in the equipment in the second area; a closed-loop tracking and monitoring model is constructed based on the characteristic value of the visible light image ratio in the second area, the temperature danger characteristic value of the equipment in the second area, and the abnormal state value of the equipment in the second area, and a closed-loop tracking and monitoring coefficient is obtained through the closed-loop tracking and monitoring model; the closed-loop tracking and monitoring model is:

[0017]

[0018] Where BH is the closed-loop tracking monitoring coefficient, PV is the characteristic value of the visible light image ratio in the second area, e is a natural constant, CF is the temperature hazard characteristic value of the equipment in the second area, n is the number of the equipment in the second inspection area, n = 1, 2, 3, ..., N, N is the total number of equipment numbers in the second inspection area, TR n The device abnormal status value of the second area of the nth device.

[0019] Furthermore, the specific method for identifying defects in photovoltaic modules is as follows: performing sub-array segmentation through image data collected by drones, dividing the photovoltaic station image into different sub-arrays, each sub-array containing multiple photovoltaic modules; accurately locating each photovoltaic module based on the latitude and longitude information of each sub-array and the position of the photovoltaic module, and marking its geographical location; processing and analyzing the collected photovoltaic module images through artificial intelligence image recognition algorithms, combining infrared image data, visible light image data and laser rangefinder data to identify and classify defects in the photovoltaic modules; and marking the identified defect type and its position relative to the image on the corresponding photovoltaic module.

[0020] Furthermore, the defect recognition coefficient is obtained by: obtaining the defect locations of the photovoltaic modules in the subarray, counting the number of defects corresponding to different defect types in each subarray; obtaining the reference value of power generation loss corresponding to each defect type, and analyzing the power generation loss value in the subarray; obtaining the total number of photovoltaic modules in each subarray to obtain the total number of photovoltaic modules; and calculating the defect recognition coefficient based on the total number of photovoltaic modules, the total number of photovoltaic module defects in the subarray, and the power generation loss value in the subarray. The defect recognition coefficient is used to reflect the severity of the defects in the photovoltaic modules. The calculation formula of the defect recognition coefficient is:

[0021]

[0022] In the formula, GQ h is the defect recognition coefficient corresponding to the h-th sub-array, is the total number of PV module defects of the jth defect type in the hth subarray, is the power generation loss value of the jth defect type in the hth sub-array, is the reference value of power generation loss corresponding to the jth defect type, GR is the total number of PV modules, h is the subarray number, h = 1, 2, 3, ..., H, H is the total number of subarray numbers, j is the number of the PV module defect type, j = 1, 2, 3, ..., J, J is the total number of PV module defect type numbers.

[0023] Furthermore, the process of transmitting to the blockchain is: integrating the first inspection data, the second inspection data, the component inspection data and the related safety coverage coefficient, the closed-loop tracking monitoring coefficient and the defect identification coefficient into a data packet; encrypting the integrated data packet, and transmitting the encrypted data packet to the blockchain network using 5G communication technology; creating a new block on the blockchain, and storing the encrypted data packet as transaction data in the block.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0025] 1. By deploying drone smart hangars, using 5G communication technology, and applying artificial intelligence image recognition algorithms, drones are used to conduct intelligent inspections of photovoltaic components, making it possible to obtain data in inclement weather and in hard-to-reach locations, thereby improving the quality of inspections at new energy stations, filling the blind spots of manual inspections, improving work quality and operation and maintenance efficiency, and effectively solving the problem of difficulty in ensuring work quality in inspections at new energy stations in existing technologies.

[0026] 2. Through artificial intelligence image recognition algorithms, PV panels are intelligently inspected, image data is divided into sub-arrays, each PV panel is accurately located, and defects are identified and classified using infrared image data, visible light image data, etc., so that the identified defect type and its location are marked on the corresponding PV panel, thereby improving the accuracy and efficiency of defect identification.

[0027] 3. Through the closed-loop tracking monitoring model, the inspection data is monitored and analyzed in real time to detect abnormal situations in time, and the data is transmitted to the smart supervision platform through 5G communication technology, so as to timely monitor and manage the operation status of the photovoltaic station. In turn, managers can monitor and analyze the operation status of the photovoltaic station anytime and anywhere, take timely response measures, and ensure the stable operation of the photovoltaic power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A schematic diagram of the structure of a new energy station intelligent management system based on 5G communication provided in an embodiment of the present application;

[0029] Figure 2 This is a structural diagram of the inspection module in the first area;

[0030] Figure 3 This is a structural diagram of the second area inspection module;

[0031] Figure 4 This is a schematic diagram of the closed-loop tracking and monitoring unit structure;

[0032] Figure 5 This is a graph showing how the defect recognition coefficient changes with the total number of PV module defects and power generation loss. DETAILED DESCRIPTION

[0033] The embodiments of the present application solve the problem in the prior art that it is difficult to ensure the quality of inspection work at new energy stations by providing an intelligent management system and method for new energy stations based on 5G communication. By utilizing the efficient data transmission capabilities of the 5G network and comprehensively utilizing technologies such as the Internet of Things, cloud computing, and AI, a "cloud-pipe-edge-end" power Internet of Things management solution for photovoltaic scenarios is constructed, thereby improving the quality of inspection work at new energy stations.

