GIS bus cabin air leakage cause analysis method and related device

Abstract

The invention belongs to the technical field of GIS bus cabin air leakage state monitoring, and discloses a GIS bus cabin air leakage cause analysis method and a related device. The GIS bus cabin air leakage cause analysis method comprises the steps that position information and state information of an air leakage point are acquired, and the state information of the air leakage point is continuous air leakage or sudden transient air leakage; and based on the position information and the state information of the air leakage point, performing air leakage cause analysis by using a pre-acquired relevance rule to obtain an air leakage cause analysis result of the GIS bus cabin. According to the technical scheme disclosed by the invention, the air leakage cause of the GIS bus cabin can be rapidly obtained, rapid development of targeted operation and maintenance work can be supported, a manager can be assisted to formulate effective measures to reduce the air leakage rate of the cabin body, and the operation stability of a power system can be improved.

Description

Technical Field

[0001] The invention belongs to the technical field of gas insulated switchgear (GIS) busbar compartment leakage state monitoring, and in particular relates to a method for analyzing the cause of gas leakage in a GIS busbar compartment and a related device. Background Art

[0002] GIS has the advantages of small footprint, safe and reliable operation, and convenient maintenance, and is widely used in many fields such as electricity, industry, and transportation. Due to the material design of GIS itself or the influence of the external environment, GIS equipment has the problem of gas leakage; gas leakage in the GIS busbar compartment may cause a power outage of the entire station or a single voltage level, and may cause personal injury and environmental pollution; the reasons for GIS gas leakage are varied, which brings challenges to operation and maintenance.

[0003] At present, the existing GIS leakage detection scheme only focuses on information such as leakage points and leakage conditions, but does not analyze the causes of leakage, resulting in the inability to carry out targeted operation and maintenance, and thus the inability to quickly eliminate the impact of GIS gas leakage. By way of further example and explanation, existing GIS leakage detection methods include traditional detection methods, infrared imaging detection methods, SF6 gas qualitative instrument detection methods and combined detection methods; among them, the traditional detection methods are soapy water detection method and bandaging detection method; the infrared imaging detection method is based on the irradiation of infrared light, SF6 will produce a special absorption spectrum, and the leaked SF6 gas can be detected by a professional infrared imaging detector; the SF6 gas qualitative instrument detection method is to use the SF6 gas qualitative detector to perform translational detection at the flange connection, welding point, pipeline interface and other parts of the GIS equipment at a speed of approximately 25mm / s, and emit sound and light signals of corresponding levels according to the amount of gas leakage around the detection contact; the combined detection method is to combine the above three existing detection methods for detection; in summary, the existing GIS leakage detection schemes can only obtain information such as leakage points and leakage conditions, but cannot know the causes of leakage, and cannot support the rapid development of targeted operation and maintenance work. Summary of the invention

[0004] The purpose of the present invention is to provide a method and related device for analyzing the causes of air leakage in a GIS bus compartment to solve one or more of the above-mentioned technical problems. The technical solution disclosed in the present invention is specifically a GIS bus compartment air leakage cause analysis solution based on multi-source data fusion, which can quickly obtain the causes of air leakage in the GIS bus compartment, support the rapid implementation of targeted operation and maintenance work, assist managers in formulating effective measures to reduce the air leakage rate of the compartment, and help improve the operational stability of the power system.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for analyzing the cause of air leakage in a GIS busbar compartment, comprising the following steps: Obtaining the location information and status information of the leak point; wherein the status information of the leak point is continuous leak or sudden transient leak, which is obtained by judging the SF6 gas pressure at the leak point; Based on the location information and status information of the leakage point, the pre-acquired correlation rules are used to analyze the leakage causes and obtain the analysis results of the leakage causes of the GIS busbar compartment; The step of obtaining the association rule includes: Acquire multi-source historical data; wherein the multi-source historical data includes micro-meteorological data in the substation, preset key parameters of the GIS busbar compartment, and SF6 gas pressure; Based on the multi-source historical data, the principal component analysis method is used to obtain the strongly correlated variables of air leakage; Based on the acquired strongly correlated variables, the improved FP-growth correlation analysis method is used for mining and analysis to obtain the correlation rules of GIS busbar compartment air leakage; wherein, in the improved FP-growth correlation analysis method, a function mapping data storage structure is used to find and determine the support, and a distributed parallel mining strategy is used to mine frequent item sets and correlation rules.

