Photovoltaic power station intelligent operation and maintenance system based on mobile 5G and unmanned aerial vehicle technology

Abstract

The invention provides a photovoltaic power station intelligent operation and maintenance system based on mobile 5G and unmanned aerial vehicle technologies. The photovoltaic power station intelligent operation and maintenance system comprises a plurality of 5G base stations, at least one unmanned aerial vehicle, a flight control platform and an intelligent operation and maintenance device. The 5G base station is used for constructing a 5G private network with omnibearing coverage, and the at least one unmanned aerial vehicle is equipped with a data acquisition device and is used for performing routing inspection on a field area of the photovoltaic power station according to preset routing inspection parameters and performing data acquisition through the acquisition device to obtain routing inspection data; the flight control platform sets inspection parameters of the unmanned aerial vehicle; the intelligent operation and maintenance device compares the inspection data with preset data in a database so as to detect faults in the photovoltaic field area; and when the fault is detected, at least one processing logic is selected and executed according to the fault type, so that automation and precision of photovoltaic power station inspection are realized, the operation and maintenance efficiency and the intelligent level are improved, and the labor cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation and maintenance technology for power systems, and in particular to an intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology. Background Technology

[0002] Routine inspections and troubleshooting of photovoltaic power plants are crucial for ensuring their stable operation. Currently, these inspections mainly rely on manual methods, which suffer from inefficiency, high labor costs, and untimely fault detection and response.

[0003] While existing technologies have attempted to incorporate drones for inspection, the lack of stable, high-speed, and low-latency communication networks often leads to problems such as delayed control command transmission, poor high-definition inspection data feedback, and the inability to achieve remote, real-time, and precise control. Furthermore, current drone inspection systems lack sufficient intelligence, typically only capable of data collection, while fault identification, diagnosis, and handling decisions still require significant manual intervention. This fails to create an automated operation and maintenance loop integrating detection, diagnosis, early warning, and handling, making it difficult to meet the high standards of efficiency and intelligence required by modern large-scale photovoltaic power plants. Summary of the Invention

[0004] This invention provides a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology, which solves the problems of low inspection efficiency and unstable data transmission in photovoltaic power plants, and realizes intelligent and efficient management of photovoltaic power plant operation and maintenance.

[0005] On the one hand, this invention provides a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology, which includes:

[0006] Multiple 5G base stations deployed in the photovoltaic field are used to build a fully covered 5G private network, which provides data transmission channels;

[0007] At least one drone, equipped with a data acquisition device, is used to inspect the photovoltaic power station area according to preset inspection parameters, and to collect data through the acquisition device to obtain inspection data.

[0008] Flight control platform, used to set inspection parameters for drones;

[0009] Intelligent operation and maintenance devices are used for:

[0010] The inspection data is compared with the preset data in the database to detect faults in the photovoltaic field.

[0011] When a fault is detected, at least one processing logic is selected and executed based on the fault type.

[0012] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided, wherein the smart operation and maintenance device is specifically used for:

[0013] When the fault is a light spot, the photovoltaic panel location information is sent to the operation and maintenance monitoring terminal, and the operation and maintenance monitoring terminal is triggered to issue an audible and visual alarm.

[0014] When the fault is a discharge phenomenon, send video and detailed location information to the operation and maintenance monitoring terminal, issue an audible and visual alarm, and ask the operation and maintenance personnel whether it is necessary to cut off the power. After obtaining the consent of the operation and maintenance personnel, cut off the power according to the preset operation procedure and provide a solution.

[0015] When the fault is a fire, determine the cause of the fire. If the cause of the fire is a system short circuit, immediately cut off the power and call fire-fighting equipment to extinguish the fire. If the cause of the fire is arson, cut off the power, call fire-fighting equipment to extinguish the fire, and send an alarm message to the regulatory authorities.

[0016] According to the present invention, a smart operation and maintenance system for a photovoltaic power station based on mobile 5G and drone technology is provided, which also includes multiple smart charging piles;

[0017] Multiple smart charging piles have been installed within the photovoltaic field area;

[0018] The intelligent operation and maintenance device is also used for:

[0019] Based on the inspection parameters, a target smart charging station compatible with the drone is selected from multiple smart charging stations to provide continuous power to the drone.

[0020] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided, wherein the inspection parameters include inspection route, hovering shooting height, equipment angle, shooting resolution and flight tilt angle;

[0021] The intelligent operation and maintenance device is also used for:

[0022] Construct a charging pile capability matrix to describe the attributes of each smart charging pile; the attributes include at least spatial coordinates, hardware compatibility, status information, and environmental conditions;

[0023] The charging demand vector of the UAV is deconstructed based on the inspection parameters; the charging demand vector includes at least the task path correlation, task urgency and energy consumption budget, and task type adaptability.

[0024] The matching calculation is performed between the charging pile capability matrix and the charging demand vector to obtain the adaptation score of each smart charging pile.

[0025] The smart charging pile with the highest compatibility score is identified as the target smart charging pile, and a charging reservation instruction is sent to it.

[0026] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided. The smart operation and maintenance device is further used for:

[0027] Based on the correlation between the spatial coordinates and the task path, the spatial accessibility score of each smart charging pile is calculated.

[0028] Based on the hardware compatibility and task type adaptability, a hardware compatibility score is calculated for each smart charging pile.

[0029] Based on the status information, the task urgency, and the energy consumption budget, the status availability score of each smart charging pile is calculated.

[0030] Based on the environmental situation and the operational safety requirements of the UAV, an environmental adaptability score for each smart charging station is calculated.

