Distribution Network Drawing Method Based on Data Mining Algorithm

Abstract

The present invention discloses a distribution network drawing method based on a data mining algorithm and a system and a storage device thereof, characterized in that the method comprises: obtaining a distribution network topology data set, obtaining a distribution network equipment component type, obtaining a local connection relationship corresponding to the distribution network equipment component type according to the distribution network topology data set and the distribution network equipment component type, processing the distribution network equipment component type and the local connection relationship by a data mining algorithm, obtaining an equipment component connection model, and in the distribution network drawing process, automatically connecting the distribution network equipment components according to the equipment component connection model, realizing automatic connection of newly added equipment components according to the attribute of each equipment component and the relationship between each equipment component, obtaining a distribution network diagram, saving time for drawing electrical wiring diagrams, and improving drawing efficiency.

Description

Technical Field

[0001] The present application relates to the field of distribution network engineering drawing, and in particular to a distribution network drawing method and system, and a storage medium based on a data mining algorithm. Background Art

[0002] In the construction planning of distribution network, it is often necessary to draw the distribution wiring diagram of the distribution network to analyze the working conditions and topological structure of each node of the distribution network. The traditional distribution wiring diagram is drawn using computer-aided design software. During the drawing process, electrical components are dragged into the operation interface and the electrical components are manually connected to complete the distribution wiring diagram representing the topological structure of the distribution network. The operation is cumbersome and the drawing efficiency is low. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the present application proposes a distribution network drawing method and system based on a data mining algorithm, and a storage medium.

[0004] In a first aspect, an embodiment of the present application provides a distribution network drawing method based on a data mining algorithm, comprising:

[0005] Obtain distribution network topology data set;

[0006] Get the type of distribution network equipment components;

[0007] Obtaining a local connection relationship corresponding to the type of distribution network equipment component according to the distribution network topology data set and the type of distribution network equipment component;

[0008] Processing the distribution network equipment component types and the local connection relationships through a data mining algorithm to obtain an equipment component connection model;

[0009] The distribution network equipment elements are automatically connected according to the equipment element connection model to obtain a distribution network diagram.

[0010] The distribution network drawing method based on machine learning and data mining algorithm in the embodiment of the present application has at least the following beneficial effects: in the process of drawing the distribution network wiring diagram, a device component connection model is obtained through a data mining algorithm according to the type of distribution network device components and the local connection relationship, and the distribution network device components are automatically connected according to the device component connection model, so that the newly added device components are automatically connected according to the attributes of each device component and the relationship between each device component, thereby saving time in drawing electrical wiring diagrams and improving drawing efficiency.

[0011] Optionally, in one embodiment of the present application, the processing of the distribution network device component type and the local connection relationship by a data mining algorithm to obtain a device component connection model includes:

[0012] Establishing a feature mapping data table for the distribution network equipment component type and the local connection relationship through a data mining algorithm;

[0013] The feature mapping data table is trained to obtain the device component connection model.

[0014] Optionally, in one embodiment of the present application, automatically connecting the power grid device elements according to the device element connection model includes:

[0015] Obtaining a local connection relationship set corresponding to the distribution network equipment element according to the equipment element connection model;

[0016] Obtaining the location of one or more interfaces provided on the distribution network equipment element;

[0017] According to the local connection relationship set and the positions of the corresponding interfaces, an automatic connection operation of the multiple interfaces between two or more distribution network equipment elements is completed.

[0018] Optionally, in one embodiment of the present application, the distribution network topology data set is a data set generated according to distribution network construction drawings and analysis reports, and the distribution network topology data set includes a distribution network electrical wiring diagram.

[0019] Optionally, in one embodiment of the present application, the distribution network equipment component type is at least one of the following: transformer; high-voltage cabinet; low-voltage cabinet; busbar bridge; DC panel; analog panel; high-voltage cable.

