Data asset knowledge graph construction method and system oriented to integrated energy system

Abstract

The invention discloses a data asset knowledge graph construction method and system oriented to an integrated energy system, and belongs to the technical field of information physical fusion of the integrated energy system. According to the construction method disclosed by the invention, by analyzing the structure of the integrated energy system and classifying the equipment types, the physical correlation between numerical point locations among the equipment and numerical point locations in the equipment can be obtained, the historical data of the numerical point locations of all the equipment can be read, and the correlation coefficient between the point locations can be obtained by calculation; a point position group with data correlation is screened out in combination with a set threshold value, finally, based on the interactive knowledge graph, numerical point positions of equipment in the energy system are stored as nodes, and physical correlation and data correlation relationships are stored as edges; the full view of the system is presented in a visual and structured manner, so that the comprehensiveness and accuracy of data correlation discovery are greatly improved, and the technical problem of subsequent research errors or low efficiency caused by insufficient data correlation mining is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of information-physical fusion of integrated energy systems, and specifically relates to a method and system for constructing a data asset knowledge graph for integrated energy systems. Background Art

[0002] In the current process of rapid development of information technology, industrial automation and intelligence, integrated energy systems have gradually occupied a core position in various industrial scenarios, and their complexity continues to grow with industrial upgrading. From the coordinated supply and allocation of various energy sources such as electricity, heat, and gas required for different production lines in large manufacturing plants, to the complex energy conversion and transmission equipment clusters in integrated energy hubs that integrate power generation, transmission, distribution, heating, and gas supply in the energy and power field, the integrated energy system is like a highly integrated and precisely operated intelligent network. The coordinated interaction and status correlation between various energy subsystems and internal equipment are extremely close. The stability, efficiency, and flexibility of its operation play a vital role in the sustainable development of the entire industrial system.

[0003] Traditional energy system operation and maintenance management, fault diagnosis and operation optimization methods often focus on the monitoring and maintenance of a single device. The device has its own monitoring instruments and simple sensors to record basic parameters and store them in isolation in the local controller or on-site database. The data is fragmented and isolated. After the operation and maintenance personnel find the equipment abnormality, they manually check the related equipment based on their personal experience and equipment manuals, which is time-consuming and laborious and easy to miss key clues, which may cause production losses in actual industrial production.

[0004] With the rise of the Industrial Internet of Things, the deployment of massive sensors has expanded the dimensions of data collection in the integrated energy system, increased the frequency, and led to an explosive growth in data volume. Current data analysis methods are limited to single-device time series analysis (statistical indicators, spectrum analysis, etc.), or simply compare the mean and threshold values ​​of the same type of devices to determine the operating status, ignoring the deep logic of physical connections and data interactions between devices.

[0005] Knowledge graph technology has emerged in other fields. It is a data structure and a way of expressing and storing knowledge. Its core is to organize real-world objects and concepts and the various relationships between them in the form of a graph, thereby providing rich and structured background knowledge for machine learning and improving the algorithm's understanding and reasoning capabilities. It has been widely promoted in common practical applications such as semantic search (search engines analyze entity relationships and accurately present results), social network analysis (mining complex social ties between users), intelligent question-and-answer systems, and recommendation systems.

[0006] However, when applied in industrial fields such as integrated energy systems, the existing knowledge graph construction solutions lack universality and pertinence. On the one hand, general knowledge graphs focus on encyclopedia knowledge integration, and entity relationships focus on common sense semantics, which are inconsistent with energy system professional terminology and physical association rules; the construction of energy system professional knowledge graphs is mostly based on theoretical design documents and standard specifications, and does not fully integrate the large amount of dynamic and multi-source data generated under actual operating conditions. The constructed graphs are difficult to accurately map the complex overall picture of the real integrated energy system, and cannot dig out the complex associations between physics and data between equipment points, resulting in the inability to provide effective decision-making support for system operation and maintenance, energy efficiency control, etc. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for constructing a data asset knowledge graph for an integrated energy system, which is used to solve the technical problems of subsequent research errors or low efficiency caused by insufficient data association mining in existing knowledge graph construction schemes.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] The present invention discloses a method for constructing a data asset knowledge graph for an integrated energy system, comprising the following steps:

