Power inspection method and system based on big data and random tree algorithm

Abstract

The invention discloses an electric power inspection method and system based on big data and a random tree algorithm, and relates to the field of electric power system management and maintenance. Comprising the following steps: collecting key information, historical information and personnel basic data information of power equipment in real time, and processing the obtained key information; based on the processed key data, a plurality of factors are comprehensively considered, and an inspection line model is constructed; solving the inspection line model by using a fast search random tree algorithm; and outputting the optimized power inspection path, and carrying out data storage. According to the method, the information subsets of the electric power equipment and the inspection maintenance personnel object provided by the big data platform are introduced, multiple feasible paths subjected to coarse screening are further screened, the optimal electric power inspection path is generated through iteration for a certain number of times, the line scheme is output and stored, and intelligent optimization of the electric power inspection path is achieved.

Description

Technical Field

[0001] The present invention relates to the field of power system management and maintenance, and in particular to a power inspection method and system based on big data and random tree algorithm. Background Art

[0002] With the continuous deepening of smart grid construction, the scale of power network is expanding, and the number of power equipment is also increasing sharply. Traditional power inspection methods are often based on experience or fixed patterns, lacking scientificity and flexibility, resulting in low inspection efficiency and serious waste of resources.

[0003] Therefore, how to use modern information technology to achieve intelligent optimization of power inspection lines, improve inspection efficiency and reduce inspection costs is an urgent problem to be solved in the current power industry. Summary of the invention

[0004] In view of the problems existing in the traditional power inspection method, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to achieve intelligent optimization of power inspection lines, improve inspection efficiency, and reduce inspection costs.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a power inspection method based on big data and a random tree algorithm, which includes collecting key information, historical information and basic personnel data information of power equipment in real time, and processing the acquired key information; based on the processed key data, comprehensively considering various factors, constructing an inspection line model; using a fast search random tree algorithm to solve the inspection line model; outputting the optimized power inspection path and storing the data.

[0008] As a preferred solution of the power inspection method based on big data and random tree algorithm described in the present invention, the processing of the acquired key information includes data cleaning and data conversion as well as standardization processing and data integration classification and feature selection extraction.

[0009] As a preferred solution of the power inspection method based on big data and random tree algorithm described in the present invention, the solution to the inspection line model includes the following steps: variable initialization definition; building RRT-Connect expansion tree; connecting two trees; applying ant colony algorithm to optimize the path; iterative optimization path.

[0010] As a preferred solution of the power inspection method based on big data and random tree algorithm described in the present invention, the RRT-Connect expansion tree construction includes: a) randomly generating a point X in spacerand ; b) Traverse the extended tree T a , find the distance X rand The nearest node X near ; c) Select X near and X rand The distance on the closest line X near The point with the rated step size λ is taken as the new node X new ; d) Monitoring X new With X near Whether the line between them collides with the obstacle. If no collision occurs, X new Add extension tree T a Otherwise, re-execute step b; e) traverse the expansion tree T b , find the distance X new The nearest node X′ near ; f) Select X new and X′ near The distance X′ on the line near The point with the rated step length λ is taken as the new node X′ new ; g) Monitoring X′ new With X′ near Whether the line between them collides with the obstacle, if no collision occurs, then X′ new Add extension tree T b Otherwise, execute step e again.

[0011] As a preferred solution of the power inspection method based on big data and random tree algorithm of the present invention, the operation steps of connecting the two trees are as follows: continuously executing the RRT-Connect expansion tree construction until the expansion tree T a The distance between the node in and the target area is less than the distance threshold or reaches the preset number of iterations; b Find the distance T a The node closest to the node, tries to establish a connection between the two points; if the connection is successfully established, the starting point X is found. start To target area X goal Path.

[0012] As a preferred solution of the power inspection method based on big data and random tree algorithm described in the present invention, the application of ant colony algorithm to optimize the path includes the following steps: initializing a certain number of ants N, each ant starting from the starting point X start Start, select the next node according to the pheromone concentration S and heuristic information; when the ant reaches the end area X goalWhen , the length of the path traversed is recorded and pheromones are released; the path optimization process is repeated until all ants complete a traversal or reach the preset number of iterations N′, where N′>N is required; the optimal path is selected according to the pheromone concentration, and S max As the basis for determining the current optimal solution.