[0034] The technical solution in the embodiment of the present application is to solve the problem that it is difficult to ensure the quality of inspection work at the new energy station mentioned above. The overall idea is as follows:

[0035] By introducing 5G communications, various inspection modules, and a new energy smart supervision platform, comprehensive inspection and monitoring of station equipment can be achieved. Inspections are carried out using trackless walking robots, AI cameras, infrared thermal imaging technology, drones, and other equipment to obtain inspection data from various areas and transmit it to the new energy smart supervision platform via 5G communications technology. On the new energy smart supervision platform, the safety coverage coefficient, closed-loop tracking monitoring coefficient, and defect identification coefficient are calculated based on the inspection data. The operating status of the station is reflected in a visual manner, and the relevant data is transmitted to the blockchain for storage, thereby achieving comprehensive monitoring of inspection work, timely identification of defects, and improving the quality of inspection work at new energy stations.

[0036] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0037] like Figure 1 As shown in the figure, it is a structural diagram of the intelligent management system of the new energy station based on 5G communication provided by the embodiment of the present application. The intelligent management system of the new energy station based on 5G communication provided by the embodiment of the present application includes: a first area inspection module, a second area inspection module, a photovoltaic component inspection module and a new energy smart supervision platform; wherein, the first area inspection module is used to inspect the first area of the new energy station according to the inspection path by a trackless walking robot, obtain the first inspection data, and transmit the first inspection data to the new energy smart supervision platform through 5G communication technology; the second area inspection module is used to inspect the second area of the new energy station through AI cameras and infrared thermal imaging technology, obtain the second inspection data, and transmit the second inspection data to the new energy smart supervision platform through 5G communication technology. The second inspection data is transmitted to the new energy smart supervision platform through 5G communication technology; the photovoltaic component inspection module is used to inspect photovoltaic components through drones, identify photovoltaic component defects, and transmit the component inspection data to the new energy smart supervision platform through 5G communication technology; the new energy smart supervision platform is used to derive the safety coverage coefficient based on the first inspection data, derive the closed-loop tracking and monitoring coefficient based on the second inspection data, and derive the defect identification coefficient based on the component inspection data. The inspection coverage coefficient, closed-loop tracking and monitoring coefficient and defect identification coefficient are used to visualize the operating status of the new energy station, and the first inspection data, second inspection data, component inspection data, safety coverage coefficient, closed-loop tracking and monitoring coefficient and defect identification coefficient are transmitted to the blockchain for storage.

[0038] In this embodiment, 5G communication technology is the fifth generation of mobile communication technology, the latest mobile communication technology after 4G, and an extension of 2G, 3G, and 4G systems. Compared with 4G mobile communication technology, 5G mobile communication technology exhibits the following three characteristics: (1) Scalability. 5G mobile communication technology realizes the integration and optimization of various traditional mobile communication technology features to provide a comprehensive and high-quality service experience. According to relevant data, the coverage of 5G mobile communication technology is about 10 times that of 4G mobile coverage, and the signal stability is better, which can ensure the communication convenience of users in various regions. (2) Reliability. The throughput capacity of mobile communication technology can meet the various different needs of people in the new era. It is an important criterion for evaluating the level of a mobile communication technology. It is also the key to evaluating whether 5G mobile communication technology can benefit the people. 5G mobile communication technology is very reliable and can significantly reduce user delays, providing people with a high-quality experience. (3) Timeliness. Compared with 4G mobile communication, 5G communication technology pays more attention to user experience. For example, 5G communication technology has a much higher reception frequency than 4G mobile communication technology. This is because 5G mobile communication technology offers excellent penetration performance, is virtually unaffected by external factors, and can provide a reliable spectrum. Therefore, 5G mobile communication technology can promote the development of distributed new energy.

[0039] The first area of the new energy station includes the external inspection area of the booster station. This station carries a large volume of inspection information, requiring inspection and recording of various meters, switch status, and indicator lights, as well as equipment temperature measurement and detection of hazardous gases. Some areas within the plant have poor environmental conditions, high dust content, or the risk of hazardous gas leaks, posing a high safety risk to personnel during long-term inspections.

[0040] Trackless walking robots are inspection robots that can replace or assist humans in inspection, patrol, security and other tasks. They can accurately execute and dock at designated locations according to path planning and work requirements, provide infrared temperature measurement, meter reading recording and abnormal status alarm functions for inspection equipment, and realize background functions such as real-time upload of inspection data, information display, and report generation. They have the characteristics of high inspection efficiency, strong stability and reliability.

[0041] An automated inspection robot is deployed at the 110kV photovoltaic substation to regularly conduct equipment inspections within the substation, transmitting video and collected data via a dedicated 5G network. The robot enables remote visualization of substation inspections, providing real-time monitoring of the substation's environmental conditions. It can perform routine inspections, fixed-point inspections, remote inspections, infrared rapid general testing, equipment defect tracking, and voice reporting.

