Photovoltaic power station inspection and diagnosis method based on multi-source data fusion and related device

Abstract

The invention discloses a photovoltaic power station inspection and diagnosis method based on multi-source data fusion and a related device, and belongs to the technical field of photovoltaic power station operation and maintenance. The method comprises the following steps: acquiring related data of a target mountain photovoltaic power station, constructing a three-dimensional digital power station model, and extracting power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library; based on the three-dimensional digital power station model, collecting operation data of a target mountain photovoltaic power station for data association to obtain fusion data; on the basis of the fusion data, comparing actual operation parameters of the equipment with theoretical parameters, and generating a preliminary fault early warning; performing root cause analysis on the preliminary fault early warning, classifying fault types based on a pre-constructed fault decision model, judging the emergency degree of the fault, and generating an unmanned aerial vehicle inspection task; based on the unmanned aerial vehicle inspection task, image data are collected, fault diagnosis and verification are carried out, and a diagnosis result is generated.

Description

Technical Field

[0001] This invention belongs to the field of photovoltaic power plant operation and maintenance technology, and relates to a method and related device for inspection and diagnosis of photovoltaic power plants based on multi-source data fusion. Background Technology

[0002] In the field of photovoltaic power plant operation and maintenance management, the accuracy of fault diagnosis is one of the key factors in ensuring the efficient and stable operation of the power plant. However, given the current state of technology, existing fault diagnosis technologies have significant shortcomings in terms of accuracy, specifically manifested in poor fault diagnosis accuracy and a high false diagnosis rate. This problem is closely related to the unique geographical environment and component layout characteristics of mountainous photovoltaic power plants.

[0003] Due to the complex terrain, the components of mountainous photovoltaic power stations exhibit poor consistency in tilt angle, orientation, and spacing, resulting in inherent differences in the power generation characteristics of each string. Existing fault diagnosis methods often employ a "one-size-fits-all" threshold judgment, which is ill-suited to this non-standardized operating environment, leading to high false alarm and false negative rates. This makes it difficult to accurately pinpoint the root cause of faults, resulting in a significant amount of ineffective verification work. Furthermore, multi-source data is isolated and lacks effective integration. Currently, advanced technologies such as drone inspections, infrared thermal imaging, and Supervisory Control and Data Acquisition (SCADA) systems are gradually being applied to the operation and maintenance of photovoltaic power stations. However, these technologies often operate independently, forming "data silos." For example, there is a lack of effective correlation and verification between visual anomalies (such as hot spots) detected by drone inspections and electrical performance anomalies (such as sudden power drops) monitored by the monitoring system. This makes it impossible to quickly confirm whether defects have actually caused power generation losses and their urgency, still requiring on-site manual verification by maintenance personnel, significantly diminishing the effectiveness of intelligent technologies.

[0004] In summary, existing technologies for fault diagnosis in mountainous photovoltaic power plants suffer from problems such as poor accuracy and insufficient fusion of multi-source data. There is an urgent need for a new diagnostic method that can effectively integrate multi-dimensional information from mountainous photovoltaic power plants to achieve accurate fault location and diagnosis, thereby improving the operation and maintenance efficiency and power generation benefits of photovoltaic power plants. Summary of the Invention

[0005] The purpose of this invention is to provide a method and related device for the inspection and diagnosis of photovoltaic power plants based on multi-source data fusion, so as to solve the technical problem of low accuracy in fault diagnosis of photovoltaic power plants in the prior art.

[0006] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention provides a method for inspection and diagnosis of photovoltaic power plants based on multi-source data fusion, comprising the following steps: Acquire relevant data of the target mountain photovoltaic power station, construct a three-dimensional digital power station model, and extract power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library; Based on the aforementioned three-dimensional digital power station model, operational data of the target mountain photovoltaic power station are collected and correlated to obtain fused data; Based on the fused data, the actual operating parameters of the equipment are compared with the theoretical parameters to generate a preliminary fault warning; Root cause analysis is performed on the preliminary fault warning, the fault type is classified based on the pre-built fault decision model, the urgency of the fault is judged, and a UAV inspection task is generated. Based on drone inspection missions, image data is collected and fault diagnosis and verification are performed to generate diagnostic results.