[0013] As a preferred solution of the power inspection method based on big data and random tree algorithm described in the present invention, the iterative optimization path includes: taking the current optimal solution as a new input, repeating the steps of building an RRT-Connect expansion tree, connecting two trees and applying the ant colony algorithm to optimize the path; comparing the path lengths L of the new and old optimal solutions. new and L old , if L new Less than L old , the new solution is better, and the optimal solution is updated; the iterative process is repeated until the convergence condition is met or the maximum number of iterations is reached.

[0014] In the second aspect, an embodiment of the present invention provides an electric power inspection system based on big data and a random tree algorithm, which includes a data acquisition module for collecting key information, historical information and basic personnel data information of electric power equipment in real time; a data processing module for processing the acquired key information; an inspection line model construction module for constructing an inspection line model based on the processed key data and taking into account various factors; a fast search random tree algorithm solution module for solving the inspection line model using a fast search random tree algorithm; and a path optimization and storage module for outputting the optimized electric power inspection path and storing the data.

[0015] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the power inspection method based on big data and random tree algorithm as described in the first aspect of the present invention are implemented.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the power inspection method based on big data and random tree algorithm as described in the first aspect of the present invention are implemented.

[0017] The beneficial effects of the present invention are as follows: the present invention applies a fast search random tree algorithm to obtain the inspection order of the target points, and then selects multiple feasible paths. By introducing the information subset of the power equipment and inspection and maintenance personnel objects provided by the big data platform, multiple feasible paths are further screened, and the optimal power inspection path is generated after a certain number of iterations, and the line plan is output and stored, thereby realizing the intelligent optimization of the power inspection route. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 This is a flow chart of the power inspection method based on big data and random tree algorithm. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1

[0024] Reference Figure 1 , which is the first embodiment of the present invention, and provides a power inspection method based on big data and random tree algorithm, such as Figure 1 As shown, including

[0025] S1: Collect key information, historical information and basic data of power equipment in real time, and process the key information obtained.

[0026] Specifically, by utilizing various sensors, drones, intelligent inspection robots and other equipment deployed in the power network, key information such as the geographic location, operating status, fault records and personnel location of power equipment can be collected in real time; at the same time, historical information such as historical inspection data, equipment maintenance records and basic personnel data can be obtained through storage media such as power system databases and cloud platforms.

[0027] The above information is cleaned, integrated and classified, and noise and outliers are eliminated to ensure the accuracy and completeness of the information.

[0028] Preferably, key data information collection and processing includes the following steps:

[0029] a) Determine the type of data to be collected to support the construction of the circuit model.

[0030] For example, the geometric parameters, electrical parameters, operating data, environmental conditions, etc. of the equipment. At the same time, the type and scope of the data should be clarified according to the analysis purpose and accuracy requirements.

[0031] b) Select data sources and data collection methods to perform data collection.

[0032] By selecting multiple data sources, such as the power company's database, operation records, maintenance logs, public data platforms, SCADA systems, online monitoring equipment and other channels, using monitoring equipment or crawlers and other technical means to collect data in real time or regularly, and collecting data according to the selected methods and data sources. At the same time, the collected data is preliminarily checked and verified to ensure the accuracy and completeness of the data.

[0033] c) Perform data cleaning, data conversion and standardization.

[0034] The collected data are initially screened by identifying and deleting duplicate, erroneous or invalid data, using interpolation, mean substitution and other methods to deal with missing values, and smoothing the data to eliminate noise and outliers. The screened data are converted into a format and data suitable for analysis. At the same time, the data are standardized to eliminate dimensional differences, facilitate subsequent calculations and analysis, and ensure the practicality of the data.

[0035] d) Perform data integration classification and feature selection extraction.

[0036] First, data from different data sources are integrated to form a complete data set. Secondly, the data is classified and reorganized according to the analysis requirements to facilitate subsequent feature extraction and model building. Then, features related to line model construction are extracted from the data that has been cleaned, converted and standardized. Finally, statistical methods, machine learning algorithms and other strategies are used to select features that have an important impact on model construction.

[0037] S2: Based on the processed key data, taking into account a variety of factors, by setting reasonable weights and constraints, a patrol line model is constructed that can truly reflect the actual situation and needs of power patrol, such as the multi-objective planning model in the optimization model.