[0006] A further improvement of the present invention is that The substation micro-meteorological data includes temperature, humidity, light, wind force, wind direction, rainfall, snowfall and atmospheric pressure in the substation; The preset key parameters of the GIS busbar cabin include the cabin outer surface temperature distribution and the cabin relative displacement.

[0007] A further improvement of the present invention is that The micro-meteorological data in the substation is collected in the representative months of the four seasons: January, April, July and October.

[0008] A further improvement of the present invention is that The relative displacement of the cabin includes the relative displacement of the two cabin sections, the displacement of the cabin relative to the ground, and the displacement of the cabin in horizontal and vertical deployment.

[0009] A further improvement of the present invention is that The steps of performing mining analysis based on the acquired strongly correlated variables and using the improved FP-growth correlation analysis method to obtain the correlation rules of GIS busbar compartment air leakage include: Define item set content and build a database based on strongly correlated variables; Traverse the entire database, calculate the support of each item in each item set and compare it with the predetermined minimum support, delete the items with support less than the minimum support, and obtain a frequent item list; Based on the frequent item list, different sub-databases of welding seams, flange joint surfaces, circuit breakers, and sealing ring positions are constructed, arranged in descending order of support, and FP-tree is constructed; Based on the constructed FP-tree, a distributed parallel mining strategy is adopted to generate the initial correlation rules of GIS busbar compartment air leakage; Based on the initial association rules, the support of single and multiple independent variables is analyzed respectively, the correlation between single independent variable, multiple independent variable coupling and dependent variable is obtained, and the final association rules are obtained.

[0010] A further improvement of the present invention is that The step of using the function mapping data storage structure to find and determine the support degree includes: The constructor performs one-to-one mapping, defines the logical address of the itemset, takes the itemset content as the independent variable and the itemset address as the dependent variable to find and determine the corresponding support.

[0011] A further improvement of the present invention is that The steps of mining frequent item sets and association rules using a distributed parallel mining strategy include: The location where the frequency of a single gas leakage point in the GIS busbar compartment exceeds the preset frequency threshold is set as the main node, and the micro-meteorological data in the substation, the preset key parameters of the GIS busbar compartment, and the SF6 gas pressure are set as the sub-nodes of distributed mining; The main node collects the data of each child node. The child nodes are responsible for collecting and processing data in their respective fields. The frequent item mining algorithm is executed on the child nodes to find out the frequent item names in their respective fields. The main node receives the frequent item name table returned by each child node, and collects and integrates the data to determine the correlation strength by support and placement, and generate the initial association rules for GIS busbar compartment leakage.

[0012] In a second aspect, the present invention provides a GIS busbar compartment air leakage cause analysis system, comprising: An information acquisition module is used to obtain the location information and status information of the leak point; wherein the status information of the leak point is continuous leakage or sudden transient leakage, which is obtained by judging the SF6 gas pressure at the leak point; The cause analysis module is used to analyze the cause of leakage based on the location information and status information of the leakage point and use the pre-acquired association rules to obtain the cause analysis results of the leakage in the GIS busbar compartment; The step of obtaining the association rule includes: Acquire multi-source historical data; wherein the multi-source historical data includes micro-meteorological data in the substation, preset key parameters of the GIS busbar compartment, and SF6 gas pressure; Based on the multi-source historical data, the principal component analysis method is used to obtain the strongly correlated variables of air leakage; Based on the acquired strongly correlated variables, the improved FP-growth correlation analysis method is used for mining and analysis to obtain the correlation rules of GIS busbar compartment air leakage; wherein, in the improved FP-growth correlation analysis method, a function mapping data storage structure is used to find and determine the support, and a distributed parallel mining strategy is used to mine frequent item sets and correlation rules.

[0013] A third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for analyzing the cause of air leakage in a GIS bus compartment as described in any one of the first aspect of the present invention is implemented.

