Pumping storage production operation model data coding method and related device

Abstract

The invention belongs to a data coding method, and provides a pumped storage production operation model data coding method and a related device aiming at the technical problems that in an operation control system of a pumped storage power station, an object in a production management system and model data in a production real-time system cannot be unified and are difficult to interact. Equipment related to the KKS model is classified through correlation analysis, and a double-layer structure of large-class dimensions and small-class dimensions is adopted. Evaluating the coincidence degree of the equipment types in the KKS model according to the equipment quantity of each equipment type in the large-class dimension and the small-class dimension, then establishing an equipment sub-book according to the coincidence degree, and further establishing a large class of the pumping and storage production operation unified model and a small class of the pumping and storage production operation unified model; on the basis, modeling is carried out on equipment types serving as objects, and then unified coding is carried out.

Description

Technical Field

[0001] The present application relates to a data encoding method, and specifically to a data encoding method for a pumped storage production operation model and a related device. Background Art

[0002] As an important means of regulating the safe, stable and efficient operation of power systems and power grids, pumped-storage power stations have gained increasing attention due to their technical characteristics such as large capacity, relatively low unit cost and strong regulation capabilities, and have entered a new stage of rapid development.

[0003] The construction of the operation and control system needs to be based on a unified model data structure, and higher requirements are put forward for the standardization of pumped storage production and operation information, the completeness of the modeling scope, the timeliness of model sharing, and the standardization of management. At present, Xinyuan Group and the pumped storage power station mainly interact with each other through the production management system and the real-time production system. Among them, the production management system refers to the KKS (Kraftwerk-Kennzeichnungs system, power plant identification system) coding rules, carries out modeling according to the equipment tree mode, and uses an object-oriented hierarchical structure to identify the actual equipment in the power plant, which reflects the hierarchical relationship of the equipment objects and better describes the relationship between objects. However, it is not associated with the object measurement points of the real-time production system, and it is impossible to carry out unified data analysis; and the model data of the real-time production system is consistent with the pumped storage station end, and the equipment data information is represented by independent measurement points, and there is no specific model yet. Summary of the invention

[0004] The present application aims to solve the technical problem that in the operation and control system of a pumped-storage power station, objects in the production management system and model data in the production real-time system cannot be unified and difficult to interact with each other, and provides a method and related devices for encoding pumped-storage production operation model data.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions: In a first aspect, the present application proposes a method for encoding pumped storage production operation model data, comprising: Conduct correlation analysis on the device names, and classify the devices involved in the KKS model according to the correlation analysis results. The classification result has a double-layer structure including the major category dimension and the minor category dimension. Calculate the number of devices of each device type in the major category and minor category dimensions respectively; The weighted results of the total number of times each device type appears in each major category and each minor category are counted as the overlap degree of each device type in the KKS model; According to the overlap degree of equipment types in the KKS model and combined with the business scope of pumped storage production and operation, set up equipment sub-volumes; According to the equipment volume and the number of equipment types in the sub-category dimension of the KKS model, the major category dimension and the minor category dimension in the KKS model are reclassified into the major category of the unified model of pumped storage production and operation and the minor category of the unified model of pumped storage production and operation; Modeling is done using the equipment types in the subclass of the unified model of pumped storage production and operation as objects; The equipment types are uniformly coded according to the equipment volumes, major categories of the unified model for pumped storage production and operation, minor categories of the unified model for pumped storage production and operation, and object modeling results.

[0006] Furthermore, the relevance analysis of the device name includes: Perform text vectorization processing on all equipment names in the pumped storage power station to obtain equipment name information; Taking the common equipment in the power dictionary as the associated object, using the equipment name information, respectively calculate the association between each equipment name and the associated object, select the equipment corresponding to the equipment name whose association with the associated object is within the preset range, and establish the equipment type set corresponding to the associated object as the association analysis result.

[0007] Furthermore, the text vectorization processing of all equipment names in the pumped storage power station includes: Perform initial word segmentation on the power dictionary and the naming methods in the power dictionary to generate equipment type information including multiple phrases sorted by time; Perform data cleaning on device type information; Perform unsupervised training on monitoring alarm information to generate high-dimensional word vectors containing semantic features; Calculate the average value of all word vectors in the high-dimensional word vector to obtain the device type information sentence vector; By calculating the cosine similarity of the words in the device type information sentence vector, the device name information contained in the device type information sentence vector is obtained according to the cosine similarity calculation result; The respectively calculating the association between each device name and the associated object includes: Calculate the cosine similarity between each device name and the associated object.

[0008] Furthermore, the classification of the equipment involved in the KKS model includes: Based on the KKS model, the major dimensions are hydro-generator sets, main transformer systems, plant power equipment, high-voltage transmission equipment, hydraulic facilities, computer monitoring systems, DC systems, SFC and starting bus systems, gate systems, lifting elevators and transportation vehicles, fire protection and fire alarm systems, ventilation and air-conditioning systems, information systems, oil systems, water systems, gas systems, tools and instruments; and the next level structure of the major dimensions of the KKS model is used as the minor dimensions.