[0038] Among them, various factors include the distribution of power equipment, the length of the inspection route, the inspection time, topography, weather conditions and the basic conditions of the inspection personnel.

[0039] Preferably, the construction of the inspection line model includes the following steps:

[0040] S2.1: Select the appropriate basic model type based on the goals and requirements of generating inspection paths.

[0041] Among them, the optimization model refers to a model established under a series of conditions to seek a reasonable allocation of limited resources to maximize (or minimize) one or more indicators of concern. The establishment of the optimization model can generally be divided into three steps: determining the optimization goal, controlling variables, and limiting conditions.

[0042] Among them, the optimization goal is the best result we hope to obtain, the control variable is the independent variable that can be manipulated to achieve the optimal result, and the constraint condition is the range of the independent variable when achieving the optimization goal. The simulation model is a tool for analysis and prediction by simulating the behavior and performance of the actual system or process. It is usually based on a deep understanding of the system or process to build a model that can reflect its key characteristics and behavior. By running the simulation model, we can observe and analyze the response and performance of the system under different conditions, thereby providing a basis for decision-making. The predictive model is a model that uses statistical methods or machine learning algorithms to predict future results or trends based on historical data and other relevant information. The predictive model can help us understand possible future situations in advance, so as to formulate corresponding strategies and plans.

[0043] Here we use the multi-objective planning model in the optimization model as an example:

[0044] Multi-objective programming refers to the study of the optimization of more than one objective function in a given area. The main mathematical description form of the multi-objective programming model is:

[0045]

[0046]

[0047] Where X in (1) = [x1, x2, ... x n ] is the decision variable T, X in (2) = (x1, x2, ... x n The space Ω where F(X) in formula (1) is located is called the target space.

[0048] If there are n decision variables, k objective functions, and m constraint equations, then:

[0049] Z=F(X) is a k-dimensional function variable; φ(X) is an m-dimensional vector function; and G is an m-dimensional constant vector.

[0050] For multi-objective programming, we cannot only consider the optimality of one objective function while ignoring other objective functions. Multi-objective programming requires making complex choices, including the choice of objective function and the choice of decision variables.

[0051] The quality of a solution cannot be measured by a single indicator, and multiple targets need to be compared. Through S1, the target space, decision space and constraints are established, and then a model suitable for the target space, decision space and constraints is constructed through S2.2, so as to obtain multiple F(X) as non-inferior solutions. Among the non-inferior solutions, Pareto is the optimal solution, which is the value obtained by S3 using the fast search random tree algorithm.

[0052] S2.2: Use professional modeling tools or software to build models based on data input and constraints. Data modeling software tools such as PowerDesigner, ER / Studio, Sparx Enterorise Architect, etc. can basically meet the above requirements.

[0053] S3: Use the fast search random tree algorithm to solve the inspection line model.

[0054] Specifically, according to the set optimization goals, such as minimizing inspection time, maximizing inspection efficiency, and reducing inspection costs, the inspection route is automatically adjusted to find the optimal inspection plan. At the same time, the strategy can be dynamically adjusted based on the real-time monitoring information and historical information of the power equipment to adapt to different inspection scenarios and needs.

[0055] Preferably, the rapid search random tree algorithm application comprises the following steps:

[0056] S3.1: Variable initialization definition.

[0057] S3.1.1: In a known spatial environment Y, define the inspection starting point X start , inspect target area point X goal and the nominal step size λ.

[0058] S3.1.2: Initialize two expansion trees T a and T b . T a X start is the root node, T b X goal is the root node.

[0059] S3.2: Build the RRT-Connect extension tree.

[0060] S3.2.1: Generate a random point X in space rand .

[0061] S3.2.2: Traverse the extended tree T a , find the distance X rand The nearest node X near .

[0062] S3.2.3: Select X near and X rand The distance on the closest line X near The point with the rated step size λ is taken as the new node X new .

[0063] S3.2.4: Monitoring X new With X near Whether the line between them collides with an obstacle. If no collision occurs, X new Add extension tree T a Otherwise, execute step 2 again.

[0064] S3.2.5: Traverse the extension tree T b , find the distance X new The nearest node X′ near .

[0065] S3.2.6: Select X new and X′ near The distance X′ on the line near The point with the rated step length λ is taken as the new node X′ new .

