Information management system and management method for gas pipe network

Abstract

The application provides an information management system and method for a gas pipe network, relates to the technical field of information management, and performs key node analysis on key node set distribution characteristic information of the gas pipe network through a key node analysis module; an Internet of Things endpoint deployment module deploys the key node set; a fault identification module obtains a multi-dimensional operation data stream and identifies faults to obtain a node fault feature set; a risk parameter analysis module transmits the node fault feature set to an information management cloud center for integrated analysis to obtain fault risk parameters; and an operation and maintenance strategy analysis module analyzes the fault risk parameters to obtain target fault operation and maintenance strategy parameters. The application solves the technical problems of low fault troubleshooting efficiency and insufficient emergency response capability caused by the lack of precise monitoring means for the gas pipe network in the prior art, improves the real-time performance and accuracy of pipe network fault detection, and enhances the operation safety and reliability of the pipe network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information management, in particular to an information management system and method for a gas pipeline network. BACKGROUND

[0002] A gas pipeline network is an important part of urban infrastructure and undertakes the important task of natural gas transportation and distribution, providing energy security for residential life and industrial production. Due to the wide distribution and complex structure of the gas pipeline network, the pipeline network faces multiple risks such as pipeline aging, leakage and external damage during operation. The traditional management method of the gas pipeline network mainly relies on manual inspection and experience judgment, supplemented by basic detection methods such as flow judgment method, sound wave detection method and pressure point analysis method. However, manual inspection is inefficient and difficult to find hidden faults in time, and with the expansion of the pipeline network scale, the workload and difficulty of inspection are also increasing.

[0003] With the development of Internet of Things technology, sensors are widely used in the monitoring and management of gas pipeline networks, improving the data collection capability. However, the existing management methods usually adopt the way of laying sensors comprehensively for monitoring, although the coverage is wide, but the deployment and maintenance cost is too high, and due to the problem of data redundancy, it is difficult to focus on the key nodes of the pipeline network for in-depth analysis, which leads to the fact that the monitoring data cannot fully support accurate fault detection and risk assessment. At the same time, these methods generally lack intelligent analysis capability of data, and cannot provide optimized operation and maintenance strategy in time, which leads to insufficient emergency response capability and increases the safety risk of gas pipeline network operation. SUMMARY

[0004] The present application provides an information management system and method for a gas pipeline network, which solves the technical problem that the existing technology lacks precise monitoring and data analysis means for key nodes of the gas pipeline network, resulting in low fault troubleshooting efficiency and insufficient emergency response capability, and achieves the technical effect of improving the real-time and accuracy of fault detection of the gas pipeline network, thereby enhancing the safety and reliability of the pipeline network operation.

[0005] In view of the above problems, in one aspect, the present application provides an information management system for a gas pipeline network, the system comprising: a key node analysis module for obtaining gas pipeline network distribution characteristic information, performing key node analysis on the gas pipeline network distribution characteristic information, and obtaining M sets of gas pipeline network key nodes; an Internet of Things endpoint deployment module for sequentially deploying Internet of Things endpoints on the M sets of gas pipeline network key nodes to obtain M sets of key node Internet of Things endpoints, each endpoint in the M sets of key node Internet of Things endpoints comprising a sensor acquisition unit, a data communication unit, and a data analysis unit; a fault identification module for obtaining M sets of gas pipeline network multi-dimensional operation data streams through the sensor acquisition unit, performing fault identification on the M sets of gas pipeline network multi-dimensional operation data streams based on the data analysis unit, and obtaining K sets of node fault feature sets; a risk parameter analysis module for wirelessly transmitting the K sets of node fault feature sets to an information management cloud center for integrated analysis through the data communication unit, obtaining gas pipeline network fault risk parameters; and an operation and maintenance strategy analysis module for performing operation and maintenance strategy analysis on the gas pipeline network fault risk parameters, obtaining target fault operation and maintenance strategy parameters, and performing gas pipeline network operation and maintenance emergency management based on the target fault operation and maintenance strategy parameters.

[0006] In another aspect, the present application also provides an information management method for a gas pipeline network, the method comprising: obtaining gas pipeline network distribution characteristic information, performing key node analysis on the gas pipeline network distribution characteristic information, and obtaining M sets of gas pipeline network key nodes; sequentially deploying Internet of Things endpoints on the M sets of gas pipeline network key nodes to obtain M sets of key node Internet of Things endpoints, each endpoint in the M sets of key node Internet of Things endpoints comprising a sensor acquisition unit, a data communication unit, and a data analysis unit; obtaining M sets of gas pipeline network multi-dimensional operation data streams through the sensor acquisition unit, performing fault identification on the M sets of gas pipeline network multi-dimensional operation data streams based on the data analysis unit, and obtaining K sets of node fault feature sets; wirelessly transmitting the K sets of node fault feature sets to an information management cloud center for integrated analysis through the data communication unit, obtaining gas pipeline network fault risk parameters; performing operation and maintenance strategy analysis on the gas pipeline network fault risk parameters, obtaining target fault operation and maintenance strategy parameters, and performing gas pipeline network operation and maintenance emergency management based on the target fault operation and maintenance strategy parameters.

[0007] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] The key node analysis module obtains the gas pipe network distribution characteristic information to perform key node analysis, screens out M gas pipe network key node sets, and determines the most important and most prone to failure nodes in the pipe network. The Internet of Things endpoint deployment module sequentially deploys Internet of Things endpoints on the M gas pipe network key node sets to obtain M key node Internet of Things endpoint sets, avoids indiscriminate comprehensive deployment of sensors, significantly reduces deployment costs, and ensures that subsequent monitoring focuses on key areas, improving resource utilization efficiency. Each endpoint in the M key node Internet of Things endpoint sets includes a sensor acquisition unit, a data communication unit, and a data analysis unit, ensuring real-time acquisition of multi-dimensional pipe network operation data and enabling preliminary analysis of the data, enhancing the real-time and accuracy of pipe network monitoring. The fault identification module obtains M gas pipe network multi-dimensional operation data streams using the sensor acquisition unit and performs fault identification on the M gas pipe network multi-dimensional operation data streams based on the data analysis unit to obtain K node fault feature sets. Through intelligent analysis, potential faults in the pipe network are automatically identified, improving the timeliness and accuracy of fault detection and enabling early warning at the initial stage of a fault. The risk parameter analysis module wirelessly transmits the K node fault feature sets to the information management cloud center for integrated analysis through the data communication unit, enabling centralized processing of information and global assessment of risks. Through risk analysis, potential pipe network problems can be further accurately predicted, gas pipe network fault risk parameters are obtained, and the accuracy of risk assessment is improved. The operation and maintenance strategy analysis module analyzes the gas pipe network fault risk parameters to obtain target fault operation and maintenance strategy parameters and performs gas pipe network operation and maintenance emergency management based on the target fault operation and maintenance strategy parameters, enhancing the emergency response capability of the pipe network and ensuring that measures can be quickly and effectively taken to handle faults.