[0009] Furthermore, the device sub-volume is established according to the overlap degree of the device types in the KKS model, including: For equipment types with a degree of overlap greater than a preset value, a separate general equipment volume is established; Set up a sub-volume for generator and motor equipment, a sub-volume for water pump and turbine equipment, a sub-volume for power transmission and transformation equipment, and a sub-volume for hydraulic engineering equipment and facilities, and record them as independent equipment sub-volumes; The equipment volume is composed of the general equipment volume and the independent equipment volume.

[0010] Furthermore, the above-mentioned re-dividing the major category dimension and the minor category dimension in the KKS model into the major category of the unified model of pumped storage production and operation and the minor category of the unified model of pumped storage production and operation includes: Based on the equipment volume, according to the major dimension of the KKS model, the equipment volume is divided into major categories of the unified model for pumped storage production and operation; For the sub-category dimension of the KKS model, the number of equipment types under each sub-category dimension is calculated. If it is greater than the preset value, the corresponding sub-category dimension and the equipment types contained therein are retained; if it is less than or equal to the preset value, the corresponding sub-category dimension is merged with other sub-category dimensions as the sub-category of the unified model of pumped storage production and operation.

[0011] Furthermore, when the equipment type in the subclass of the unified model of pumped storage production and operation is used as an object for modeling, the modeling dimensions include three, wherein the first dimension is the object basic information model, the second dimension is the object relationship information model, and the third dimension is the basic system information model; The object basic information model includes a name and an object ID code; The object relationship information model includes the operation control center, power station and equipment; The basic system information model includes modification time, check code and mapping code.

[0012] Furthermore, when the device types are uniformly coded, the coding rules used include: The equipment type is uniformly encoded through the object's volume code, major category code, minor category code, data management agency code and serial number; the volume code, major category code, minor category code and data management agency code all include at least one digit, and the serial number is used to represent the order number of the object among the same type of objects in the data management agency, using 0-n as the digital number, where n is an integer greater than or equal to 1.

[0013] Furthermore, the unified coding of the device type also includes: Each pumped storage power station carries out extended coding for private data objects in combination with the equipment volumes.

[0014] Furthermore, it is characterized by comprising: In the unified model of pumped storage production and operation, metadata management methods are used to manage and maintain the uniformly coded equipment types.

[0015] In the second aspect, the present application proposes a pumped storage production operation model data encoding system, comprising: The association analysis module is used to perform association analysis on the device names and classify the devices involved in the KKS model according to the association analysis results. The classification result has a double-layer structure including the major category dimension and the minor category dimension. The quantity calculation module is used to calculate the number of devices of each device type in the major category dimension and the minor category dimension respectively; The statistical module is used to count the total number of weighted results of each device type in each major category and each subcategory as the overlap degree of each device type in the KKS model; The sub-volume module is used to set up equipment sub-volumes according to the overlap of equipment types in the KKS model and the business scope of pumped storage production and operation; A unified category division module is used to re-divide the major category dimension and minor category dimension in the KKS model into major categories of the unified model of pumped storage production and operation and minor categories of the unified model of pumped storage production and operation according to the equipment volume and the number of equipment types in the minor category dimension of the KKS model; A modeling module, used for modeling with the equipment types in the subclass of the unified model of pumped storage production and operation as objects; The coding module is used to uniformly code the equipment types according to the equipment volumes, the major categories of the unified model of pumped storage production and operation, the minor categories of the unified model of pumped storage production and operation, and the object modeling results.

[0016] In the third aspect, the present application proposes an electronic device, comprising: a memory, one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code includes computer instructions, and when the computer instructions are executed by the processor, the electronic device performs the steps of the above-mentioned method for encoding pumped storage production operation model data.

[0017] In a fourth aspect, the present application proposes a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for encoding pumped storage production operation model data are implemented.

[0018] Compared with the prior art, this application has the following beneficial effects: The present application proposes a data encoding method for a pumped storage production and operation model, which classifies the equipment involved in the KKS model through correlation analysis, and adopts a double-layer structure of major category dimension and minor category dimension. The degree of overlap of the equipment type in the KKS model is evaluated according to the number of equipment of each equipment type in the major category dimension and the minor category dimension, and then the equipment volume is established according to the degree of overlap, and then the major categories of the unified model of pumped storage production and operation and the minor categories of the unified model of pumped storage production and operation are established. On this basis, the equipment types as objects are modeled and then uniformly encoded. The present application realizes the overall planning of the data model through object-oriented unified model modeling of pumped storage production and operation model data, divides the model according to the degree of commonality, and realizes the association between models through association relationships. It can consolidate the foundation of business collaboration and data interactive sharing among various professions and institutions, improve the ability of global monitoring, centralized decision-making and deep value mining of data for pumped storage operation, and improve the level of intensive production and operation management and standardized information application. In addition, this application also uses metadata management methods to manage and maintain uniformly coded equipment types in the unified model of pumped storage production and operation. Through unified management of table structures, flexible maintenance and automatic generation of pumped storage production and operation business data object modeling in the production and operation monitoring center can also be achieved.