[0042] The second area of new energy stations involves internal inspections of substations. These stations contain numerous key equipment, such as transformers, which require regular inspections to prevent equipment failures. This results in low O&M efficiency, requiring on-site personnel to complete inspections. Furthermore, there are inconsistent inspection standards, non-standardized inspection processes, and a lack of closed-loop tracking of inspection defects. Robotic inspection systems primarily address the low efficiency and non-standardized processes of manual O&M. However, wheeled or mounted robots are used, depending on the site conditions. Using built-in AI cameras and infrared thermal imaging, they identify switchgear voltage and current meters, switch status displays, and energy storage indicators along planned routes and locations. Combined with infrared temperature measurement of transformers and switchgear, equipment appearance identification, and noise detection, they automatically generate inspection reports based on inspection standards, improving inspection efficiency and preventing the escalation of risks caused by non-standardized inspections. Furthermore, when a system reports a fault or anomaly, the robot can be remotely controlled for a remote inspection, improving troubleshooting efficiency and avoiding wasted travel time.

[0043] The inspection coverage coefficient, closed-loop tracking and monitoring coefficient, and defect identification coefficient are used to visualize the operating status of new energy stations. Specifically, the distribution of safety coverage coefficients for each first-inspection sub-area is displayed through heat maps or maps. The closed-loop tracking and monitoring coefficient and defect identification coefficient are displayed on the supervision platform interface in the form of charts, curves, and heat maps, providing an intuitive view of the operating status of new energy stations.

[0044] Further, such as Figure 2 As shown, this is a structural schematic diagram of the first area inspection module. The first area inspection module includes an area division unit, a mobile inspection unit and a 5G transmission unit; the area division unit is used to obtain the inspection area map A of the first area of the new energy station from the blockchain, divide the first area into the first inspection sub-area according to the inspection area map A, and number the first inspection sub-area, and obtain the inspection path according to the full coverage path planning algorithm; the mobile inspection unit is used to inspect the first inspection sub-area in the first area in sequence based on the inspection path by a trackless walking robot, and obtain the first inspection data corresponding to the first area; the 5G transmission unit is used to transmit the first inspection data to the new energy smart supervision platform through 5G communication technology.

[0045] In this embodiment, the first area of the new energy station is divided into multiple inspection sub-areas using an area division unit. Each sub-area is assigned a number and an inspection path. A mobile inspection unit then performs inspections using a trackless walking robot, acquiring corresponding first inspection data within each sub-area. Finally, a 5G transmission unit transmits this data via 5G communication technology to the new energy smart supervision platform, enabling operations and maintenance personnel to monitor and manage station safety and equipment status in real time.

[0046] Furthermore, the process for deriving the safety coverage factor based on the first inspection data is as follows: preprocessing the first inspection data includes data cleaning, which removes outliers, null values, and duplicate values to ensure data accuracy and completeness; data integration, which integrates data from different sources and time periods into a unified format to facilitate subsequent model calculations; and anomaly detection, which marks or corrects anomalies in the data to reduce interference with the model. The first inspection data includes: switch status information, indicator light status information, equipment temperature values, and hazardous gas detection values; constructing a safety coverage factor model based on the preprocessed first inspection data; and deriving the safety coverage factor for each first inspection sub-area in the first area based on the safety coverage factor model. The safety coverage factor is used to reflect the safety level of the first inspection sub-area.

[0047] In this embodiment, the calculation process of the safety coverage coefficient is for the first inspection data. The safety coverage coefficient model is constructed through the preprocessed data, and then the safety coverage coefficient of each first inspection sub-area is obtained. It can objectively reflect the safety situation of the first inspection sub-area, provide important safety assessment basis for operation and maintenance personnel, facilitate timely identification of potential safety risks and problems, and thus take corresponding management and maintenance measures to ensure the safe and stable operation of new energy stations.

[0048] Furthermore, the trackless walking robot includes a first patrol data acquisition unit, a real-time interaction unit and a photoelectric obstacle stop navigation system; the first patrol data acquisition unit is used to acquire first patrol data; the real-time interaction unit is used to transmit the first patrol data to the first area patrol module; the photoelectric obstacle stop navigation system is used to immediately stop the trackless walking robot from moving when an obstacle is detected in front, and is also used to obtain three-dimensional data of the robot's surrounding environment through a 3D laser radar device, and match the surrounding environment in the form of a three-dimensional point cloud map.

[0049] In this embodiment, the trackless walking robot is equipped with an infrared thermal imager, a visible light HD camera, an interactive real-time intercom platform, and a photoelectric obstacle prevention system. It consists of a wheeled inspection robot body, a four-wheel drive, four-turn off-road chassis, a power supply unit, a sensor unit, a control unit, and a positioning and navigation unit. The combination of these multiple modules and the switching of multiple algorithms enables optimal strategy-based image acquisition during motion.