[0009] In summary, the present application realizes intelligent monitoring and management of the gas pipe network through key node analysis and accurate deployment of Internet of Things endpoints, improves the real-time and accuracy of fault detection, enhances the emergency response capability of the gas pipe network, and effectively reduces the time and cost of fault troubleshooting. At the same time, by analyzing the data to develop operation and maintenance strategies, potential risks can be warned in advance to prevent accidents, thereby significantly improving the operation safety and reliability of the gas pipe network and providing a strong guarantee for the stability of urban energy supply.

[0010] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the following specific embodiments of the present application can be implemented in accordance with the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1A structural schematic diagram of an information management system for a gas pipeline network is provided for the embodiments of the present application.

[0012] Figure 2 A flowchart for obtaining M sets of key nodes of a gas pipeline network in an information management system for a gas pipeline network is provided for the embodiments of the present application.

[0013] Figure 3 A flowchart for obtaining K sets of node fault characteristics in an information management system for a gas pipeline network is provided for the embodiments of the present application.

[0014] Figure 4 A flowchart of an information management method for a gas pipeline network is provided for the embodiments of the present application.

[0015] Legend: key node analysis module 10, Internet of Things endpoint deployment module 20, fault identification module 30, risk parameter analysis module 40, operation and maintenance strategy analysis module 50. DETAILED DESCRIPTION

[0016] The embodiments of the present application provide an information management system and method for a gas pipeline network, which solves the technical problem of low fault troubleshooting efficiency and insufficient emergency response capability due to the lack of precise monitoring and data analysis means for key nodes of a gas pipeline network in the prior art, and achieves the technical effects of improving the real-time performance and accuracy of fault detection of a gas pipeline network, thereby enhancing the operation safety and reliability of the pipeline network.

[0017] Embodiment one, as shown in the drawings, the embodiments of the present application provide an information management system for a gas pipeline network, the system comprises: Figure 1

[0018] A key node analysis module 10 is configured to obtain gas pipeline network distribution characteristic information, analyze the key nodes of the gas pipeline network distribution characteristic information, and obtain M sets of key nodes of the gas pipeline network.

[0019] Specifically, the gas pipeline network distribution characteristic information refers to the physical and operating characteristics of the gas pipeline network, including the layout of the pipeline network, the length, diameter, material, burial depth, pressure, flow rate, and other data of the pipeline. The key nodes are points that have a significant impact on the stability and safety of the gas pipeline network, such as intersection points, branch points, important valves, pressure regulating stations, etc.

[0020] ​Various basic information of the gas pipe network is collected, such as pipe layout in a geographic information system (GIS), pipe diameter data, node connection relationship, and the like, and operating parameter information of the pipe network, such as pressure, flow, and the like. The acquired distribution characteristic information is analyzed by using data mining and machine learning algorithms. For example, a clustering analysis algorithm is used to identify a node with larger flow and frequent pressure change as a key node according to the flow, pressure, and the like of the node; or a decision tree algorithm is used to find a node with higher fault occurrence frequency as a key node according to historical fault data. By analyzing the distribution characteristic information of the gas pipe network, M key nodes are determined to form a key node set. M is a positive integer and is used to represent the total number of key nodes. The key node set of the gas pipe network provides a precise target area for subsequent Internet of Things endpoint deployment, ensures reasonable allocation of sensor resources, avoids waste of resources at non-key nodes, and improves resource utilization efficiency.

[0021] The Internet of Things endpoint deployment module 20 is configured to sequentially deploy Internet of Things endpoints on the M key node sets of the gas pipe network to obtain M key node Internet of Things endpoint sets, each endpoint in the M key node Internet of Things endpoint sets including a sensor acquisition unit, a data communication unit, and a data analysis unit.

[0022] Specifically, the Internet of Things endpoint is an Internet of Things device installed at a key node and capable of real-time acquisition, transmission, and analysis of data, including a sensor acquisition unit, a data communication unit, and a data analysis unit. The sensor acquisition unit is responsible for real-time acquisition of various operating parameters of the key node, such as pressure, temperature, flow, and the like. The data communication unit is responsible for transmitting the acquired data to the information management cloud center through a wireless network. The data analysis unit is used to preliminarily analyze the acquired data to identify abnormal conditions. The M key node sets of the gas pipe network are sequentially deployed with Internet of Things endpoints, and an Internet of Things endpoint device is installed at each key node, each device including a sensor acquisition unit, a data communication unit, and a data analysis unit. The Internet of Things endpoint device at each key node forms an endpoint set, and M key node Internet of Things endpoint sets are obtained in total.

[0023] By deploying Internet of Things endpoints at key nodes, comprehensive perception and data acquisition of key parts of the gas pipe network are achieved, and an Internet of Things monitoring network of the gas pipe network is established to provide real-time data sources for fault identification and risk assessment.

[0024] The fault identification module 30 is configured to acquire M gas pipe network multi-dimensional operating data streams through the sensor acquisition unit and identify K node fault feature sets based on the data analysis unit.

[0025] Specifically, the multi-dimensional operation data stream refers to the operation data of the gas pipeline network obtained from the sensor acquisition unit, which contains multiple dimensions such as pressure, temperature, flow, etc. The node fault feature set is the fault node and its feature data set identified by the data analysis unit.

[0026] The sensor acquisition unit in the M key node Internet of Things endpoint set is called to collect various operation parameters of the key node in real time, forming a multi-dimensional operation data stream. These data streams contain various data types, such as pressure, flow, temperature, etc. For example, by calling the pressure sensor, temperature sensor and flow sensor installed at the key node, pressure data, temperature data and flow data are collected respectively, forming a data stream containing three dimensions of pressure, temperature and flow. The multi-dimensional operation data stream collected by the sensor acquisition unit of each endpoint is input into the data analysis unit of the endpoint for data analysis to identify abnormal conditions. The data analysis unit analyzes the input data stream according to historical data and predefined fault patterns to determine whether there is a fault feature, determine K fault nodes and their feature data set, and obtain K node fault feature sets. Wherein, K is a positive integer, representing the number of fault nodes identified by the data analysis unit, K is less than or equal to M. For example, by analyzing the multi-dimensional operation data stream of 5 key nodes, 3 fault nodes are determined, which are pipeline leakage, valve damage and pressure regulating station failure, forming a data set containing 3 node fault features.