[0019] The present application also proposes a pumped storage production operation model data encoding system, electronic equipment and computer storage medium, which have all the advantages of the above-mentioned pumped storage production operation model data encoding method. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a first flow chart of a method for encoding pumped storage production operation model data in this application; Figure 2 This is a second flow chart of the method for encoding pumped storage production operation model data of this application; Figure 3 Schematic diagram of the process for evaluating the coincidence of the KKS model; Figure 4 The figure shows a schematic diagram of the pumped storage production operation model data encoding system of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0023] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0024] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0025] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invented product is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0026] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0027] In the description of the embodiments of the present application, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0028] A pumped-storage power station is a hydropower station that uses excess electricity in the power system to pump water from the lower pool (a reservoir with a low elevation) to the upper pool (a reservoir with a high elevation) and store it in the form of potential energy. When the system needs electricity, water is released from the upper pool to the lower pool to generate electricity. Specifically, a pumped-storage power station uses changes in the load of the power grid to pump and release water to generate electricity by building two reservoirs with a large difference in height. When the power load is low (usually at night), the excess electricity in the power grid is used to pump water from the lower reservoir to the upper reservoir to increase the gravitational potential energy of the water; when the power load is high (usually during the day), the gate of the upper reservoir is opened to release the water in the upper reservoir to flow to the lower reservoir. During the flow of water, the turbine is driven to rotate, thereby driving the generator to generate electricity and converting the gravitational potential energy into electricity to supply the power grid.

[0029] In the construction of the operation control system, the unified model data structure can not only ensure the accuracy and consistency of the data, but also improve the operating efficiency and reliability of the system. The unified model data structure requires the standardization of all production and operation information, including data naming, coding, format, etc., so that it can be seamlessly transmitted and shared between different systems.

[0030] Among them, the production management system refers to the KKS coding rule, which is a standardized coding system for identifying and managing power plant equipment. The KKS coding rule is modeled through the equipment tree mode and uses an object-oriented hierarchical structure to identify the actual equipment in the power plant. This method clearly shows the hierarchical relationship of equipment objects and effectively describes the association relationship between objects. However, the current production management system is not associated with the object measurement points of the production real-time system, which limits the unified analysis capability of the data.

[0031] The model data of the real-time production system is consistent with the pumped storage station, and the equipment data information is represented by independent measuring points. This method can reflect the operating status of the equipment in real time, but lacks a specific model to support deeper data analysis and decision support. Since the real-time production system has not yet achieved data association with the production management system, it is difficult to achieve cross-system data integration and sharing. Therefore, it is urgent to deeply analyze the differences and commonalities of the existing operation monitoring system model data, operation model data, and real-time data based on the top-level design concept, establish an efficient and complete model data design system and structure, solve the problems of cross-institutional data sharing and resource allocation, and provide a basis for group monitoring of production operation model data.

[0032] Based on the above situation, the existing pumped-storage power stations are configured and constructed in an independent manner, and the model data structure lacks a unified design, which objectively limits the comprehensive application of global information and the technical problem of the global unified decision-making ability of pumped-storage operation. This application proposes a pumped-storage production operation model data encoding method and related devices. The application is described in detail below in conjunction with the embodiments and drawings.

[0033] like Figure 1 As shown, it is a first flow chart of a method for encoding pumped storage production operation model data of the present application, which may include: S101, performing a correlation analysis on the device names, and classifying the devices involved in the KKS model according to the correlation analysis results. The structure of the classification result is a double-layer structure including a major category dimension and a minor category dimension.

[0034] First, it is necessary to perform text analysis on the device names to identify the similarities and associations between the names. In practical applications, this can be achieved through text mining techniques such as word frequency analysis, word embedding (such as Word2Vec), and similarity calculation. Then, based on the results of the association analysis, the devices in the KKS model are classified into different major and minor categories according to their functions and characteristics. For example, the major category dimension can represent the main functions or systems of the equipment (such as "power generation system", "transmission system", etc.), and the minor category dimension further subdivides the specific equipment types under these functions or systems (such as "generator", "transformer", etc.).

[0035] S102, calculating the number of devices of each device type in the major category dimension and the minor category dimension respectively.

[0036] Counting the number of device types in each category under the already classified major and minor categories will help us understand the distribution and quantity of each type of equipment and provide a basis for subsequent analysis and coding.

[0037] S103, respectively counting the total number of times of each device type in each major category dimension and each minor category dimension as the overlap degree of each device type in the KKS model.

[0038] For each device type, the total number of occurrences is calculated in the major and minor categories, and weights are set as needed for weighted processing. The weights can be set based on factors such as the importance, frequency of use, and maintenance cost of the device. The weighted results reflect the overlap and importance of the device in the KKS model.

[0039] S104: Establish equipment sub-volumes based on the overlap of equipment types in the KKS model and the business scope of pumped storage production and operation.

