Intelligent operation and maintenance method and system for state monitoring and fault early warning of power distribution network equipment

Abstract

The invention discloses an intelligent operation and maintenance method and system for state monitoring and fault early warning of power distribution network equipment, relates to the technical field of power inspection, and aims to solve the technical problem that the intelligent degree and the refinement degree of operation and maintenance of the power distribution network equipment are insufficient due to the fact that traditional manual inspection is limited by topography and weather and fault response and resource allocation are not timely. According to the method, the unmanned aerial vehicle initial inspection strategy is constructed according to the scene features and the equipment features of the to-be-inspected area, the inspection auxiliary facilities are obtained by relying on the three-dimensional point cloud model of the power distribution network line so as to provide the dynamic planning response, and then the unmanned aerial vehicle target inspection strategy is determined by combining the initial inspection strategy and the auxiliary facilities. And finally, executing equipment operation and maintenance according to the target inspection strategy, thereby improving the equipment operation and maintenance efficiency of the power distribution network, guaranteeing accurate early warning and rapid handling of faults, and enhancing the power supply reliability of the power distribution network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power inspection, in particular, to an intelligent operation and maintenance method and system for power distribution network equipment state monitoring and fault early warning. BACKGROUND

[0002] Power distribution network equipment state monitoring and fault early warning is a key link to ensure the reliability of power supply of the power system, and its operation and maintenance work needs to cope with technical challenges such as dense equipment quantity, complex terrain in the covered area, and high time efficiency requirement for fault response. In the prior art, the traditional manual inspection method is low in efficiency and is greatly limited by bad weather and complex terrain, and it is difficult to meet the operation and maintenance needs of large-scale power distribution networks. Although unmanned aerial vehicle (UAV) inspection has been gradually applied, the path planning is not fully adapted to the equipment operation characteristics and environmental parameters, which may cause excessive energy consumption and insufficient endurance, and uneven signal coverage may affect the integrity of data collection. At the same time, fault identification relies on single sensor data, which may be misjudged due to environmental interference, and the matching degree of operation and maintenance resources and fault levels is low, which may cause lag in emergency fault response. In addition, historical operation and maintenance data and real-time operation and maintenance process data are separated, which makes it difficult to form an efficient operation and maintenance optimization closed loop, and thus the intelligent and fine level of operation and maintenance of power distribution network equipment is restricted.

[0003] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present application, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0004] The purpose of the present application is to solve the technical problem of insufficient intelligent and fine level of operation and maintenance of power distribution network equipment caused by the limitation of traditional manual inspection by terrain and weather, and untimely fault response and resource allocation, and an intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning is proposed. The present application first constructs an initial UAV inspection strategy according to the scene characteristics and equipment characteristics of the area to be inspected, then obtains inspection auxiliary facilities by a three-dimensional point cloud model of the power distribution network line to provide dynamic planning response, then determines a target UAV inspection strategy in combination with the initial inspection strategy and the auxiliary facilities, and finally performs equipment operation and maintenance according to the target inspection strategy, thereby improving the efficiency of operation and maintenance of power distribution network equipment, ensuring accurate fault early warning and rapid disposal, and enhancing the reliability of power supply of the power distribution network.

[0005] In a first aspect, a technical solution provided in an embodiment of the present application is an intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning, comprising the following steps: S1, constructing an initial UAV inspection strategy according to the scene characteristics and equipment characteristics of the area to be inspected; S2, obtaining inspection auxiliary facilities in the area to be inspected through a three-dimensional point cloud model of the power distribution network line; S3, determine a target inspection strategy of the UAV by combining the initial inspection strategy of the UAV with the auxiliary inspection facilities; S4, perform equipment operation and maintenance of the area to be inspected according to the target inspection strategy of the UAV.

[0006] Preferably, the initial inspection strategy of the UAV is constructed according to the scene characteristics and the equipment characteristics of the area to be inspected, including the following steps: S11, scene division and feature extraction are performed on the obtained multi-element data to generate a scene feature vector, the multi-element data including geographic information, meteorological information and electromagnetic environment information of the area to be inspected; S12, a device-environment correlation matrix is constructed by extracting device key parameters and environment parameters in the historical operation and maintenance database, the device key parameters at least including device type, operation life, load level, fault history record and current alarm information; S13, the scene feature vector and the device-environment correlation matrix are input into a strategy generation engine, and the initial inspection strategy is output with the minimum inspection risk and the highest inspection efficiency as the dual objective functions.

[0007] Preferably, the scene feature vector and the device-environment correlation matrix are input into a strategy generation engine, and the initial inspection strategy is output with the minimum inspection risk and the highest inspection efficiency as the dual objective functions, including the following steps: S131, the inspection risk value is determined by weighted summation of the device failure probability and the scene risk coefficient, the inspection efficiency value is determined by weighted summation of the inspection path length and the device inspection time, and the dual objective function is determined by weighted summation of the inspection risk value and the inspection efficiency value; S132, the scene feature vector and the device-environment correlation matrix are input into the strategy generation engine, and NSGA-II is used as the kernel of the strategy generation engine to perform dual objective optimization operation to obtain a Pareto optimal solution set; S133, constraint rules are set according to the failure-sensitive device constraint, the electromagnetic interference constraint and the UAV power constraint, the optimal solution in the Pareto optimal solution set that meets the multi-constraint condition is selected according to the constraint rules, and the optimal solution is used as the initial inspection strategy of the UAV; wherein the initial inspection strategy of the UAV includes the UAV inspection path, the device inspection time sequence, the inspection area stay time and the electromagnetic interference shielding strategy.

[0008] Preferably, the auxiliary inspection facilities in the area to be inspected are obtained by the three-dimensional point cloud model of the distribution network line, including the following steps: S21, original three-dimensional point cloud data of the distribution network line in the area to be inspected are obtained, and the original three-dimensional point cloud data are registered with the geographic information in the inspection area by using the ICP algorithm to obtain a standardized three-dimensional point cloud model in a unified coordinate system; S22, construct a multi-dimensional feature library based on the physical properties of the inspection auxiliary facility, and associate the multi-dimensional feature library with the functional properties of the inspection auxiliary facility to construct a structured feature index table; S23, extract local geometric features and global semantic features of the standardized three-dimensional point cloud model, use the multi-dimensional feature library as a reference, perform feature matching through a K nearest neighbor algorithm, and classify the point cloud clustering areas according to the feature matching degree; S24, perform semantic analysis and functional verification on the classified point cloud clustering areas based on the structured feature index table, and filter out effective point cloud clustering areas to generate an inspection auxiliary facility list.