[0031] Based on the task urgency in the charging demand vector, dynamic weights are assigned to the spatial accessibility score, hardware compatibility score, state availability score, and environmental adaptability score, and the adaptability score of each smart charging pile is obtained by weighted summation.

[0032] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided. The smart operation and maintenance device is further used for:

[0033] Obtain the real-time location of the drone and the coordinates of the endpoint of the current inspection task path;

[0034] Calculate the path from the drone's current location to the candidate charging station, and the path from the charging station to the mission endpoint, and combine this with the preset optimal mission path to obtain the path deviation.

[0035] Based on the drone's current remaining battery power and energy consumption per unit distance, calculate the battery safety margin for reaching the charging station and continuing the mission;

[0036] Based on the path deviation and the power safety margin, a spatial reachability score is calculated by weighted summation.

[0037] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided. The smart operation and maintenance device is further used for:

[0038] The portion of the optimal task path from the UAV's real-time location to the task endpoint is defined as the original remaining path.

[0039] Construct a charging path to a candidate charging station, the charging path including a first segment from the real-time location of the drone to the candidate charging station, and a second segment from the charging station back to the connecting point on the original remaining path;

[0040] Calculate the ratio of the difference between the total length of the charging path and the original remaining path length, and use it as the length deviation component;

[0041] Identify high-priority waypoints in the original remaining path and calculate the time penalty value for delayed access to these waypoints due to the execution of the charging path, as a task interruption component;

[0042] The path deviation is obtained by weighted summation of the length deviation component and the task interruption component.

[0043] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided. The smart operation and maintenance device is further used for:

[0044] By comparing the charging interface and communication protocol of the drone with the hardware compatibility of the charging station, a basic compatibility score is obtained.

[0045] Under the premise of basic compatibility, if the maximum output power of the charging pile is greater than the standard charging power of the drone, the fast charging incentive score will be calculated according to the power increase ratio using a preset logarithmic function.

[0046] The hardware compatibility score is obtained by adding the basic compatibility score to the fast charging incentive score.

[0047] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided. The smart operation and maintenance device is further used for:

[0048] Based on the real-time status of the charging pile, if it is idle, it is assigned the highest time availability score; if it is occupied, the time availability score is calculated according to the expected waiting time and the exponential decay law.

[0049] Calculate the urgency correction factor for the time availability score based on the task urgency level;

[0050] By combining the health status indicators of the charging pile, the time availability score adjusted by the aforementioned urgency correction factor is multiplied by the health status indicators to obtain the status availability score.

[0051] According to the present invention, a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology is provided. The smart operation and maintenance device is further used for:

[0052] Based on wind speed, precipitation probability, and temperature data within a future preset time window, a meteorological risk score is calculated using a risk function and then converted into a meteorological adaptability score.

[0053] Based on the geographical features and security information of the charging pile's location, calculate the geographical risk value;

[0054] The environmental adaptability score is obtained by multiplying the meteorological adaptability score by the complement of the geographical risk value.

[0055] This invention provides a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology. It constructs a comprehensive 5G private network by deploying multiple 5G base stations in the photovoltaic field, providing a high-speed, low-latency channel for data transmission. Drones equipped with data acquisition devices complete photovoltaic field inspections and data collection under the guidance of preset inspection parameters on the flight control platform. The smart operation and maintenance device compares the collected inspection data with preset data in the database to detect faults and adaptively selects processing logic based on the fault type. Thus, through the synergistic effect of 5G base stations, drones, the flight control platform, and the smart operation and maintenance device, the system achieves automated and precise photovoltaic power plant inspections, enabling rapid fault identification, real-time early warning, and efficient handling. This effectively optimizes the allocation of operation and maintenance resources, improves operation and maintenance efficiency and intelligence, and reduces labor costs. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0057] Figure 1 This is a schematic diagram of the structure of a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology provided in an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0059] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0060] Figure 1 This is a schematic diagram of the structure of a smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology, provided in an embodiment of the present invention. Figure 1 As shown, the photovoltaic power plant smart operation and maintenance system based on mobile 5G and drone technology in this embodiment may include multiple 5G base stations 11 deployed in the photovoltaic field, at least one drone 12, a flight control platform 13, and a smart operation and maintenance device 14.

[0061] Among them, multiple 5G base stations 11 deployed in the photovoltaic field are used to build a 5G private network with full coverage, and the 5G private network provides data transmission channels;

[0062] At least one drone 12 is equipped with a data acquisition device to inspect the photovoltaic power station area according to preset inspection parameters and to collect data through the acquisition device to obtain inspection data.

[0063] Flight control platform 13 is used to set the inspection parameters of UAV 12;

[0064] Intelligent operation and maintenance device 14 is used for:

[0065] The inspection data is compared with the preset data in the database to detect faults in the photovoltaic field.

[0066] When a fault is detected, at least one processing logic is selected and executed based on the fault type.

[0067] In a specific implementation process, the 5G base station 11 can be implemented in various forms such as macro base stations, micro base stations, or pico base stations. For example, multiple macro base stations can be deployed in the photovoltaic field to ensure signal coverage without dead zones, mainly to achieve a stable data transmission channel. The data acquisition device of the drone 12 can be implemented using a combination of various sensors, such as infrared cameras, visible light cameras, or temperature sensors, to acquire operational status information of the photovoltaic field. The inspection parameter setting function of the flight control platform 13 can be implemented through manual input or automatic generation. For example, it can generate the optimal inspection route based on the layout of the photovoltaic field and historical inspection records, aiming to improve inspection efficiency and targeting. The data comparison function of the intelligent operation and maintenance device 14 can be implemented based on rule matching or machine learning algorithms. For example, it can judge anomalies by setting thresholds or identify fault types using classification models, aiming to quickly locate the fault location and nature. Furthermore, the processing logic selection function of the intelligent operation and maintenance device 14 can be implemented through a preset rule base or dynamic decision tree, for example, it can allocate processing strategies according to the priority of different fault types, aiming to achieve automated fault handling.

