Gas pipeline accident disaster monitoring and management method and system based on knowledge graph

Abstract

The present invention provides a gas pipeline accident disaster monitoring and management method and system based on knowledge graph, which relates to the field of data intelligent analysis technology, collects multi-dimensional data of gas pipeline network and constructs pipeline network knowledge graph, monitors and obtains pipeline network monitoring data, inputs the data into the pipeline network knowledge graph for relevant data analysis and extraction, constructs an analysis data relationship network, constructs an accident assessment model and combines the pipeline network monitoring data to obtain accident assessment information, conducts a global analysis of the gas pipeline network to determine the global early warning information of the pipeline network, and solves the technical problems that the supervision methods for gas pipeline accidents and disasters in the existing technology are relatively conventional, the coverage of prediction analysis is not complete, and the data processing method is not rigorous enough, resulting in insufficient accuracy of the final accident prediction results, causing potential risks to affect management efficiency. By constructing a complete pipeline network system, correlation node analysis is performed based on influencing factors to determine comprehensive impact information and ensure the comprehensiveness and accuracy of accident prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent data analysis, and in particular to a knowledge graph-based gas pipeline accident and disaster monitoring and management method and system. Background Art

[0002] Gas is the transmission medium in the gas pipeline network. If gas leaks, it may cause risk accidents such as fire and explosion. At the same time, the gas pipeline network has a wide coverage and complex interlaced structure, which leads to uncontrollable dangerous sources. The safety prevention and control of accidents is the current key issue to be solved.

[0003] Currently, pipeline safety risks are primarily identified through operational data monitoring or regular manual inspections to facilitate emergency response. Current regulatory approaches are relatively traditional, inevitably leading to omissions and irreversible consequences. Further updating and optimization of current regulatory approaches are needed to improve their effectiveness.

[0004] In existing technologies, the supervision methods for gas pipeline accidents and disasters are relatively conventional, the coverage of predictive analysis is not complete, and the data processing method is not rigorous enough, resulting in insufficient accuracy of the final accident prediction results, causing potential risks that affect management efficiency. Summary of the Invention

[0005] This application provides a gas pipeline accident disaster monitoring and management method and system based on knowledge graph, which is used to solve the technical problems in the existing technology that the supervision methods for gas pipeline accident disasters are relatively conventional, the coverage of prediction analysis is not complete, and the data processing method is not rigorous enough, resulting in insufficient accuracy of the final accident prediction results, causing potential risks affecting management efficiency.

[0006] In view of the above problems, this application provides a gas pipeline accident disaster monitoring and management method and system based on knowledge graph.

[0007] In a first aspect, the present application provides a method for monitoring and managing gas pipeline accidents and disasters based on a knowledge graph, the method comprising:

[0008] Collect data on gas transmission, connection equipment, transmission nodes, and laying locations of the gas pipeline network to obtain multi-dimensional data of the gas pipeline network;

[0009] Constructing a pipeline network knowledge graph based on the multi-dimensional data of the gas pipeline network;

[0010] Monitor the gas pipeline network through data monitoring equipment to obtain pipeline network monitoring data;

[0011] Inputting the pipe network monitoring data into the pipe network knowledge graph, performing relevant data analysis and extraction, and constructing an analysis data relationship network;

[0012] Based on the analysis data relationship network, an accident assessment model is constructed, and accident assessment information is obtained according to the pipeline network monitoring data and the accident assessment model;

[0013] Based on the accident assessment information and the pipeline network knowledge graph, a global analysis of the gas pipeline network is performed to determine the global early warning information of the pipeline network.

[0014] In a second aspect, the present application provides a gas pipeline accident and disaster monitoring and management system based on a knowledge graph, the system comprising:

[0015] A data acquisition module is used to collect data on the gas pipeline network, including transmission gas, connection equipment, transmission nodes, and laying locations, to obtain multi-dimensional data of the gas pipeline network;

[0016] A graph construction module, the graph construction module is used to construct a pipeline network knowledge graph based on the multi-dimensional data of the gas pipeline network;

[0017] A data monitoring module, which is used to monitor the gas pipeline network through data monitoring equipment to obtain pipeline network monitoring data;

[0018] A relationship network construction module, which is used to input the pipeline network monitoring data into the pipeline network knowledge graph, perform relevant data analysis and extraction, and construct an analysis data relationship network;

[0019] An accident assessment module, configured to construct an accident assessment model based on the analysis data relationship network, and obtain accident assessment information based on the pipe network monitoring data and the accident assessment model;

[0020] The pipeline network early warning module is used to perform a global analysis of the gas pipeline network based on the accident assessment information and the pipeline network knowledge graph, and determine the global early warning information of the pipeline network.