[0020] Optionally, in one embodiment of the present application, obtaining a local connection relationship corresponding to the distribution network device component type according to the distribution network topology data set and the distribution network device component type includes:

[0021] Analyzing and processing the distribution network topology data set by image recognition technology to obtain a recognition result, wherein the distribution network topology data set includes a distribution network topology diagram and distribution network topology data;

[0022] A local connection relationship corresponding to the type of the distribution network equipment component is obtained according to the identification result.

[0023] Optionally, in one embodiment of the present application, after the distribution network equipment elements are automatically connected according to the equipment element connection model to obtain the distribution network diagram, the method further includes: when the coordinates corresponding to the distribution network equipment elements change, automatically generating related elements and related element combinations corresponding to the first distribution network equipment elements according to the equipment element connection model.

[0024] In a second aspect, an embodiment of the present application provides a distribution network drawing system, including:

[0025] A data preprocessing module, the data preprocessing module is used to obtain a distribution network topology data set, obtain a distribution network device component type, and obtain a local connection relationship corresponding to the distribution network device component type according to the distribution network topology data set and the distribution network device component type;

[0026] A data mining module, the data mining module is used to process the distribution network equipment component type and the local connection relationship through a data mining algorithm to obtain an equipment component connection model;

[0027] An auxiliary drawing module is used to automatically connect the distribution network equipment components according to the equipment component connection model to obtain a distribution network diagram.

[0028] The distribution network drawing system of the embodiment of the present application has at least the following beneficial effects: in the process of drawing the distribution network wiring diagram using the distribution network drawing system, the data preprocessing module obtains the type of distribution network equipment components and the local connection relationship, the data mining module obtains the equipment component connection model according to the type of distribution network equipment components and the local connection relationship through the data mining algorithm, the auxiliary drawing module automatically connects the distribution network equipment components according to the equipment component connection model, and automatically connects the newly added equipment components according to the attributes of each equipment component and the relationship between each equipment component, thereby saving time in drawing electrical wiring diagrams and improving drawing efficiency.

[0029] In a third aspect, an embodiment of the present application provides a distribution network drawing system, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the distribution network drawing method as described in any one of claims 1 to 7.

[0030] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the distribution network drawing method as described in any one of claims 1 to 7. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0032] Figure 1 is a flow chart of a distribution network drawing method based on a data mining algorithm provided in an embodiment of the present application;

[0033] Figure 2 is a flow chart of a distribution network drawing method based on a data mining algorithm provided by another embodiment of the present application;

[0034] Figure 3 is a flow chart of a distribution network drawing method based on a data mining algorithm provided by another embodiment of the present application;

[0035] Figure 4 is a flow chart of a distribution network drawing method based on a data mining algorithm provided by another embodiment of the present application;

[0036] Figure 5 This is a module diagram of a distribution network mapping system provided in another embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0038] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0039] In the construction planning of distribution network, it is often necessary to draw the distribution wiring diagram of the distribution network to analyze the working conditions and topological structure of each node of the distribution network. The traditional distribution wiring diagram is drawn using computer-aided design software. During the drawing process, electrical components are dragged into the operation interface and the electrical components are manually connected to complete the distribution wiring diagram representing the topological structure of the distribution network. The operation is cumbersome and the drawing efficiency is low.

[0040] Based on this, the present application provides a distribution network drawing method and system, and a storage medium based on a data mining algorithm. In the process of drawing the distribution network wiring diagram, a device component connection model is obtained through a data mining algorithm according to the type of distribution network equipment components and the local connection relationship, and the distribution network equipment components are automatically connected according to the device component connection model. It is realized that according to the attributes of each device component and the relationship between each device component, the newly added device components are automatically connected, thereby saving time in drawing electrical wiring diagrams and improving drawing efficiency.

[0041] The embodiments of the present application are further described below in conjunction with the accompanying drawings.

[0042] refer to Figure 1 , Figure 1 It is a flowchart of a distribution network drawing method based on a data mining algorithm provided in an embodiment of the present application. The drawing method includes but is not limited to step S110, step S120, step S130, step S140, and step S150.