[0068] In detail, the intelligent operation and maintenance system for photovoltaic power plants of the present invention constructs a comprehensive 5G private network by deploying multiple 5G base stations 11 in the photovoltaic field, providing a high-speed, low-latency data transmission channel for the entire operation and maintenance system. The seamless coverage of the 5G private network ensures real-time communication between the drone 12 and the intelligent operation and maintenance device 14, solving the problems of command transmission delays and poor data feedback caused by network instability in traditional technologies. At least one drone 12 is equipped with a data acquisition device to automatically inspect the photovoltaic power plant area according to the inspection parameters preset by the flight control platform 13, and acquires inspection data through the acquisition device. Specifically, the drone 12 executes tasks according to preset inspection routes, hovering altitudes, and other parameters, achieving standardized and high-precision automatic inspection, avoiding the subjectivity and randomness of manual inspection, thereby improving inspection efficiency and coverage. Furthermore, the intelligent operation and maintenance device 14 compares the inspection data collected by the drone 12 with preset data in the database to detect faults in the photovoltaic field. For example, when an anomaly is detected, the system can quickly identify the fault type and select the appropriate handling method based on preset logic.

[0069] Therefore, this invention realizes an intelligent decision-making closed loop from fault detection to handling, significantly reducing the need for manual intervention while improving fault response speed and processing efficiency. Overall, the various technical features work together to effectively overcome the technical problems of low efficiency in traditional manual inspections, communication delays affecting control accuracy, and reliance on manual intervention in fault handling, forming an efficient and automated operation and maintenance system.

[0070] In some embodiments, the present invention further proposes a specific implementation of the intelligent operation and maintenance device 14: when the fault is a light spot, the photovoltaic panel positioning information is sent to the operation and maintenance monitoring terminal, and the operation and maintenance monitoring terminal is triggered to issue an audible and visual alarm; when the fault is a discharge phenomenon, video and detailed location information are sent to the operation and maintenance monitoring terminal, an audible and visual alarm is issued, and the operation and maintenance personnel are asked whether the power supply needs to be cut off. After the operation and maintenance personnel agree, the power supply is cut off according to the preset operation procedure, and a solution is provided; when the fault is a fire, the cause of the fire is determined. If the cause of the fire is a system short circuit, the power supply is immediately cut off and fire-fighting facilities are called to extinguish the fire. If the cause of the fire is arson, the power supply is cut off, fire-fighting facilities are called to extinguish the fire, and an alarm message is sent to the regulatory authorities.

[0071] Specifically, a light spot refers to an area on the surface of a photovoltaic panel with abnormal reflectivity caused by localized shading or damage, which can be detected by scanning with an infrared detector. In practical applications, the system identifies the specific location of the light spot by comparing real-time collected data with preset data in the database, and automatically sends this location information to the operation and maintenance monitoring terminal, while triggering an audible and visual alarm to remind maintenance personnel to handle the situation promptly. The purpose of this mechanism is to quickly locate the problem area and avoid excessively time-consuming manual troubleshooting.

[0072] Among these, the discharge phenomenon can be the abnormal current release behavior caused by insulation failure in high-voltage equipment or lines, which is usually detected by combining a drone's 12 cameras and an infrared detector. When the system detects such a fault, it transmits real-time video and detailed location information to the operation and maintenance monitoring terminal and proactively requests instructions from operation and maintenance personnel on whether to perform critical operations (such as cutting off the power). The purpose of this design is to combine human experience for safety verification, while using preset operating procedures to ensure automated execution after authorization, thereby effectively preventing the escalation of accidents caused by misoperation.

[0073] In practical applications, a fire refers to a combustion event within a photovoltaic power plant caused by a short circuit or human error, which can be determined through a combination of temperature sensors, infrared detectors, and video analytics. Upon detecting a fire, the system first determines the cause: if it's a system short circuit, it immediately cuts off the relevant power supply and activates fire-fighting facilities; if the cause is human error, it sends an alarm to regulatory authorities while simultaneously extinguishing the fire. This differentiated handling mechanism is designed to take targeted measures based on different fire causes, both maximizing firefighting time and meeting external coordination needs.

[0074] Specifically, the above solution achieves precise and automated operation and maintenance decision-making by constructing a hierarchical response system. For spot faults, since this is a non-emergency performance degradation issue, the system only needs to send location information and trigger an audible and visual alarm, allowing maintenance personnel to directly focus on the fault point and ensure rapid repair of small-scale problems without affecting overall operation. For discharge phenomena, considering the significant safety risks involved, the system not only provides intuitive evidence (such as video and location information) but also conducts safety verification through a request mechanism combined with human experience. Upon authorization, it automatically executes preset operating procedures, effectively preventing the accident from escalating. In fire scenarios, the system implements differentiated strategies based on cause judgment: fires caused by short circuits can be directly cut off and extinguished without request, while arson triggers an alarm from regulatory authorities. This branching processing mechanism ensures that in emergency situations, both rapid fire control and external coordination needs can be met.