[0014] A fourth aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for analyzing the cause of air leakage in a GIS busbar compartment as described in any one of the first aspects of the present invention.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for analyzing the causes of air leakage in a GIS busbar compartment. For the leakage point to be analyzed, the pre-acquired correlation rules of the GIS busbar compartment air leakage are used to quickly analyze and know the cause of the leakage only by obtaining the location information and status information of the leakage point. This method can effectively support the rapid development of targeted operation and maintenance work, and can assist managers in formulating effective measures to reduce the air leakage rate of the compartment, which helps to improve the operational stability of the power system. Further explaining, the main causes of air leakage in the GIS busbar compartment include loose GIS interfaces, rust, etc. in addition to installation problems and quality problems. The main factors leading to the above situations come from environmental changes (for example, high temperature causes device aging, etc.); in addition, GIS is affected by a variety of external factors during operation, and it is necessary to consider multi-source data; the correlation rules obtained by the present invention take into account multi-source historical data and have high accuracy and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below; obviously, the drawings described below are some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 The present invention is a flowchart of a method for analyzing the cause of air leakage in a GIS busbar compartment in an embodiment of the present invention.

[0018] Figure 2 It is a schematic diagram of the framework of a method for analyzing the air leakage status of a GIS busbar compartment based on multi-source data fusion in a specific embodiment of the present invention.

[0019] Figure 3 It is a schematic diagram of an improved FP-Growth multi-dimensional factor temporal association mining algorithm in an embodiment of the present invention.

[0020] Figure 4 It is a schematic diagram of a distributed parallel mining strategy in an embodiment of the present invention.

[0021] Figure 5 It is a schematic diagram of a GIS busbar compartment air leakage cause analysis system in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention; it is obvious that the described embodiments and technical solutions are only part of the embodiments of the present invention, not all of the embodiments.

[0023] All other embodiments obtained by those of ordinary skill in the art without creative work based on the technical solutions disclosed in the embodiments of the present invention belong to the scope of protection of the present invention. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] See also Figure 1 A method for analyzing the causes of air leakage in a GIS busbar compartment disclosed in an embodiment of the present invention comprises the following steps: Step 1, obtaining the location information and status information of the leak point; wherein the status information of the leak point is continuous leakage or sudden transient leakage, which can be determined by collecting the SF6 gas pressure at the leak point; Step 2: Based on the information obtained in step 1, the pre-acquired association rules are used to perform leakage cause analysis to obtain the leakage cause analysis results of the GIS busbar compartment; The step of obtaining the association rule includes: Acquire multi-source historical data; wherein the multi-source historical data includes micro-meteorological data in the substation, preset key parameters of the GIS busbar compartment, and SF6 gas pressure; Based on the multi-source historical data obtained, the principal component analysis (PCA) method was used to obtain the strongly correlated variables of air leakage; Based on the acquired strongly correlated variables, the improved FP-growth correlation analysis method is used to analyze and obtain the correlation rules of GIS busbar compartment gas leakage; wherein, in the improved FP-growth correlation analysis method, a function mapping data storage structure is adopted, and a distributed parallel frequent item set mining method is used to find the correlation rules between multi-source historical data and GIS busbar compartment gas leakage.

[0025] In view of the existing problems in the cause analysis of GIS busbar compartment leakage, the embodiment of the present invention specifically proposes an efficient and accurate cause analysis method. The method of the present invention uses the pre-acquired correlation rules of GIS busbar compartment leakage, and only needs to obtain the location information and status information of the leakage point to quickly analyze and determine the cause of the leakage. This method greatly simplifies the analysis process, shortens the diagnosis time, provides strong support for targeted operation and maintenance work, and helps managers to formulate and implement effective measures in a timely manner, thereby reducing the cabin leakage rate and improving the overall operation stability of the power system. Explanatory, there are various reasons for air leakage in GIS busbar compartment, including but not limited to: installation problems (such as poor sealing during installation, untightened bolts, etc.), quality problems (such as defects in materials or components themselves, such as aging of sealing rings, rusting of metal parts, etc.), GIS interface problems (such as loose, corroded or damaged interfaces, resulting in reduced sealing performance, etc.), environmental changes (such as environmental factors such as high temperature, humidity, corrosion, etc., which accelerate equipment aging and reduce sealing effects, etc.); in addition, during the operation of GIS busbar compartment, its state is affected by a variety of external factors, including but not limited to ambient temperature, humidity, air pressure, equipment operating load, maintenance history, etc.; therefore, in order to accurately analyze the cause of air leakage, these multi-source data must be comprehensively considered. The association rules obtained by the present invention are obtained by deep learning and mining based on a large amount of historical data (including air leakage event records, environmental monitoring data, equipment operation data, etc.). The association rules reflect the complex relationship between the cause of air leakage and various influencing factors, and have high accuracy and reliability.