[0050] Utilizing 3D LiDAR navigation, the robot captures three-dimensional data of its surroundings using a 3D LiDAR device, mapping the surrounding environment to a 3D point cloud. This point cloud technology increases scanning density by 30 times, achieving position accuracy of ±1cm and heading angle accuracy of ±0.5°. This precise positioning demonstrates exceptional environmental adaptability. The system boasts strong anti-interference capabilities, ensuring effective and stable positioning even with sparse natural features. It also captures the robot's posture information, adapting to height differences and uneven surfaces, and enabling three-dimensional environmental detection. It automatically detects the forward 3D area, addressing potholes and falling surfaces, and provides comprehensive obstacle avoidance and fall prevention.

[0051] Further, such as Figure 3 As shown, this is a structural schematic diagram of the second area inspection module. The second area inspection module includes a second inspection data acquisition unit, a 5G communication unit and a closed-loop tracking and monitoring unit; the second inspection data acquisition unit is used to obtain the second inspection data, and the second inspection data includes the visible light image of the second area, the temperature of the equipment in the second area and the abnormal status of the equipment in the second area; the 5G communication unit is used to transmit the second inspection data to the new energy smart supervision platform through 5G communication technology; the closed-loop tracking and monitoring unit is used to derive the closed-loop tracking and monitoring coefficient based on the second inspection data.

[0052] In this embodiment, the 5G communication unit is used to transmit the acquired inspection data to the new energy smart supervision platform via 5G communication technology, ensuring real-time data transmission and rapid response. The closed-loop tracking and monitoring unit calculates and derives a closed-loop tracking and monitoring coefficient based on the second inspection data, which is used to assess and reflect the demand level of the second inspection area, thereby enabling monitoring and control of the inspection process. The collaborative operation of the entire module provides timely and accurate data support for the operation and management of the new energy station, ensuring its safe and efficient operation.

[0053] Further, such as Figure 4 The figure shows a schematic diagram of the structure of the closed-loop tracking and monitoring unit, which includes a data processing unit, a closed-loop demand monitoring unit, a trend analysis unit and a closed-loop control unit; the data processing unit is used to receive, store and pre-process the second inspection data; the closed-loop demand monitoring unit constructs a closed-loop tracking and monitoring model based on the pre-processed second inspection data, and obtains a closed-loop tracking and monitoring coefficient through the closed-loop tracking and monitoring model. The closed-loop tracking and monitoring coefficient is used to reflect the degree of demand for re-inspection of the second inspection area; the closed-loop control unit is used to issue an alarm to notify the user to re-inspect the second inspection data using a remote adjustment device based on the closed-loop tracking and monitoring coefficient when the closed-loop tracking and monitoring coefficient exceeds the threshold value A. When the closed-loop tracking and monitoring coefficient does not exceed the threshold value A, no notification is given.

[0054] In this embodiment, the characteristic value of the visible light image ratio in the second area is set to 1, that is, the visible light image reaches the maximum, the characteristic value of the device temperature danger in the second area is set to 1, that is, the device temperature reaches the maximum, and the total value of the abnormal state value of the device in the second area is set to 1, that is, the minimum number of devices in the abnormal state (excluding the case where all states are normal), and the threshold value A is obtained to be 7.389.

[0055] Furthermore, the analysis method of the closed-loop tracking monitoring coefficient is as follows: obtain the second inspection data for preprocessing and extract inspection feature data, including the visible light image feature value of the second area, the temperature feature value of the equipment in the second area and the abnormal state value of the equipment in the second area, obtain the historical re-inspection data and extract the cause feature data of the re-inspection; normalize the inspection feature data and the cause feature data; find the mapping relationship between the inspection feature data and the cause feature data through the support vector machine algorithm; find the maximum value of the inspection feature data corresponding to the cause feature data according to the mapping relationship; obtain the maximum visible light image feature value of the second area, and compare the visible light image feature value of the second area with the maximum visible light image feature value of the second area. The ratio is used to obtain the characteristic value of the visible light image ratio in the second area; the temperature characteristic value of the equipment in the second area is obtained, and the temperature characteristic value of the equipment in the second area is compared with the maximum temperature characteristic value of the equipment in the second area to obtain the temperature danger characteristic value of the equipment in the second area; the abnormal state value of the equipment in the second area includes 0 and 1. When the abnormal state value of the equipment in the second area is 0, it means that there is no abnormality in the equipment in the second area; when the abnormal state value of the equipment in the second area is 1, it means that there is an abnormality in the equipment in the second area; a closed-loop tracking and monitoring model is constructed based on the characteristic value of the visible light image ratio in the second area, the temperature danger characteristic value of the equipment in the second area, and the abnormal state value of the equipment in the second area, and the closed-loop tracking and monitoring coefficient is obtained through the closed-loop tracking and monitoring model; the closed-loop tracking and monitoring model is:

[0056]

[0057] Where BH is the closed-loop tracking monitoring coefficient, PV is the characteristic value of the visible light image ratio in the second area, e is a natural constant, CF is the temperature hazard characteristic value of the equipment in the second area, n is the number of the equipment in the second inspection area, n = 1, 2, 3, ..., N, N is the total number of equipment numbers in the second inspection area, TR n The second area device abnormal status value of the nth device.