[0075] Furthermore, the aforementioned intelligent operation and maintenance device 14 works closely with the 5G base station 11, drone 12, and their data acquisition devices deployed in the photovoltaic field. For example, the high-speed, low-latency communication capabilities provided by the 5G private network ensure the real-time transmission of inspection data, enabling the system to complete fault detection and response decisions in a very short time; the drone 12 executes inspection tasks according to preset parameters, ensuring the comprehensiveness and accuracy of data collection. These components work together to significantly improve the timeliness and reliability of fault handling, solving the problems of inefficiency and potential risks caused by relying on manual experience in traditional methods.

[0076] In some embodiments, the present invention further proposes a scheme of multiple smart charging piles. Multiple smart charging piles are installed within the photovoltaic field, and the intelligent operation and maintenance device 14 is also used to select a target smart charging pile compatible with the drone 12 from the multiple smart charging piles based on inspection parameters, so as to provide continuous power to the drone 12.

[0077] Specifically, smart charging piles are charging devices with intelligent management functions. They can be implemented using charging piles that support multiple charging protocols and have status monitoring and remote communication capabilities. In practical applications, smart charging piles are typically equipped with hardware compatibility modules, status monitoring modules, and environmental situation awareness modules to ensure they can adapt to the charging needs of different drone models and provide real-time feedback on their own operational status. The purpose is to provide efficient and reliable charging services for the drones, avoiding mission interruptions due to insufficient or incompatible charging facilities.

[0078] Inspection parameters refer to a series of indicators describing the current mission requirements of the UAV 12, which may include inspection route, hovering shooting altitude, equipment angle, shooting resolution, and flight tilt angle. These parameters define the specific requirements for the UAV 12 to perform its mission, and their purpose is to provide a decision-making basis for the intelligent operation and maintenance device 14, so as to accurately select the charging pile with the highest compatibility.

[0079] In detail, the deployment of multiple smart charging stations creates a charging infrastructure covering the entire site, enabling the drone 12 to quickly access charging services from any location, effectively avoiding situations where inspections are forced to be interrupted due to a scarcity of charging points. The intelligent operation and maintenance device 14 analyzes inspection parameters, calculates spatial reachability based on task path correlation, assesses the drone 12's remaining battery power and energy consumption budget availability, and comprehensively considers hardware compatibility and task urgency to ultimately select the optimal target smart charging station. This dynamic decision-making mechanism not only reduces the drone 12's extra flight distance and wasted time but also ensures the efficiency and reliability of the charging process, thereby optimizing resource utilization efficiency and guaranteeing the continuous execution of inspection tasks.

[0080] In some embodiments, the present invention further proposes inspection parameters including inspection route, hovering shooting height, equipment angle, shooting resolution, and flight tilt angle; the intelligent operation and maintenance device 14 is also used to: construct a charging pile capability matrix to describe the attributes of each intelligent charging pile; the attributes include at least spatial coordinates, hardware compatibility, status information, and environmental situation; deconstruct the charging demand vector of the drone 12 based on the inspection parameters; the charging demand vector includes at least task path correlation, task urgency and energy consumption budget, and task type adaptability; perform matching calculations on the charging pile capability matrix and the charging demand vector to obtain the adaptability score of each intelligent charging pile; determine the intelligent charging pile with the highest adaptability score as the target intelligent charging pile, and send a charging reservation instruction to it.

[0081] The inspection parameters can include the inspection route to plan the flight path of the UAV 12, the hovering shooting altitude to ensure the clarity of the collected data, the device angle to optimize the shooting perspective, the shooting resolution to meet image quality requirements, and the flight tilt angle to adapt to complex terrain or specific inspection needs. The purpose is to provide precise task characteristic input for the subsequent analysis of charging needs, thereby ensuring that charging decisions are closely linked to actual inspection behavior.

[0082] Specifically, the charging pile capability matrix can be understood as a multi-dimensional data structure used to comprehensively characterize the integrated service capabilities of smart charging piles. It can describe the geographical accessibility of charging piles by incorporating spatial coordinates, assess equipment adaptability through hardware compatibility, reflect the real-time availability of charging piles through status information, and demonstrate the impact of external conditions on charging pile usage through environmental conditions. Its purpose is to avoid the one-sidedness of evaluation caused by relying on a single indicator, thereby improving the accuracy of resource allocation.

[0083] In practical applications, the charging demand vector is a quantitative expression generated based on the dynamic characteristics of the UAV 12's current inspection mission. It can use task path correlation to measure the fit between the charging station and the mission route, task urgency and energy budget to assess the time pressure and expected energy consumption for mission completion, and task type suitability to determine whether the charging station meets the needs of a specific mission. Its purpose is to deeply couple the demand expression with the UAV 12's real-time mission status, rather than using static rules, thereby improving the accuracy of demand prediction.

[0084] Specifically, the above technical solution effectively solves the intelligent challenge of charging resource allocation during UAV 12 inspections by establishing a quantitative matching mechanism between task requirements and resource status. First, the specific composition of inspection parameters is clarified, providing precise task characteristic input for subsequent requirement deconstruction. Next, attributes such as spatial coordinates and hardware compatibility are incorporated when constructing the charging pile capability matrix, enabling the system to comprehensively characterize the geographical accessibility, equipment adaptability, and environmental adaptability of charging piles. Based on this, the charging demand vector is deconstructed based on the inspection parameters, transforming dynamic factors such as task path relevance, urgency, and energy consumption budget into a computable vector, deeply coupling the demand expression with the real-time task status of UAV 12. Subsequently, by matching and calculating the charging pile capability matrix and the charging demand vector, a compatibility score is generated by comprehensively evaluating the degree of fit across various dimensions, achieving multi-factor collaborative optimization. Finally, the target charging pile is selected based on the compatibility score, and a reservation command is sent, ensuring that UAV 12 completes efficient charging with minimal task interruption, guaranteeing the continuity of the inspection process and the optimization of resource utilization.