[0026] In practical applications, using the method proposed in the embodiment of the present invention, operation and maintenance personnel can quickly analyze the cause of the leakage based on the correlation rules according to the located leakage point. This not only greatly improves the operation and maintenance efficiency, but also reduces the risk of power outages and equipment damage caused by leakage, which is of great significance to ensuring the safe and stable operation of the power system.

[0027] In summary, the technical solution of the embodiment of the present invention realizes rapid and accurate analysis of the cause of leakage by utilizing the pre-acquired correlation rules of GIS busbar compartment leakage, combined with the location information and status information of the leakage point. This method not only takes into account the influence of multi-source data, but also has high accuracy and reliability, providing strong support for the operation and maintenance management of the power system.

[0028] See also Figure 2 and Figure 3 A method for analyzing the leakage status of a GIS busbar compartment based on multi-source data fusion disclosed in a specific embodiment of the present invention comprises the following steps: Step S1: Collect relevant micro-meteorological data, cabin key parameters and gas pressure data; wherein, the representative months of the four seasons, January, April, July and October, are used as the collection period to collect the micro-meteorological data in the substation, the preset key parameters of the GIS bus cabin and the corresponding SF6 gas pressure data; wherein, the micro-meteorological data in the substation mainly collects the micro-meteorological parameters such as temperature, humidity, light, wind force, wind direction, rainfall, snowfall, atmospheric pressure and the like in the substation; the preset key parameters of the GIS bus cabin mainly collect the temperature distribution of the outer surface of the cabin (exemplarily, such as the temperature of the yin and yang sides, etc.), the relative displacement of the cabin (exemplarily, such as the relative displacement of the two cabins, the displacement of the cabin to the ground, the displacement of the cabin in horizontal and vertical deployment) and other information; Step S2: PCA is used to perform dimensionality reduction processing on the data collected in step S1 to screen out strongly correlated variables of gas leakage; wherein the multi-source data collected in step S1 is regarded as a eigenvector, standardized, and a covariance matrix is ​​constructed with its eigenvalues ​​to obtain the degree of correlation between the variables; according to the size of the eigenvalue, the eigenvector corresponding to the eigenvalue is selected as the principal component, and the data variables with higher loads on the principal component are determined as strongly correlated variables, and weakly correlated variables about gas leakage are screened out; further illustratively, if a data variable has higher loads on multiple principal components, it may have multiple correlations with gas leakage; Step S3, based on the obtained strongly correlated variables, the improved FP-growth correlation analysis method is used to analyze and obtain the correlation rules of GIS busbar compartment gas leakage; Explanation: Only the PCA method cannot directly obtain all the factors directly related to gas leakage. Therefore, the improved FP-growth correlation analysis method of the embodiment of the present invention adopts the data storage structure of function mapping combined with the distributed parallel frequent item set mining technology to find the correlation rules between multi-source data and GIS busbar compartment gas leakage, such as Figure 3 shown.

[0029] See also Figure 3 In the improved FP-growth correlation analysis method of the embodiment of the present invention, Step 1) Define the item set content based on the strongly correlated variables and construct a database; explanatory, the database W may include micro-meteorological data such as light, rainfall, snowfall, and strong wind, as well as key cabin parameters such as cabin displacement and cabin temperature, and GIS gas pressure data in the corresponding scene, and each item set is exemplarily represented by letters A, B, C, ...; Step 2), traverse the entire database, calculate the support of each item in each item set and compare it with the predetermined minimum support, delete the items with support less than the minimum support, and obtain a frequent item list; Step 3), based on the frequent item list, construct different sub-databases of welding seams, flange joint surfaces, circuit breakers, and sealing ring positions, arrange them in descending order of support, and construct FP-tree (frequent pattern tree); Step 4), based on the constructed FP-tree, a distributed parallel mining strategy is adopted to generate the initial association rules of GIS busbar compartment air leakage; Step 5), based on the initial association rules, analyze the support of single or multiple (such as 2, 3) independent variables respectively, obtain the correlation between single or multiple (such as 2, 3) independent variables (coupling effects) and dependent variables, and obtain the final association rules.