[0010] Conduct structural analysis and equipment classification of the integrated energy system to obtain the physical correlation between the numerical points in the integrated energy system;

[0011] Read the historical data of all numerical points in the integrated energy system, and solve the correlation coefficients between all numerical points based on the historical data; then set the correlation coefficient threshold, and screen the correlation between the numerical points based on the comparison between the correlation coefficient and the correlation coefficient threshold;

[0012] All numerical points are stored as nodes in the graph database, and the physical correlations and correlations between the numerical points are stored as edges in the graph database to establish an interactive data asset knowledge graph.

[0013] Furthermore, the physical correlation between the numerical points includes the physical correlation between the numerical points between devices and the physical correlation between the numerical points inside the devices;

[0014] The physical correlation between the numerical points of the devices is obtained after structural analysis of the integrated energy system;

[0015] The physical correlation relationship between the numerical points inside the equipment is obtained after classifying the equipment in the integrated energy system.

[0016] Furthermore, the steps for structural analysis of the integrated energy system and obtaining the physical correlation between the numerical points of the devices are as follows:

[0017] Determine the connection relationship between various devices based on the physical topological relationship between devices in the integrated energy system and the actual functions of the devices;

[0018] Based on the equipment connection relationship, the flow direction of the material flow in the connection relationship and the equipment numerical points corresponding to the flow direction of the material flow are analyzed, so as to obtain the physical correlation relationship between the numerical points between the equipment.

[0019] Furthermore, the steps for classifying the equipment categories of the integrated energy system and obtaining the physical correlation between the internal numerical points of the equipment are as follows:

[0020] All equipment in the integrated energy system is classified according to the equipment type, the physical quantities of each type of equipment are extracted, and the node relationship between the physical quantities is constructed according to the physical relationship, so as to obtain the physical correlation relationship between the numerical points inside the equipment.

[0021] Furthermore, the integrated energy system is an electrical system; the specific steps of classifying the equipment categories of the integrated energy system and obtaining the physical correlation relationship of the internal numerical points of the equipment are as follows:

[0022] All equipment in the integrated energy system is divided into electricity meters, inverters and DC choppers according to the equipment type; all internal numerical points of the electricity meters, inverters and DC choppers are extracted, and the node relationship formula is constructed according to the basic physical relationship between current, voltage and power, so as to obtain the physical correlation between the internal numerical points of the equipment in the electrical system.

[0023] Furthermore, the specific steps of constructing a node relationship based on the basic physical relationship between current, voltage and power to obtain the physical correlation relationship between the internal numerical points of the equipment in the electrical system are as follows:

[0024] For electric meters:

[0025] Line voltage = √3 × phase voltage;

[0026] Apparent total power 2 = Total active power 2 + Total reactive power 2 ;

[0027] Total power factor = total active power / total apparent power;

[0028] For inverter:

[0029] DC side power = DC current × DC lower half bus voltage;

[0030] For DC chopper:

[0031] Total power = battery side voltage × total battery side current.

[0032] Furthermore, the steps of reading the historical data of all numerical points in the integrated energy system and solving the correlation coefficients between all numerical points according to the historical data include:

[0033] Read the data collection time, equipment name, equipment point name and collection value in the integrated energy system; for each device, use the data collection time as the horizontal axis and the corresponding collection value as the vertical axis to draw a time series line chart of the device, visualize the operating status of the device, and analyze the operating status of the device;

[0034] Aggregate all time series point data of all devices into a matrix, represented by Z t×n ; The rows of the matrix represent the data collection time, which is denoted as t, and the columns of the matrix represent the sum of all points of all devices, which is denoted as n. Then, the correlation coefficient matrix between the columns in the matrix is ​​calculated;