[0058] In this embodiment, PV≠0, the closed-loop tracking and monitoring coefficient BH can be obtained by the above method, and can also be calculated by multivariate regression analysis. The specific steps are: collecting historical inspection data and fault data; cleaning and standardizing the collected historical inspection data and fault data, removing missing values and outliers, and extracting characteristic values to form a data set, dividing the data set into a training set and a test set, constructing a multivariate linear regression model, fitting the multivariate linear regression model using the training data set, and estimating the regression coefficient by the least squares method to minimize the sum of squared errors between the predicted value and the actual value. The performance of the model is evaluated using the test data set. Common evaluation indicators include mean square error (MSE), root mean square error (RMSE), etc., to analyze the relationship between equipment status indicators and fault risks; according to the multivariate linear regression model, the health status of the equipment and the closed-loop tracking and monitoring coefficient are calculated.

[0059] The characteristic value of the visible light image proportion in the second area can be obtained by using an AI camera to obtain the visible light image data of the second area, and then extracting the characteristic value and normalizing it through an image processing algorithm (such as edge detection, morphological processing, etc.).

[0060] The temperature hazard characteristic value of the equipment in the second area can be obtained by obtaining temperature data of the equipment in the second area using infrared thermal imaging technology. Alternatively, the temperature of the equipment can be regularly measured using a temperature sensor and a thermal imaging camera, and the temperature hazard characteristic value of the equipment in the second area can be obtained by calculation.

[0061] The device abnormality status value for the second zone of the nth device is determined by monitoring the device's operating status. An abnormality status value of 0 indicates a normal device, while a value of 1 indicates an abnormal device. The monitoring system determines the device's status through sensors, diagnostic software, and historical data analysis.

[0062] Table 1 is an example table of closed-loop tracking and monitoring coefficients, assuming N = 3, as shown in the following table:

[0063] PV CF <![CDATA[TR1]]> <![CDATA[TR2]]> <![CDATA[TR3]]> BH 0.5 0.1 0 0 0 2.2288 1.0 0.2 0 1 0 4.5036 1.5 0.3 1 0 1 7.3641 2.0 0.4 1 1 1 12.5186 2.5 0.5 0 0 1 4.3404

[0064] It can be seen from the table that when the number of abnormal state values of the equipment in the second area is abnormal value 1 is greater, the temperature hazard characteristic value of the equipment in the second area is higher, and the characteristic value of the visible light image ratio in the second area is smaller (that is, the characteristic value of the light image ratio is lower), the closed-loop tracking monitoring coefficient increases faster and the value of the closed-loop tracking monitoring coefficient is larger, and vice versa, the smaller it is, which reflects the potential equipment failure, facilitates the optimization of resource allocation, reduces blind maintenance, and improves inspection efficiency.

[0065] Furthermore, the specific method for identifying defects in photovoltaic modules is as follows: performing sub-array segmentation through image data collected by drones, dividing the photovoltaic station image into different sub-arrays, each sub-array containing multiple photovoltaic modules; accurately locating each photovoltaic module based on the latitude and longitude information of each sub-array and the position of the photovoltaic module, and marking its geographical location; processing and analyzing the collected photovoltaic module images through artificial intelligence image recognition algorithms, combining infrared image data, visible light image data and laser rangefinder data to identify and classify photovoltaic module defects; marking the identified defect type and its position relative to the image on the corresponding photovoltaic module.

[0066] In this embodiment, by deploying drone smart hangars and industry-grade drones, and based on 5G private network link communication, fully unmanned 5G control and 5G backhaul of drones are achieved, enabling automatic route planning and automatic data collection for each regional array. Utilizing 5G UPF to carry the edge of the photovoltaic module defect recognition and intelligent positioning algorithm, inspection and collection data are based on AI-based rapid inspection and problem analysis, enabling rapid location, identification, and annotation of module fault points (hot spots, diodes, string defects, etc.), and automatically generating PDF reports by array, promptly and accurately feeding back the fault phenomenon and coordinates to operation and maintenance personnel, and simultaneously presenting the intelligent integrated management platform of the power station.

[0067] Utilizing artificial intelligence image recognition algorithms, the captured images are processed and analyzed to determine the defect type and location relative to the image. The system automatically segments all inspection images into corresponding subarrays based on geographic location and acquisition posture, intelligently analyzing the inspection image data classified into each subarray. Defects are identified, classified, and geographically labeled after fitting infrared and visible light image data with laser rangefinder data.

[0068] By integrating with the station's established panel inventory system (including array grouping, panel numbering, and longitude and latitude information), defect panels can be accurately matched based on longitude and latitude information, assisting management personnel in accurately troubleshooting defective panels. Finally, based on the results of defect identification and location, a defect report is automatically generated. This report includes defect statistics for each subarray, defect category, and defect location, providing O&M personnel with a basis for troubleshooting. Furthermore, power generation losses are calculated based on defect category, and a report of the results is provided to assist in O&M decision-making.