[0009] As a preferred, the structured feature index table is used to perform semantic analysis and functional verification on the classified point cloud clustering areas, and the effective point cloud clustering areas are filtered out according to the verification results to generate an inspection auxiliary facility list, which includes the following steps: S241, extract the semantic features of the classified point cloud clustering areas, and perform multi-dimensional matching of the extracted semantic features with the structured feature index table to calculate the feature matching degree; S242, map the functional properties of the point cloud clustering areas according to the semantic feature matching results, and mark the areas with a feature matching degree greater than a set threshold and meeting the functional property threshold range as effective point cloud clustering areas; S243, parameterize the effective point cloud clustering areas to obtain an inspection auxiliary facility list, and associate the inspection auxiliary facility with the corresponding coordinate position of the standardized three-dimensional point cloud model.

[0010] As a preferred, the initial inspection strategy of the unmanned aerial vehicle is combined with the inspection auxiliary facility to determine the target inspection strategy of the unmanned aerial vehicle, which includes the following steps: S31, extract the core parameters of the initial inspection strategy of the unmanned aerial vehicle and the functional property parameters of the inspection auxiliary facility list to construct a compatibility evaluation matrix; the compatibility evaluation matrix includes energy consumption compatibility indicators, signal compatibility indicators, and timing compatibility indicators; S32, perform compatibility verification on the energy consumption compatibility indicators to obtain an energy supply path interval, perform compatibility verification on the signal compatibility indicators to obtain a weak signal path interval, and perform compatibility verification on the timing compatibility indicators to obtain a timing conflict path interval; S33, adjust the energy supply path interval, the weak signal path interval, and the timing conflict path interval according to the constraint rules to obtain the target inspection strategy of the unmanned aerial vehicle.

[0011] As a preferred, the core parameters include the total length of the inspection path, the estimated energy consumption of each inspection segment, the device inspection timing, and the corresponding signal demand of the electromagnetic interference shielding; The functional attribute parameters include charging station charging power, charging efficiency, base station coverage radius, and signal strength.

[0012] As preferred, the target unmanned aerial vehicle inspection strategy is obtained by adjusting the energy supply path section, the weak signal path section, and the time sequence conflict path section according to the constraint rules, and includes the following steps: S331, based on the energy consumption estimation of the inspection section of the energy supply path section combined with the power constraint of the unmanned aerial vehicle, the total energy consumption of the section is determined, the minimum supply time corresponding to the required minimum supply power is calculated according to the functional attribute parameters of the charging station, and the charging station with the closest distance and the charging efficiency greater than a set threshold is selected as the supply node according to the geographic information of the area to be inspected; the coordinates of the selected charging station are embedded as a passing node in the energy supply path section, and the supply time is embedded in the inspection gap of the non-fault sensitive equipment in the energy supply path section according to the equipment inspection time sequence; S332, based on the electromagnetic interference constraint, the signal demand and the functional attribute parameters of the base station are analyzed; if the distance between the path node and the base station is greater than the coverage radius, the weak signal path node is adjusted to the coverage range of the base station and the energy consumption of the adjusted energy supply path section is calculated; if the distance between the path node and the base station is less than or equal to the coverage radius and the signal strength is less than a set threshold, the signal receiving gain of the unmanned aerial vehicle is improved and the inspection stay time in the weak signal path section is shortened; S333, the time sequence conflict node is located based on the fault sensitive equipment constraint, if the conflict is caused by the energy supply time sequence, the energy supply time sequence is advanced to before the sensitive equipment inspection window or delayed to after the sensitive equipment inspection window to obtain a new time sequence conflict path section; if the conflict is caused by the weak signal adjustment time sequence, the equipment inspection time is compressed by a set proportion to form a new time sequence conflict path section; S334, the newly generated energy supply path section, weak signal path section, and time sequence conflict path section are spliced with the path section and time sequence section in the initial unmanned aerial vehicle inspection strategy which are not adjusted to obtain the target unmanned aerial vehicle inspection strategy.

[0013] As preferred, the device operation and maintenance of the area to be inspected is performed according to the target unmanned aerial vehicle inspection strategy, and includes the following steps: S41, the target unmanned aerial vehicle inspection strategy is decomposed into operation and maintenance sub-tasks according to the size of the unmanned aerial vehicle cluster, and the unmanned aerial vehicle receives the operation and maintenance sub-tasks and collects equipment data according to the task requirements; S42, the equipment data is input into a fault identification model to obtain a fault level, and the fault position is calibrated in a visualization interface through the standardized three-dimensional point cloud model of the equipment coordinates to generate a fault detail report.

[0014] In a second aspect, an intelligent operation and maintenance system is also provided in the embodiments of the present application, which is suitable for the intelligent operation and maintenance method of the power distribution network equipment state monitoring and fault early warning, and includes: The construction module: according to the scene characteristics and equipment characteristics of the area to be inspected, an initial inspection strategy of the unmanned aerial vehicle is constructed; The acquisition module: through the power distribution network line three-dimensional point cloud model, auxiliary inspection facilities in the area to be inspected are acquired; The determination module: through the initial inspection strategy of the unmanned aerial vehicle combined with the auxiliary inspection facilities, a target inspection strategy of the unmanned aerial vehicle is determined; The execution module: according to the target inspection strategy of the unmanned aerial vehicle, the equipment operation and maintenance of the area to be inspected is executed.