[0035] Calculating the correlation coefficient matrix between the columns in the matrix includes the following steps:

[0036] For the matrix Z t×n For two columns of sample points X and Y, estimate the expectation, variance and covariance based on the samples:

[0037]

[0038] Where: X i represents the i-th observation in the sample, n represents the size of the sample, that is, the total number of observations, and E(X) is the expectation of the random variable X, which represents the average of all observations; The value is the sample mean, is the variance of the random variable X, which indicates how dispersed the observations are relative to the mean; cov(X,Y) is the covariance of the random variables X and Y, which indicates how the two variables vary together;

[0039] Substituting the above formula into the definition of the correlation coefficient, its definition is as follows:

[0040]

[0041] Where: X σ Y are the standard deviations of X and Y, respectively, and E(XY) is the expectation of the product of X and Yρ X,Y is the correlation coefficient;

[0042] The calculation formula of the correlation coefficient is further processed as follows:

[0043]

[0044] Furthermore, when the absolute value of the correlation coefficient between two points is greater than a threshold, it is considered that the point group has data-level correlation, and the correlation relationship between the numerical points is obtained accordingly.

[0045] Furthermore, the setting standard of the correlation coefficient threshold is as follows:

[0046]

[0047] Where r represents the correlation coefficient between two sets of data;

[0048] The correlation coefficient threshold is 0.5;

[0049] The interactive data asset knowledge graph is a data asset knowledge graph established based on the interaction between python and neo4j.

[0050] The present invention also discloses a data asset knowledge graph construction system for an integrated energy system, which is used to implement the above-mentioned construction method.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention discloses a method for constructing a data asset knowledge graph for an integrated energy system. By analyzing the structure of the integrated energy system and classifying the equipment into categories, it is possible to obtain the physical correlation between numerical points between devices and numerical points inside devices, read the historical data of all equipment numerical points, and calculate the correlation coefficients between the points. The point groups with data correlation are screened out in combination with set thresholds. The above process can fully mine potential and imperceptible data connections based on big data analysis. Compared with traditional technologies that only rely on limited rules or empirical judgments, it greatly improves the comprehensiveness and accuracy of data correlation discovery, and avoids technical problems such as subsequent research errors or inefficiency caused by insufficient data association mining.

[0053] Furthermore, the graph construction method disclosed in the present invention is based on the knowledge graph of the interaction between python and neo4j. The numerical points of the equipment in the energy system are stored as nodes, and the physical and data related relationships are stored as edges, presenting the overall picture of the system in an intuitive and structured manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A method block diagram of a method for constructing a data asset knowledge graph for an integrated energy system according to the present invention;

[0055] Figure 2 A device topology diagram of an example of an electrical system of the present invention;

[0056] Figure 3 The node label information and edge category information generated after the storage nodes and edges of Embodiment 1 of the present invention are completed;

[0057] Figure 4 This is the final knowledge graph visualization result of Example 1 of the present invention. DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0059] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0060] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0061] like Figure 1 As shown, the present invention discloses a method for constructing a data asset knowledge graph for an integrated energy system, which can establish a knowledge graph of the system according to the physical topology, equipment category and historical data information of the system, and mainly includes the following steps:

[0062] Conduct structural analysis on the integrated energy system to obtain the physical correlation between the numerical points of the equipment; classify the equipment in the integrated energy system and find the physical correlation between the numerical points of each type of equipment based on the principles of physics;

[0063] Read the historical data of all numerical points in the integrated energy system, and solve the correlation coefficients between all numerical points based on the historical data; then set the correlation coefficient threshold, and screen the correlation between the numerical points based on the comparison between the correlation coefficient and the correlation coefficient threshold;

[0064] All numerical points are stored as nodes (entities) in the graph database, and the physical correlations and correlations between the numerical points are stored as edges (relationships) in the graph database, and a comprehensive energy system knowledge graph based on the interaction of python and neo4j is established.