[0066] S3.2.7: Monitoring X′ new With X′ near Whether the line between them collides with an obstacle. If no collision occurs, X′ new Add extension tree T b Otherwise, execute step 5 again.

[0067] S3.3: Connect two trees.

[0068] S3.3.1: Continue to execute step S3.2 until the tree T is expanded a The nodes in are close enough to the target area or the preset number of iterations is reached.

[0069] Among them, the extended tree T is close enough to the target area. a The distance between the node in and the target area is less than the distance threshold.

[0070] S3.3.2: Try to connect the extended tree T a and T b .

[0071] The specific method is: From T b Find the distance T aThe node closest to the node and then tries to establish a connection between the two points.

[0072] S3.3.3: If the connection is successfully established, the start To target area X goal Path.

[0073] S3.4: Apply ant colony algorithm to optimize the path.

[0074] S3.4.1: Use the ACO algorithm to further optimize the path. Initialize a certain number of ants N, each ant starts from the starting point X start Start and select the next node according to the pheromone concentration S and heuristic information.

[0075] S3.4.2: When the ant reaches the end area X goal When the insect moves, the length of the path it has traveled is recorded, and pheromones are released to enhance the pheromone concentration on the path.

[0076] S3.4.3: Repeat the above process until all ants complete a traversal or reach a preset number of iterations N′, where the condition N′>N needs to be satisfied to ensure data accuracy.

[0077] S3.4.4: Select the optimal path based on the pheromone concentration, where S max As the basis for determining the current optimal solution.

[0078] S3.5: Iterate the optimization path.

[0079] S3.5.1: Use the current optimal solution as the new input and repeat steps 2 to 4 to further optimize the path.

[0080] S3.5.2: Compare the path lengths L of the new and old optimal solutions new and L old , if L new Less than L old , then the new solution is better, and the optimal solution is updated.

[0081] S3.5.3: Repeat the iterative process until convergence conditions are met (e.g., the path length no longer changes significantly) or the maximum number of iterations is reached.

[0082] S3.5.4: By introducing the information subset of the power equipment and inspection and maintenance personnel objects provided by the big data platform, multiple feasible paths are further screened, and the optimal power inspection path is generated after a certain number of iterations.

[0083] S3.5.5: Output the final optimal inspection path, that is, from the starting point X start To target area X goal inspection path.

[0084] S4: Output the optimized power inspection path and store the data.

[0085] The output content includes detailed line diagrams, equipment inspection sequence, estimated inspection time, key equipment information, and inspection and maintenance personnel information, etc. At the same time, it will provide data storage function to facilitate inspection personnel to import optimized inspection line plans into inspection equipment and to iterate and optimize the present invention as an information cluster.

[0086] Among them, outputting the path and storing the data include: presenting the planned route in various forms such as visualization, including but not limited to text description, chart display and electronic documents, so as to facilitate the relevant personnel to view and understand; storing the planned route locally and in the cloud in kml, kmz, shp and other formats, and taking appropriate security measures to protect sensitive or confidential route plans.

[0087] It can be seen that the present invention collects basic information of power equipment, inspection and maintenance personnel, real-time monitoring information and historical information, and combines big data technology to analyze and obtain inspection environment maps, including but not limited to vector maps, satellite maps, electronic charts and three-dimensional maps, as well as inspection multiple target points, including but not limited to the location information of target points such as inspection starting points, key monitoring points and ordinary monitoring points. According to the goals and requirements of generating inspection paths, the appropriate basic model type is selected, and the inspection line model is constructed based on the key data information obtained by big data technology analysis and the constraints existing in the actual scene by using professional modeling tools or software. The inspection order of the target points is obtained by applying the fast search random tree algorithm, and then multiple feasible paths are selected. By introducing the information subset of the power equipment and inspection and maintenance personnel objects provided by the big data platform, multiple feasible paths are further screened, and the optimal power inspection path is generated by iterating a certain number of times, and the line plan is output and stored to realize the intelligent optimization of the power inspection route.