[0015] The beneficial effects of the application are as follows: (1) In view of the problem that the existing unmanned aerial vehicle inspection path planning does not fully adapt to the equipment operation characteristics and environmental parameters, and energy consumption is easy to exceed the standard, resulting in insufficient endurance, uneven signal coverage and affecting data collection integrity, the application first divides the scene and extracts features from multiple data such as geographic information, weather information and electromagnetic environment information to generate a scene feature vector, constructs an equipment environment correlation matrix combined with key parameters such as device type, operation life and fault record in the historical operation and maintenance database, executes double-target optimization of minimum inspection risk and highest inspection efficiency based on the NSGA-Ⅱ algorithm as the core to obtain the initial inspection strategy, and then relies on the power distribution network line three-dimensional point cloud model registered by the ICP algorithm, selects auxiliary facilities such as charging stations and signal base stations through multi-dimensional feature library matching and function verification, and further extracts the initial strategy core parameters and auxiliary facility function attribute parameters to construct a compatibility evaluation matrix, positions the energy supply, weak signal and time sequence conflict path interval, and adjusts based on the power, electromagnetic and fault sensitive equipment constraints, realizes the dynamic adaptation of the inspection path and the equipment fault risk, environmental interference intensity and auxiliary facility distribution, effectively solves the problems of unmanned aerial vehicle endurance interruption and data collection interruption, and significantly improves the inspection efficiency and data collection integrity; (2) In view of the problem that the existing power distribution network fault identification relies on single sensor data and is easy to be misjudged by environmental interference, and the matching degree of operation and maintenance resources and fault level is low, resulting in lag of emergency fault response, the application synchronously collects multi-dimensional state data (such as device appearance image, temperature data, electromagnetic interference intensity, etc.) by the unmanned aerial vehicle (carrying high-definition camera, infrared thermal imager, electromagnetic sensor) according to the target inspection strategy, associates and fuses the collected data with the power distribution network line three-dimensional point cloud model and the historical operation and maintenance database, inputs the fault identification model to determine the fault level through defect feature matching and operation risk value calculation, simultaneously realizes accurate calibration of fault location and generation of a detail report containing fault type and influence range on the visual interface relying on the three-dimensional point cloud model, dynamically schedules the unmanned aerial vehicle secondary inspection resources, emergency repair team and spare parts warehouse resources based on the fault level, realizes the technical leap from single data judgment to multi-source data fusion judgment in fault identification, and upgrades the strategy from general response to hierarchical linkage in fault disposal, greatly improves the fault identification accuracy and emergency fault response time efficiency; (3) In view of the problem that the historical operation and maintenance data and the real-time operation and maintenance process data are separated in the existing power distribution network operation and maintenance, it is difficult to form a continuous optimization operation and maintenance closed loop, and the intelligent level of operation and maintenance is restricted, the application integrates the equipment running time, load level, fault frequency and other parameters in the historical operation and maintenance database into the equipment environment correlation matrix in the initial inspection strategy construction stage, provides historical data support for double objective optimization to ensure the rationality of the initial strategy; after the operation and maintenance is completed, the unmanned aerial vehicle inspection data, fault processing results, resource scheduling records and other full data are archived to the historical operation and maintenance database, the equipment fault probability, environment adaptation coefficient and other key parameters in the equipment environment correlation matrix are updated, the operation and maintenance efficiency indexes such as inspection coverage rate and fault processing time are calculated, if the indexes do not reach the preset threshold, the double objective function weight and constraint rule of the subsequent initial inspection strategy are fed back to the strategy generation engine, the fine and intelligent level of power distribution network operation and maintenance is continuously iterated and improved, and the long-term power supply reliability is ensured.

[0016] The above summary of the application is only a summary of the technical scheme of the application, in order to more clearly understand the technical means of the application, the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the specific embodiments of the application are described below. BRIEF DESCRIPTION OF DRAWINGS

[0017] Other features, objects and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments made with reference to the accompanying drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not considered as limiting the application. Moreover, the same reference symbols are used throughout the drawings to denote the same components.

[0018] Figure 1 The intelligent operation and maintenance method flow chart of the power distribution network equipment state monitoring and fault early warning of the application.

[0019] Figure 2 The unmanned aerial vehicle initial inspection strategy construction flow chart of the embodiment of the application.

[0020] Figure 3 The unmanned aerial vehicle target inspection strategy construction flow chart of the embodiment of the application.

[0021] Figure 4 The intelligent operation and maintenance system block diagram of the embodiment of the application. DETAILED DESCRIPTION

[0022] In order to make the objects, technical solutions and advantages of the present application clearer, further detailed description will be given to the present application in combination with the drawings and examples. It should be understood that the specific implementation described herein is only one of the best embodiments of the present application, which is only used to explain the present application and does not limit the protection scope of the present application. All other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0023] Before discussing the example embodiments in more detail, it should be mentioned that some example embodiments are described as processes or methods depicted as flow diagrams. Although the flow diagrams describe the operations (or steps) as a sequential process, many of the operations (or steps) can be performed in parallel, concurrently, or at the same time. In addition, the order of the operations can be re-arranged. The process can be terminated when its operations are completed, but can also have additional steps not included in the figure; the process can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0024] Embodiment 1: As shown in the figure, the intelligent operation and maintenance method of power distribution network equipment state monitoring and fault early warning comprises the following steps: Figure 1 Figure 1 S1, constructing an initial inspection strategy of a UAV according to the scene characteristics and equipment characteristics of a region to be inspected; S2, obtaining inspection auxiliary facilities in the region to be inspected through a three-dimensional point cloud model of a power distribution network line; S3, determining a target inspection strategy of the UAV by combining the initial inspection strategy of the UAV with the inspection auxiliary facilities; S4, performing equipment operation and maintenance of the region to be inspected according to the target inspection strategy of the UAV.

[0025] ​​It can be understood that the embodiment first constructs an initial unmanned aerial vehicle inspection strategy according to the scene characteristics and equipment characteristics of the region to be inspected, then obtains the inspection auxiliary facilities in the region to be inspected through the power distribution network line three-dimensional point cloud model, then determines the target unmanned aerial vehicle inspection strategy by combining the initial unmanned aerial vehicle inspection strategy and the inspection auxiliary facilities, and finally executes the technical means of equipment operation and maintenance of the region to be inspected according to the target unmanned aerial vehicle inspection strategy, realizes the intelligent adaptation of the whole process of power distribution network equipment operation and maintenance from strategy formulation to execution, preliminarily matches the region scene and equipment characteristics through the initial inspection strategy, accurately obtains the auxiliary facilities by means of the three-dimensional point cloud model to provide support for strategy optimization, and the target inspection strategy further makes up for the possible problems of the initial strategy, such as insufficient energy consumption and signal adaptation, finally guarantees the effectiveness of data collection and timeliness of fault response through standardized operation and maintenance execution, effectively solves the problems of traditional manual inspection being limited by terrain and weather, poor adaptability of conventional unmanned aerial vehicle inspection path, and disconnection between operation and maintenance resource scheduling and fault disposal, and improves the efficiency of power distribution network equipment operation and maintenance, fault early warning accuracy and power supply reliability.

[0026] As an optional embodiment, an initial unmanned aerial vehicle inspection strategy is constructed according to the scene characteristics and equipment characteristics of the region to be inspected, as shown in Figure 2 The steps include: S11, scene division and feature extraction are performed on the obtained multi-element data to generate a scene feature vector, the multi-element data including geographic information, weather information and electromagnetic environment information of the region to be inspected; S12, a device environment correlation matrix is constructed by extracting device key parameters and environment parameters in the historical operation and maintenance database, the device key parameters at least including: device type, operation life, load level, fault history record and current alarm information; S13, the scene feature vector and the device environment correlation matrix are input into a strategy generation engine, taking the minimum inspection risk and the highest inspection efficiency as double objective functions, and outputting an initial inspection strategy.