[0043] Step S110: Acquire a distribution network topology data set.

[0044] In some embodiments, the topological structure of the distribution network refers to the distribution network connecting transformers, high-voltage cabinets, low-voltage cabinets, busbar bridges, DC panels, analog panels, high-voltage cables and other distribution network equipment components through switching devices such as circuit breakers, simplifying them into nodes that are unrelated to the specific construction situation, abstracting the power lines connecting these nodes into lines, and representing the relationship between these nodes in the form of a topological structure diagram.

[0045] In some embodiments, obtaining a distribution network topology data set includes: obtaining a distribution network topology data set based on distribution network construction drawings and analysis reports, the distribution network topology data set including a distribution network electrical wiring diagram; it is conceivable that in the process of planning and constructing a distribution network, by scanning historical distribution station construction drawings and analysis reports, the electrical wiring diagram portion of the distribution network is obtained, and the portion is stored in the power grid topology data, thereby effectively utilizing historical data, improving the utilization rate of historical data, and facilitating subsequent data mining.

[0046] In some embodiments, the staff improves the power grid topology data set based on the classification statistics of the distribution network topology data set and by inputting a specially drawn electrical wiring diagram, which corresponds to a structure not covered by the distribution network topology data set, so that the power grid topology data set can more comprehensively correspond to the actual power wiring situation, making the subsequent automatic connection operation of the distribution network equipment components according to the equipment component connection model more intelligent.

[0047] Step S120: Obtain the type of distribution network equipment components.

[0048] In some embodiments, the types of distribution network equipment components include transformers, high-voltage cabinets, low-voltage cabinets, busbar bridges, DC panels, analog panels, high-voltage cables, reactive power compensators and custom equipment components. Custom equipment components are a type of distribution network equipment component or a combination of distribution network equipment components set by the user according to the actual construction conditions of the distribution network. It can be thought that the types of distribution network equipment components include connecting lines, supporting towers, transformer components, disconnectors, reactive power compensators and some ancillary facilities based on their functions.

[0049] In some embodiments, the distribution network equipment elements to be used in the subsequent distribution network drawing process are preset by the user to become the distribution network equipment element type. When presetting the power grid equipment element type, the name, icon and built-in parameter type of the same preset power grid equipment element are unified. The built-in parameter type includes the interface position, interface quantity and interface type used to connect with other power grid equipment element types, so that the automatic connection between related distribution network equipment elements can be completed subsequently according to the interface position, interface quantity and interface type.

[0050] In some implementations, the types of distribution network equipment components can be obtained through big data analysis combined with image recognition technology. By building cloud and local power network equipment component type databases, image recognition is performed on the distribution network topology data set, and cluster analysis is performed to obtain the types of power network equipment components, thereby reducing human resource consumption and improving drawing efficiency.

[0051] It is conceivable that data can be collected by targeting keywords through Python crawlers, and graphic information about power grid equipment components and power grid topology structures on the Internet can be obtained. A cloud-based and local database of power grid equipment component types can be built to increase the data volume of the distribution network topology data set and the data volume of power grid equipment component types, so that the automatic connection function between subsequent power grid equipment components can be improved according to the situation.

[0052] Step S130: obtaining a local connection relationship corresponding to the type of distribution network equipment component according to the distribution network topology data set and the type of distribution network equipment component.

[0053] In some embodiments, the local connection relationship refers to the actual situation of circuit connection between distribution network equipment elements and surrounding distribution network equipment elements, including the wiring conditions corresponding to the transmission, distribution and conversion of electric energy. Each combination of power grid equipment elements has a corresponding local connection relationship; it can be imagined that the distribution network equipment elements are preset with interfaces for line connection, and the local connection relationship includes nearby component combinations and specific connection conditions. The specific connection conditions are the interface position, interface quantity and interface type of the corresponding interface for connection.