[0007] Furthermore, the steps of acquiring relevant data of the target mountain photovoltaic power station, constructing a three-dimensional digital power station model, and extracting power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library specifically include: Acquire geographic information data, equipment layout data, and image data of the target mountain photovoltaic power station, and construct a three-dimensional digital power station model that includes terrain, roads, photovoltaic equipment locations, and electrical connection relationships; Based on the aforementioned three-dimensional digital power station model, spatial characteristic parameters of each photovoltaic string and inverter are extracted and recorded using image recognition and analysis technology to form a power station equipment feature library; the spatial characteristic parameters include at least the installation tilt angle, orientation, altitude, and information on surrounding obstructions.

[0008] Furthermore, the step of collecting operational data of the target mountain photovoltaic power station based on the three-dimensional digital power station model and performing data association to obtain fused data specifically includes: Periodically or triggeredly collect real-time operating data from the power plant monitoring system, as well as visible light and infrared image data obtained by drone inspections; The real-time operating data and UAV inspection data are spatially aligned and time-synchronized in the three-dimensional digital power station model, so that the electrical performance data of each device is associated with its visual status data, resulting in fused data.

[0009] Furthermore, the step of comparing the actual operating parameters and theoretical parameters of the equipment based on the fused data to generate a preliminary fault warning specifically includes: Based on fused data, gridded irradiance assessment is performed using self-organizing groups of equipment as units; the actual operating parameters of the equipment in each group are compared with the theoretical expected parameters calculated based on the spatial characteristic parameters and real-time environmental data, and a preliminary fault warning is generated when the deviation exceeds a preset threshold.

[0010] Furthermore, the steps of performing root cause analysis on the preliminary fault warning, classifying fault types based on a pre-built fault decision model, determining the urgency of the fault, and generating a UAV inspection task specifically include: Root cause analysis is performed on the preliminary fault warning, and the fault types are classified based on the fault decision model to determine the urgency of the fault. The fault types include at least hot spots, obstruction, open circuit, short circuit, attenuation, inverter fault, excessive vegetation, and pollution. The fault decision model is constructed using a power plant equipment feature library and historical fault data. For faults requiring visual confirmation, generate a drone inspection task that includes the target location, inspection type, and shooting requirements; for electrical faults, directly generate an on-site maintenance work order that includes the location of the faulty equipment, preliminary diagnostic conclusions, and maintenance suggestions.

[0011] Furthermore, the steps of collecting image data and performing fault diagnosis and verification based on the UAV inspection task to generate diagnostic results specifically include: The drone inspection task is sent to the drone inspection system. The drone flies to the target location according to the task requirements, collects multi-angle image data and transmits it back. The returned images are analyzed and cross-validated with the operational data diagnostic results to ultimately confirm the cause and severity of the fault. The confirmed diagnostic results are then updated to the work order, and the optimal path is planned to locate the on-site maintenance personnel.

[0012] Furthermore, the method for planning the optimal path is as follows: based on the road network information in the three-dimensional digital power station model, combined with the current location of the operation and maintenance personnel and the locations of multiple fault points that need to be handled, a path planning algorithm is used to calculate the inspection and maintenance path with the shortest total time, and then visualized navigation is performed on the map.

[0013] Secondly, the present invention provides a photovoltaic power plant inspection and diagnosis system based on multi-source data fusion, comprising: The data acquisition module is used to acquire relevant data of the target mountain photovoltaic power station, construct a three-dimensional digital power station model, and extract power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library. The data fusion module is used to collect the operation data of the target mountain photovoltaic power station based on the three-dimensional digital power station model, perform data association, and obtain fused data; The preliminary early warning module is used to compare the actual operating parameters and theoretical parameters of the equipment based on the fused data to generate a preliminary fault warning; The fault diagnosis module is used to perform root cause analysis on the preliminary fault warning, classify the fault type based on the pre-built fault decision model, determine the urgency of the fault, and generate UAV inspection tasks. The inspection and diagnosis module is used to collect image data and perform fault diagnosis and verification based on UAV inspection tasks, and generate diagnostic results.