[0085] Furthermore, the aforementioned technical solution, combined with the overall architecture of multiple 5G base stations 11 deployed in the photovoltaic field, at least one drone 12 and its data acquisition device, flight control platform 13, and intelligent operation and maintenance device 14, further enhances the intelligence level of the drone 12's inspection operations. Through the high-speed, low-latency communication support provided by the 5G private network, real-time matching and calculation of charging demand vectors and charging pile capacity matrices are ensured, thereby significantly improving the efficiency and accuracy of resource scheduling.

[0086] In some embodiments, the present invention further proposes to calculate the spatial accessibility score of each smart charging pile based on the correlation between spatial coordinates and task path; to calculate the hardware compatibility score of each smart charging pile based on hardware compatibility and task type adaptability; to calculate the state availability score of each smart charging pile based on state information, task urgency, and energy consumption budget; to calculate the environmental adaptability score of each smart charging pile based on environmental conditions and the operational safety requirements of the UAV12; and to assign dynamic weights to the spatial accessibility score, hardware compatibility score, state availability score, and environmental adaptability score according to the task urgency in the charging demand vector, and to obtain the adaptability score of each smart charging pile by weighted summation.

[0087] Specifically, spatial accessibility scoring refers to quantifying the impact on mission continuity by analyzing the correlation between the spatial location of the smart charging station and the current mission path of the UAV 12. This is achieved by calculating the shortest path length from the UAV 12's current location to the charging station and the deviation from the mission path. The aim is to ensure that the charging station with the optimal path is prioritized in emergency missions, avoiding additional flight time consumption due to improper path planning.

[0088] The hardware compatibility score can be understood as an assessment of the compatibility between the smart charging station and the drone 12 in terms of hardware interface and communication protocol. It can be achieved by comparing the charging interface type, communication protocol version, and power output capability, with the aim of preventing charging interruptions due to hardware incompatibility, while also supporting fast charging to improve efficiency.

[0089] In practical applications, status availability scoring refers to a comprehensive assessment of whether a smart charging station is suitable for the current task requirements, combining real-time status information with the task urgency level. This can be achieved by weighting time availability scores and health status indicators, aiming to prioritize idle and healthy charging stations and reduce task delays caused by waiting or equipment malfunctions.

[0090] Furthermore, the environmental adaptability score can be understood as assessing the safety of the area where the smart charging station is located based on meteorological conditions and geographical features. It can be achieved by calculating meteorological risk scores and geographical risk values ​​using risk functions, and then converting these into an adaptability score. The aim is to prevent the drone from encountering potential threats when charging in severe weather or high-risk areas.

[0091] Specifically, the above solution addresses the problem of rigid matching between task urgency and scoring weights during charging station selection through a multi-dimensional dynamic scoring mechanism. The system first generates a spatial accessibility score based on the correlation between spatial coordinates and task paths, thereby accurately selecting the charging station with the optimal path. Simultaneously, a hardware compatibility score ensures that the selected charging station meets the fast-charging requirements of the UAV 12, preventing task interruptions due to interface incompatibility. Building on this, a status availability score combines the real-time status of the charging station with task urgency, enabling the system to respond quickly in emergencies, while an environmental adaptability score further ensures the operational safety of the UAV 12 in complex environments. Finally, the weights of each scoring dimension are dynamically adjusted according to task urgency, allowing the system to flexibly respond to different scenario requirements. For example, in high-urgency tasks such as fires, spatial accessibility is prioritized, while in routine inspections, energy consumption budget optimization is emphasized.

[0092] In some embodiments, the present invention further proposes that the intelligent operation and maintenance device 14 is also used to: obtain the real-time location of the drone 12 and the endpoint coordinates of the current inspection task path; calculate the path from the current location of the drone 12 to the candidate charging pile, and the path from the charging pile to the task endpoint, and obtain the path deviation by combining the preset optimal task path; calculate the power safety margin for reaching the charging pile and continuing the task by combining the current remaining power of the drone 12 and the energy consumption per unit distance; and calculate the spatial reachability score by weighted summation based on the path deviation and the power safety margin.

[0093] Specifically, path deviation refers to the quantitative indicator of the difference between the actual charging path and the original mission path. It can be achieved by comparing path length, critical waypoint visit order, or time consumption, with the aim of revealing the potential interference of charging behavior on mission continuity. Battery safety margin can be understood as the ratio between the remaining battery power and the expected energy consumption. It can be calculated in real time by dynamically monitoring the remaining battery power and combining it with energy consumption per unit distance, with the aim of mitigating the risk of mission interruption due to insufficient battery power.

[0094] In detail, this solution constructs a multi-dimensional spatial accessibility assessment mechanism by dynamically fusing real-time location and battery status data. First, it acquires the real-time location of the drone 12 and the coordinates of the endpoint of the current inspection mission path, ensuring that subsequent decisions are always based on actual mission progress and avoiding potential delays caused by relying solely on preset paths. Based on this, it calculates the path from the drone 12's current location to a candidate charging station, and the path from that charging station to the mission endpoint. Combined with the preset optimal mission path, it generates path deviation, a process that not only considers changes in spatial distance but also implicitly assesses the risk of mission interruption. Simultaneously, it calculates the battery safety margin by combining the drone 12's current remaining battery power and energy consumption per unit distance, incorporating energy constraints into the core decision-making process to predict the feasibility of executing the charging path. Finally, based on path deviation and battery safety margin, a spatial reachability score is generated by weighted summation. This allows the system to dynamically adjust the weights of the two dimensions according to the urgency of the task. For example, it can emphasize battery safety margin in high-priority tasks and balance path efficiency in regular tasks, thereby generating a comprehensive score that better meets the needs of actual scenarios and ultimately improving the accuracy of charging pile selection and the continuity of inspection tasks.