[0054] In some embodiments, the distribution network topology is digitized and then a machine learning algorithm is used to obtain a local connection relationship corresponding to the type of distribution network equipment component. It can be imagined that a multi-branch tree structure is used to digitally represent the distribution network topology, and a machine learning algorithm is used to analyze the digitized distribution network topology to obtain a mapping relationship between the distribution network equipment components and the local connection relationship. The machine learning algorithm includes a classification algorithm and a regression algorithm.

[0055] Step S140: obtaining a device component connection model through a data mining algorithm according to the types of distribution network device components and local connection relationships.

[0056] In some embodiments, the data mining algorithm includes common algorithms such as cosine similarity, K-Means clustering algorithm, maximum expectation (EM) algorithm, K-value nearest neighbor algorithm, classification and regression tree, etc.

[0057] In some embodiments, according to the type of distribution network equipment components and the local connection relationship, the equipment component connection model is obtained by fitting using cosine similarity in the data mining algorithm. The process is as follows: first, the combination of nearby components, interface positions, interface quantity and interface types are set as input parameters, and the connection relationship between the interfaces is set as output parameters; according to the data set of the type of distribution network equipment components and the local connection relationship, the input parameters are vectorized, and a weight matrix is ​​preset at the same time. The input parameter vectorization results are weighted according to the weight matrix, and the cosine similarity is calculated for the generated vector set after the weight matching to obtain a cosine similarity matrix. The cosine similarity matrix is ​​used to generate the equipment component connection model, and a similarity threshold is preset. During the drawing process, the predicted vector parameters of the newly added distribution network equipment components are obtained according to the situation, substituted into the cosine similarity matrix, and compared with the preset similarity threshold. If it is higher than the preset similarity threshold, the corresponding interfaces are connected to complete the automatic connection of the newly added distribution network equipment components during the drawing process.

[0058] Cosine similarity calculation formula:

[0059] It can be imagined that it is difficult to generate an accurate prediction model by relying solely on cosine similarity, so the weight matrix is ​​added to improve the accuracy of the prediction model. At the same time, in the process of vectorizing the input parameters, an additional one-dimensional vector can be generated based on the existing latitude of the vectorization to represent the connection relationship corresponding to the input parameter in the original data set. The introduction of the latitude of the corresponding connection relationship retains more information about the local connection relationship and can improve the relevance of the data. At the same time, in the data processing process, the input data and output data are clustered, such as the k-nearest neighbor algorithm based on Euclidean distance, which can reduce the data processing time. Relevant technical personnel can choose whether to increase the latitude of the input vector and whether to cluster the input and output data according to actual conditions. It is worth noting that the higher the data latitude, the longer the processing time, and clustering will reduce the accuracy of the model prediction.

[0060] Euclidean distance calculation formula:

[0061] Technical personnel in the relevant fields can understand the input data dimension increase and data clustering in the above example by combining the sentence vector Doc2vec and synonym processing in the natural language processing process.

[0062] In some embodiments, a data mining algorithm is used to obtain a device component connection model, which can be combined with the original data set to repeatedly train the device component connection model, and the prediction results obtained from the training are returned to the device component connection model for further training, thereby improving the fit of the device component connection model and making the automatic connection of distribution network device components according to the device component connection model more accurate; at the same time, in order to reduce the occurrence of overfitting, the original data set of distribution network device component types and local connection relationships is divided, one part is used for model training, and the other part is used as a test set to determine whether the generated device component connection model is overfitting. When the device component connection model is overfitting, the original data is subjected to correlation analysis to improve the correlation between the distribution network device component types and the local connection relationships.

[0063] Step S150: Automatically connect the distribution network equipment components according to the equipment component connection model to obtain a distribution network diagram.

[0064] In some embodiments, automatic connection includes automatically connecting corresponding interfaces between corresponding distribution network equipment elements. Connection types include common distribution network topology lines such as broken lines, curves, and wavy lines. The connection type is selected according to the equipment element connection model.