[0030] In one embodiment of the present invention, the support and confidence of FP-Growth are defined; wherein the support is the ratio of the number of tuples containing M and N to the total number of tuples, that is, the probability that item set A and item set B appear simultaneously in the database; the confidence is the ratio of the number of tuples containing M and N to the number of tuples containing M, that is, the probability that item set N appears simultaneously in an event containing item set M. The calculation expressions of support and confidence are shown in formula (1) and formula (2), respectively. (1) (2) In the formula, is the number of tuples that contain M and N; W is the total number of tuples, is the number of tuples containing M.

[0031] In one embodiment of the present invention, the constructor performs one-to-one mapping, and defines the logical addresses of the item set as: 01, 02, 03, ..., 09, 10, ...; the item set content is used as the independent variable, and the item set address is used as the dependent variable, and the corresponding support is determined, as shown in Table 1. When determining to find the item set content, its storage location in the memory can be directly locked, and the support of the corresponding item set can be obtained.

[0032] Table 1. Function mapping relationship

[0033] See also Figure 4In one embodiment of the present invention, a distributed parallel mining strategy is designed; wherein, the position with the highest frequency of single leakage point in GIS busbar compartment is determined as the main node, such as flange joint surface, sealing ring position, etc., and each micro-meteorological data, cabin parameter and gas pressure are set as sub-nodes for distributed mining, such as light, rainfall, strong wind, cabin displacement, air pressure, etc.; the main node collects the data of each sub-node, and the sub-node is responsible for collecting and processing the data in their respective fields, and the frequent item mining algorithm is executed on the sub-node to find out the frequent item names in their respective fields. The main node receives the frequent item name table returned by each sub-node, and collects and integrates the data, determines the correlation strength by support and position, and generates the initial correlation rules of GIS busbar compartment leakage; based on the initial correlation rules, the support of single (2, 3) independent variables is analyzed respectively, and the correlation between single (2, 3) independent variables (coupling effect) and dependent variables is obtained.

[0034] In summary, GIS equipment usually operates in a complex environment, and environmental factors may have an adverse effect on the sealing performance of the equipment; the current traditional leakage detection method only focuses on the leakage point, leakage situation, etc., ignoring the key reasons that cause the deformation, displacement, and reduced sealing stability of the cabin (explanatory, temperature changes may cause thermal expansion and contraction of sealing materials, thereby affecting the sealing effect; humidity changes may cause aging or corrosion of sealing materials; impurities such as wind, sand, and dust may enter the sealing surface and affect the sealing performance). It is crucial to analyze the impact of environmental factors on the sealing and stability of the GIS cabin. The technical solution of the embodiment of the present invention fully considers the impact of climate and environmental changes on the durability, corrosion, and sealing of the GIS cabin, and can analyze and determine the specific reasons for the leakage of the GIS busbar cabin, with high accuracy and reliability. In a further specific exemplary technical solution, the correlation rules can be obtained through a GIS busbar gas leakage intelligent perception model, which includes a PCA data preprocessing module and an FP-Growth correlation analysis module; wherein, in the data preprocessing stage, the PCA data preprocessing module preliminarily screens out factors with low correlation according to the fitting situation, and screens out strong correlation factors with great influence on gas leakage; the FP-Growth correlation analysis module adopts an improved FP-growth correlation analysis method to perform data mining to analyze the hidden rules between factors, and obtain the correlation rules of GIS busbar compartment gas leakage.

[0035] In addition, the amount of micro-meteorological and cabin data is large, and the existing FP-Growth correlation analysis method has the defects of high computational complexity and large memory usage. Explanatory, for the multi-source data such as micro-meteorological and cabin data involved in the present invention, the computational complexity and memory usage of the correlation analysis method are a challenge. The FP-Growth correlation analysis model itself needs to be calculated multiple times and deeply traverse all data. Especially when mining frequent item sets, the FP-Growth algorithm needs to recursively construct the conditional FP-Tree. As the amount of data increases, the amount of calculation of these steps will also increase significantly. In view of the problem that the traditional FP-Growth algorithm needs to scan the frequent item list every time it searches for frequent item sets, the technical solution of the embodiment of the present invention constructs a one-to-one mapping function, with the item set content as the independent variable and the item set address as the dependent variable. When the support of a certain item set is to be found, when the item is input, the item set address can be directly read through the function to obtain its corresponding item set support, thereby improving the traversal efficiency. In addition, in view of the scattered characteristics of the data collected by the sensors in the GIS busbar compartment, a distributed parallel method is adopted, with the single location with the highest frequency of air leakage (such as flange interface, sealing ring, etc.) as the main node, and each micro-meteorological data and cabin parameters as the sub-nodes of distributed mining, and the sub-node frequent item names are formed into a table and returned to the main node. The main node collects other dimensional information returned by each sub-node, and further comprehensively analyzes the causes of air leakage in the GIS busbar compartment, which improves the analysis efficiency and can mine association rules more quickly.