[0088] Example 2

[0089] The present embodiment provides a power inspection system based on big data and random tree algorithm, including a data acquisition module, which is used to collect key information, historical information and basic data information of power equipment in real time; a data processing module, which is used to process the acquired key information; an inspection line model construction module, which is used to construct an inspection line model based on the processed key data and comprehensively consider various factors; a fast search random tree algorithm solution module, which is used to solve the inspection line model using a fast search random tree algorithm; a path optimization and storage module, which is used to output the optimized power inspection path and store the data.

[0090] Example 3

[0091] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0092] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0093] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0094] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following techniques well known in the art or a combination thereof.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power inspection method based on big data and random tree algorithm, characterized by: include, Collect key information, historical information and basic personnel data of power equipment in real time, and process the key information obtained; Based on the processed key data, a patrol route model is constructed by taking into account various factors; The inspection line model is solved using the fast search random tree algorithm; The optimized power inspection path is output and the data is stored.

2. The power inspection method based on big data and random tree algorithm according to claim 1, characterized in that: The processing of the acquired key information includes data cleaning, data conversion, standardization, data integration and classification, and feature selection and extraction.

3. The power inspection method based on big data and random tree algorithm as claimed in claim 2, characterized in that: The solving of the inspection line model comprises the following steps: Variable initialization definition; Build RRT-Connect extension tree; Connect two trees; Apply ant colony algorithm to optimize the path; Iterate the optimization path.

4. The power inspection method based on big data and random tree algorithm as claimed in claim 3, characterized in that: The RRT-Connect expansion tree construction includes: a) Randomly generate a point X in space rand ; b) Traverse the extended tree T a , find the distance X rand The nearest node X near ; c) Select X near and X rand The distance on the closest line X near The point with the rated step size λ is taken as the new node X new ; d) Monitoring X new With X near Whether the line between them collides with the obstacle. If no collision occurs, X new Add extension tree T a Otherwise, execute step b again; e) Traverse the extended tree T b , find the distance X new The nearest node X′ near ; f) Select X new and X′ near The distance X′ on the line near The point with the rated step length λ is taken as the new node X′ new ; g) Monitoring X′ new With X′ near Whether the line between them collides with the obstacle, if no collision occurs, then X′ new Add extension tree T b Otherwise, execute step e again.

5. The power inspection method based on big data and random tree algorithm as claimed in claim 4, characterized in that: The steps of connecting two trees are as follows: Continue to execute the RRT-Connect expansion tree construction until the expansion tree T a The distance between the node in and the target area is less than the distance threshold or the preset number of iterations is reached; From T b Find the distance T a The node closest to the node, tries to establish a connection between the two points; If the connection is successfully established, the start To target area X goal Path.

6. The power inspection method based on big data and random tree algorithm as claimed in claim 5, characterized in that: The application of ant colony algorithm to optimize the path includes the following steps: Initialize a certain number of ants N, each ant starts from the starting point X start Start and select the next node according to the pheromone concentration S and heuristic information; When the ant reaches the end area X goal When the traversal is started, the length of the path traveled is recorded and pheromones are released; Repeat the path optimization process until all ants complete a traversal or reach the preset number of iterations N′, where N′>N is required; Select the optimal path according to the pheromone concentration and set S max As the basis for determining the current optimal solution.

7. The power inspection method based on big data and random tree algorithm according to claim 6, characterized in that: The iterative optimization path includes: Using the current optimal solution as a new input, repeat the steps of building the RRT-Connect expansion tree, connecting the two trees, and applying the ant colony algorithm to optimize the path; Compare the path lengths L of the new and old optimal solutions new and L old , if L new Less than L old , then the new solution is better, and the optimal solution is updated; The iterative process is repeated until the convergence condition is met or the maximum number of iterations is reached.

8. A power inspection system based on big data and random tree algorithm, based on the power inspection method based on big data and random tree algorithm according to any one of claims 1 to 7, characterized in that: Also includes, Data acquisition module, used to collect key information, historical information and basic data of personnel of power equipment in real time; A data processing module, used to process the acquired key information; Inspection line model building module, used to build inspection line model based on processed key data and comprehensive consideration of multiple factors; A fast search random tree algorithm solution module is used to solve the inspection line model using a fast search random tree algorithm; The path optimization and storage module is used to output the optimized power inspection path and store data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the power inspection method based on big data and random tree algorithm described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power inspection method based on big data and random tree algorithm described in any one of claims 1 to 7 are implemented.

Images