[0014] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the photovoltaic power station inspection and diagnosis method based on multi-source data fusion as described above.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the photovoltaic power station inspection and diagnosis method based on multi-source data fusion as described above.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This invention discloses a photovoltaic power station inspection and diagnosis method and related device based on multi-source data fusion. It constructs a three-dimensional digital power station model and extracts equipment parameters to form a feature library. Simultaneously, it collects operational data and correlates it to obtain fused data, integrating static equipment information and dynamic operational information of the photovoltaic power station. This multi-source data fusion avoids misjudgments caused by incomplete information from a single data source, more accurately reflecting the actual operating status of the equipment, providing rich and reliable evidence for fault diagnosis, and significantly improving the accuracy of fault diagnosis. Comparing actual operating parameters with theoretical parameters generates preliminary fault warnings, enabling timely detection of deviations during equipment operation. Finally, root cause analysis is performed on the preliminary fault warnings, and fault types are classified based on a pre-constructed fault decision model, allowing for in-depth exploration of the root causes of faults. Different fault types may have similar manifestations; through root cause analysis and classification, the essence of the fault can be accurately distinguished, avoiding inappropriate handling measures due to incorrect fault type judgment, further improving the accuracy of fault diagnosis. Furthermore, this invention generates drone inspection tasks based on the urgency of the fault, realizing intelligent allocation of inspection tasks. For urgent faults, drones can be prioritized for inspection to obtain detailed information about the fault site in a timely manner; for non-urgent faults, inspection time can be rationally scheduled to improve the utilization efficiency of inspection resources. This intelligent task generation method avoids the blindness and arbitrariness of manually assigning inspection tasks, and improves the pertinence and timeliness of inspection work. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a schematic diagram of the system of the present invention; Figure 3 This is a schematic diagram of the computer device structure of the present invention. Detailed Implementation

[0019] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0020] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0021] See Figure 1 This invention discloses a method for inspecting and diagnosing photovoltaic power plants based on multi-source data fusion, comprising the following steps: S1. Obtain relevant data of the target mountain photovoltaic power station, construct a three-dimensional digital power station model, and extract power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library. S101: Obtain geographic information data, equipment layout data, and image data of the target mountain photovoltaic power station, and construct a three-dimensional digital power station model that includes terrain, roads, photovoltaic equipment locations, and electrical connection relationships. S102, Based on the three-dimensional digital power station model, spatial feature parameters of each photovoltaic string and inverter are extracted and recorded through image recognition and analysis technology to form a power station equipment feature library; the spatial feature parameters include at least the installation tilt angle, orientation, altitude and surrounding obstruction information.

[0022] Preferably, semantic segmentation is performed on the high-definition orthophotos collected by the UAV to identify the outlines and positions of individual photovoltaic modules, strings, and inverters; the identified equipment outlines are registered with the three-dimensional digital power station model to accurately calculate the three-dimensional coordinates of the center point of each photovoltaic string; based on the three-dimensional coordinates and the digital elevation model, the installation tilt angle, orientation, and altitude of each string are automatically calculated; by analyzing the three-dimensional model of the surrounding terrain and vegetation, the potential shading situation of the string in different seasons and time periods is assessed, and the shading coefficient is stored as a feature parameter in the feature library.

[0023] S2, Based on the three-dimensional digital power station model, collect the operation data of the target mountain photovoltaic power station and perform data association to obtain fused data; S201 periodically or triggeredly collects real-time operating data from the power plant monitoring system, as well as visible light and infrared image data obtained by drone inspections. S202, the real-time operation data and the UAV inspection data are spatially aligned and time-synchronized in the three-dimensional digital power station model, so that the electrical performance data of each device is associated with its visual status data, and fused data is obtained.

[0024] S3. Based on the fused data, the actual operating parameters of the equipment are compared with the theoretical parameters to generate a preliminary fault warning; Based on fused data, gridded irradiance assessment is performed using self-organizing groups of equipment as units; the actual operating parameters of the equipment in each group are compared with the theoretical expected parameters calculated based on the spatial characteristic parameters and real-time environmental data, and a preliminary fault warning is generated when the deviation exceeds a preset threshold.

[0025] The preferred method for gridded irradiance assessment is as follows: continuous photovoltaic strings with similar terrain conditions are divided into a self-organizing group. Using the group as a unit, irradiance sensor data deployed in the power station is combined with the spatial characteristic parameters of the strings to calculate the theoretical received irradiance of each string in the group through an irradiance transmission model, thereby realizing the differentiated assessment of local microclimates in complex mountainous environments.