[0027] Through fault identification, possible fault features can be identified from complex gas pipeline network operation data stream in a timely and accurate manner, improving the efficiency and accuracy of fault detection and providing a basis for subsequent risk assessment and operation strategy formulation.

[0028] The risk parameter analysis module 40 is used to wirelessly transmit the K node fault feature sets to the information management cloud center through the data communication unit for integrated analysis to obtain the gas pipeline network fault risk parameter.

[0029] Specifically, the fault risk parameter is obtained by integrated analysis of the node fault feature set, which is a parameter used to evaluate the risk of gas pipeline network failure.

[0030] After obtaining the K node fault feature sets, the data communication unit of the M endpoints is called to transmit the corresponding node fault feature sets to the information management cloud center in a wireless transmission mode (such as Wi-Fi, 4G or 5G wireless communication technology). In the information management cloud center, big data analysis and machine learning algorithms are used to integrate and analyze these fault feature sets. For example, a neural network algorithm is used to consider the feature data and historical data of each fault node to calculate the risk value of each node and perform risk sorting and classification to obtain the gas pipeline network fault risk parameter.

[0031] By acquiring the gas pipe network fault risk parameter, the fault risk of the gas pipe network is quantified, accurate risk assessment results are provided for operation and maintenance strategy analysis, operation and maintenance decisions are more scientific and reasonable, and the risk prevention and control capability is improved.

[0032] The operation and maintenance strategy analysis module 50 is configured to analyze the operation and maintenance strategy based on the gas pipe network fault risk parameter, obtain a target fault operation and maintenance strategy parameter, and perform gas pipe network operation and maintenance emergency management based on the target fault operation and maintenance strategy parameter.

[0033] Specifically, the target fault operation and maintenance strategy parameter is an operation and maintenance strategy parameter for a specific fault condition, which is used to guide the operation and maintenance emergency management of the gas pipe network. According to the gas pipe network fault risk parameter obtained by the risk parameter analysis module 40, in combination with the pre-established operation and maintenance strategy knowledge base, the operation and maintenance strategy is analyzed through rule matching or intelligent algorithm (such as decision tree algorithm), and the target fault operation and maintenance strategy parameter of the fault node is determined. According to these target fault operation and maintenance strategy parameters, the gas pipe network operation and maintenance emergency management is performed to deal with sudden failures. For example, if the risk parameter indicates that the fault risk of a certain node reaches a certain threshold, the corresponding strategy in the operation and maintenance strategy knowledge base may be to dispatch maintenance personnel for on-site inspection and maintenance, and to allocate corresponding resources according to the severity of the fault.

[0034] Through operation and maintenance strategy analysis, the target fault operation and maintenance strategy parameter is determined, the emergency response capability of the gas pipe network is improved, the probability of accidents is reduced, and the safe and stable operation of the gas pipe network is ensured.

[0035] Further, as shown in Figure 2 The key node analysis module 10 is further configured to perform the following steps:

[0036] Step P11: using GIS to perform entity extraction and topological modeling on the gas pipe network distribution characteristic information to obtain a gas pipe network visualization model.

[0037] Step P12: determining a preset grid size according to the gas pipe network information management requirement, and performing grid segmentation on the gas pipe network visualization model according to the preset grid size to obtain an initial grid node set.

[0038] Step P13: performing dynamic simulation based on the gas pipe network visualization model to obtain pipe network flow simulation information, pressure change simulation information, and pipe network leakage simulation information.

[0039] Step P14: performing key degree evaluation and screening on the initial grid node set based on the pipe network flow simulation information, pressure change simulation information, and pipe network leakage simulation information to obtain the M gas pipe network key node set.

[0040] Specifically, first, the gas pipe network distribution characteristic information (including pipe geographic coordinates, pipe diameter, node position, and other data) is input into the GIS. The GIS uses its data processing and analysis functions to perform entity extraction on this information, and identifies entities such as pipes and nodes. Then, according to the connection relationships between entities and other information, a topological model is built, and the topological structure of the gas pipe network is constructed, and finally a gas pipe network visualization model is obtained. This gas pipe network visualization model can intuitively show the layout and structural relationship of the gas pipe network. For example, through the GIS software, the topological structure of the pipe network is represented on the map as lines of different colors and thicknesses, intuitively showing the distribution of the gas pipe network.

[0041] The preset grid size is a grid size that is preset according to the gas pipe network information management requirement, and is used to segment the gas pipe network visualization model. The initial grid node set is a set containing all grid nodes obtained after grid segmentation. These nodes are the basis for subsequent key degree evaluation and screening. According to the management requirements of the gas pipe network, such as the monitoring accuracy requirements of different areas of the pipe network, the granularity of data analysis, and the like, a suitable preset grid size is determined. For example, for the gas pipe network in the urban center area, a smaller grid size, such as a 10m x 10m grid unit, needs to be set to improve the management precision; and for the pipe network in the suburban area, a larger grid size, such as a 100m x 100m grid unit, can be set. According to the preset grid size, the gas pipe network visualization model is subjected to grid processing, and the pipe network is divided into multiple grid units. Each grid unit corresponds to a node, which can be the vertex or the center position of the grid unit, and all grid nodes are aggregated to form the initial grid node set. By segmenting the gas pipe network visualization model, the complex gas pipe network can be divided into smaller management units, providing an ordered and discretized analysis object set for subsequent key degree evaluation and screening, and helping to more finely analyze the importance of each part of the gas pipe network.

[0042] The pipe network flow simulation information is simulation data about the flow of natural gas in the gas pipe network under different conditions (such as different time periods, different node usage, etc.) obtained through dynamic simulation; the pressure change simulation information is simulation data about the change of the pressure in the pipe with various factors; and the pipe network leakage simulation information is related information when the pipe network leaks, such as the leakage position, leakage amount, and influence on the pressure and flow of the pipe network. Using computer simulation technology, the dynamic changes of the flow, pressure, and leakage of the gas pipe network under different operating conditions are simulated. Exemplarily, the visual model of the gas pipe network and related operating parameters (such as initial flow, pressure set value, pipe material, and the like) can be input into fluid simulation software such as ANSYS Fluent and OpenFOAM. The software performs dynamic simulation of the gas pipe network according to the physical model and mathematical algorithm, calculates the flow and pressure change at each position of the gas pipe network under different operating conditions, simultaneously simulates the pipe network leakage and records related information, thereby obtaining the pipe network flow simulation information, the pressure change simulation information, and the pipe network leakage simulation information. These simulation information provides important data support for subsequent key degree assessment and screening, and can more accurately assess the importance of each node.