[0069] Further, such as Figure 5 As shown in the figure, the defect recognition coefficient changes with the total number of photovoltaic module defects and power generation loss value. GR = 1000. The defect recognition coefficient is obtained as follows: obtain the defect location of the photovoltaic modules in the subarray, count the corresponding number of defects of different defect types in each subarray, and sum the corresponding number of defects of different defect types in the subarray to obtain the total number of photovoltaic module defects of the same defect type in the subarray; obtain the reference value of power generation loss corresponding to each defect type, and analyze the power generation loss value in the subarray; obtain the total number of photovoltaic modules in each subarray to obtain the total number of photovoltaic modules; calculate the defect recognition coefficient based on the total number of photovoltaic modules, the total number of photovoltaic module defects in the subarray, and the power generation loss value in the subarray. The defect recognition coefficient is used to reflect the severity of the defects of the photovoltaic modules; the calculation formula of the defect recognition coefficient is:

[0070]

[0071] In the formula, GQ h is the defect recognition coefficient corresponding to the h-th sub-array, is the total number of PV module defects of the jth defect type in the hth subarray, is the power generation loss value of the jth defect type in the hth sub-array, is the reference value of power generation loss corresponding to the jth defect type, GR is the total number of PV modules, h is the subarray number, h = 1, 2, 3, ..., H, H is the total number of subarray numbers, j is the number of the PV module defect type, j = 1, 2, 3, ..., J, J is the total number of PV module defect type numbers.

[0072] In this embodiment, the defect recognition coefficient GQ corresponding to the hth sub-array is h In addition to obtaining it through the above methods, the defect recognition coefficient can also be obtained through a machine learning algorithm. The specific steps include: first, collecting a large amount of photovoltaic module image data and annotating this data, annotating the defect type and location information in each image; then, using this annotated data to construct a training set and a test set; then, selecting a machine learning algorithm, such as a convolutional neural network (CNN) or a support vector machine (SVM), and inputting the training set into the model for training; after training is completed, using the test set to evaluate the performance of the model and tune the model; finally, using the trained model to identify newly collected photovoltaic module images to obtain the defect recognition coefficient.

[0073] Reference value of power generation loss corresponding to the jth defect type The acquisition method is as follows: obtain historical photovoltaic module monitoring data for preprocessing, obtain the time-based mapping relationship between defect types and power generation information, extract power generation information A when a single defect type occurs, power generation information A includes power generation power A and power generation duration A, and extract power generation information B when no defects occur, power generation information B includes power generation power per unit duration B and power generation duration B; calculate the power generation loss value corresponding to the defect type based on the absolute value of the difference between power generation information A and power generation information B corresponding to the defect type, and then average all power generation loss values corresponding to the defect type to obtain the power generation loss reference value. The specific calculation formula is as follows:

[0074]

[0075] Where RV0 is the power generation per unit time B, AT0 is the power generation per unit time B, k is the number of occurrences of the j-th defect type, k = 1, 2, 3, ... k0, k0 is the total number of occurrences of the j-th defect type, is the power generation power A corresponding to the kth occurrence of the jth defect type, is the current power generation detection time corresponding to the kth occurrence of the jth defect type, is the defect detection time corresponding to the kth occurrence of the jth defect type.

[0076] The power generation per unit time B and the power generation time B can be extracted from historical PV module monitoring data. Generally, the power generation per unit time B refers to the average power generated by the PV module per unit time, assuming no defects, while the power generation time B refers to the average time it takes for the PV module to start and stop generating power under normal operating conditions.

[0077] Power generation A is obtained from historical PV module monitoring data. For the jth defect type, all monitoring records where that defect occurred can be identified and the power generation data from these records can be extracted to obtain the power generation corresponding to the kth occurrence of that defect type.

[0078] The current power generation detection time indicates the time when the defect occurred. This can be obtained from historical PV module monitoring data. When a defect occurs, the power generation detection time at that moment is recorded.

[0079] The defect detection time represents the time when the jth defect type first occurs. It can also be obtained from historical PV module monitoring data. When the jth defect type is identified, the time of occurrence is recorded.

[0080] PV module defects include contamination, damage, aging, partial shading, electrical faults, hot spots, condensation, and damaged connectors. These defects can affect the power and efficiency of PV modules, leading to power loss. Different defect types can cause varying degrees of power loss.

[0081] It is also possible to use mathematical models to simulate the impact of different defect types on power generation based on the physical properties and lighting conditions of photovoltaic modules. That is, by cleaning and standardizing the data of factors such as the photovoltaic module's photoelectric conversion efficiency, light intensity, and temperature, and then extracting features, the extracted feature result data set is divided into corresponding training sets and test sets. The training data set is used to fit a multivariate linear regression model, and the regression coefficient is estimated by the least squares method to minimize the sum of squared errors between the predicted value and the actual value. The performance of the model is evaluated using the test data set. Common evaluation indicators include mean square error (MSE), root mean square error (RMSE), etc., to calculate the reference value of power generation loss corresponding to different defect types.

[0082] Furthermore, the process of transmission to the blockchain is: integrating the first inspection data, the second inspection data, the component inspection data and the related safety coverage coefficient, the closed-loop tracking monitoring coefficient and the defect identification coefficient into a data packet; encrypting the integrated data packet, and using 5G communication technology to transmit the encrypted data packet to the blockchain network; creating a new block on the blockchain, and storing the encrypted data packet as transaction data in the block.