[0027] It can be understood that the embodiment first performs scene division and feature extraction on the obtained multi-element data containing geographical information, meteorological information and electromagnetic environment information of the to-be-inspected area to generate a scene feature vector, then extracts device key parameters at least containing device type, running age, load level, fault history record and current alarm information from a historical operation and maintenance database, constructs a device environment correlation matrix in combination with the environment parameters, finally inputs the scene feature vector and the device environment correlation matrix into a strategy generation engine, and outputs the technical means of the initial inspection strategy with the dual objective functions of the minimum inspection risk and the highest inspection efficiency, realizes the precise adaptation of the initial inspection strategy of the unmanned aerial vehicle to the scene characteristics (such as terrain complexity, meteorological interference intensity and electromagnetic environment stability) and the device operation characteristics (such as device fault risk degree, load bearing capacity and historical fault law) of the to-be-inspected area, quantifies the potential influence of the regional environment on the inspection (such as the restriction of complex terrain on the inspection path and the threat of severe weather to the inspection safety) through the scene feature vector, establishes the correlation between the device state and the environmental factors (such as the fault probability correlation of high-load devices under specific weather or electromagnetic environment) through the device environment correlation matrix, and guides the strategy generation direction through the dual objective functions, so that the initial inspection strategy not only has the priority coverage ability for high-risk scenes and fault-sensitive devices, but also takes into account the inspection efficiency, and preliminarily solves the problems of the traditional manual inspection being greatly restricted by terrain and weather and the conventional unmanned aerial vehicle inspection path not being fully adapted to the scene and device characteristics.

[0028] As an optional embodiment, the scene feature vector and the device environment correlation matrix are input into the strategy generation engine, the dual objective optimization operation is performed to obtain a Pareto optimal solution set by taking NSGA-II as the kernel of the strategy generation engine, the constraint rules are set according to the fault-sensitive device constraint, the electromagnetic interference constraint and the unmanned aerial vehicle power constraint, the optimal solution in the Pareto optimal solution set that meets the multi-constraint condition is selected according to the constraint rules, and the optimal solution is taken as the initial inspection strategy of the unmanned aerial vehicle. S131, the inspection risk value is determined by weighted summation of the device fault probability and the scene risk coefficient, the inspection efficiency value is determined by weighted summation of the inspection path length and the device inspection time length, and the dual objective function is determined by weighted summation of the inspection risk value and the inspection efficiency value; S132, the scene feature vector and the device environment correlation matrix are input into the strategy generation engine, NSGA-II is taken as the kernel of the strategy generation engine to perform the dual objective optimization operation to obtain a Pareto optimal solution set; S133, constraint rules are set according to the fault-sensitive device constraint, the electromagnetic interference constraint and the unmanned aerial vehicle power constraint, the optimal solution in the Pareto optimal solution set that meets the multi-constraint condition is selected according to the constraint rules, and the optimal solution is taken as the initial inspection strategy of the unmanned aerial vehicle; wherein the initial inspection strategy of the unmanned aerial vehicle includes the unmanned aerial vehicle inspection path, the device inspection time sequence, the inspection area stay time and the electromagnetic interference shielding strategy.

[0029] It can be understood that, in the embodiment, firstly, the inspection risk value is determined by weighted summation of the device failure probability and the scene risk coefficient, the inspection efficiency value is determined by weighted summation of the inspection path length and the device inspection time length, and the double-objective function is determined according to weighted summation of the inspection risk value and the inspection efficiency value; then, the scene feature vector and the device environment association matrix are input into the strategy generation engine with NSGA-II as the kernel to perform double-objective optimization operation to obtain a Pareto optimal solution set; finally, constraint rules are set according to the failure-sensitive device constraint, the electromagnetic interference constraint and the unmanned aerial vehicle power constraint, and the optimal solution in the Pareto optimal solution set that meets the multi-constraint condition is selected as the technical means of the initial inspection strategy of the unmanned aerial vehicle, which includes the unmanned aerial vehicle inspection path, the device inspection timing, the inspection area stay time and the electromagnetic interference shielding strategy, so as to realize quantitative balance of the double-objective function on the inspection risk and efficiency, the NSGA-II algorithm guarantees the scientificity of the double-objective optimization and the diversity of the optimal solution set, and the multi-constraint rule ensures that the selected initial inspection strategy meets the needs of failure-sensitive device priority inspection and electromagnetic interference avoidance, and matches the power bearing capacity of the unmanned aerial vehicle, effectively avoiding the one-sidedness of the strategy caused by only pursuing the minimum risk or the highest efficiency, and the inspection execution problem caused by not considering the key constraints, so that the initial inspection strategy has higher rationality and executability.

[0030] S2, obtaining inspection auxiliary facilities in the to-be-inspected area through the power distribution network line three-dimensional point cloud model.

[0031] As a preferred embodiment, the obtaining inspection auxiliary facilities in the to-be-inspected area through the power distribution network line three-dimensional point cloud model comprises the following steps: S21, obtaining original three-dimensional point cloud data of the power distribution network line in the to-be-inspected area, and registering the original three-dimensional point cloud data with geographic information in the inspection area by using an ICP algorithm to obtain a standardized three-dimensional point cloud model in a unified coordinate system; S22, constructing a multi-dimensional feature library based on physical properties of the inspection auxiliary facilities, and associating the multi-dimensional feature library with functional properties of the inspection auxiliary facilities to construct a structured feature index table; S23, extracting local geometric features and global semantic features of the standardized three-dimensional point cloud model, taking the multi-dimensional feature library as a benchmark, performing feature matching through a K nearest neighbor algorithm, and classifying point cloud clustering areas according to feature matching degrees; S24, performing semantic analysis and functional verification on the classified point cloud clustering areas based on the structured feature index table, and screening effective point cloud clustering areas to generate an inspection auxiliary facility list according to the verification results.