[0043] According to the pipe network flow simulation information, the pressure change simulation information, and the pipe network leakage simulation information, the nodes in the initial grid node set are assessed for key degree, and key nodes are screened out. For example, according to the flow simulation information, nodes with larger flow are identified; according to the pressure change simulation information, nodes with frequent pressure change or larger fluctuation are identified; and according to the pipe network leakage simulation information, nodes with higher leakage risk are identified. After assessment and screening, M key nodes are determined, forming a set of key nodes of the gas pipe network.

[0044] By constructing a visual model of the gas pipe network and performing dynamic simulation of the pipe network, key nodes in the gas pipe network can be accurately identified. These key nodes are key parts that affect the operation safety and stability of the gas pipe network, and key monitoring and management of them can improve the overall safety and reliability of the gas pipe network.

[0045] Further, step P11 includes:

[0046] Step P111: constructing a gas pipe network entity tag library, performing entity extraction on the gas pipe network distribution characteristic information based on the gas pipe network entity tag library, and obtaining a set of gas pipe network entities.

[0047] Step P112: obtaining gas pipe network entity attribute information, the gas pipe network entity attribute information including entity type, structure size, spatial position, and distribution direction.

[0048] Step P113: Attribute labeling of the gas pipeline network entities according to the obtained gas pipeline network entity attribute information.

[0049] Step P114: Creating an entity element symbol library and using GIS to perform topological modeling on the gas pipeline network entity attribute parameter set based on the entity element symbol library to obtain the gas pipeline network visualization model.

[0050] Specifically, the gas pipeline network entity label library is a predefined database containing label information for identifying different entities in the gas pipeline network, such as pipelines, valves, nodes, etc. These labels are a kind of classification identification of various entities in the gas pipeline network. First, an entity label library is constructed to define the labels and attributes of various gas pipeline network entities, such as pipelines, valves, pipeline access points, pressure regulating stations, etc. Based on the constructed gas pipeline network entity label library, various entities are identified from the gas pipeline network distribution characteristic information using GIS software, thereby obtaining the gas pipeline network entity set.

[0051] The gas pipeline network entity attribute information is related characteristic description information about the gas pipeline network entities, including entity type (whether it is a pipeline or a valve, etc.), structural size (such as the diameter and length of the pipeline, etc.), spatial position (coordinate position in geographic space), and distribution trend (whether the pipeline trend is straight or curved, and the starting point and end point of the pipeline, etc.). The attribute information is obtained by querying relevant design documents, databases, or field measurements, etc. For example, for a pipeline entity, its structural size (diameter, wall thickness, etc.) can be obtained from design drawings, its spatial position (coordinate information) can be obtained through GIS, and its distribution trend can be determined according to the overall layout, etc. These information provides detailed data support for subsequent attribute labeling and modeling.

[0052] Using the attribute labeling tool in GIS software, each entity in the gas pipeline network entity set is labeled according to the obtained gas pipeline network entity attribute information. For example, for a certain pipeline entity, its type is labeled as "pipeline", its diameter is 200mm, its length is 500m, its starting point coordinates are (x1, y1), its end point coordinates are (x2, y2), etc. After attribute labeling, a set containing all entities and their attribute information is obtained, which is the gas pipeline network entity attribute parameter set.

[0053] A symbol library of entity elements is created, and symbols corresponding to different gas pipe network entities (such as pipes, valves, etc.) are defined. Then, the set of entity attribute parameters of the gas pipe network and the symbol library of entity elements are input into the GIS. The GIS labels the entities in the set of entity attribute parameters of the gas pipe network according to the symbols in the symbol library of entity elements, and simultaneously performs topological modeling according to the connection relationships between the entities. For example, according to the information in the set of entity attribute parameters, the entities such as pipes, valves, and pressure regulating stations are labeled on the GIS map with corresponding symbols, and the connection relationships between them are established, forming a complete pipe network topology, and obtaining a visual model of the gas pipe network.

[0054] Through the construction of the entity tag library, the attribute marking, and the topological modeling, the visual display of the gas pipe network is realized, which provides an important basis and reference for subsequent steps such as grid segmentation, dynamic simulation, and key node analysis, making the analysis and management of the pipe network more intuitive and efficient.

[0055] Further, as shown in Figure 3 The fault identification module 30 is further used to perform the following steps:

[0056] Step P31: respectively performing associated feature extraction on the M gas pipe network multi-dimensional operation data streams to obtain M sets of gas pipe network associated operation features.

[0057] Step P32: performing correlation analysis and feature selection on the M sets of gas pipe network associated operation features to determine M sets of key operation features of the gas pipe network.

[0058] Step P33: acquiring, by the data analysis unit, M key node fault analysis trees of the M sets of key node Internet of Things endpoint sets.

[0059] Step P34: performing fault identification integration on the M sets of key operation features of the gas pipe network based on the M key node fault analysis trees to obtain the K sets of node fault features.

[0060] Specifically, for each gas pipeline network multi-dimensional operation data stream, a data mining algorithm (such as an association rule mining algorithm, such as the Apriori algorithm) is used for association feature extraction, and the association features are discovered by analyzing the frequent patterns between different variables in the data stream. For example, input the operation data stream containing pressure, flow, temperature and other data into the Apriori algorithm, and the algorithm will find the internal relationship between different dimensions of data, such as the proportional relationship between pressure change and flow change. M gas pipeline network multi-dimensional operation data streams are respectively subjected to association feature extraction, and M gas pipeline network association operation feature sets are obtained. Each association operation feature set corresponds to an operation data stream of a gas pipeline network, and the features in these sets reflect the association relationship between variables in the operation of the gas pipeline network, providing rich feature data support for subsequent fault identification.