[0040] In actual applications, device volumes are divided according to device type or function to facilitate management and query of device information. When setting up device volumes, you can consider actual business needs to ensure that the division of volumes is both logical and easy to use.

[0041] S105, based on the equipment volume and the number of equipment types in the sub-category dimension of the KKS model, the major category dimension and the minor category dimension in the KKS model are re-divided into major categories of the unified model of pumped storage production and operation and minor categories of the unified model of pumped storage production and operation.

[0042] Based on the establishment of equipment sub-volumes and the number of equipment types in the sub-category dimension of the KKS model, the major and minor categories of the KKS model are re-divided. The purpose of the re-division is to make the model more in line with the actual needs of pumped storage production and operation, and to improve the usability and accuracy of the model. When re-dividing, ensure that there are clear boundaries and logical relationships between the new major and minor categories.

[0043] S106, modeling is performed using the equipment types in the subclass of the unified model of pumped storage production and operation as objects.

[0044] The equipment types in the subclass of the unified model of pumped storage production and operation are used as objects for modeling. The purpose of modeling is to describe the properties, behaviors and relationships between equipment and other equipment.

[0045] S107, uniformly encode the equipment types according to the equipment volumes, the major categories of the unified model for pumped storage production and operation, the minor categories of the unified model for pumped storage production and operation, and the object modeling results.

[0046] The code is the unique identifier of the device information, which is used to uniquely identify a device in the system. The coding rules can be set according to the actual situation. In practical applications, it can be concise, easy to understand and remember, and can also take into account possible future expansion and changes. Through unified coding, the device information can be quickly queried and managed, and the processing efficiency and quality of the pumped storage production operation model data can be improved.

[0047] The present application is further described below by a more detailed embodiment. Figure 2 As shown, it is a second flow chart of the method for encoding the pumped storage production operation model data of the present application. The encoding method of the present application can be divided into three steps as a whole: S201, object-oriented method for evaluating the overlap degree of pumped storage production operation model.

[0048] The KKS model is usually used in the production management system of pumped storage power stations. The KKS model uses an object-oriented hierarchical structure to identify the actual equipment in the power plant, reflecting the hierarchical relationship of equipment objects, and is widely used in the production management system of hydropower stations. The equipment model structure under this model structure has a clear association relationship, but the degree of generalization of the model is ignored due to the direct association relationship. According to the object-oriented modeling idea, it is necessary to evaluate the overlap degree of the KKS model and divide the equipment of the same or similar equipment type to adapt to the unified modeling of pumped storage.

[0049] As Figure 3 shown, it is a schematic flow chart for evaluating the coincidence of the KKS model. Specifically, the following methods can be adopted: 1) Perform text vectorization on all device names, conduct correlation analysis on the device names, and use it to extract device type information: (1) Word segmentation.

[0050] Collect a professional power word library to form a power dictionary and common naming methods through data查阅, and use the accurate mode of the jieba word segmentation tool to perform initial word segmentation, generating device type information consisting of a series of Chinese phrases sorted by time.

[0051] It should be noted that the jieba word segmentation tool is an open-source word segmentation tool for Chinese text processing. Its core function is to split continuous Chinese text into meaningful words. Word segmentation is a basic step in Chinese natural language processing, and accurate word segmentation is of great significance for subsequent text processing and analysis. (2)Remove stop words.

[0052] Remove meaningless characters in the stop word list to achieve data cleaning and improve the training effect in the later stage. In text processing, stop words usually refer to those words that appear frequently but contribute little to the meaning of the text, such as "de", "le", "zai", etc. These words exist in large numbers in the text but often do not contain valuable information for text analysis. Therefore, in many natural language processing tasks, it is necessary to remove stop words to reduce noise and improve the training effect of subsequent models.

[0053] (3)Vectorization modeling.

[0054] Use the Word2vec model to perform unsupervised training on the device type information after data cleaning, generating high-dimensional word vectors containing semantic features. It should be noted that Word2Vec is a model for calculating word vectors, which can map words into a high-dimensional vector space, so that words with similar semantics are close in the vector space. In the processing of device type information, using the Word2vec model to perform unsupervised training on the device type after data cleaning can generate high-dimensional word vectors containing semantic features, and these vectors can be used for subsequent classification, clustering, similarity calculation and other tasks.

[0055] (4)Averaging processing.

[0056] Calculate the average value of all word vectors in the device name information to obtain the sentence vector of the device information. This method can express information semantics to a certain extent.

[0057] (5)Cosine similarity calculation.

[0058] In order to express the semantic association between words in the device name, the clustering idea is used. The closer the distance in the vector space, the closer the semantics expressed by the words are. In this embodiment, cosine similarity cos is used as the distance calculation formula:

[0059] in, Representation vector and vector The angle of Representation vector No. dimension, Representation vector No. dimension, Represents the total dimension of the vector.

[0060] Words with the same meaning but different expressions and words with similar contexts have a high similarity, and the cosine similarity value is close to 1.