[0065] Preferably, the method of structurally analyzing the integrated energy system to obtain the physical correlation between the numerical points of the system equipment is as follows:

[0066] Determine the connection relationship between devices based on the physical topology relationship between devices in the system and the actual functions of the devices;

[0067] Based on the equipment connection relationship, the flow direction of the material flow in the connection relationship and the corresponding equipment numerical points are analyzed to obtain the physical association between the numerical points between the equipment.

[0068] Preferably, the integrated energy system is divided into equipment categories, and the method for obtaining the physical correlation between the internal numerical points of each type of equipment according to the principles of physics is as follows:

[0069] Taking the electrical system as an example, the equipment in the electrical system is divided into three categories according to type: electric meter, inverter (DC / AC), and DC chopper (DC / DC);

[0070] All internal numerical points of each device are extracted, and node relationship equations are constructed based on the basic physical relationships between physical quantities such as current, voltage, and power, so as to obtain the physical relationships between the internal numerical points of the device.

[0071] More preferably, the method of constructing a point relationship equation according to the basic physical relationship between physical quantities such as current, voltage, power, etc., so as to obtain the physical relationship between the numerical points inside the device is as follows:

[0072] For electric meter equipment, it is easy to know:

[0073] Line voltage = √3 × phase voltage;

[0074] Apparent total power 2 = Total active power 2 + Total reactive power 2 ;

[0075] Total power factor = total active power / total apparent power;

[0076] For inverters (DC / AC), it is easy to know:

[0077] DC side power = DC current × DC lower half bus voltage;

[0078] For DC chopper (DC / DC), it is easy to know:

[0079] Total power = battery side voltage × total battery side current.

[0080] Preferably, the method of reading the historical data of all numerical points in the system from the database and solving the correlation coefficients between all points based on the historical data is as follows:

[0081] Taking the electrical system as an example, Navicat is used to export all numerical point data of all equipment in a certain month from the database of the electrical system according to the equipment category, including basic elements such as data collection time, equipment name, equipment point name, and collection value;

[0082] For each device, a time series line graph of the device is drawn with the data collection time as the horizontal axis and the corresponding collection value as the vertical axis to visualize the operation status of the device, so as to analyze the operation status of the device. If there are missing or large sections of abnormal data collected by the device, the data of other months are re-exported from the database, and finally a data set of all devices in normal operation is obtained;

[0083] Aggregate all time series point data of all devices into a new matrix Z t×n , where the row t of the matrix represents the data collection time (i.e., the number of point data), and the column n of the matrix represents the number of points (i.e., the sum of all points of all equipment in the electrical system). The correlation coefficient matrix between the columns in the matrix is ​​calculated;

[0084] For the matrix Z t×n For two columns of sample points X and Y, estimate the expectation, variance, and covariance based on the samples:

[0085]

[0086] Where: X i represents the i-th observation in the sample, n represents the size of the sample, that is, the total number of observations, and E(X) is the expectation of the random variable X, which represents the average of all observations; The value is the sample mean, is the variance of the random variable X, which indicates how dispersed the observations are relative to the mean; cov(X,Y) is the covariance of the random variables X and Y, which indicates how the two variables vary together;

[0087] Substituting the above formula into the definition of the correlation coefficient, its definition is as follows:

[0088]

[0089] Where: X σ Y are the standard deviations of X and Y, respectively, and E(XY) is the expectation of the product of X and YρX,Y is the correlation coefficient;

[0090] The calculation formula of the correlation coefficient is:

[0091]

[0092] The correlation coefficient between two sets of point data can be calculated by the above formula.

[0093] Preferably, the method of setting a suitable correlation coefficient threshold h and obtaining all value point groups with data correlation in the system according to the threshold is as follows:

[0094] Historical experience shows that:

[0095]

[0096] Where r represents the correlation coefficient between two sets of data;

[0097] Based on historical experience and actual system requirements, the threshold is selected as h = 0.5;

[0098] If the absolute value of the correlation coefficient between two points is greater than the threshold, it is considered that the point group has data-level correlation, and the data correlation between all numerical points in the system is obtained based on this.