[0036] In the specific application scheme of the embodiment of the present invention, firstly, multiple types of sensors such as pressure sensors, temperature sensors, and humidity sensors are deployed at welding seams, flange joint surfaces, circuit breakers, sealing rings, etc. in the station, and multi-source data such as micro-meteorological parameters and key parameters of the cabin in the station in January, April, July, and October are collected in a four-season cycle; secondly, a GIS busbar cabin air leakage intelligent perception model is constructed, which includes a PCA data preprocessing module and an FP-Growth correlation analysis module, wherein the PCA data preprocessing module is used to screen out the strongly correlated factors causing the air leakage, and then the item set mapping function is constructed, and the FP-growth is improved by combining the parallel distributed strategy to quickly mine the association rules between the factors; finally, based on the air leakage status of the GIS busbar cabin, including "no leakage", "continuous leakage" and "transient leakage", the cause of the leakage is diagnosed through association rules.

[0037] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0038] See also Figure 5 In an embodiment of the present invention, a GIS busbar compartment air leakage cause analysis system is provided, comprising: An information acquisition module is used to obtain the location information and status information of the leak point; wherein the status information of the leak point is continuous leakage or sudden transient leakage, which is obtained by judging the SF6 gas pressure at the leak point; The cause analysis module is used to analyze the cause of leakage based on the location information and status information of the leakage point and use the pre-acquired association rules to obtain the cause analysis results of the leakage in the GIS busbar compartment; The step of obtaining the association rule includes: Acquire multi-source historical data; wherein the multi-source historical data includes micro-meteorological data in the substation, preset key parameters of the GIS busbar compartment, and SF6 gas pressure; Based on the multi-source historical data, the principal component analysis method is used to obtain the strongly correlated variables of air leakage; Based on the acquired strongly correlated variables, the improved FP-growth correlation analysis method is used for mining and analysis to obtain the correlation rules of GIS busbar compartment air leakage; wherein, in the improved FP-growth correlation analysis method, a function mapping data storage structure is used to find and determine the support, and a distributed parallel mining strategy is used to mine frequent item sets and correlation rules.

[0039] A third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for analyzing the cause of air leakage in a GIS bus compartment as described in any one of the first aspect of the present invention is implemented.

[0040] In one embodiment of the present invention, a computer device is provided, the computer device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used to perform the operation of the GIS busbar compartment air leakage cause analysis method.

[0041] In one embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM (Random Access Memory) memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for analyzing the cause of air leakage in the GIS busbar compartment in the above embodiment.

[0042] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program codes.

[0043] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0044] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0045] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for analyzing the causes of air leakage in a GIS busbar compartment, characterized in that: The following steps are involved: Obtaining the location information and status information of the leak point; wherein the status information of the leak point is continuous leak or sudden transient leak, which is obtained by judging the SF6 gas pressure at the leak point; Based on the location information and status information of the leakage point, the pre-acquired correlation rules are used to analyze the leakage causes and obtain the analysis results of the leakage causes of the GIS busbar compartment; The step of obtaining the association rule includes: Acquire multi-source historical data; wherein the multi-source historical data includes micro-meteorological data in the substation, preset key parameters of the GIS busbar compartment, and SF6 gas pressure; Based on the multi-source historical data, the principal component analysis method is used to obtain the strongly correlated variables of air leakage; Based on the acquired strongly correlated variables, the improved FP-growth correlation analysis method is used for mining and analysis to obtain the correlation rules of GIS busbar compartment air leakage; wherein, in the improved FP-growth correlation analysis method, a function mapping data storage structure is used to find and determine the support, and a distributed parallel mining strategy is used to mine frequent item sets and correlation rules.