[0083] In this embodiment, inspection data and correlation coefficients are integrated into a single data package, encrypted, and then transmitted to the blockchain network, achieving secure data transmission and storage. The characteristics of blockchain technology, such as decentralization, immutability, and traceability, ensure data transparency and reliability while providing an effective mechanism to prevent data tampering and errors, thereby providing a reliable data foundation for the operation and management of new energy stations.

[0084] To summarize, the embodiments of the present application utilize drones to conduct intelligent inspections of photovoltaic modules by deploying drone smart hangars, using 5G communication technology, and applying artificial intelligence image recognition algorithms. This enables data to be acquired in inclement weather and in hard-to-reach locations, thereby improving the quality of inspections at new energy stations, addressing the blind spots of manual inspections, and improving work quality and operational efficiency.

[0085] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0089] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0090] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. The intelligent management system for new energy stations based on 5G communication is characterized by: include: First area inspection module, second area inspection module, photovoltaic module inspection module and new energy smart supervision platform; The first area inspection module is configured to inspect the first area of the new energy station along an inspection path using a trackless walking robot, obtain first inspection data, and transmit the first inspection data to the new energy smart supervision platform via 5G communication technology; The second area inspection module is used to inspect the second area of the new energy station using AI cameras and infrared thermal imaging technology, obtain second inspection data, and transmit the second inspection data to the new energy smart supervision platform through 5G communication technology; The photovoltaic module inspection module is used to inspect photovoltaic modules using drones, identify photovoltaic module defects, and transmit module inspection data to the new energy smart supervision platform via 5G communication technology; The new energy smart supervision platform is used to derive a safety coverage coefficient based on the first inspection data, a closed-loop tracking and monitoring coefficient based on the second inspection data, and a defect identification coefficient based on the component inspection data. The inspection coverage coefficient, the closed-loop tracking and monitoring coefficient, and the defect identification coefficient are used to visualize the operating status of the new energy station. The first inspection data, the second inspection data, the component inspection data, the safety coverage coefficient, the closed-loop tracking and monitoring coefficient, and the defect identification coefficient are transmitted to the blockchain for storage; The analysis method of the closed-loop tracking monitoring coefficient is: Obtain the second inspection data for preprocessing and extract inspection feature data, including the second area visible light image feature value, the second area device temperature feature value and the second area device abnormal state value, Obtain historical re-inspection data and extract the characteristic data of the reasons for re-inspection; Normalize inspection feature data and cause feature data; Use support vector machine algorithm to find the mapping relationship between inspection feature data and cause feature data; Find the maximum value of the inspection feature data corresponding to the cause feature data according to the mapping relationship; Obtaining a maximum visible light image characteristic value of the second region, and comparing the second region visible light image characteristic value with the maximum visible light image characteristic value of the second region to obtain a visible light image proportion characteristic value of the second region; Obtaining a temperature characteristic value of equipment in the second area, comparing the temperature characteristic value of the equipment in the second area with a maximum temperature characteristic value of the equipment in the second area, and obtaining a temperature danger characteristic value of the equipment in the second area; The second-area device abnormal state value includes 0 and 1. When the second-area device abnormal state value is 0, it indicates that the second-area device has no abnormality. When the second-area device abnormal state value is 1, it indicates that the second-area device has an abnormality. A closed-loop tracking and monitoring model is constructed based on the characteristic value of the visible light image proportion in the second area, the temperature hazard characteristic value of the equipment in the second area, and the abnormal state value of the equipment in the second area, and the closed-loop tracking and monitoring coefficient is obtained through the closed-loop tracking and monitoring model.

2. The new energy station intelligent management system based on 5G communication as claimed in claim 1, characterized in that: The first area inspection module includes an area division unit, a mobile inspection unit and a 5G transmission unit; The area division unit is configured to obtain an inspection area map A of a first area of the new energy station from the blockchain, divide the first area into first inspection sub-areas based on the inspection area map A, number the first inspection sub-areas, and determine an inspection path based on a full coverage path planning algorithm; The mobile inspection unit is configured to inspect the first inspection sub-area in the first area in sequence based on the inspection path using a trackless walking robot, and obtain first inspection data corresponding to the first area; The 5G transmission unit is used to transmit the first inspection data to the new energy smart supervision platform through 5G communication technology.

3. The new energy station intelligent management system based on 5G communication as claimed in claim 2, characterized in that: The process of obtaining the safety coverage factor based on the first inspection data is as follows: Preprocessing the first inspection data, wherein the first inspection data includes: switch status information, indicator light status information, device temperature value, and harmful gas detection value; Constructing a safety coverage coefficient model based on the pre-processed first inspection data; The security coverage coefficient of each first inspection sub-area in the first area is obtained according to the security coverage coefficient model, and the security coverage coefficient is used to reflect the security level of the first inspection sub-area.