[0061] 2) Take the common equipment involved in the power dictionary as the associated object, calculate the cosine similarity of the equipment names, and identify the equipment type as the extracted equipment type information if there is a device with a high similarity (greater than the threshold). Then determine the equipment type set and use express.

[0062] 3) Based on the KKS model, the hydroelectric (electric) generator set, main transformer system, power equipment for plant use, high-voltage power transmission equipment, hydraulic facilities, computer monitoring system, DC system, SFC and starting bus system, gate system, lifting elevator and transportation, fire protection and fire alarm system, ventilation and air conditioning system, information system, oil system, water system, gas system, tools and instruments are selected as the major screening dimension set. Indicates that the next level of the major category dimension is the minor category dimension, Indicates that the equipment involved in the KKS model is classified.

[0063] 4) Count the number of devices included in each major category and subcategory, using Indicates Within the major category dimension The number of devices of the device type, using Indicates Within the sub-category The number of devices of each device type.

[0064] 5) Count whether each device type has appeared in the major and minor categories. The weighted result of the total number of times each major and minor category dimension includes the device type represents the overlap degree of the device type in the KKS model. The larger the result, the higher the overlap degree of this type of device. The overlap of the major categories of equipment types is Indicates that The overlap of the subclasses of the device types is The expression is as follows: ,

[0065] in, Indicates The device type is in There are many categories, Indicates The device type is in Exists in a small category.

[0066] Therefore, the The degree of overlap between device types is express, is the weight coefficient: .

[0067] S202, unified modeling method for pumped storage production and operation.

[0068] (1) Set up a model description method for pumped storage production.

[0069] The design of pumped storage production model usually follows the principle of commonality collection and professional classification, and is divided and compiled by categories. Taking the KKS model as the basis for the division, firstly, according to the overlap degree of equipment types extracted from the object-oriented pumped storage production operation model generalization degree assessment method, the equipment types with overlap degree scores exceeding the threshold (manually set) are divided into a separate volume as the general equipment volume.

[0070] In addition, considering that most of the operations of pumped storage production revolve around generator motors, pumps and turbines, main transformers and switch station equipment, and reservoirs, generator motor volumes, pump and turbine volumes, power transmission and transformation equipment volumes, and hydraulic engineering equipment and facilities volumes are set up as independent equipment volumes.

[0071] The equipment volume is composed of the general equipment volume and the independent equipment volume.

[0072] Based on the equipment volume results, the major category dimension of the KKS model is divided into major categories of the unified model according to the equipment volume. The relationship between the major categories and minor categories of the KKS model is used as the basis for the division of major categories and minor categories of the unified model of pumped storage production and operation. First, the importance of minor categories is evaluated based on the number of equipment types under the minor category. express:

[0073] in, Indicated in There is a device type.

[0074] when , then keep the subclass and the following equipment types, when , then the subclass cannot be retained and it is necessary to merge the subclass with other subclasses to form a new subclass. The merged subclass will be used as the subclass of the unified model of pumped storage production and operation.

[0075] After the subclass is determined, the corresponding equipment type is the object. Modeling according to the object can include three dimensions: one is the basic information model of the object, including but not limited to information attributes such as name and object ID code; the second is the object relationship information model, including but not limited to relationship attributes such as the operation and control center, the power station, and the equipment; the third is the basic system information model, including but not limited to information models required by the basic system such as modification time, checksum, and mapping code.

[0076] (2) Set up object ID coding rules for pumped storage production operations.

[0077] In order to ensure the global uniqueness of pumped storage production and operation business objects in operation and control (vertical) and different businesses (horizontal), without affecting the existing applications, a unified pumped storage model coding rule (i.e., ID coding rule) is designed for data interaction and sharing as the unique identifier of the pumped storage production and operation business object.

[0078] In this embodiment, the object ID coding rule adopts a "five-segment" method, which consists of five parts: data object "volume code", "major category code", "minor category code", "data management agency code" and "serial number", which is composed of no more than 18 decimal digits, stored in character type, and is unique. The specific definition of the object ID coding rule is as follows: a) The first two digits are two fixed digits in total, which are the "volume code" and represent the volume type of the data object.

[0079] b) The 3rd and 4th digits are two fixed digits in total, which are the "major category code" representing the major classification of the data object.

[0080] c) Digits 5-6: A total of 2 fixed digits, which are the "sub-category code" representing the detailed sub-classification of the data object.

[0081] d) Digits 7 to 10: A total of 4 fixed digits, which are the "Data Management Agency Code" and represent the data management agency.

[0082] e) Digits 11-18: A total of 0 to 8 unfixed digits, which are the "serial number" representing the sequence number of the object instance among similar objects in the organization. The specific length may vary according to actual conditions.

[0083] (3) Object extension rules Each unit is allowed to design its own private data objects to meet individual needs. However, the modeling of private data objects should follow these design rules, and a unified and complete object model within each unit is formed by combining public objects and private objects.