[0095] In some embodiments, the present invention further proposes an intelligent operation and maintenance device 14, which is also used to: define the portion of the optimal task path from the real-time position of the UAV 12 to the task endpoint as the original remaining path; construct a charging path to a candidate charging station, the charging path including a first segment from the real-time position of the UAV 12 to the candidate charging station, and a second segment from the charging station back to the connecting point on the original remaining path; calculate the ratio of the difference between the total length of the charging path and the length of the original remaining path as a length deviation component; identify high-priority waypoints in the original remaining path and calculate the time penalty value for delayed access to these waypoints due to the execution of the charging path as a task interruption component; and perform a weighted summation of the length deviation component and the task interruption component to obtain the path deviation degree.

[0096] The original remaining path refers to the unfinished portion of the path from the current location of UAV 12 to the mission endpoint during the inspection mission. This can be implemented using a GIS-based path planning algorithm to provide a benchmark for subsequent path deviation calculations. The charging path describes the complete trajectory of UAV 12 from its current location to a candidate charging station and back to the mission path. It can be generated by combining real-time positioning data with a path planning algorithm, aiming to simulate the impact of actual charging operations on the mission flow. The length deviation component is quantified by calculating the ratio of the difference between the total length of the charging path and the length of the original remaining path. Its purpose is to eliminate evaluation bias caused by differences in mission scale and ensure the comparability of path efficiency losses for missions of different lengths. The mission interruption component quantifies the delayed access time of high-priority waypoints in the original remaining path. It can be calculated by multiplying the priority weight by the delay time, highlighting the timeliness requirements of critical fault detection points.

[0097] Specifically, the above scheme achieves comprehensive optimization of charging path evaluation through a multi-dimensional path deviation quantification mechanism. First, the portion of the optimal task path from the UAV's real-time position to the task endpoint is defined as the original remaining path. Establishing this baseline provides a clear reference for subsequent deviation calculations, avoiding potential biases from isolated evaluations. Based on this, when constructing the charging path to candidate charging stations, the first and second path segments are clearly defined. This segmented design not only accurately simulates the actual disturbance process of the charging operation on the task flow but also ensures the realism of the path modeling and the continuity of the task. Subsequently, the length deviation component is formed by calculating the ratio of the difference between the total length of the charging path and the length of the original remaining path. This ratio effectively eliminates the impact of task scale differences on the evaluation results. Simultaneously, high-priority waypoints in the original remaining path are identified, and their delayed access time penalties are calculated, forming a task interruption component. This design specifically focuses on the timeliness requirements of critical fault detection points, thereby avoiding task delays caused by ignoring priorities. Finally, by weighting and summing the length deviation component and the task interruption component, the evaluation center of gravity is dynamically adjusted so that the path deviation can comprehensively reflect the balance between efficiency loss and critical task assurance, thereby supporting the charging pile selection decision to optimize path efficiency while ensuring the achievement of the core objective of the inspection task.

[0098] In some embodiments, the present invention further proposes to compare the charging interface and communication protocol of the drone 12 with the hardware compatibility of the charging pile to obtain a basic compatibility score; under the premise of basic compatibility, if the maximum output power of the charging pile is greater than the standard charging power of the drone 12, then according to the power improvement ratio, the fast charging incentive score is calculated by a preset logarithmic function; the basic compatibility score and the fast charging incentive score are added together to obtain the hardware compatibility score.

[0099] Specifically, the basic compatibility score is a quantitative indicator obtained by comparing the matching degree between the drone 12's charging interface and communication protocol and the charging station. This can be achieved through methods such as interface shape matching detection and communication protocol version consistency verification. In practical applications, the fast charging incentive score is a quantitative value calculated based on the increase in the charging station's output power relative to the drone 12's standard charging power. It can handle power differences through a preset logarithmic function to suppress the excessive influence of extreme power values ​​on the scoring results. The hardware compatibility score can be understood as an indicator that comprehensively reflects the reliability of the connection between the charging station and the drone 12 and the charging efficiency. Its purpose is to ensure that the system prioritizes devices that can both connect safely and improve charging speed when selecting charging stations.

[0100] In detail, the solution first compares the physical connection characteristics and data interaction capabilities of the drone's charging interface and the charging station to ensure that the basic compatibility score accurately reflects the feasibility of a basic connection. Based on this, when the charging station's maximum output power exceeds the drone's standard charging power, the system introduces a fast-charging incentive score calculation mechanism based on the power increase ratio. A logarithmic function handles power differences, preventing score inflation due to excessive power, thus reasonably quantifying the advantages of fast charging. Finally, the basic compatibility score and the fast-charging incentive score are added to form a hardware compatibility score. This summarization method ensures the score includes both connection reliability and charging efficiency. This effectively reflects the benefits of fast charging during charging station selection, thereby optimizing the drone's power replenishment efficiency and ensuring the continuity and timeliness of photovoltaic power station inspection tasks.

[0101] In some embodiments, the present invention further proposes to assign the highest time availability score to the charging pile if it is idle, and to calculate the time availability score according to the expected waiting time in an exponential decay law if it is occupied, based on the real-time status of the charging pile; to calculate the urgency correction factor for the time availability score according to the urgency level of the task; and to multiply the time availability score adjusted by the urgency correction factor with the health status index of the charging pile to obtain the status availability score.