4. The new energy station intelligent management system based on 5G communication as claimed in claim 1, characterized in that: The trackless walking robot includes a first inspection data acquisition unit, a real-time interaction unit and a photoelectric obstacle prevention navigation system; The first inspection data acquisition unit is used to acquire first inspection data; The real-time interaction unit is used to transmit the first inspection data to the first area inspection module; The photoelectric obstacle-stopping navigation system is used to immediately stop the trackless walking robot from moving when an obstacle is detected in front. It is also used to match the surrounding environment in the form of a three-dimensional point cloud map using the three-dimensional data of the robot's surrounding environment obtained through a 3D laser radar device.

5. The new energy station intelligent management system based on 5G communication as claimed in claim 1, characterized in that: The second area inspection module includes a second inspection data acquisition unit, a 5G communication unit and a closed-loop tracking and monitoring unit; The second inspection data acquisition unit is used to acquire second inspection data, where the second inspection data includes a visible light image of the second area, a temperature of equipment in the second area, and an abnormal state of equipment in the second area; The 5G communication unit is used to transmit the second inspection data to the new energy smart supervision platform through 5G communication technology; The closed-loop tracking and monitoring unit is used to obtain a closed-loop tracking and monitoring coefficient based on the second inspection data.

6. The new energy station intelligent management system based on 5G communication as claimed in claim 5, characterized in that: The closed-loop tracking and monitoring unit includes a data processing unit, a closed-loop demand monitoring unit, a trend analysis unit and a closed-loop control unit; The data processing unit is used to receive, store and pre-process the second inspection data; The closed-loop demand monitoring unit is configured to construct a closed-loop tracking monitoring model based on the pre-processed second inspection data, and to obtain a closed-loop tracking monitoring coefficient through the closed-loop tracking monitoring model, wherein the closed-loop tracking monitoring coefficient is used to reflect the degree of need for re-inspection of the second inspection area; The closed-loop control unit: when the closed-loop tracking monitoring coefficient exceeds threshold A, an alarm is issued to notify the user to use the remote adjustment device to re-inspect the second inspection data according to the closed-loop tracking monitoring coefficient; when the closed-loop tracking monitoring coefficient does not exceed threshold A, no notification is given.

7. The new energy station intelligent management system based on 5G communication as claimed in claim 1, characterized in that: The closed-loop tracking and monitoring model is: Where BH is the closed-loop tracking monitoring coefficient, PV is the characteristic value of the visible light image ratio in the second area, e is a natural constant, CF is the temperature hazard characteristic value of the equipment in the second area, n is the number of the equipment in the second inspection area, n = 1, 2, 3, ..., N, N is the total number of equipment numbers in the second inspection area, TR n The device abnormal status value of the second area of the nth device.

8. The new energy station intelligent management system based on 5G communication as claimed in claim 1, characterized in that: The specific method for identifying defects in photovoltaic modules is as follows: The image data collected by the drone is used to perform sub-array segmentation, dividing the photovoltaic station image into different sub-arrays, each of which contains multiple photovoltaic modules; Based on the latitude and longitude information of each sub-array and the location of the photovoltaic modules, each photovoltaic module is accurately located and its geographical location is marked; The collected PV module images are processed and analyzed using artificial intelligence image recognition algorithms, and defects in PV modules are identified and classified by combining infrared image data, visible light image data, and laser rangefinder data. The identified defect types and their locations relative to the image are annotated on the corresponding PV modules.

9. The new energy station intelligent management system based on 5G communication as claimed in claim 8, characterized in that: The defect recognition coefficient is obtained as follows: Obtain the defect locations of the photovoltaic modules within the sub-array and count the number of defects corresponding to different defect types in each sub-array; Obtain the power generation loss reference value corresponding to each defect type and analyze the power generation loss value within the sub-array; Obtain the total number of photovoltaic modules in each sub-array to obtain the total number of photovoltaic modules; Calculating a defect recognition coefficient based on the total number of photovoltaic modules, the total number of defects in the photovoltaic modules in the sub-array, and the power generation loss value in the sub-array. The defect recognition coefficient is used to reflect the severity of defects in the photovoltaic modules. The calculation formula of the defect recognition coefficient is: In the formula, GQ h is the defect recognition coefficient corresponding to the h-th sub-array, is the total number of PV module defects of the jth defect type in the hth subarray, is the power generation loss value of the jth defect type in the hth sub-array, is the reference value of power generation loss corresponding to the jth defect type, GR is the total number of PV modules, h is the subarray number, h = 1, 2, 3, ..., H, H is the total number of subarray numbers, j is the number of the PV module defect type, j = 1, 2, 3, ..., J, J is the total number of PV module defect type numbers.

10. The method for the intelligent management system of a new energy station based on 5G communication according to any one of claims 1 to 9 is characterized in that: include: The process of transferring to the blockchain is as follows: Integrate the first inspection data, the second inspection data, the component inspection data, and the related safety coverage coefficient, closed-loop tracking monitoring coefficient, and defect identification coefficient into one data package; Encrypt the integrated data packets and transmit them to the blockchain network using 5G communication technology; Create a new block on the blockchain and store the encrypted data packet as transaction data in the block.

Images