[0084] To expand a data object, you must first determine the volume. If the classification cannot be found in the current volume, add a volume, that is, determine the volume code (2 characters). Then find the object category based on the volume code. If the classification cannot be found in the current category, add a category, that is, determine the category code (2 characters). After determining the category, add the subcategory code while ensuring that it does not overlap with existing objects. A data object consists of a data object table. After creating a data object, you need to create a data object table according to the rules. The basic information table of a data object is a required data table for the object. After the data object table is created, you need to define the attributes in the table, that is, the database columns, and define a data dictionary for the values ​​that can be standardized in the attributes.

[0085] S203, a method for maintaining a pumped storage production operation model structure based on metadata.

[0086] In order to realize the flexible maintenance and automatic generation of data object modeling for pumping and storage production operation business in the production operation monitoring center, this application adopts the basic method of metadata management. Metadata is data that describes information resources or data and other objects, so as to realize simple and efficient management of large amounts of data, and realize effective discovery, search, integrated organization of information resources and effective management of used resources. This method establishes metadata management table structures such as data objects, data object tables, data object table attributes and data dictionaries to manage data structures. The basic relationship is as follows: first, data objects are established. Each type of data object contains multiple data object tables, and each data object table contains multiple data object table attributes. Some of the same data object table attributes abstract the data dictionary. The metadata management function is used to realize standardized design and scalable requirements for data objects. Specifically, the following methods can be used: (1) Data object modeling The database modeling structure of "Data Object (SG_META_OBJECT)" specifically includes "Object Code", "Classification", "Object Name", "Object English Name", "Object Serial Number Length", "Effective Flag", "Creator", "Creation Time", "Modifier", "Modification Time" and "Description" attributes.

[0087] (2) Data object table modeling The database modeling structure of the "Data Object Table (SG_META_TABLE)" specifically includes the "Object Code", "Table Name", "English Table Name", "Effective Flag", "Creator", "Creation Time", "Modifier", "Modification Time" and "Description" attributes.

[0088] (3) Data object table attribute modeling The database modeling structure of "Object Table Properties (SG_META_PROPERTY)" specifically includes "English Table Name", "Attribute Name", "English Attribute Name", "Data Type", "Constraints", "Generation Form", "Creator", "Creation Time", "Modifier", "Modification Time" and "Description" attributes.

[0089] (4) Dictionary object modeling The database modeling structure of the "Dictionary Object (SG_META_DICOBJ)" specifically includes attributes such as "Table Name", "English Table Name", "Category", "Effective Flag", "Creator", "Creation Time", "Modifier", "Modification Time" and "Description".

[0090] (5) Data dictionary modeling The data dictionary model adopts a standard format, and its attributes include code (CODE), name (NAME), effectiveness flag (EFFECTIVE_FLAG), creation time (CREATE_TIME) and description (NOTES).

[0091] In the coding method of this application, the unified pumped storage model obtained by modeling satisfies the following attributes: uniqueness, universality, scalability, difference, consistency, etc., ensuring the unified naming and consistent parameters of various application devices, providing basic guarantees for global data sharing and business collaboration, and improving the integrated collaborative operation capabilities of pumped storage production, which is specifically reflected in: 1) Uniqueness: Without affecting existing applications, in order to realize the global sharing of pumped storage data objects in operation and control (vertical) and different businesses (horizontal), a unified ID coding rule is set for pumped storage data objects to realize the global planning of data object ID. The ID generated in accordance with the ID coding rule is the unique identifier of the pumped storage data object, which is invariant in the life cycle and global application scope, that is, once generated, it will not change with the change of data object attributes. It can be used as an identity confirmation code for horizontal and vertical interactions between various applications in the pumped storage production system, while not changing the original application's own unique identifier.

[0092] 2) Universality: Based on universality requirements, abstract modeling and table design are performed for pumped storage production and operation business objects and the relationships between objects for physical power grids, pumped storage power stations, physical equipment and organizational structures, providing a universal basic information model for various production operations and business management businesses.

[0093] 3) Scalability: The emergence of a large number of new equipment and new technologies means that model management cannot be limited to traditional pumped storage power station equipment. The unified model design must consider the scalability of data objects. Using metadata management tools, the expansion, modification, validation and invalidation definitions of common data object types or attributes can be realized without changing the program code. Through online maintenance of data objects and data object attributes, the dynamic expansion and improvement of the model can be realized.

[0094] 4) Difference: This application allows regional operations control to have personalized needs and private data tables. However, it should follow the rules and modeling methods of standardized design, associate private data with common objects, form a unified and complete data organization method within the relevant regional operations control, and limit the scope of use of private data tables.

[0095] 5) Consistency: In order to ensure that data models can be shared, integrated and coordinated among multiple business systems and multiple operation control centers, and support the global analysis and decision-making capabilities of production operations, the comparison relationship between the original system model and the structured design model is considered to achieve compatibility of model data among multiple systems with various business applications. Make full use of modeling tools, general equipment organizational structure and general attributes, and realize the information consistency association between proprietary attributes and general objects through object ID mapping.