2. A method for analyzing the causes of air leakage in a GIS busbar compartment according to claim 1, characterized in that: The substation micro-meteorological data includes temperature, humidity, light, wind force, wind direction, rainfall, snowfall and atmospheric pressure in the substation; The preset key parameters of the GIS busbar cabin include the cabin outer surface temperature distribution and the cabin relative displacement.

3. A method for analyzing the causes of air leakage in a GIS busbar compartment according to claim 2, characterized in that: The micro-meteorological data in the substation is collected in the representative months of the four seasons: January, April, July and October.

4. A method for analyzing the causes of air leakage in a GIS busbar compartment according to claim 2, characterized in that: The relative displacement of the cabin includes the relative displacement of the two cabin sections, the displacement of the cabin relative to the ground, and the displacement of the cabin in horizontal and vertical deployment.

5. The method for analyzing the causes of air leakage in a GIS busbar compartment according to claim 1, characterized in that: The steps of performing mining analysis based on the acquired strongly correlated variables and using the improved FP-growth correlation analysis method to obtain the correlation rules of GIS busbar compartment air leakage include: Define item set content and build a database based on strongly correlated variables; Traverse the entire database, calculate the support of each item in each item set and compare it with the predetermined minimum support, delete the items with support less than the minimum support, and obtain a frequent item list; Based on the frequent item list, different sub-databases of welding seams, flange joint surfaces, circuit breakers, and sealing ring positions are constructed, arranged in descending order of support, and FP-tree is constructed; Based on the constructed FP-tree, a distributed parallel mining strategy is adopted to generate the initial correlation rules of GIS busbar compartment air leakage; Based on the initial association rules, the support of single and multiple independent variables is analyzed respectively, the correlation between single independent variable, multiple independent variable coupling and dependent variable is obtained, and the final association rules are obtained.

6. A method for analyzing the causes of air leakage in a GIS busbar compartment according to claim 5, characterized in that: The step of using the function mapping data storage structure to find and determine the support degree includes: The constructor performs one-to-one mapping, defines the logical address of the itemset, takes the itemset content as the independent variable and the itemset address as the dependent variable to find and determine the corresponding support.

7. A method for analyzing the causes of air leakage in a GIS busbar compartment according to claim 5, characterized in that: The steps of mining frequent item sets and association rules using a distributed parallel mining strategy include: The location where the frequency of a single gas leakage point in the GIS busbar compartment exceeds the preset frequency threshold is set as the main node, and the micro-meteorological data in the substation, the preset key parameters of the GIS busbar compartment, and the SF6 gas pressure are set as the sub-nodes of distributed mining; The main node collects the data of each child node. The child nodes are responsible for collecting and processing data in their respective fields. The frequent item mining algorithm is executed on the child nodes to find out the frequent item names in their respective fields. The main node receives the frequent item name table returned by each child node, and collects and integrates the data to determine the correlation strength by support and placement, and generate the initial association rules for GIS busbar compartment leakage.

8. A GIS busbar compartment air leakage cause analysis system, characterized in that: include: An information acquisition module is used to obtain the location information and status information of the leak point; wherein the status information of the leak point is continuous leakage or sudden transient leakage, which is obtained by judging the SF6 gas pressure at the leak point; The cause analysis module is used to analyze the cause of leakage based on the location information and status information of the leakage point and use the pre-acquired association rules to obtain the cause analysis results of the leakage in the GIS busbar compartment; The step of obtaining the association rule includes: Acquire multi-source historical data; wherein the multi-source historical data includes micro-meteorological data in the substation, preset key parameters of the GIS busbar compartment, and SF6 gas pressure; Based on the multi-source historical data, the principal component analysis method is used to obtain the strongly correlated variables of air leakage; Based on the acquired strongly correlated variables, the improved FP-growth correlation analysis method is used for mining and analysis to obtain the correlation rules of GIS busbar compartment air leakage; wherein, in the improved FP-growth correlation analysis method, a function mapping data storage structure is used to find and determine the support, and a distributed parallel mining strategy is used to mine frequent item sets and correlation rules.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for analyzing the cause of air leakage in the GIS busbar compartment according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing the cause of air leakage in a GIS busbar compartment according to any one of claims 1 to 7 is implemented.

Images