[0026] S4. Perform root cause analysis on the preliminary fault warning, classify the fault type based on the pre-built fault decision model, determine the urgency of the fault, and generate a UAV inspection task. S401, perform root cause analysis on the preliminary fault warning, classify the fault type based on the fault decision model, and determine the urgency of the fault; the fault decision model is constructed through the power plant equipment feature library and historical fault data; Preferably, the fault types are not limited to hot spots, obstruction, open circuit, short circuit, attenuation, inverter fault, excessive vegetation, and pollution; the urgency of the fault is judged by comprehensively considering the impact of the fault type on power generation efficiency and the location of the faulty equipment in the electrical structure, and is divided into three levels: urgent, important, and general. S402 generates a drone inspection task that includes the target location, inspection type, and shooting requirements for faults requiring visual confirmation; for electrical faults, it directly generates an on-site maintenance work order that includes the location of the faulty equipment, preliminary diagnostic conclusions, and maintenance suggestions.

[0027] For faults requiring visual confirmation, such as "hot spots" or "obstructions," priority is given to generating detailed UAV inspection tasks; for electrical faults such as "open circuits" or "short circuits," high-urgency on-site repair work orders are generated directly.

[0028] S5, based on drone inspection missions, collects image data and performs fault diagnosis and verification, generating diagnostic results.

[0029] The drone inspection task generated by S4 is sent to the drone inspection system; the drone flies to the target location according to the task requirements, collects multi-angle image data and transmits it back; the system automatically analyzes the transmitted images, cross-verifies them with the operational data diagnosis results, and finally confirms the cause and level of the fault; the confirmed diagnosis results are updated to the work order, and the optimal path is planned to find the on-site maintenance personnel, forming a closed-loop management from fault discovery, diagnosis, task assignment to review and confirmation.

[0030] Preferably, the method for planning the optimal path is as follows: based on the road network information in the three-dimensional digital power station model, combined with the current location of the operation and maintenance personnel and the locations of multiple fault points that need to be handled, a path planning algorithm is used to calculate the inspection and maintenance path with the shortest total time, and then visualized navigation is performed on the map.

[0031] See Figure 2This invention discloses a photovoltaic power station inspection and diagnosis system based on multi-source data fusion, comprising a data acquisition module, a data fusion module, a preliminary early warning module, a fault judgment module, and an inspection and diagnosis module. The data acquisition module acquires relevant data of the target mountain photovoltaic power station, constructs a three-dimensional digital power station model, and extracts power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library. The data fusion module collects operational data of the target mountain photovoltaic power station based on the three-dimensional digital power station model and performs data association to obtain fused data. The preliminary early warning module compares the actual operating parameters and theoretical parameters of the equipment based on the fused data to generate a preliminary fault warning. The fault judgment module performs root cause analysis on the preliminary fault warning, classifies the fault type based on a pre-constructed fault decision model, determines the urgency of the fault, and generates a drone inspection task. The inspection and diagnosis module collects image data based on the drone inspection task, performs fault diagnosis and verification, and generates diagnostic results.

[0032] In one embodiment of the invention, see [link to embodiment]. Figure 3 A computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve a corresponding method flow or function. The processor described in this embodiment can be used in the operation of a photovoltaic power station inspection and diagnosis method based on multi-source data fusion.

[0033] This invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the photovoltaic power station inspection and diagnosis method based on multi-source data fusion in the above embodiments.