[0096] This application can be applied to the unified model design work of the pumping and storage centralized control center. It can extract the equipment type based on the production management system model information, implement object ID encoding according to the five-segment format, and design the model attributes. Through the metadata of the pumping and storage production operation model structure maintenance method, relevant tools can be developed to achieve unified management and meet the requirements of standardized design and scalability of data objects.

[0097] like Figure 4As shown, it is a schematic diagram of the data encoding system of the pumped storage production operation model of the present application, which may include: The association analysis module is used to perform association analysis on the device names and classify the devices involved in the KKS model according to the association analysis results. The classification result has a double-layer structure including the major category dimension and the minor category dimension. The quantity calculation module is used to calculate the number of devices of each device type in the major category dimension and the minor category dimension respectively; The statistical module is used to count the total number of weighted results of each device type in each major category and each subcategory as the overlap degree of each device type in the KKS model; The sub-volume module is used to set up equipment sub-volumes according to the overlap of equipment types in the KKS model and the business scope of pumped storage production and operation; A unified category division module is used to re-divide the major category dimension and minor category dimension in the KKS model into major categories of the unified model of pumped storage production and operation and minor categories of the unified model of pumped storage production and operation according to the equipment volume and the number of equipment types in the minor category dimension of the KKS model; A modeling module, used for modeling with the equipment types in the subclass of the unified model of pumped storage production and operation as objects; The coding module is used to uniformly code the equipment types according to the equipment volumes, the major categories of the unified model of pumped storage production and operation, the minor categories of the unified model of pumped storage production and operation, and the object modeling results.

[0098] It should be noted that in the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of each module is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another device, or some features can be ignored or not executed. The module described as a separate component may or may not be physically separated. The component displayed as a module may be a physical unit or multiple physical units, that is, it may be located in one place, or it may be distributed in multiple different places. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0099] In addition, each module in each embodiment of the present invention may be integrated into a processing unit, each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0100] An embodiment of the present application also provides an electronic device, which may include one or more processors, a memory, and a communication interface.

[0101] The memory, the communication interface and the processor are coupled, for example, the memory, the communication interface and the processor may be coupled together via a bus.

[0102] The communication interface is used to transmit data with other devices. The memory stores computer program code. The computer program code includes computer instructions. When the computer instructions are executed by the processor, the electronic device executes the steps of the method for encoding the pumped storage production operation model data in the embodiment of the present application.

[0103] Wherein, the processor can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the present disclosure. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of DSP and microprocessors, and the like. The processor can be used to support electronic devices to execute the method steps provided in the above embodiments.

[0104] The bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The above buses may be divided into address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0105] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the method for encoding pumped storage production operation model data as described in any of the above embodiments are implemented.

[0106] The computer-readable storage medium involved in the present application includes random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field.

[0107] For the description of the relevant parts of the pumped storage production operation model data encoding system, electronic device and computer-readable storage medium provided in the embodiment of the present application, please refer to the detailed description of the corresponding parts in the pumped storage production operation model data encoding method provided in the embodiment of the present application, which will not be repeated here. In addition, the parts of the above-mentioned technical solutions provided in the embodiment of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0108] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for encoding pumped storage production operation model data, characterized in that: include: Conduct correlation analysis on the device names, and classify the devices involved in the KKS model according to the correlation analysis results. The classification result has a double-layer structure including the major category dimension and the minor category dimension. Calculate the number of devices of each device type in the major category and minor category dimensions respectively; The weighted results of the total number of times each device type appears in each major category and each minor category are counted as the overlap degree of each device type in the KKS model; According to the overlap degree of equipment types in the KKS model and combined with the business scope of pumped storage production and operation, set up equipment sub-volumes; According to the equipment volume and the number of equipment types in the sub-category dimension of the KKS model, the major category dimension and the minor category dimension in the KKS model are reclassified into the major category of the unified model of pumped storage production and operation and the minor category of the unified model of pumped storage production and operation; Modeling is done using the equipment types in the subclass of the unified model of pumped storage production and operation as objects; The equipment types are uniformly coded according to the equipment volumes, major categories of the unified model for pumped storage production and operation, minor categories of the unified model for pumped storage production and operation, and object modeling results.

2. According to the method for encoding pumped storage production operation model data in claim 1, it is characterized in that: The relevance analysis of the device name includes: Perform text vectorization processing on all equipment names in the pumped storage power station to obtain equipment name information; Taking the common equipment in the power dictionary as the associated object, using the equipment name information, respectively calculate the association between each equipment name and the associated object, select the equipment corresponding to the equipment name whose association with the associated object is within the preset range, and establish the equipment type set corresponding to the associated object as the association analysis result.