[0065] In some embodiments, distribution network equipment elements are automatically connected according to the equipment element connection model. The specific process is as follows: the user drags a distribution network equipment element from the distribution network equipment element database to the power grid wiring diagram canvas, and the processor reads the basic parameters such as the component type, interface position, interface quantity and interface attributes of the dragged distribution network equipment element, and combines the basic parameters such as the component type, interface position, interface quantity and interface attributes of the existing distribution network equipment elements around the dragged distribution network equipment element on the power grid wiring diagram canvas, and brings them into the equipment element connection model, traverses all interfaces, and obtains corresponding interface connection relationship data according to the equipment element connection model, and connects corresponding interfaces according to the corresponding interface connection relationship numbers, so as to realize automatic wiring of distribution network equipment elements and improve drawing efficiency.

[0066] In some embodiments, during the distribution network drawing process, the distribution network equipment elements are automatically connected according to the equipment element connection model, and also include: when dragging the distribution network equipment elements, the related elements and related element combinations corresponding to the first distribution network equipment element are automatically brought out; it can be imagined that in the process of drawing the electrical wiring diagram, some distribution network equipment elements need to be matched to function. When dragging the distribution network equipment elements, the corresponding related elements and related element combinations are displayed in dotted lines. After confirmation, the corresponding related elements and related element combinations become solid lines and become part of the electrical wiring diagram, thereby improving drawing efficiency.

[0067] In some embodiments, during the distribution network drawing process, when a distribution network equipment element is dragged close to the existing distribution network equipment elements around it on the power grid wiring diagram canvas for the first time, the distribution network equipment element is automatically connected according to the equipment element connection model. If the distribution network equipment element is dragged away, the automatic connection of the currently dragged distribution network equipment element is canceled.

[0068] In some embodiments, during the distribution network drawing process, by monitoring the position of the dragged distribution network equipment elements, when the distribution network equipment elements are dragged to move along a first set motion trajectory, the power grid equipment elements are automatically connected; when the distribution network equipment elements are dragged to move along a second set motion trajectory, the automatic connection of the power grid equipment elements is canceled; it can be imagined that the first set motion trajectory and the second set motion trajectory can be adjusted according to actual conditions to further improve the drawing efficiency.

[0069] Another embodiment of the present application also provides a drawing method, such as Figure 2 As shown, Figure 2 yes Figure 1 FIG. 1 is a schematic diagram of another embodiment of the detailed process of step S140 in FIG. 1 , wherein step S140 includes but is not limited to:

[0070] Step S210: establishing a feature mapping data table for distribution network equipment component types and local connection relationships through a data mining algorithm.

[0071] In some embodiments, establishing a feature mapping data table based on the type of distribution network equipment components and local connection relationships through a data mining algorithm includes vectorizing the original data to obtain a feature vector representing the original data, the feature vector includes an input feature vector and an output feature vector, the latitude parameters of the input feature vector include the type of distribution network equipment components, interface location, number of interfaces and interface attributes, the latitude parameters of the output feature vector include the location, number, attributes and type of connection relationship of the interfaces with a connection relationship, and establishing a mapping table of the two feature vectors for equipment component connection model training.

[0072] In some embodiments, during the drawing process, data retrieval is directly performed based on the established feature mapping data table to determine whether the corresponding interface should be connected. If there is a representation corresponding to the drawn distribution network equipment element in the feature mapping data table, the connection is automatically performed. It is conceivable that before using the equipment element connection model to automatically connect, data retrieval can be performed to connect the determined connection relationship, thereby improving the accuracy of automatic connection of distribution network equipment elements.

[0073] Step S220, training the feature mapping data table to obtain a device component connection model.