[0032] It can be understood that the embodiment adopts the technical means of first acquiring the original three-dimensional point cloud data of the power distribution network line in the to-be-inspected area, registering it with the geographic information of the inspection area through the ICP algorithm to obtain a standardized three-dimensional point cloud model in a unified coordinate system, then constructing a multi-dimensional feature library based on the physical properties of the inspection auxiliary facilities and constructing a structured feature index table by associating the functional properties of the inspection auxiliary facilities, then extracting the local geometric features and global semantic features of the standardized three-dimensional point cloud model, performing feature matching based on the multi-dimensional feature library through the K nearest neighbor algorithm, and classifying the point cloud clustering areas according to the matching degree, and finally performing semantic analysis and functional verification on the classified point cloud clustering areas based on the structured feature index table, screening the effective areas according to the verification results to generate an inspection auxiliary facility list, which realizes the geographic location accuracy of the standardized three-dimensional point cloud model due to the unified coordinate system, provides clear attribute basis for the identification of auxiliary facilities through the multi-dimensional feature library and the structured feature index table, improves the accuracy of feature matching and area classification through the K nearest neighbor algorithm, and guarantees the authenticity and effectiveness of the screened inspection auxiliary facilities through semantic analysis and functional verification. The finally generated list can provide reliable auxiliary facility information support for subsequent unmanned aerial vehicle inspection strategy optimization, and avoid affecting the adaptability of the inspection strategy due to inaccurate and incomplete auxiliary facility acquisition.

[0033] It should be noted that in the embodiment, the original three-dimensional point cloud data of the power distribution network line in the to-be-inspected area is acquired, and this data is used to represent the three-dimensional spatial form of the power distribution network line and the surrounding environment. At the same time, the geographic information (such as terrain, topography, coordinate reference, etc.) corresponding to the inspection area is acquired. Subsequently, the ICP algorithm (iterative closest point algorithm) is used to register the above two types of data. The ICP algorithm continuously minimizes the spatial distance error of the corresponding points in the two types of data by iteratively calculating the optimal transformation matrix (including translation, rotation, etc.) between the original three-dimensional point cloud data and the geographic information, and finally realizes the unification of the original three-dimensional point cloud data and the geographic information of the inspection area in the spatial coordinates, thereby obtaining a standardized three-dimensional point cloud model in a unified coordinate system. This model provides spatial position accuracy and matching with the actual geographic environment for the subsequent extraction of inspection auxiliary facilities (such as charging stations, signal base stations, etc.), avoiding the positioning deviation problem of auxiliary facilities caused by the non-uniformity of data coordinate systems.

[0034] As an optional embodiment, the semantic analysis and functional verification of the classified point cloud clustering areas based on the structured feature index table, according to the verification results, screening out the effective point cloud clustering areas to generate an inspection auxiliary facility list, includes the following steps: S241, extract the semantic features of the classified point cloud clustering areas, and perform multi-dimensional matching calculation of the extracted semantic features and the structured feature index table to obtain the feature matching degree; S242, mapping the functional attribute of the point cloud clustering area according to the semantic feature matching result, and marking the area with a feature matching degree greater than a set threshold and meeting a functional attribute threshold range as an effective point cloud clustering area; S243, parameter structuring the effective point cloud clustering area to obtain an inspection auxiliary facility list, and associating the inspection auxiliary facility to a corresponding coordinate position of the standardized three-dimensional point cloud model.

[0035] It can be understood that the embodiment adopts the technical means of first extracting the semantic features of the point cloud clustering area completed by classification, performing multi-dimensional matching of the semantic features with the structured feature index table to calculate the feature matching degree (using the K nearest neighbor algorithm for calculation), then mapping the functional attribute of the point cloud clustering area according to the semantic feature matching result, marking the area with a feature matching degree greater than a set threshold and meeting a functional attribute threshold range as an effective point cloud clustering area, and finally performing parameter structuring processing on the effective point cloud clustering area to generate an inspection auxiliary facility list, and associating the inspection auxiliary facility to a corresponding coordinate position of the standardized three-dimensional point cloud model, which realizes the dynamic technical effects of ensuring the accuracy of the inspection auxiliary facility recognition through double screening of multi-dimensional matching and functional attribute verification (excluding areas with unmatched features and substandard functions), making the auxiliary facility information more standardized and easy to call through parameter structuring, providing accurate space and attribute support for subsequent unmanned aerial vehicle inspection strategy optimization (such as integrating auxiliary facility positions in path planning) through the association of three-dimensional point cloud model coordinates, and avoiding the problem of strategy adaptation caused by inaccurate auxiliary facility information and no coordinate association.

[0036] S3, determining the target inspection strategy of the unmanned aerial vehicle by combining the initial inspection strategy of the unmanned aerial vehicle with the inspection auxiliary facility.

[0037] As an optional embodiment, the determination of the target inspection strategy of the unmanned aerial vehicle by combining the initial inspection strategy of the unmanned aerial vehicle with the inspection auxiliary facility, as shown in Figure 3 includes the following steps: S31, constructing a compatibility evaluation matrix by extracting the core parameters of the initial inspection strategy of the unmanned aerial vehicle and the functional attribute parameters of the inspection auxiliary facility list; the compatibility evaluation matrix includes energy consumption compatibility indicators, signal compatibility indicators, and timing compatibility indicators; S32, performing compatibility verification on the energy consumption compatibility indicators to obtain an energy supply path interval, performing compatibility verification on the signal compatibility indicators to obtain a weak signal path interval, and performing compatibility verification on the timing compatibility indicators to obtain a timing conflict path interval; S33, adjusting the energy supply path interval, the weak signal path interval, and the timing conflict path interval according to constraint rules to obtain the target inspection strategy of the unmanned aerial vehicle.

[0038] It can be understood that the embodiment adopts the technical means of first extracting the core parameters of the initial unmanned aerial vehicle inspection strategy and the functional attribute parameters of the inspection auxiliary facility list, constructing a compatibility evaluation matrix containing energy consumption compatibility indicators, signal compatibility indicators and timing compatibility indicators, then performing compatibility verification on the energy consumption compatibility indicators, signal compatibility indicators and timing compatibility indicators respectively, and correspondingly obtaining the energy supply path interval, the weak signal path interval and the timing conflict path interval, and finally adjusting the above three path intervals according to the constraint rules to obtain the target unmanned aerial vehicle inspection strategy, so as to realize the accurate identification of the adaptation of the initial inspection strategy and the inspection auxiliary facility in the energy consumption, signal and timing dimensions through the compatibility evaluation matrix, the positioning of the specific path interval that needs to be adjusted through targeted verification, and the full adaptation of the target inspection strategy to the auxiliary facility (such as solving the endurance by combining the charging station, optimizing the signal by relying on the base station, and coordinating the timing to avoid conflicts) after adjustment according to the constraint rules, effectively making up the possible adaptation defects of the initial strategy, and improving the feasibility and rationality of the unmanned aerial vehicle inspection strategy.