[0061] The gas pipeline network key operation feature set is obtained after correlation analysis and feature selection, and contains the most critical operation features for gas pipeline network fault identification. For M gas pipeline network association operation feature sets, correlation analysis is performed using statistical analysis software to calculate the correlation coefficients (such as Pearson correlation coefficient, Spearman rank correlation coefficient, etc.) between features to determine the correlation between features. Then, according to the correlation results, feature selection is performed to select the key features most useful for fault identification, and the key operation feature set of M gas pipeline networks is determined. For example, if two features are highly correlated (correlation coefficient close to 1 or -1), and one of them has less contribution to fault identification, the more representative feature is selected to determine the key operation feature set of M gas pipeline networks. Through correlation analysis and feature selection, redundant or unimportant features are removed, reducing the complexity of data processing and improving the efficiency and accuracy of fault identification.

[0062] The key node fault analysis tree is a hierarchical fault analysis model used to represent different fault modes and their possible causes in the pipeline network. Using the data analysis unit in the Internet of Things endpoint, the key node fault analysis tree is constructed through pre-defined algorithms and models. These algorithms and models can be established based on historical fault data, expert experience, etc. For example, based on past gas pipeline network fault records, the relationship between pressure anomalies, flow anomalies and node faults is summarized, and a tree structure is constructed to obtain M key node fault analysis trees. The construction of the key node fault analysis tree provides a structured analysis framework for fault identification, which helps to systematically analyze the possible fault conditions of the key node.

[0063] The M key node fault analysis trees and the M key operation feature sets of gas pipe networks are taken as inputs, the key operation feature sets are analyzed according to the logical structure of the fault analysis trees, and K node fault feature sets are obtained. The fault identification and integration of the key operation feature sets based on the key node fault analysis trees can accurately identify the nodes that may exist faults and the fault features, thereby providing key input information for subsequent risk parameter analysis and operation and maintenance strategy analysis.

[0064] Further, step P33 comprises:

[0065] Step P331: acquiring, by the data analysis unit, M key node fault operation feature sets of the M key node Internet of Things endpoint sets.

[0066] Step P332: top event extraction is performed on the M key node fault operation feature sets respectively, and M key node fault top events are determined.

[0067] Step P333: based on the M key node fault top events, logical step-by-step decomposition is performed on the M key node fault operation data sets, and M key node fault event logic gates are determined.

[0068] Step P334: based on the M key node fault event logic gates, cascade construction optimization is performed on the M key node fault operation feature sets, M key node fault analysis trees are obtained, and the data analysis unit is stored.

[0069] Specifically, the key node fault operation feature set is a feature set related to the operation of the fault node, which contains various information related to the fault of the key node during operation, such as pressure fluctuation range, flow rate change rate, temperature abnormality, etc. The data analysis unit is connected with the sensor acquisition unit in the Internet of Things endpoint to acquire the data collected by the sensor about the M key node Internet of Things endpoint set. These data include various fault operation related information, such as pressure, flow, temperature, etc. Then, the data analysis unit sorts and extracts features from these data, such as calculating the fluctuation amplitude of pressure, the change trend of flow, etc., thereby obtaining the M key node fault operation feature set.

[0070] The key node fault top event is the most critical event in the key node fault and is the starting point for constructing the fault analysis tree. For each key node fault operating feature set, the importance and relevance of each feature in the feature set to the fault are analyzed, and expert experience or data analysis algorithms (such as rule-based algorithms) are used for top event extraction. For example, if a feature indicates that the pressure at the node suddenly drops to zero, and this situation is one of the most serious situations in the past fault cases, then the "node pressure drops to zero" is extracted as the top event. Through the above top event extraction operation, the top event of each node is determined node by node, and M key node fault top events are obtained.

[0071] The key node fault event logic gate refers to the logical relationship between the fault events, such as an "and gate" indicating that the output event occurs only when all input events occur, and an "or gate" indicating that the output event occurs as long as one input event occurs. According to the M key node fault top events determined, the corresponding key node fault operating data set is logically decomposed level by level, i.e., on the basis of the top event, the top event is analyzed level by level according to the causal chain of the fault occurrence, the top event is decomposed into multiple sub-events, and the sub-events are further decomposed into lower-level sub-events, and so on, to clarify the causal relationship and logical relationship between the events. This process can be based on the basic principles of fault tree analysis (FTA), by analyzing historical fault data, expert knowledge, etc., to determine the logical relationship between the sub-events, thereby determining the M key node fault event logic gates to clarify the logical relationship between the fault events.

[0072] Based on the M key node fault event logic gates, the M key node fault operating feature set is cascaded and constructed. In the construction process, the features and events are connected according to the relationship of the logic gates to form a tree structure. At the same time, the constructed fault analysis tree is optimized to remove redundant logical branches and simplify complex logical relationships, and finally M key node fault analysis trees are obtained and stored in the data analysis unit.

[0073] The fault analysis tree constructed through the above steps comprehensively and accurately describes the potential fault modes of each node, providing an intuitive and effective analysis tool for subsequent fault diagnosis and improving the accuracy and efficiency of fault identification.

[0074] Further, the risk parameter analysis module 40 of the embodiment of the present application is further used to perform the following steps:

[0075] Step P41: Obtain a gas pipe network fault risk data set through the information management cloud center, and train the gas pipe network fault risk data set according to the M key node set of the gas pipe network to obtain M key node fault risk analysis networks.

[0076] Step P42: Perform fault risk impact analysis on the M sets of key nodes of the gas pipe network to obtain M key node impact factor information.

[0077] Step P43: Based on the M key node impact factor information, integrate and fuse the M key node fault risk analysis networks to generate a fault risk analysis adaptive network.

[0078] Step P44: Based on the fault risk analysis adaptive network, perform integrated analysis on the K sets of node fault characteristics to obtain the gas pipe network fault risk parameters.

[0079] Specifically, the information management cloud center obtains a gas pipe network fault risk data set from historical fault records, sensor data and other sources. The gas pipe network fault risk data set is a collection of risk data of the gas pipe network under different conditions, including the frequency of failure, the range of influence, the degree of loss, and other information. The fault risk data set is divided according to the M sets of key nodes of the gas pipe network, and the data of each key node is trained to obtain key node fault risk analysis networks for different nodes. These key node fault risk analysis networks can be constructed based on neural networks, decision trees and other machine learning algorithms, and can predict the fault risk of the node according to the input node fault characteristic data. For example, for each key node after shunting, the fault risk data subset is trained using a neural network, the structure of the network (such as the number of nodes in the input layer, hidden layer and output layer) is set, the training parameters (such as learning rate, number of iterations) are set, and M key node fault risk analysis networks are obtained after iterative training.