[0099] Preferably, the method of storing all numerical points of all devices in the system as nodes (entities) in a graph database is as follows:

[0100] Before performing specific operations, install the third-party library py2neo in the Python environment to operate neo4j;

[0101] Connect to the database according to the browser access address, username and password of neo4j;

[0102] Create point nodes for all devices of each type according to the device type. The following process takes the electric meter type as an example.

[0103] In the Python project, create a node list of all devices in the meter in turn. The objects in the list are:

[0104] Node(*labels, **properties)

[0105] *labels is the label of the node, representing the type of the node, which is set to the device name here;

[0106] **properties is the properties of the node. The data structure is a dictionary, which can store the properties of the node. Here it is set to the device point name;

[0107] For example, the specific objects obtained are:

[0108] Node('Energy Station No. 1 Electricity Meter', name = 'Phase A Voltage')

[0109] Use Subgraph to create a node list to create nodes in batches;

[0110] By storing all the created batch nodes into the graph database using graph.create(), all the numerical points of all the equipment in the electrical system can be stored as nodes in the graph database.

[0111] Preferably, the method of storing the physical correlation and data correlation relationship between the numerical points as edges (relationships) in the graph database is as follows:

[0112] The structure for creating an edge is:

[0113] Relationship(start_node,type,end_node)

[0114] Where start_node indicates the starting node of the edge, end_node indicates the end point of the edge, and type indicates the attribute of the edge, which is used to distinguish the physical relevance and data relevance of the edge.

[0115] Create physical related edges and data related edges between nodes respectively;

[0116] Use graph.create() to store the created edges in the graph database.

[0117] Example 1

[0118] A method for constructing a data asset knowledge graph for an integrated energy system, in which an electrical system is used in this embodiment, specifically includes the following steps:

[0119] Step 1: Analyze the overall structure of the system and obtain the physical correlation between the numerical points of the system devices;

[0120] The structure of the equipment diagram of the electrical system in this embodiment is as follows Figure 2 As shown, the connection relationship between the devices in the electrical system is determined based on the physical topological relationship between the devices and the actual functions of the devices. On the basis of the device connection relationship, the flow direction of electricity in the connection relationship and the corresponding device numerical points are analyzed to obtain the physical association between the numerical points of the devices.

[0121] Some examples of numerical points with physical associations between specific devices obtained according to the above method are shown in Table 1:

[0122] Table 1 Physical correlation between numerical points of equipment

[0123]

[0124]

[0125] Step 2: Classify all devices in the system according to device type, and find out the physical relationship between the internal numerical points of each type of device (physical correlation relationship between the internal numerical points of the device) based on the principles of physics;

[0126] The equipment in the electrical system is divided into three categories according to type: electric meters, inverters (DC / AC), and direct current choppers (DC / DC); all internal numerical points of each device are extracted, and node relationship equations are constructed based on the basic physical relationships between physical quantities such as current, voltage, and power, so as to obtain the physical relationships between the internal numerical points of the equipment;

[0127] For electric meter equipment, it is easy to know:

[0128] Line voltage = √3 × phase voltage;

[0129] Apparent total power 2 = Total active power 2 + Total reactive power 2 ;

[0130] Total power factor = total active power / total apparent power;

[0131] For inverters (DC / AC), it is easy to know:

[0132] DC side power = DC current × DC lower half bus voltage;

[0133] For DC chopper (DC / DC), it is easy to know:

[0134] Total power = battery side voltage × total battery side current;

[0135] Based on the above physical relationship, some examples of numerical points with physical relationship inside the device are shown in Table 2:

[0136] Table 2 Physical correlation of numerical points inside the equipment

[0137]

[0138]

[0139] Step 3, read the historical data of all numerical points in the system from the database, and solve the correlation coefficient between all points based on the historical data; use Navicat to export all numerical point data of all equipment in a certain month from the database of the electrical system according to the equipment category, including basic elements such as data collection time, equipment name, equipment point name, and collection value. The sampling interval is 5 minutes. Table 3 is part of the data information of the equipment;