[0039] As an optional embodiment, the core parameters include the total length of the inspection path, the estimated energy consumption of each inspection section, the device inspection timing and the signal demand corresponding to the electromagnetic interference shielding; The functional attribute parameters include the charging power of the charging station, the charging efficiency, the coverage radius of the base station and the signal strength.

[0040] As an optional embodiment, the target unmanned aerial vehicle inspection strategy is obtained by adjusting the energy supply path interval, the weak signal path interval and the timing conflict path interval according to the constraint rules; comprising the following steps: S331, based on the power constraint of the unmanned aerial vehicle and the estimated energy consumption of the inspection section of the energy supply path interval, the total energy consumption of the interval is determined, the minimum required supply power corresponding to the supply time is calculated according to the functional attribute parameters of the charging station, and the charging station closest to the inspection area and with charging efficiency greater than a set threshold is selected as the supply node according to the geographic information of the area to be inspected; the coordinates of the selected charging station are embedded as a passing node in the energy supply path interval, and the supply time is embedded in the inspection gap of the non-fault sensitive device in the energy supply path interval according to the device inspection timing; S332, based on the electromagnetic interference constraint, the signal demand and the functional attribute parameters of the base station are analyzed; if the distance between the path node and the base station is greater than the coverage radius, the weak signal path node is adjusted to the coverage range of the base station and the energy consumption of the adjusted energy supply path interval is calculated; if the distance between the path node and the base station is less than or equal to the coverage radius and the signal strength is less than a set threshold, the signal reception gain of the unmanned aerial vehicle is increased and the inspection stay time in the weak signal path interval is shortened; S333, positioning the timing conflict node based on the fault-sensitive equipment constraint, if the conflict is caused by the energy supply timing, the energy supply timing is adjusted to be before the start of the sensitive equipment inspection window or after the end of the sensitive equipment inspection window to obtain a new timing conflict path interval; if the conflict is caused by the weak signal adjustment timing, the equipment inspection time is compressed by a certain proportion to form a new timing conflict path interval; S334, splicing the newly generated energy supply path interval, weak signal path interval, and timing conflict path interval with the unadjusted path segment and timing segment in the initial unmanned aerial vehicle inspection strategy to obtain the unmanned aerial vehicle target inspection strategy.

[0041] It can be understood that the embodiment first determines the core parameters of the initial unmanned aerial vehicle inspection strategy (including the total length of the inspection path, the estimated energy consumption of each inspection segment, the signal demand corresponding to the equipment inspection timing and electromagnetic interference shielding), and the functional attribute parameters of the inspection auxiliary facility list (including the charging power of the charging station, the charging efficiency, the coverage radius and signal strength of the base station), and then adjusts the path interval in steps according to the constraint rules. Specifically, based on the power constraint of the unmanned aerial vehicle and the estimated energy consumption of the inspection segment of the energy supply path interval, the total energy consumption is determined, the minimum supply amount corresponding to the supply time is calculated according to the functional attribute parameters of the charging station, and the charging stations that meet the charging efficiency standard and are close to the to-be-inspected area are selected as the supply nodes according to the geographic information of the to-be-inspected area. The coordinates of the supply nodes are embedded in the path interval, and the supply time is embedded in the inspection gap of the non-fault-sensitive equipment; based on the electromagnetic interference constraint, the signal demand and the base station parameters are analyzed, and if the path node exceeds the coverage radius of the base station, the path node is adjusted to be within the coverage range and the new energy consumption is calculated, and if the path node does not exceed the coverage radius but the signal is weak, the signal reception gain of the unmanned aerial vehicle is improved and the inspection dwell time is shortened; based on the fault-sensitive equipment constraint, the timing conflict node is positioned, and if the energy supply timing conflicts, the energy supply timing is adjusted, and if the weak signal adjustment timing conflicts, the equipment inspection time is compressed by a certain proportion; the three newly generated path intervals and the unadjusted path segment and timing segment in the initial strategy are spliced to obtain the unmanned aerial vehicle target inspection strategy. The technical means realizes the adaptation of the target inspection strategy to the endurance requirement of the unmanned aerial vehicle (avoiding endurance interruption through accurate supply of the charging station), guarantees the data acquisition integrity (avoiding data interruption through base station coverage adjustment and signal gain optimization), and prioritizes the inspection of fault-sensitive equipment (avoiding delay in the inspection of critical equipment through timing conflict adjustment), effectively compensating for the defects of the initial inspection strategy and the insufficient adaptation of auxiliary facilities, and greatly improving the feasibility of unmanned aerial vehicle inspection, data acquisition effectiveness, and fault response timeliness.

[0042] S4, performing equipment operation and maintenance of the to-be-inspected area according to the unmanned aerial vehicle target inspection strategy.

[0043] As an optional embodiment, the step of performing equipment operation and maintenance of the to-be-inspected area according to the unmanned aerial vehicle target inspection strategy includes the following steps: S41, according to the unmanned aerial vehicle cluster size, the unmanned aerial vehicle target inspection strategy is disassembled to obtain an operation and maintenance subtask, and the unmanned aerial vehicle receives the operation and maintenance subtask and collects equipment data according to the task requirement; S42, inputting the equipment data into a fault identification model to obtain a fault level, calibrating a fault position in a visual interface through the standardized three-dimensional point cloud model, and generating a fault detail report.

[0044] It can be understood that, in the embodiment, the unmanned aerial vehicle target inspection strategy is first disassembled according to the unmanned aerial vehicle cluster size to obtain an operation and maintenance subtask, the unmanned aerial vehicle receives the operation and maintenance subtask and collects equipment data according to the task requirement (for example, the cluster contains 5 unmanned aerial vehicles, the endurance capability (for example, single endurance of 2 hours) of each unmanned aerial vehicle, the sensor load (for example, whether a high-definition camera, an infrared thermal imager, and an electromagnetic sensor are carried) and other hardware parameters, the core information (for example, the total area of the region to be inspected, containing 100 power distribution network equipment, and 20 of which are fault sensitive equipment) in the unmanned aerial vehicle target inspection strategy is extracted, then the region is divided into 5 equal areas according to the geographical continuity (corresponding to the cluster size) according to the region fragmentation + equipment priority matching logic, the collected equipment data is input into the fault identification model to obtain the fault level, the fault position is calibrated in the visual interface through the standardized three-dimensional point cloud model, and the fault detail report is generated, thereby realizing the adaptive allocation of the operation and maintenance task and the unmanned aerial vehicle cluster size (avoiding task overload or resource idling, improving the inspection coverage efficiency), the pertinence of the equipment data collection (ensuring that the data meets the fault identification requirements), the accurate evaluation of the fault level (providing a priority basis for subsequent disposal), and the intuitive calibration of the fault position and the complete information presentation.