[0080] Key node impact factor information is information describing various factors that affect the key node fault on the gas pipe network, such as the size of the influence range, the degree of influence, etc. For the M sets of key nodes of the gas pipe network, by analyzing the geographical location, connection relationship, importance of the supply area and other factors of each node, the fault risk impact analysis is performed to determine the possible impact of each key node on the entire gas pipe network when it fails, including the influence range, the degree of influence and other factors. For example, for a key node located in the city center, due to the high population density and large gas supply influence range, its impact factor may be high; while for a node connected to fewer pipelines, its fault risk impact is relatively small. Through fault risk impact analysis, the impact factor information of the M key nodes is obtained.

[0081] Based on the influencing factor information of M key nodes, the fault risk analysis networks of these M key nodes are integrated and fused. A weighted fusion method can be used, that is, different weights are assigned to each key node fault risk analysis network according to the magnitude of the influencing factor, with the fault risk analysis network corresponding to the key node with a larger influencing factor being given a larger weight during integration. In this way, the various networks are combined and optimized to generate an adaptive fault risk analysis network. This adaptive fault risk analysis network integrates the advantages of each key node fault risk analysis network and can adaptively adjust the analysis strategy according to different fault characteristic data, accurately predicting the fault risk of the gas pipeline network.

[0082] The fault feature sets of K nodes are input into an adaptive network for fault risk analysis. The network performs integrated analysis on these fault feature sets based on its internal algorithms and structure. For example, the network calculates fault risk parameters for the gas pipeline network, such as the probability of fault occurrence and the potential impact range of the fault, based on different fault characteristics and their relationship with key nodes.

[0083] By constructing an adaptive network for fault risk analysis, a comprehensive assessment of the overall fault risk of the gas pipeline network was achieved, providing a quantitative basis for the analysis of operation and maintenance strategies and enhancing the dynamic risk adaptability and operation and maintenance decision support capabilities of the gas pipeline network.

[0084] Furthermore, in this embodiment of the application, the operation and maintenance strategy parsing module 50 is also used to perform the following steps:

[0085] Step P51: Analyze the operation and maintenance strategy of the gas pipeline network fault risk parameters to obtain the target fault operation and maintenance strategy, and construct the fault operation and maintenance strategy space based on the target fault operation and maintenance strategy.

[0086] Step P52: Fit the fault operation and maintenance effect evaluation function, and randomly select multiple fault operation and maintenance strategy parameters within the fault operation and maintenance strategy space.

[0087] Step P53: Use the fault operation and maintenance effect evaluation function to evaluate the effect of the multiple fault operation and maintenance strategy parameters, and obtain the fitness of the multiple fault operation and maintenance strategy parameters.

[0088] Step P54: Based on the fitness of the multiple fault operation and maintenance strategy parameters, perform cross-mutation expansion and global comparison optimization on the multiple fault operation and maintenance strategy parameters to determine the target fault operation and maintenance strategy parameters.

[0089] Specifically, according to the gas pipeline network fault risk parameters, combined with the operation requirements, safety standards, cost constraints and other factors of the gas pipeline network, the operation and maintenance strategy is analyzed, and the best operation and maintenance scheme in the historical case is extracted as the target fault operation and maintenance strategy. The target fault operation and maintenance strategy is a preliminary maintenance and operation strategy framework formulated for the gas pipeline network fault risk situation. Based on the target fault operation and maintenance strategy, the value range of each possible strategy parameter (such as the number of maintenance personnel, the type of maintenance equipment, the maintenance time arrangement, etc.) is determined, thereby constructing a fault operation and maintenance strategy space and determining the range of subsequent optimal fault operation and maintenance strategy parameters.

[0090] The historical operation and maintenance data are analyzed to determine various factors (such as maintenance cost, maintenance efficiency, and impact on users) affecting the fault operation and maintenance effect, and a fault operation and maintenance effect evaluation function is established based on a multi-objective optimization algorithm. For example, the weighted sum of the quantitative values of maintenance cost, maintenance time and user impact can be obtained to obtain a comprehensive evaluation value. At the same time, in the fault operation and maintenance strategy space, a plurality of fault operation and maintenance strategy parameters are randomly selected by using a random number generator and the like. These parameters represent different fault operation and maintenance strategies.

[0091] The plurality of fault operation and maintenance strategy parameters randomly selected are substituted into the fault operation and maintenance effect evaluation function for calculation to determine the fault operation and maintenance strategy parameter fitness corresponding to each fault operation and maintenance strategy parameter. The higher the fitness, the more the strategy parameter meets the requirements and is more effective in solving the gas pipeline network fault operation and maintenance problem.

[0092] According to the fitness of the plurality of fault operation and maintenance strategy parameters, a genetic algorithm or a similar optimization algorithm is used for cross variation expansion. For example, the fault operation and maintenance strategy parameters with higher fitness are selected for cross operation to exchange their partial strategy parameter values, and mutation operation is performed to randomly change some strategy parameter values to expand the diversity of the strategy parameters. Then, the expanded fault operation and maintenance strategy parameters are compared in the global range to find the strategy parameter with the highest fitness, which is determined as the target fault operation and maintenance strategy parameter.

[0093] Through operation and maintenance strategy analysis and optimization, the target fault operation and maintenance strategy parameter is determined, the optimal or near-optimal strategy parameter in the fault operation and maintenance strategy space is found, the fault handling effect is optimized, and the gas pipeline network fault operation and maintenance efficiency and pipeline network operation safety are improved.

[0094] In summary, the information management system for the gas pipeline network provided by the embodiments of the present application has the following technical effects:

[0095] The key node analysis module 10 uses GIS technology to perform entity extraction and topological modeling on the gas pipe network, constructs a visual model of the gas pipe network, and accurately identifies a key node set through dynamic simulation simulation and key degree evaluation screening. This step provides a precise target area for subsequent monitoring and management, optimizes resource allocation, and improves the pertinence and accuracy of monitoring. Next, the Internet of Things endpoint deployment module 20 deploys Internet of Things endpoints at the key nodes, collects multi-dimensional operation data in real time, and provides a rich data basis for fault identification and risk assessment. The fault identification module 30 accurately identifies fault nodes and their characteristics through correlation feature extraction, correlation analysis, and fault analysis tree construction, providing a reliable basis for risk assessment and operation strategy formulation. The risk parameter analysis module 40 uses data from the information management cloud center to generate a fault risk analysis adaptive network through shunt training, fault risk impact analysis, and integrated fusion, comprehensively assesses the fault risk of the gas pipe network, and provides early warning of potential risks. Finally, the operation strategy analysis module 50 determines the optimal fault operation strategy parameters through operation strategy analysis, effect evaluation function fitting, and global comparison optimization, guides the operation and emergency management of the gas pipe network, improves the emergency response capability, and reduces the probability of accidents.