[0140] Table 3 Equipment data information

[0141] load_time system_name device_name position_name load_value 2024 / 9 / 1 0:00:00 Photovoltaic system DC / DC-No.1DC / DC 1#DCDC DC bus voltage 2.4 2024 / 9 / 1 0:00:00 Photovoltaic system DC / DC-No.1DC / DC 1#DCDC battery side voltage 8.8 2024 / 9 / 1 0:00:00 Photovoltaic system DC / DC-No.1DC / DC 1#DCDC total discharge capacity 48.5 2024 / 9 / 1 0:00:00 Photovoltaic system DC / DC-No.2DC / DC 2#DCDC DC bus voltage 759.1 2024 / 9 / 1 0:00:00 Photovoltaic system DC / DC-No.2DC / DC 2#DCDC battery side voltage 10 2024 / 9 / 1 0:00:00 Distribution system DC / AC-No.1DC / AC 1# DC lower half bus voltage 375.3 2024 / 9 / 1 0:00:00 Distribution system DC / AC-No.1DC / AC 1# Reactive power 2.9 2024 / 9 / 1 0:00:00 Distribution system DC / AC-No.1DC / AC 1# DC bus voltage 749.4 2024 / 9 / 1 0:00:00 Distribution system DC / AC-No.2DC / AC 2#Uab voltage 388.6 2024 / 9 / 1 0:00:00 Distribution system DC / AC-No.2DC / AC 2#Ubc voltage 387.3 2024 / 9 / 1 0:00:00 Electricity Meter DK1 Electricity Meter - DK1 Electricity Meter No. 1 DK1_No.1 isolation transformer switch cabinet A phase voltage 241.5 2024 / 9 / 1 0:00:00 Electricity Meter DK1 Electricity Meter - DK1 Electricity Meter No. 1 DK1_No.1 isolation transformer switch cabinet AB line voltage 419 2024 / 9 / 1 0:00:00 Electricity Meter DK1 Electricity Meter - DK1 Electricity Meter No. 1 DK1_1 No.1 isolation transformer switch cabinet A phase current 2.4 2024 / 9 / 1 0:00:00 Electricity Meter DK1 Electricity Meter - DK1 Electricity Meter No. 2 Total active power of DK1_2 isolation transformer switch cabinet 28.8 2024 / 9 / 1 0:00:00 Electricity Meter DK1 Electricity Meter - DK1 Electricity Meter No. 2 Apparent total power of DK1_2 isolation transformer switch cabinet 29.6

[0142] For each device, a time series line graph of the device is drawn with the data collection time as the horizontal axis and the corresponding collection value as the vertical axis to visualize the operating status of the device, so as to analyze the operating status of the device. If there are missing or large sections of abnormal data collected by the device, the data of other months are re-exported from the database, and finally the data set of all devices in normal operation is obtained; all the time series point data of all devices are aggregated into a new matrix Z t×n , where the row t of the matrix represents the data collection time (i.e., the number of point data), and the column n of the matrix represents the number of points (i.e., the sum of all points of all equipment in the electrical system). The correlation coefficient matrix between the columns in the matrix is ​​calculated.

[0143] For the matrix Z t×n For two columns of sample points X and Y, estimate the expectation, variance, and covariance based on the samples:

[0144]

[0145] Substituting the above formula into the definition of the correlation coefficient, its definition is as follows:

[0146]

[0147] The calculation formula of the correlation coefficient is:

[0148]

[0149] The correlation coefficient between two sets of point data can be calculated by the above formula.

[0150] Step 4: Set a suitable correlation coefficient threshold h, and filter all value point groups with data correlation in the system according to the threshold. From historical experience, we know that:

[0151]

[0152] Based on historical experience and actual requirements of the electrical system, the threshold is selected as h = 0.5;

[0153] If the absolute value of the correlation coefficient between two points is greater than the threshold, it is considered that the point group has data-level correlation, and the data correlation between all numerical points in the electrical system is obtained.