3. The method for encoding pumped storage production operation model data according to claim 2, characterized in that: The text vectorization processing of all equipment names in the pumped storage power station includes: Perform initial word segmentation on the power dictionary and the naming methods in the power dictionary to generate equipment type information including multiple phrases sorted by time; Perform data cleaning on device type information; Perform unsupervised training on monitoring alarm information to generate high-dimensional word vectors containing semantic features; Calculate the average value of all word vectors in the high-dimensional word vector to obtain the device type information sentence vector; By performing cosine similarity calculation on the words in the device type information sentence vector, the device name information contained in the device type information sentence vector is obtained according to the cosine similarity calculation result; The respectively calculating the association between each device name and the associated object includes: Calculate the cosine similarity between each device name and the associated object.

4. The method for encoding pumped storage production operation model data according to claim 3, characterized in that: The equipment involved in the KKS model is classified as follows: Based on the KKS model, the major dimensions are hydro-generator sets, main transformer systems, plant power equipment, high-voltage transmission equipment, hydraulic facilities, computer monitoring systems, DC systems, SFC and starting bus systems, gate systems, lifting elevators and transportation vehicles, fire protection and fire alarm systems, ventilation and air-conditioning systems, information systems, oil systems, water systems, gas systems, tools and instruments; and the next level structure of the major dimensions of the KKS model is used as the minor dimensions.

5. The method for encoding pumped storage production operation model data according to claim 4, characterized in that: According to the overlap degree of equipment types in the KKS model, equipment sub-volumes are established, including: For equipment types with a degree of overlap greater than a preset value, a separate general equipment volume is established; Set up a sub-volume for generator and motor equipment, a sub-volume for water pump and turbine equipment, a sub-volume for power transmission and transformation equipment, and a sub-volume for hydraulic engineering equipment and facilities, and record them as independent equipment sub-volumes; The equipment volume is composed of the general equipment volume and the independent equipment volume.

6. The method for encoding pumped storage production operation model data according to claim 5, characterized in that: The above-mentioned re-dividing the major category dimension and minor category dimension in the KKS model into the major category of the unified model of pumped storage production and operation and the minor category of the unified model of pumped storage production and operation includes: Based on the equipment volume, according to the major dimension of the KKS model, the equipment volume is divided into major categories of the unified model for pumped storage production and operation; For the sub-category dimension of the KKS model, the number of equipment types under each sub-category dimension is calculated. If it is greater than the preset value, the corresponding sub-category dimension and the equipment types contained therein are retained; if it is less than or equal to the preset value, the corresponding sub-category dimension is merged with other sub-category dimensions as the sub-category of the unified model of pumped storage production and operation.

7. The method for encoding pumped storage production operation model data according to claim 6, characterized in that: When the equipment type in the subclass of the unified model of pumped storage production and operation is used as the object for modeling, the modeling dimensions include three, wherein the first dimension is the object basic information model, the second dimension is the object relationship information model, and the third dimension is the basic system information model; The object basic information model includes a name and an object ID code; The object relationship information model includes the operation control center, power station and equipment; The basic system information model includes modification time, check code and mapping code.

8. The method for encoding pumped storage production operation model data according to claim 7, characterized in that: When uniformly encoding the device types, the encoding rules used include: The equipment type is uniformly encoded through the object's volume code, major category code, minor category code, data management agency code and serial number; the volume code, major category code, minor category code and data management agency code all include at least one digit, and the serial number is used to represent the order number of the object among the same type of objects in the data management agency, using 0-n as the digital number, where n is an integer greater than or equal to 1.

9. The method for encoding pumped storage production operation model data according to claim 8, characterized in that: The unified coding of the device type also includes: Each pumped storage power station carries out extended coding for private data objects in combination with the equipment volumes.

10. The method for encoding pumped storage production operation model data according to any one of claims 1 to 9, characterized in that: Also includes: In the unified model of pumped storage production and operation, metadata management methods are used to manage and maintain the uniformly coded equipment types.

11. A pumped storage production operation model data encoding system, characterized in that: include: The association analysis module is used to perform association analysis on the device names and classify the devices involved in the KKS model according to the association analysis results. The classification result has a double-layer structure including the major category dimension and the minor category dimension. The quantity calculation module is used to calculate the number of devices of each device type in the major category dimension and the minor category dimension respectively; The statistical module is used to count the total number of weighted results of each device type in each major category and each subcategory as the overlap degree of each device type in the KKS model; The sub-volume module is used to set up equipment sub-volumes according to the overlap of equipment types in the KKS model and the business scope of pumped storage production and operation; A unified category division module is used to re-divide the major category dimension and minor category dimension in the KKS model into major categories of the unified model of pumped storage production and operation and minor categories of the unified model of pumped storage production and operation according to the equipment volume and the number of equipment types in the minor category dimension of the KKS model; A modeling module, used for modeling with the equipment types in the subclass of the unified model of pumped storage production and operation as objects; The coding module is used to uniformly code the equipment types according to the equipment volumes, the major categories of the unified model of pumped storage production and operation, the minor categories of the unified model of pumped storage production and operation, and the object modeling results.

12. An electronic device, characterized in that: include: A memory and one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code includes computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the steps of the method for encoding pumped storage production operation model data as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for encoding pumped storage production operation model data as claimed in any one of claims 1 to 10 are implemented.

Images