[0096] Overall, the embodiments of the present application realize intelligent monitoring and management of the gas pipe network, not only improving the real-time and accuracy of fault detection, but also enhancing the emergency response capability of the gas pipe network, effectively reducing the time and cost of fault troubleshooting. At the same time, by analyzing the data to formulate operation and maintenance strategies, potential risks can be warned in advance to prevent accidents, thereby significantly improving the operation safety and reliability of the gas pipe network, providing a strong guarantee for the stability of urban energy supply.

[0097] Embodiment two, as shown in the figure, the embodiments of the present application provide an information management method for a gas pipe network, the method comprising: Figure 4

[0098] Step S1: Obtain the distribution characteristic information of the gas pipe network, analyze the key nodes of the distribution characteristic information of the gas pipe network, and obtain M key node sets of the gas pipe network.

[0099] Step S2: Deploy Internet of Things endpoints on the M key node sets of the gas pipe network in turn to obtain M key node Internet of Things endpoint sets, each endpoint in the M key node Internet of Things endpoint sets includes a sensor acquisition unit, a data communication unit and a data analysis unit.

[0100] Step S3: Obtain M multi-dimensional operation data streams of the gas pipe network through the sensor acquisition unit, and perform fault identification on the M multi-dimensional operation data streams of the gas pipe network based on the data analysis unit to obtain K node fault feature sets. ​

[0101] Step S4: transmitting the K node fault feature set to the information management cloud center through the data communication unit for integrated analysis to obtain a gas pipeline network fault risk parameter.

[0102] Step S5: analyzing the gas pipeline network fault risk parameter to obtain a target fault operation and maintenance strategy parameter, and performing gas pipeline network operation and maintenance emergency management based on the target fault operation and maintenance strategy parameter.

[0103] Further, the step S1 of the embodiment of the application comprises:

[0104] The GIS is used to perform entity extraction and topological modeling on the gas pipeline network distribution characteristic information to obtain a gas pipeline network visualization model; a preset grid size is determined according to the gas pipeline network information management requirement, the gas pipeline network visualization model is divided into grids according to the preset grid size to obtain an initial grid node set; dynamic simulation is performed based on the gas pipeline network visualization model to obtain pipeline network flow simulation information, pressure change simulation information and pipeline network leakage simulation information; the initial grid node set is evaluated and screened based on the pipeline network flow simulation information, pressure change simulation information and pipeline network leakage simulation information to obtain the M gas pipeline network key node set.

[0105] Further, the gas pipeline network visualization model comprises:

[0106] A gas pipeline network entity label library is constructed, the gas pipeline network distribution characteristic information is extracted based on the gas pipeline network entity label library to obtain a gas pipeline network entity set; gas pipeline network entity attribute information is obtained, the gas pipeline network entity attribute information comprises entity type, structure size, spatial position and distribution direction; the gas pipeline network entity set is marked with attributes according to the gas pipeline network entity attribute information to obtain a gas pipeline network entity attribute parameter set; an entity element symbol library is created, and the gas pipeline network entity attribute parameter set is labeled and topologically modeled based on the entity element symbol library by using the GIS to obtain the gas pipeline network visualization model.

[0107] Further, the step S3 of the embodiment of the application comprises:

[0108] The M gas pipeline network multi-dimensional operation data streams are respectively extracted for associated features to obtain M gas pipeline network associated operation feature sets; the M gas pipeline network associated operation feature sets are analyzed for correlation and features are selected to determine M gas pipeline network key operation feature sets; M key node fault analysis trees of the M key node Internet of Things endpoint sets are obtained through the data analysis unit; the M gas pipeline network key operation feature sets are integrated for fault recognition based on the M key node fault analysis trees to obtain the K node fault feature set.

[0109] Further, the M key node fault analysis trees of the M key node Internet of Things endpoint sets are acquired by the data analysis unit, including:

[0110] The M key node fault operation feature sets of the M key node Internet of Things endpoint sets are collected by the data analysis unit; top event extraction is performed on the M key node fault operation feature sets respectively to determine M key node fault top events; the M key node fault operation data sets are logically decomposed level by level based on the M key node fault top events to determine M key node fault event logic gates; the M key node fault operation feature sets are cascaded and constructed based on the M key node fault event logic gates to obtain M key node fault analysis trees and store them to the data analysis unit.

[0111] Further, the step S4 of the embodiment of the application includes:

[0112] The gas pipe network fault risk data set is acquired by the information management cloud center, and the gas pipe network fault risk data set is shunted and trained according to the M gas pipe network key node sets to obtain M key node fault risk analysis networks; the M gas pipe network key node sets are analyzed for fault risk influence to obtain M key node influence factor information; the M key node fault risk analysis networks are integrated and fused based on the M key node influence factor information to generate a fault risk analysis adaptive network; the K node fault feature sets are analyzed based on the fault risk analysis adaptive network to obtain the gas pipe network fault risk parameters.

[0113] Further, the step S5 of the embodiment of the application includes:

[0114] The gas pipe network fault risk parameters are analyzed for operation and maintenance strategy to obtain a target fault operation and maintenance strategy, and a fault operation and maintenance strategy space is constructed based on the target fault operation and maintenance strategy; a fault operation and maintenance effect evaluation function is fitted to obtain, and multiple fault operation and maintenance strategy parameters are randomly selected in the fault operation and maintenance strategy space; the multiple fault operation and maintenance strategy parameters are evaluated for effect by using the fault operation and maintenance effect evaluation function to obtain multiple fault operation and maintenance strategy parameter fitness; the multiple fault operation and maintenance strategy parameters are cross-variation expanded and globally compared and optimized based on the multiple fault operation and maintenance strategy parameter fitness to determine the target fault operation and maintenance strategy parameters.

[0115] The foregoing detailed description of the information management system for gas pipeline network has enabled those skilled in the art to clearly understand the information management method for gas pipeline network in the embodiment. For the method disclosed in Embodiment Two, since it corresponds to the system disclosed in Embodiment One, it has corresponding execution steps and beneficial effects. For the relevant parts, refer to the system part description.