[0154] Step 5: Store all numerical points of all devices in the system as nodes (entities) in the graph database, store the physical and data-related relationships between the numerical points as edges (relationships) in the graph database, and establish an electrical system knowledge graph based on the interaction between python and neo4j.

[0155] Before performing specific operations, install the third-party library py2neo in the Python environment to operate neo4j;

[0156] Connect to the database according to the browser access address, username and password of neo4j;

[0157] Create point nodes for all devices of each type according to the device type. The following process takes the electric meter type as an example.

[0158] In the Python project, create a node list of all devices in the meter in turn. The objects in the list are:

[0159] Node(*labels, **properties)

[0160] *labels is the label of the node, representing the type of the node, which is set to the device name here;

[0161] **properties is the properties of the node. The data structure is a dictionary, which can store the properties of the node. Here it is set to the device point name;

[0162] For example, the specific objects obtained are:

[0163] Node('Energy Station No. 1 Electricity Meter', name = 'Phase A Voltage')

[0164] Use Subgraph to create a node list to create nodes in batches;

[0165] On the basis of creating all point nodes, a new node is created for each device, named device node, which is used to connect all point nodes of the device in the future for easy management. The label of the device node is set to device;

[0166] By storing all the created batch nodes into the graph database using graph.create(), all the numerical points of all the equipment in the electrical system can be stored as nodes in the graph database.

[0167] The structure for creating an edge is:

[0168] Relationship(start_node,type,end_node)

[0169] Where start_node indicates the starting node of the edge, end_node indicates the end point of the edge, and type indicates the attribute of the edge, which is used to distinguish the physical relevance and data relevance of the edge.

[0170] Create physical related edges and data related edges between nodes respectively;

[0171] Use graph.create() to store the created edges into the graph database;

[0172] After storage, the node label information and edge type information are as follows: Figure 3 As shown in the figure, the Node labels section shows the node label information. Each node is labeled with the name of the device to which it belongs. The device node is labeled as device. Different types of devices are distinguished by different colors. The Relationship types section shows the edge type information, which are physical related and data related, and are distinguished by different colors.

[0173] The final knowledge graph visualization result is as follows Figure 4 shown.

[0174] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for constructing a data asset knowledge graph for an integrated energy system, characterized in that: The following steps are involved: Conduct structural analysis and equipment classification of the integrated energy system to obtain the physical correlation between the numerical points in the integrated energy system; Read the historical data of all numerical points in the integrated energy system, and solve the correlation coefficients between all numerical points based on the historical data; then set the correlation coefficient threshold, and screen the correlation between the numerical points based on the comparison between the correlation coefficient and the correlation coefficient threshold; All numerical points are stored as nodes in the graph database, and the physical correlations and correlations between the numerical points are stored as edges in the graph database to establish an interactive data asset knowledge graph.

2. According to claim 1, a method for constructing a data asset knowledge graph for an integrated energy system is characterized in that: The physical correlation between the numerical points includes the physical correlation between the numerical points between devices and the physical correlation between the numerical points inside the devices; The physical correlation between the numerical points of the devices is obtained after structural analysis of the integrated energy system; The physical correlation relationship between the numerical points inside the equipment is obtained after classifying the equipment in the integrated energy system.

3. According to claim 2, a method for constructing a data asset knowledge graph for an integrated energy system is characterized in that: The steps to perform structural analysis on the integrated energy system and obtain the physical correlation between the numerical points of the equipment are as follows: Determine the connection relationship between various devices based on the physical topological relationship between devices in the integrated energy system and the actual functions of the devices; Based on the equipment connection relationship, the flow direction of the material flow in the connection relationship and the equipment numerical points corresponding to the flow direction of the material flow are analyzed, so as to obtain the physical correlation relationship between the numerical points between the equipment.