[0074] In some embodiments, the process of training the device component connection model according to the feature mapping data table also includes performing model evaluation on the generated device component connection model, and setting corresponding indicators. If the corresponding indicators are not met, the training is restarted; the model evaluation method includes a cross-validation method, which is as follows: the original data is divided into several parts, one of which is used as a test set, and the other samples are used as training sets. After obtaining a model and a set of prediction values ​​and model evaluation values, the process is repeated n times to obtain n groups of model evaluation values, and the average of the n groups of model evaluation values ​​is taken to obtain the final evaluation result.

[0075] Another embodiment of the present application also provides a drawing method, such as Figure 3 As shown, Figure 3 yes Figure 1 FIG. 1 is a schematic diagram of another embodiment of the detailed process of step S150 in FIG. 1 , wherein step S150 includes but is not limited to:

[0076] Step S310: obtaining a local connection relationship set corresponding to the distribution network equipment components according to the equipment component connection model.

[0077] In some embodiments, the distribution network equipment component type, interface location, interface quantity and interface attributes are used to form an input feature vector, and the equipment component connection model is input to obtain a corresponding output feature vector. Based on the location, quantity, attributes of the interface of the connection relationship in the output feature vector and the attributes of the connection relationship type, a local connection relationship set corresponding to the distribution network equipment component is obtained.

[0078] Step S320, obtaining the location of one or more interfaces provided on the distribution network equipment component.

[0079] In some embodiments, according to a distribution network equipment component parameter attribute table preset by the system, the distribution coordinates of multiple interfaces set on the distribution network equipment component are obtained, and the position of each interface is represented in the form of the distribution coordinates.

[0080] It is conceivable that, in the drawing process, while obtaining the positions of multiple interfaces set on the distribution network equipment components, the properties, quantity and layout of other nearby distribution network equipment components of the corresponding interfaces are also obtained.

[0081] Step S330, completing the automatic connection operation of multiple interfaces between two or more power distribution network equipment components according to the local connection relationship set and the positions of the corresponding interfaces.

[0082] In some embodiments, while performing an automatic connection operation, a variety of different connection methods will be generated. In order to improve drawing efficiency, the connection method first obtained in the process of analyzing the position of the local connection relationship set and the corresponding interface is used to automatically connect the interface; it is conceivable that when a variety of different connection methods are generated, the system determines the most preferred one through machine learning, and the automatic connection operation of the interface can improve the accuracy of automatic drawing; it is conceivable that when a variety of different connection methods are generated, the connection method first obtained in the process of analyzing the position of the local connection relationship set and the corresponding interface is used to automatically connect the interface, and other connection methods are displayed at the same time for users to manually select, which is more flexible, and technical personnel in related fields can choose according to actual conditions.

[0083] It is worth noting that some embodiments of this step have been proposed in the embodiment of step S150 in order to more clearly express the technical points, and will not be repeated here.

[0084] Another embodiment of the present application also provides a drawing method, such as Figure 4 As shown, Figure 4 yes Figure 1 FIG. 1 is a schematic diagram of another embodiment of the detailed process of step S130 in FIG. 1 , wherein step S130 includes but is not limited to:

[0085] Step S410: Analyze and process the distribution network topology data set by image recognition technology to obtain a recognition result. The distribution network topology data set includes a distribution network topology diagram and distribution network topology data.

[0086] In some embodiments, through the deep neural network technology in image recognition technology, the distribution network topology structure data set is image extracted and normalized, and corresponding identification is performed according to the corresponding features of the distribution network equipment components and each interface to obtain the recognition results. The recognition results include the type of distribution network equipment components, the corresponding interface location, quantity, attributes and connection status.

[0087] It is conceivable that the image recognition technology analysis is performed on the distribution network topology diagram in the distribution network topology data set, and there is no need to perform image recognition technology analysis on the digitized distribution network topology data.

[0088] Step S420: obtaining a local connection relationship corresponding to the type of distribution network equipment component according to the identification result.

[0089] In some embodiments, the identification results are classified and processed to determine a direct correspondence table between the distribution network equipment components and interfaces and the connection relationships, and the correspondence table is used as a data form for expressing the local connection relationship.