[0034] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0035] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0036] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0037] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0038] 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 it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A photovoltaic power station inspection and diagnosis method based on multi-source data fusion, characterized in that, Includes the following steps: Acquire relevant data of the target mountain photovoltaic power station, construct a three-dimensional digital power station model, and extract power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library; Based on the aforementioned three-dimensional digital power station model, operational data of the target mountain photovoltaic power station are collected and correlated to obtain fused data; Based on the fused data, the actual operating parameters of the equipment are compared with the theoretical parameters to generate a preliminary fault warning; Root cause analysis is performed on the preliminary fault warning, the fault type is classified based on the pre-built fault decision model, the urgency of the fault is judged, and a UAV inspection task is generated. Based on the drone inspection mission, image data is collected and fault diagnosis and verification are performed to generate diagnostic results. 2.The photovoltaic power station inspection and diagnosis method based on multi-source data fusion of claim 1, characterized in that, The steps of acquiring relevant data of the target mountain photovoltaic power station, constructing a three-dimensional digital power station model, and extracting power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library specifically include: Acquire geographic information data, equipment layout data, and image data of the target mountain photovoltaic power station, and construct a three-dimensional digital power station model that includes terrain, roads, photovoltaic equipment locations, and electrical connection relationships; Based on the aforementioned three-dimensional digital power station model, spatial characteristic parameters of each photovoltaic string and inverter are extracted and recorded using image recognition and analysis technology to form a power station equipment feature library; the spatial characteristic parameters include at least the installation tilt angle, orientation, altitude, and information on surrounding obstructions. 3.The photovoltaic power station inspection and diagnosis method based on multi-source data fusion of claim 1, characterized in that, The step of collecting operational data of the target mountain photovoltaic power station based on the three-dimensional digital power station model, performing data association, and obtaining fused data specifically includes: Periodically or triggeredly collect real-time operating data from the power plant monitoring system, as well as visible light and infrared image data obtained by drone inspections; The real-time operating data and UAV inspection data are spatially aligned and time-synchronized in the three-dimensional digital power station model, so that the electrical performance data of each device is associated with its visual status data, resulting in fused data. 4.The photovoltaic power station inspection and diagnosis method based on multi-source data fusion of claim 1, characterized in that, The step of comparing the actual operating parameters and theoretical parameters of the equipment based on the fused data to generate a preliminary fault warning specifically includes: Based on fused data, gridded irradiance assessment is performed using self-organizing groups of equipment as units; the actual operating parameters of the equipment in each group are compared with the theoretical expected parameters calculated based on the spatial characteristic parameters and real-time environmental data, and a preliminary fault warning is generated when the deviation exceeds a preset threshold.

5. The photovoltaic power station inspection and diagnosis method based on multi-source data fusion according to claim 1, characterized in that, The steps of performing root cause analysis on the preliminary fault warning, classifying fault types based on a pre-built fault decision model, determining the urgency of the fault, and generating a UAV inspection task specifically include: Root cause analysis is performed on the preliminary fault warning, and the fault types are classified based on the fault decision model to determine the urgency of the fault. The fault types include at least hot spots, obstruction, open circuit, short circuit, attenuation, inverter fault, excessive vegetation, and pollution. The fault decision model is constructed using a power plant equipment feature library and historical fault data. For faults requiring visual confirmation, generate a drone inspection task that includes the target location, inspection type, and shooting requirements; for electrical faults, directly generate an on-site maintenance work order that includes the location of the faulty equipment, preliminary diagnostic conclusions, and maintenance suggestions. 6.The photovoltaic power station inspection and diagnosis method based on multi-source data fusion of claim 1, characterized in that, The steps of collecting image data and performing fault diagnosis and verification based on UAV inspection tasks to generate diagnostic results specifically include: The drone inspection task is sent to the drone inspection system. The drone flies to the target location according to the task requirements, collects multi-angle image data and transmits it back. The returned images are analyzed and cross-validated with the operational data diagnostic results to ultimately confirm the cause and severity of the fault. The confirmed diagnostic results are then updated to the work order, and the optimal path is planned to locate the on-site maintenance personnel.

7. The photovoltaic power station inspection and diagnosis method based on multi-source data fusion according to claim 6, characterized in that, The method for planning the optimal path is as follows: based on the road network information in the three-dimensional digital power station model, combined with the current location of the operation and maintenance personnel and the locations of multiple fault points that need to be handled, a path planning algorithm is used to calculate the inspection and maintenance path with the shortest total time, and then visualized navigation is performed on the map.

8. A photovoltaic power station inspection and diagnosis system based on multi-source data fusion, characterized in that, include: The data acquisition module is used to acquire relevant data of the target mountain photovoltaic power station, construct a three-dimensional digital power station model, and extract power station equipment parameters from the three-dimensional digital power station model to form a power station equipment feature library. The data fusion module is used to collect the operation data of the target mountain photovoltaic power station based on the three-dimensional digital power station model, perform data association, and obtain fused data; The preliminary early warning module is used to compare the actual operating parameters and theoretical parameters of the equipment based on the fused data to generate a preliminary fault warning; The fault diagnosis module is used to perform root cause analysis on the preliminary fault warning, classify the fault type based on the pre-built fault decision model, determine the urgency of the fault, and generate UAV inspection tasks. The inspection and diagnosis module is used to collect image data and perform fault diagnosis and verification based on UAV inspection tasks, and generate diagnostic results.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the photovoltaic power station inspection and diagnosis method based on multi-source data fusion as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the photovoltaic power station inspection and diagnosis method based on multi-source data fusion as described in any one of claims 1-7.

Images