[0116] The foregoing description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information management system for a gas pipeline network, characterized in that, The system comprises: a key node analysis module, configured to acquire gas pipe network distribution characteristic information, perform key node analysis on the gas pipe network distribution characteristic information, and obtain M sets of gas pipe network key nodes; an Internet of Things endpoint deployment module, configured to sequentially perform Internet of Things endpoint deployment on the M sets of gas pipe network key nodes to obtain M sets of key node Internet of Things endpoints, each endpoint in the M sets of key node Internet of Things endpoints comprising a sensor acquisition unit, a data communication unit and a data analysis unit; a fault identification module, configured to acquire M sets of gas pipe network multi-dimensional operation data streams through the sensor acquisition unit, perform fault identification on the M sets of gas pipe network multi-dimensional operation data streams based on the data analysis unit, and obtain K sets of node fault feature sets; a risk parameter analysis module, configured to wirelessly transmit the K sets of node fault feature sets to an information management cloud center through the data communication unit for integrated analysis to obtain a gas pipe network fault risk parameter; an operation and maintenance strategy analysis module, configured to perform operation and maintenance strategy analysis on the gas pipe network fault risk parameter, obtain a target fault operation and maintenance strategy parameter, and perform gas pipe network operation and maintenance emergency management based on the target fault operation and maintenance strategy parameter; the risk parameter analysis module is further configured to perform the following steps: acquire a gas pipe network fault risk data set through the information management cloud center, perform shunt training on the gas pipe network fault risk data set according to the M sets of gas pipe network key nodes to obtain M key node fault risk analysis networks; perform fault risk influence analysis on the M sets of gas pipe network key nodes to obtain M key node influence factor information; integrate and fuse the M key node fault risk analysis networks based on the M key node influence factor information to generate a fault risk analysis adaptive network; perform integrated analysis on the K sets of node fault feature sets based on the fault risk analysis adaptive network to obtain the gas pipe network fault risk parameter; the operation and maintenance strategy analysis module is further configured to perform the following steps: perform operation and maintenance strategy analysis on the gas pipe network fault risk parameter to obtain a target fault operation and maintenance strategy, and construct a fault operation and maintenance strategy space based on the target fault operation and maintenance strategy; fit to obtain a fault operation and maintenance effect evaluation function, and randomly select a plurality of fault operation and maintenance strategy parameters in the fault operation and maintenance strategy space; evaluate the plurality of fault operation and maintenance strategy parameters by using the fault operation and maintenance effect evaluation function to obtain a plurality of fault operation and maintenance strategy parameter fitness; based on the plurality of fault operation and maintenance strategy parameter fitness, perform cross variation expansion and global comparison optimization on the plurality of fault operation and maintenance strategy parameters to determine the target fault operation and maintenance strategy parameter.

2. A system for information-based management of a gas distribution network according to claim 1, characterized in that, the key node analysis module is further configured to perform the following steps: perform entity extraction and topological modeling on the gas pipe network distribution characteristic information by using GIS to obtain a gas pipe network visualization model; determine a preset grid size according to a gas pipe network information management requirement, perform grid segmentation on the gas pipe network visualization model according to the preset grid size to obtain an initial grid node set, and Performing dynamic simulation based on the gas pipe network visualization model to obtain pipe network flow simulation information, pressure change simulation information and pipe network leakage simulation information; Performing key degree evaluation and screening on the initial grid node set based on the pipe network flow simulation information, pressure change simulation information and pipe network leakage simulation information to obtain the M gas pipe network key node set.

3. A system for information-based management of a gas distribution network according to claim 2, characterized in that, The key node analysis module is further configured to perform the following steps: Building a gas pipe network entity tag library, performing entity extraction on the gas pipe network distribution characteristic information based on the gas pipe network entity tag library, and obtaining a gas pipe network entity set; Obtaining gas pipe network entity attribute information, which includes entity type, structure size, spatial position and distribution direction; Marking the gas pipe network entity set with attributes according to the gas pipe network entity attribute information to obtain a gas pipe network entity attribute parameter set; Creating an entity element symbol library, and using GIS to perform annotation topology modeling on the gas pipe network entity attribute parameter set based on the entity element symbol library to obtain the gas pipe network visualization model.

4. The information management system for a gas pipeline network according to claim 1, wherein The fault identification module is further configured to perform the following steps: Respectively extracting associated features from the M gas pipe network multi-dimensional operation data streams to obtain M gas pipe network associated operation feature sets; Performing correlation analysis and feature selection on the M gas pipe network associated operation feature sets to determine M gas pipe network key operation feature sets; Obtaining M key node fault analysis trees of the M key node Internet of Things endpoint sets through the data analysis unit; Performing fault identification and integration on the M gas pipe network key operation feature sets based on the M key node fault analysis trees to obtain the K node fault feature sets.

5. A system for information-based management of a gas distribution network according to claim 4, characterized in that, The fault identification module is further configured to perform the following steps: Collecting M key node fault operation feature sets of the M key node Internet of Things endpoint sets through the data analysis unit; Respectively extracting top events from the M key node fault operation feature sets to determine M key node fault top events; Performing logical step-by-step decomposition on the M key node fault operation data sets based on the M key node fault top events to determine M key node fault event logic gates; Performing cascade construction and optimization on the M key node fault operation feature sets based on the M key node fault event logic gates to obtain M key node fault analysis trees and store them in the data analysis unit.

6. A method for information management of a gas pipeline network, characterized in that, The method is performed by the information management system for gas pipe networks of any one of claims 1-5, comprising: Obtaining gas pipe network distribution characteristic information, performing key node analysis on the gas pipe network distribution characteristic information, and obtaining M gas pipe network key node sets; Respectively deploying Internet of Things endpoints on the M gas pipe network key node sets to obtain M key node Internet of Things endpoint sets, each endpoint in the M key node Internet of Things endpoint sets including a sensor collection unit, a data communication unit and a data analysis unit; M multi-dimensional operation data streams of the gas pipe network are acquired by the sensor acquisition unit, fault identification is performed on the M multi-dimensional operation data streams of the gas pipe network respectively based on the data analysis unit, and K node fault feature sets are obtained; The K node fault feature sets are wirelessly transmitted to an information management cloud center for integrated analysis by the data communication unit, and a gas pipe network fault risk parameter is obtained; The gas pipe network fault risk parameter is analyzed for operation and maintenance strategy, target fault operation and maintenance strategy parameters are obtained, and gas pipe network operation and maintenance emergency management is performed based on the target fault operation and maintenance strategy parameters.

Images