[0090] refer to Figure 5 Another embodiment of the present application further provides a distribution network drawing system, comprising:

[0091] A data preprocessing module 510, the data preprocessing module is used to obtain a distribution network topology data set, obtain a distribution network device component type, and obtain a local connection relationship corresponding to the distribution network device component type according to the distribution network topology data set;

[0092] A data mining module 520, which is used to obtain a device component connection model through a data mining algorithm according to the type of distribution network device components and the local connection relationship;

[0093] The auxiliary drawing module 530 is used to automatically connect the distribution network equipment components according to the equipment component connection model during the distribution network drawing process.

[0094] The distribution network drawing system of the embodiment of the present application has at least the following beneficial effects: in the process of drawing the distribution network wiring diagram using the distribution network drawing system, the data preprocessing module 510 obtains the type of distribution network equipment components and the local connection relationship, the data mining module 520 obtains the equipment component connection model according to the type of distribution network equipment components and the local connection relationship through the data mining algorithm, the auxiliary drawing module 530 automatically connects the distribution network equipment components according to the equipment component connection model, and automatically connects the newly added equipment components according to the attributes of each equipment component and the relationship between each equipment component, thereby saving time in drawing electrical wiring diagrams and improving drawing efficiency.

[0095] It can be imagined that the distribution network drawing system also includes a visualization interface, which is used to visualize the distribution network drawing process during the distribution network drawing process, facilitate user operation, save time in drawing electrical wiring diagrams, and improve drawing efficiency.

[0096] Another embodiment of the present application further provides a distribution network drawing system, which can be used to execute the drawing method in any of the above embodiments, for example, to execute the above described Figure 1 Steps S110 to S150 of the method, Figure 2 Steps S210 to S220 of the method, Figure 3 Steps S310 to S330 of the method, Figure 4 Method steps S410 to S420 in.

[0097] For the specific definition of the distribution network drawing system, please refer to the definition of the distribution network drawing method based on the data mining algorithm in the above text, which will not be repeated here. Each module in the above distribution network drawing system can be implemented in whole or in part by software, hardware and their combination. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0098] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, one embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by one or more control processors, for example, to execute the above-described Figure 1 Steps S110 to S150 of the method, Figure 2 Steps S210 to S220 of the method, Figure 3 Steps S310 to S330 of the method, Figure 4 Method steps S410 to S420 in.

[0100] It will be appreciated by those skilled in the art that all or some of the steps and systems in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0101] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present application. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A distribution network drawing method based on data mining algorithm, characterized in that: The method comprises: Obtain distribution network topology data set; Get the type of distribution network equipment components; Obtaining a local connection relationship corresponding to the type of distribution network equipment component according to the distribution network topology data set and the type of distribution network equipment component; Processing the distribution network equipment component types and the local connection relationships through a data mining algorithm to obtain an equipment component connection model; Automatically connect the distribution network equipment elements according to the equipment element connection model to obtain a distribution network diagram; The method of processing the distribution network equipment component type and the local connection relationship by a data mining algorithm to obtain an equipment component connection model includes: The combination of nearby components, interface positions, number of interfaces and interface types are set as input parameters, and the connection relationship between interfaces is set as output parameters; according to the data set of distribution network equipment component types and local connection relationships, the input parameters are vectorized, and a weight matrix is ​​preset at the same time. The input parameter vectorization results are weighted according to the weight matrix, and the cosine similarity is calculated for the vector set generated after the weight matching to obtain a cosine similarity matrix. The cosine similarity matrix is ​​the equipment component connection model. The cosine similarity matrix is ​​used to obtain the predicted vector parameters of the newly added distribution network equipment components according to the situation during the drawing process, substitute them into the cosine similarity matrix, and compare them with the preset similarity threshold. If it is higher than the preset similarity threshold, the corresponding interfaces are connected to complete the automatic connection of the newly added distribution network equipment components during the drawing process.