[0102] The real-time status of a charging pile refers to the information obtained by the system through sensors or communication protocols regarding whether the charging pile is currently idle or occupied. This can be achieved by monitoring the charging pile's operating current, voltage signals, or communication handshake status in real time, aiming to dynamically reflect the charging pile's immediate availability. The estimated waiting time refers to the time interval from the current moment until the charging pile is expected to become idle. This can be achieved using prediction algorithms based on historical data statistics or real-time queue analysis technology, aiming to provide a more accurate time reference for task allocation.

[0103] Task urgency level refers to the priority assigned based on the importance and urgency of the inspection task. It can be implemented through a preset rule base or a dynamic weight allocation mechanism, with the aim of ensuring that high-priority tasks receive priority resource support. Health status indicators are comprehensive parameters reflecting the long-term stability and reliability of charging piles. They can be implemented through equipment self-inspection data, fault record statistics, or performance degradation models, with the aim of avoiding the selection of charging piles with low reliability.

[0104] Specifically, firstly, the system calculates a time availability score based on the real-time status of charging piles. Charging piles are assigned the highest score when idle, prioritizing the use of available resources. When a charging pile is occupied, the score is calculated using an exponential decay law based on the estimated waiting time. This non-linear calculation method more realistically simulates the impact of waiting time on task execution in actual scenarios. Secondly, an urgency correction factor is calculated based on the task urgency level to dynamically adjust the weight of the time availability score, making the score more aligned with task requirements. For example, in emergency fault handling scenarios, the system mitigates the negative impact of waiting time, ensuring that critical tasks receive charging support quickly. Finally, the system combines the charging pile's health status indicators with a multiplicative calculation, integrating equipment reliability considerations and avoiding the selection of charging piles that are idle but have poor health status, thereby reducing the risk of charging interruptions. This provides the intelligent operation and maintenance device 14 with a more accurate basis for selecting charging piles, enabling the drone 12 to perform its inspection tasks continuously and efficiently.

[0105] In some embodiments, the present invention further proposes to calculate a meteorological risk score based on wind speed, precipitation probability and temperature data within a future preset time window, and convert it into a meteorological adaptability score; calculate a geographical risk value based on the geographical features and security information of the charging pile's location; and multiply the meteorological adaptability score by the complement of the geographical risk value to obtain an environmental adaptability score.

[0106] Specifically, the meteorological risk score refers to a risk indicator derived from a quantitative assessment of dynamic meteorological parameters such as wind speed, precipitation probability, and temperature. It can be achieved by constructing a multivariate risk function model, for example, by using weighted summation or nonlinear mapping to integrate multiple meteorological parameters into a single risk value. The purpose of introducing this feature is to proactively capture the impact of weather changes on the charging operation of drones, avoiding decision-making delays due to real-time data latency. The geographical risk value, on the other hand, is a quantitative indicator calculated based on spatial safety factors such as the distribution of terrain obstacles and surveillance coverage density in the charging station's area. It can be achieved through comprehensive analysis using a geographic information system combined with security data. The introduction of this feature aims to identify potential hazards, such as near high-voltage lines or surveillance blind spots, thereby improving the safety of charging station selection.

[0107] In detail, the above technical solution achieves refined calculation of environmental adaptability scores by systematically quantifying meteorological and geographical risk factors. First, based on wind speed, precipitation probability, and temperature data within a preset future time window, a meteorological risk score is calculated using a risk function and converted into a meteorological adaptability score. This process utilizes meteorological forecast data to proactively capture the impact of dynamic weather changes on the drone's charging operation, ensuring timely avoidance of high-risk areas before strong winds or precipitation. Second, a geographical risk value is calculated based on the geographical features and security information of the charging station's location. This integrates spatial safety factors such as terrain obstacle distribution and surveillance coverage density, quantifying the inherent risks of the geographical location into an assessable value. Finally, the meteorological adaptability score is multiplied by the complement of the geographical risk value to obtain the environmental adaptability score. This coupled assessment method comprehensively reflects the overall environmental risk level, avoiding the one-sidedness of single-dimensional assessments. This guides the system to prioritize meteorologically stable and geographically safe charging stations in dynamic environments, effectively ensuring the safe execution of the drone's charging process.

[0108] Furthermore, by combining quantitative assessments of meteorological and geographical risks, the system can dynamically adjust the selection strategy of charging piles in complex environments, significantly improving the flight stability and equipment safety of the drone during charging, and solving the problem of inaccurate risk assessment caused by insufficient quantification of environmental conditions.

[0109] It should be noted that all relevant information that may be involved in the various embodiments of the present invention is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and is information that users actively provide or generate during the use of the product / service, as well as information obtained with user authorization.

[0110] The information processed by this invention may vary depending on the specific product / service scenario and should be based on the specific scenario in which the user uses the product / service. This may involve user account information, device information, or other related information. This invention will treat the relevant information and its processing with the utmost diligence.

[0111] This invention places great importance on the security of related information and has adopted reasonable and feasible security protection measures that comply with industry standards to protect related information and prevent unauthorized access, public disclosure, use, modification, damage or loss of related information.

[0112] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology, characterized in that, include: Multiple 5G base stations deployed in the photovoltaic field are used to build a fully covered 5G private network, which provides data transmission channels; At least one drone, equipped with a data acquisition device, is used to inspect the photovoltaic power station area according to preset inspection parameters, and to collect data through the acquisition device to obtain inspection data. Flight control platform, used to set inspection parameters for drones; Intelligent operation and maintenance devices are used for: The inspection data is compared with the preset data in the database to detect faults in the photovoltaic field. When a fault is detected, at least one processing logic is selected and executed based on the fault type.

2. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 1, characterized in that, The intelligent operation and maintenance device is specifically used for: When the fault is a light spot, the photovoltaic panel location information is sent to the operation and maintenance monitoring terminal, and the operation and maintenance monitoring terminal is triggered to issue an audible and visual alarm. When the fault is a discharge phenomenon, send video and detailed location information to the operation and maintenance monitoring terminal, issue an audible and visual alarm, and ask the operation and maintenance personnel whether it is necessary to cut off the power. After obtaining the consent of the operation and maintenance personnel, cut off the power according to the preset operation procedure and provide a solution. When the fault is a fire, determine the cause of the fire. If the cause of the fire is a system short circuit, immediately cut off the power and call fire-fighting equipment to extinguish the fire. If the cause of the fire is arson, cut off the power, call fire-fighting equipment to extinguish the fire, and send an alarm message to the regulatory authorities.

3. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 1, characterized in that, It also includes multiple smart charging stations; Multiple smart charging piles have been installed within the photovoltaic field area; The intelligent operation and maintenance device is also used for: Based on the inspection parameters, a target smart charging station compatible with the drone is selected from multiple smart charging stations to provide continuous power to the drone.

4. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 1, characterized in that, The inspection parameters include the inspection route, hovering shooting height, equipment angle, shooting resolution, and flight tilt angle; The intelligent operation and maintenance device is also used for: Construct a charging pile capability matrix to describe the attributes of each smart charging pile; the attributes include at least spatial coordinates, hardware compatibility, status information, and environmental conditions; The charging demand vector of the UAV is deconstructed based on the inspection parameters; the charging demand vector includes at least the task path correlation, task urgency and energy consumption budget, and task type adaptability. The matching calculation is performed between the charging pile capability matrix and the charging demand vector to obtain the adaptation score of each smart charging pile. The smart charging pile with the highest compatibility score is identified as the target smart charging pile, and a charging reservation instruction is sent to it.

5. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 4, characterized in that, The intelligent operation and maintenance device is also used for: Based on the correlation between the spatial coordinates and the task path, the spatial accessibility score of each smart charging pile is calculated. Based on the hardware compatibility and task type adaptability, a hardware compatibility score is calculated for each smart charging pile. Based on the status information, the task urgency, and the energy consumption budget, the status availability score of each smart charging pile is calculated. Based on the environmental situation and the operational safety requirements of the UAV, an environmental adaptability score for each smart charging station is calculated. Based on the task urgency in the charging demand vector, dynamic weights are assigned to the spatial accessibility score, hardware compatibility score, state availability score, and environmental adaptability score, and the adaptability score of each smart charging pile is obtained by weighted summation.

6. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 5, characterized in that, The intelligent operation and maintenance device is also used for: Obtain the real-time location of the drone and the coordinates of the endpoint of the current inspection task path; Calculate the path from the drone's current location to the candidate charging station, and the path from the charging station to the mission endpoint, and combine this with the preset optimal mission path to obtain the path deviation. Based on the drone's current remaining battery power and energy consumption per unit distance, calculate the battery safety margin for reaching the charging station and continuing the mission; Based on the path deviation and the power safety margin, a spatial reachability score is calculated by weighted summation.

7. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 6, characterized in that, The intelligent operation and maintenance device is also used for: The portion of the optimal task path from the UAV's real-time location to the task endpoint is defined as the original remaining path. Construct a charging path to a candidate charging station, the charging path including a first segment from the real-time location of the drone to the candidate charging station, and a second segment from the charging station back to the connecting point on the original remaining path; Calculate the ratio of the difference between the total length of the charging path and the original remaining path length, and use it as the length deviation component; Identify high-priority waypoints in the original remaining path and calculate the time penalty value for delayed access to these waypoints due to the execution of the charging path, as a task interruption component; The path deviation is obtained by weighted summation of the length deviation component and the task interruption component.

8. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 5, characterized in that, The intelligent operation and maintenance device is also used for: By comparing the charging interface and communication protocol of the drone with the hardware compatibility of the charging station, a basic compatibility score is obtained. Under the premise of basic compatibility, if the maximum output power of the charging pile is greater than the standard charging power of the drone, the fast charging incentive score will be calculated according to the power increase ratio using a preset logarithmic function. The hardware compatibility score is obtained by adding the basic compatibility score to the fast charging incentive score.

9. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 5, characterized in that, The intelligent operation and maintenance device is also used for: Based on the real-time status of the charging pile, if it is idle, it is assigned the highest time availability score; if it is occupied, the time availability score is calculated according to the expected waiting time and the exponential decay law. Calculate the urgency correction factor for the time availability score based on the task urgency level; By combining the health status indicators of the charging pile, the time availability score adjusted by the aforementioned urgency correction factor is multiplied by the health status indicators to obtain the status availability score.

10. The intelligent operation and maintenance system for photovoltaic power plants based on mobile 5G and drone technology according to claim 5, characterized in that, The intelligent operation and maintenance device is also used for: Based on wind speed, precipitation probability, and temperature data within a future preset time window, a meteorological risk score is calculated using a risk function and then converted into a meteorological adaptability score. Based on the geographical features and security information of the charging pile's location, calculate the geographical risk value; The environmental adaptability score is obtained by multiplying the meteorological adaptability score by the complement of the geographical risk value.

Images