4. According to claim 2, a method for constructing a data asset knowledge graph for an integrated energy system is characterized in that: The steps to classify the equipment of the integrated energy system and obtain the physical correlation between the internal numerical points of the equipment are as follows: All equipment in the integrated energy system is classified according to the equipment type, the physical quantities of each type of equipment are extracted, and the node relationship between the physical quantities is constructed according to the physical relationship, so as to obtain the physical correlation relationship between the numerical points inside the equipment.

5. According to claim 4, a method for constructing a data asset knowledge graph for an integrated energy system is characterized in that: The integrated energy system is an electrical system. The specific steps of classifying the equipment categories of the integrated energy system and obtaining the physical correlation relationship of the internal numerical points of the equipment are as follows: All equipment in the integrated energy system is divided into electricity meters, inverters and DC choppers according to the equipment type; all internal numerical points of the electricity meters, inverters and DC choppers are extracted, and the node relationship formula is constructed according to the basic physical relationship between current, voltage and power, so as to obtain the physical correlation between the internal numerical points of the equipment in the electrical system.

6. A method for constructing a data asset knowledge graph for an integrated energy system according to claim 5, characterized in that: The specific steps for constructing node relationships based on the basic physical relationship between current, voltage and power to obtain the physical correlation relationship between the internal numerical points of the equipment in the electrical system are as follows: For electric meters: Line voltage = √3 × phase voltage; Apparent total power 2 = total active power 2 + total reactive power 2; Total power factor = total active power / total apparent power; For inverter: DC side power = DC current × DC lower half bus voltage; For DC chopper: Total power = battery side voltage × total battery side current.

7. The method for constructing a data asset knowledge graph for an integrated energy system according to claim 1, characterized in that: The steps of reading the historical data of all numerical points in the integrated energy system and solving the correlation coefficients between all numerical points according to the historical data include: Read the data collection time, equipment name, equipment point name and collection value in the integrated energy system; for each device, use the data collection time as the horizontal axis and the corresponding collection value as the vertical axis to draw a time series line chart of the device, visualize the operating status of the device, and analyze the operating status of the device; Aggregate all time series point data of all devices into a matrix, represented by Z t×n ; The rows of the matrix represent the data collection time, which is denoted as t, and the columns of the matrix represent the sum of all points of all devices, which is denoted as n. Then, the correlation coefficient matrix between the columns in the matrix is ​​calculated; Calculating the correlation coefficient matrix between the columns in the matrix includes the following steps: For the matrix Z t×n For two columns of sample points X and Y, estimate the expectation, variance and covariance based on the samples: Where: X i represents the i-th observation in the sample, n represents the size of the sample, that is, the total number of observations, and E(X) is the expectation of the random variable X, which represents the average of all observations; The value is the sample mean, is the variance of the random variable X, which indicates how dispersed the observations are relative to the mean; cov(X,Y) is the covariance of the random variables X and Y, which indicates how the two variables vary together; Substituting the above formula into the definition of the correlation coefficient, its definition is as follows: Where: X σ Y are the standard deviations of X and Y, respectively, and E(XY) is the expectation of the product of X and Yρ X,Y is the correlation coefficient; The calculation formula of the correlation coefficient is further processed as follows:

8. According to claim 1, a method for constructing a data asset knowledge graph for an integrated energy system is characterized in that: When the absolute value of the correlation coefficient between two points is greater than the threshold, it is considered that the point group has data-level correlation, and the correlation relationship between the numerical points is obtained accordingly.

9. The method for constructing a data asset knowledge graph for an integrated energy system according to claim 1, characterized in that: The setting standard of the correlation coefficient threshold is as follows: Where r represents the correlation coefficient between two sets of data; The correlation coefficient threshold is 0.5; The interactive data asset knowledge graph is a data asset knowledge graph established based on the interaction between python and neo4j.

10. A data asset knowledge graph construction system for integrated energy systems, characterized in that: Used to implement the construction method described in any one of claims 1 to 9.

Images