2. The distribution network drawing method based on data mining algorithm according to claim 1 is characterized in that: The method of processing the distribution network equipment component type and the local connection relationship by a data mining algorithm to obtain an equipment component connection model includes: Establishing a feature mapping data table for the distribution network equipment component type and the local connection relationship through a data mining algorithm; The feature mapping data table is trained to obtain the device component connection model.

3. The distribution network drawing method based on data mining algorithm according to claim 1 is characterized in that: The automatically connecting the distribution network equipment elements according to the equipment element connection model comprises: Obtaining a local connection relationship set corresponding to the distribution network equipment element according to the equipment element connection model; Obtaining the location of one or more interfaces provided on the distribution network equipment element; According to the local connection relationship set and the positions of the corresponding interfaces, an automatic connection operation of the multiple interfaces between two or more distribution network equipment elements is completed.

4. The distribution network drawing method based on data mining algorithm according to claim 1 is characterized in that: The distribution network topology data set is a data set generated according to the distribution network construction drawings and analysis reports, and the distribution network topology data set includes a distribution network electrical wiring diagram.

5. The distribution network drawing method based on data mining algorithm according to claim 1 is characterized in that: The types of distribution network equipment components include at least one of the following: transformer; high-voltage cabinet; low-voltage cabinet; busbar bridge; DC panel; analog panel; high-voltage cable.

6. The distribution network drawing method based on data mining algorithm according to claim 1 is characterized in that: The obtaining, according to the distribution network topology data set and the distribution network device component type, a local connection relationship corresponding to the distribution network device component type comprises: Analyzing and processing the distribution network topology data set by image recognition technology to obtain a recognition result, wherein the distribution network topology data set includes a distribution network topology diagram and distribution network topology data; A local connection relationship corresponding to the type of the distribution network equipment component is obtained according to the identification result.

7. The distribution network drawing method based on data mining algorithm according to claim 1 is characterized in that: After automatically connecting the distribution network equipment elements according to the equipment element connection model to obtain a distribution network diagram, the method further includes: When the coordinates corresponding to the distribution network equipment element are changed, the related elements and related element combinations corresponding to the first distribution network equipment element are automatically generated according to the equipment element connection model.

8. A distribution network mapping system, characterized in that: include: A data preprocessing module, the data preprocessing module is used to obtain a distribution network topology data set, obtain a distribution network device component type, and obtain a local connection relationship corresponding to the distribution network device component type according to the distribution network topology data set and the distribution network device component type; A data mining module, the data mining module is used to process the distribution network equipment component type and the local connection relationship through a data mining algorithm to obtain an equipment component connection model; An auxiliary drawing module, the auxiliary drawing module is used to automatically connect the distribution network equipment elements according to the equipment element connection model to obtain a distribution network diagram; The method of processing the distribution network equipment component type and the local connection relationship by a data mining algorithm to obtain an equipment component connection model includes: The combination of nearby components, interface positions, number of interfaces and interface types are set as input parameters, and the connection relationship between interfaces is set as output parameters; according to the data set of distribution network equipment component types and local connection relationships, the input parameters are vectorized, and a weight matrix is ​​preset at the same time. The input parameter vectorization results are weighted according to the weight matrix, and the cosine similarity is calculated for the vector set generated after the weight matching to obtain a cosine similarity matrix. The cosine similarity matrix is ​​the equipment component connection model. The cosine similarity matrix is ​​used to obtain the predicted vector parameters of the newly added distribution network equipment components according to the situation during the drawing process, substitute them into the cosine similarity matrix, and compare them with the preset similarity threshold. If it is higher than the preset similarity threshold, the corresponding interfaces are connected to complete the automatic connection of the newly added distribution network equipment components during the drawing process.

9. A distribution network mapping system, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the distribution network drawing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the distribution network drawing method according to any one of claims 1 to 7.

Images