[0045] It should be noted that the fault identification model is generated based on the historical operation and maintenance database. Specifically, the equipment data (appearance image, temperature / electromagnetic data at the time of fault) corresponding to the power distribution network equipment fault cases (for example, 10 types of faults such as insulator damage and line icing) in the past 5 years is first extracted from the database, and the fault type (for example, insulator damage) and the fault level (for example, 1st level emergency and 2nd level general) are labeled for each type of data; then a convolutional neural network (processing image features) and a gradient boosting tree (processing temperature / electromagnetic numerical features) are used to construct a model architecture, the labeled data is divided into a training set and a test set in a 7:3 ratio, the model parameters are optimized through iterative training, and finally the model input is determined as multi-dimensional equipment data (image + numerical value) and the output is determined as the fault level (for example, 1-5 levels), thereby forming a fault identification model adapted to the scene.

[0046] In the embodiment of the application, a technical solution is also provided: an intelligent operation and maintenance system suitable for the intelligent operation and maintenance method of the power distribution network equipment state monitoring and fault early warning, as shown in Figure 4 , comprising: The construction module constructs an initial inspection strategy of the unmanned aerial vehicle according to the scene characteristics and the equipment characteristics of the area to be inspected. The acquisition module acquires inspection auxiliary facilities in the area to be inspected through the three-dimensional point cloud model of the power distribution network line. The determination module determines a target inspection strategy of the unmanned aerial vehicle by combining the initial inspection strategy of the unmanned aerial vehicle with the inspection auxiliary facilities. The execution module executes the equipment operation and maintenance of the area to be inspected according to the target inspection strategy of the unmanned aerial vehicle.

[0047] It can be understood that the embodiment adopts the setting of the construction module, the acquisition module, the determination module and the execution module, and the construction module constructs an initial inspection strategy of the unmanned aerial vehicle according to the scene characteristics and the equipment characteristics of the area to be inspected, the acquisition module acquires inspection auxiliary facilities in the area to be inspected through the three-dimensional point cloud model of the power distribution network line, the determination module determines a target inspection strategy of the unmanned aerial vehicle by combining the initial inspection strategy of the unmanned aerial vehicle with the inspection auxiliary facilities, and the execution module executes the equipment operation and maintenance of the area to be inspected according to the target inspection strategy of the unmanned aerial vehicle. The technical means realizes the full-process modularization and cooperation of the intelligent operation and maintenance of the power distribution network equipment state monitoring and fault early warning from strategy construction, auxiliary facility acquisition, strategy optimization to operation and maintenance execution, effectively connects the early-stage strategy formulation and the later-stage operation and maintenance landing, avoids the data fragmentation and the process fault in each link, simultaneously relies on the professional functions of each module to improve the initial strategy adaptability, the auxiliary facility acquisition accuracy, the target strategy rationality and the operation and maintenance execution standardization, and further solves the problems of the traditional manual inspection being limited by the terrain and weather, the conventional unmanned aerial vehicle inspection strategy optimization being insufficient and the like, guarantees the accurate fault early warning and rapid disposal, and enhances the power supply reliability of the power distribution network.

[0048] From the above description of the embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the specific device is divided into different functional modules to complete all or part of the functions described above.

[0049] In the embodiments provided in the present application, it should be understood that the disclosed structures and methods can be implemented in other ways. For example, the above-described embodiments of the structure are only illustrative, for example, the division of the modules or units is only a logical function division, and in actual implementation, another division mode can be adopted, for example, a plurality of units or components can be combined or integrated into another structure, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed ones can be indirect coupling or communication connection through some interfaces, structures or units, which can be electrical, mechanical or other forms.

[0050] The units described as separate components may or may not be physically separate, and the components displayed as units may be a physical unit or multiple physical units, that is, may be located in one place, or also can be distributed to multiple different places. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0051] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0052] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a readable storage medium. Based on such understanding, the technical scheme of the embodiments of the present application essentially or the part that contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product. The software product is stored in a storage medium, including a plurality of instructions for causing an apparatus (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0053] The above specific embodiments are the preferred embodiments of the power distribution network equipment state monitoring and fault early warning intelligent operation method and system of the present application, and are not intended to limit the specific implementation range of the present application. The scope of the present application includes but is not limited to the specific embodiments, and equivalent changes made in accordance with the shape and structure of the present application are within the scope of protection of the present application.

Claims

1. An intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning, characterized in that, Comprise the following steps: S1, constructing a UAV initial inspection strategy according to the scene characteristics and equipment characteristics of the area to be inspected; S2, obtaining inspection auxiliary facilities in the area to be inspected through a power distribution network line three-dimensional point cloud model; S3, determining a UAV target inspection strategy through the UAV initial inspection strategy combined with the inspection auxiliary facilities; S4, performing equipment operation and maintenance of the area to be inspected according to the UAV target inspection strategy. 2.The power distribution network equipment state monitoring and fault early warning intelligent operation and maintenance method of claim 1, characterized in that, The constructing a UAV initial inspection strategy according to the scene characteristics and equipment characteristics of the area to be inspected comprises the following steps: S11, performing scene division and feature extraction to generate a scene feature vector from the obtained multi-element data, the multi-element data including geographic information, meteorological information, and electromagnetic environment information of the area to be inspected; S12, constructing an equipment environment correlation matrix by extracting equipment key parameters and environment parameters in a historical operation and maintenance database, the equipment key parameters at least including: equipment type, operation life, load level, fault history record, and current alarm information; S13, inputting the scene feature vector and the equipment environment correlation matrix into a strategy generation engine, taking the minimum inspection risk and the highest inspection efficiency as double objective functions, and outputting an initial inspection strategy.

3. The intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning according to claim 2, characterized in that: The inputting the scene feature vector and the equipment environment correlation matrix into the strategy generation engine, taking the minimum inspection risk and the highest inspection efficiency as double objective functions, and outputting an initial inspection strategy comprises the following steps: S131, determining an inspection risk value by weighted summation of equipment failure probability and scene risk coefficient, and determining an inspection efficiency value by weighted summation of inspection path length and equipment inspection time length; determining a double objective function by weighted summation of the inspection risk value and the inspection efficiency value; S132, inputting the scene feature vector and the equipment environment correlation matrix into the strategy generation engine, taking NSGA-II as the kernel of the strategy generation engine to perform double objective optimization operation to obtain a Pareto optimal solution set; S133, setting a constraint rule according to fault sensitive equipment constraint, electromagnetic interference constraint, and UAV power constraint, screening optimal solutions in the Pareto optimal solution set that meet the multi-constraint condition according to the constraint rule, and taking the optimal solution as the UAV initial inspection strategy; wherein the UAV initial inspection strategy includes UAV inspection path, equipment inspection time sequence, inspection area stay time, and electromagnetic interference shielding strategy.

4. The intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning according to claim 1, characterized in that: The obtaining inspection auxiliary facilities in the area to be inspected through a power distribution network line three-dimensional point cloud model comprises the following steps: S21, obtaining original three-dimensional point cloud data of the power distribution network line in the area to be inspected, registering the original three-dimensional point cloud data with geographic information in the inspection area by using an ICP algorithm, and obtaining a standardized three-dimensional point cloud model in a unified coordinate system; S22, constructing a multi-dimensional feature library based on physical properties of the inspection auxiliary facilities, associating the multi-dimensional feature library with functional properties of the inspection auxiliary facilities, and constructing a structured feature index table. S23, extract the local geometric features and global semantic features of the standardized three-dimensional point cloud model, use the multi-dimensional feature library as the benchmark, perform feature matching through the K nearest neighbor algorithm, and classify the point cloud clustering areas according to the feature matching degree; S24, based on the structured feature index table, perform semantic analysis and function verification on the classified point cloud clustering areas, and filter out the effective point cloud clustering areas to generate an inspection auxiliary facility list.

5. The intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning according to claim 4, characterized in that: the semantic analysis and function verification on the classified point cloud clustering areas based on the structured feature index table, and the filtering out of the effective point cloud clustering areas to generate an inspection auxiliary facility list according to the verification result, comprises the following steps: S241, extract the semantic features of the classified point cloud clustering areas, and perform multi-dimensional matching between the extracted semantic features and the structured feature index table to calculate the feature matching degree; S242, map the function attributes of the point cloud clustering areas according to the semantic feature matching result, and mark the areas with a feature matching degree greater than a set threshold and meeting the function attribute threshold range as effective point cloud clustering areas; S243, perform parameter structuring on the effective point cloud clustering areas to obtain an inspection auxiliary facility list, and associate the inspection auxiliary facility to the corresponding coordinate position of the standardized three-dimensional point cloud model.

6. The intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning according to claim 3, characterized in that: the determination of the UAV target inspection strategy by combining the UAV initial inspection strategy with the inspection auxiliary facility comprises the following steps: S31, extract the core parameters of the UAV initial inspection strategy and the function attribute parameters of the inspection auxiliary facility list to construct a compatibility evaluation matrix; the compatibility evaluation matrix comprises energy consumption compatibility indexes, signal compatibility indexes, and time sequence compatibility indexes; S32, perform compatibility verification on the energy consumption compatibility indexes to obtain an energy supply path interval, perform compatibility verification on the signal compatibility indexes to obtain a weak signal path interval, and perform compatibility verification on the time sequence compatibility indexes to obtain a time sequence conflict path interval; S33, adjust the energy supply path interval, the weak signal path interval, and the time sequence conflict path interval according to constraint rules to obtain a UAV target inspection strategy.

7. The intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning according to claim 6, characterized in that: the core parameters comprise the total length of the inspection path, the estimated energy consumption of each inspection section, the device inspection time sequence, and the corresponding signal demand of the electromagnetic interference shielding; the function attribute parameters comprise the charging power of the charging station, the charging efficiency, the base station coverage radius, and the signal strength.

8. The intelligent operation and maintenance method for power distribution network equipment state monitoring and fault early warning according to claim 6, characterized in that: the adjustment of the energy supply path interval, the weak signal path interval, and the time sequence conflict path interval according to constraint rules to obtain a UAV target inspection strategy comprises the following steps: S331, determine the total energy consumption of the energy supply path interval based on the UAV power constraint combined with the estimated energy consumption of the inspection section of the energy supply path interval, calculate the minimum required supply power corresponding to the supply time based on the charging station function attribute parameters, and select the charging station closest to the inspection area and with a charging efficiency greater than a set threshold as the supply node based on the geographic information of the inspection area; embed the coordinates of the selected charging station as a passing node into the energy supply path interval, and embed the supply time into the inspection gap of the non-fault-sensitive equipment in the energy supply path interval according to the equipment inspection timing; S332, analyze the signal demand and base station function attribute parameters based on the electromagnetic interference constraint; if the distance between the path node and the base station is greater than the coverage radius, adjust the weak signal path node to the base station coverage range and calculate the energy consumption of the adjusted energy supply path interval; if the distance between the path node and the base station is less than or equal to the coverage radius and the signal strength is less than a set threshold, increase the UAV signal reception gain and shorten the inspection stay time in the weak signal path interval; S333, locate the timing conflict node based on the fault-sensitive equipment constraint, if the conflict is caused by the energy supply timing, advance the energy supply timing to before the sensitive equipment inspection window or delay it to after the sensitive equipment inspection window to obtain a new timing conflict path interval; if the conflict is caused by the weak signal adjustment timing, compress the equipment inspection time by a set proportion to form a new timing conflict path interval; S334, splice the newly generated energy supply path interval, weak signal path interval, and timing conflict path interval with the unadjusted path segment and timing segment in the UAV initial inspection strategy to obtain the UAV target inspection strategy.

9. The intelligent operation and maintenance method for power distribution network equipment state monitoring and fault warning according to claim 1, characterized in that, the device operation and maintenance of the inspection area according to the UAV target inspection strategy comprises the following steps: S41, decompose the UAV target inspection strategy according to the UAV cluster size to obtain operation and maintenance sub-tasks, and the UAV receives the operation and maintenance sub-tasks and collects equipment data according to the task requirements; S42, input the equipment data into the fault identification model to obtain the fault level, and calibrate the fault position in the visualization interface through the standardized three-dimensional point cloud model and generate a fault detail report.

10. An intelligent operation and maintenance system suitable for the intelligent operation and maintenance method of power distribution network equipment state monitoring and fault early warning according to any one of claims 1-9, characterized in that, including: a construction module for constructing a UAV initial inspection strategy according to the scene characteristics and equipment characteristics of the inspection area; an acquisition module for acquiring inspection auxiliary facilities in the inspection area through a power distribution network line three-dimensional point cloud model; a determination module for determining a UAV target inspection strategy based on the UAV initial inspection strategy combined with the inspection auxiliary facilities; an execution module for performing device operation and maintenance of the inspection area according to the UAV target inspection strategy.

Images