[0021] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0022] The knowledge graph-based gas pipeline accident and disaster monitoring and management method provided in the embodiment of the present application collects data on gas transmission, connection equipment, transmission nodes, and laying locations of the gas pipeline network to obtain multi-dimensional data of the gas pipeline network and construct a pipeline network knowledge graph; the gas pipeline network is monitored by data monitoring equipment to obtain pipeline network monitoring data, which is input into the pipeline network knowledge graph for relevant data analysis and extraction to construct an analysis data relationship network; an accident assessment model is constructed based on the analysis data relationship network, and accident assessment information is obtained based on the pipeline network monitoring data and the accident assessment model; based on the accident assessment information and the pipeline network knowledge graph, a global analysis of the gas pipeline network is performed to determine global pipeline network warning information, thereby solving the technical problem that the existing supervision methods for gas pipeline accidents and disasters are relatively conventional, the coverage of prediction analysis is not complete, and the data processing method is not rigorous enough, resulting in insufficient accuracy of the final accident prediction results, causing potential risks to affect management efficiency. By constructing a complete pipeline network system, correlation node analysis is performed based on influencing factors to determine comprehensive influencing information, thereby ensuring the comprehensiveness and accuracy of accident prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flow chart of the gas pipeline accident and disaster monitoring and management method based on knowledge graph is provided for this application;

[0024] Figure 2 A schematic diagram of the pipeline network knowledge graph construction process in the gas pipeline accident disaster monitoring and management method based on the knowledge graph is provided for this application;

[0025] Figure 3 A schematic diagram of the process of constructing an accident assessment model in a gas pipeline accident disaster monitoring and management method based on a knowledge graph is provided for this application;

[0026] Figure 4 A structural diagram of a gas pipeline accident and disaster monitoring and management system based on a knowledge graph is provided for this application.

[0027] Explanation of the accompanying symbols: data collection module 11, map construction module 12, data monitoring module 13, relationship network construction module 14, accident assessment module 15, pipeline network early warning module 16. DETAILED DESCRIPTION

[0028] The present application provides a gas pipeline accident and disaster monitoring and management method and system based on a knowledge graph, collects multi-dimensional data of the gas pipeline network and constructs a pipeline network knowledge graph, monitors and obtains pipeline network monitoring data, inputs the data into the pipeline network knowledge graph for relevant data analysis and extraction, constructs an analysis data relationship network, constructs an accident assessment model and combines the pipeline network monitoring data to obtain accident assessment information, conducts a global analysis of the gas pipeline network based on the accident assessment information and the pipeline network knowledge graph, and determines the global early warning information of the pipeline network. This application is used to solve the technical problems in the existing technology of relatively conventional supervision methods for gas pipeline accidents and disasters, incomplete coverage of prediction analysis, and insufficiently rigorous data processing methods, resulting in insufficient accuracy of the final accident prediction results, causing potential risks affecting management efficiency.

[0029] Example 1

[0030] like Figure 1 As shown, this application provides a gas pipeline accident disaster monitoring and management method based on a knowledge graph, the method comprising:

[0031] Step S100: Collecting data on gas transmission, connection equipment, transmission nodes, and laying locations of the gas pipeline network to obtain multi-dimensional data of the gas pipeline network;

[0032] Specifically, gas is the transmission medium in the gas pipeline network. If gas leaks, it may cause risk accidents such as fire and explosion. At the same time, the gas pipeline network has a wide coverage and complex interlaced structure, which leads to uncontrollable dangerous sources. The safety prevention and control of accidents is the current key problem to be solved. In order to ensure the accuracy of early warning and management efficiency of accident disasters, the knowledge graph-based gas pipeline accident disaster monitoring and management method provided in this application builds a pipeline knowledge graph for real-time monitoring data analysis and identification, and determines the established real-time data relationship network to ensure the regularity, order and relevance of information in the analysis process. On this basis, a global analysis is carried out, taking into account the mutual influence of each node to improve the comprehensiveness and accuracy of the early warning.

[0033] Specifically, the gas transmitted by the gas pipeline network is determined. For example, the main transmission gas in the gas pipeline is coal gas, and there may also be certain mixed gases such as high-temperature steam, oxygen, and hydrogen. The gas pipeline network is connected to gas reaction equipment and transmission operation equipment, which are used for gas generation and gas-based operations respectively, and are connected to different structural positions of the gas pipeline network as the connection equipment. The execution functions of different connection positions of the gas pipeline network are different. At the same time, there may be gas interaction and diversion during the transmission process. The relevant position nodes are extracted as the transmission nodes. The layout position of each functional node is determined as the laying position. The transmission gas, the connection equipment, the transmission node and the laying position are associated with the data collection and attribution integration to generate the multi-dimensional data of the gas pipeline network. The multi-dimensional data of the gas pipeline network is the basic data that constitutes the pipeline network system.

[0034] Step S200: constructing a pipeline network knowledge graph based on the multi-dimensional data of the gas pipeline network;

[0035] Furthermore, if Figure 2 As shown, based on the multi-dimensional data of the gas pipeline network, a pipeline network knowledge graph is constructed. Step S200 of this application also includes:

[0036] Step S210: performing data type identification and classification based on the multidimensional data of the gas pipeline network to determine a first data set and a second data set, wherein the first data set is structured data and the second data set is semi-structured data or unstructured data;

[0037] Step S220: performing knowledge fusion on the first data set to obtain fused data, and extracting attributes, relationships, and entities from the second data set to obtain extracted data;

[0038] Step S230: inputting the fused data and the extracted data into a data processing module to eliminate target parameters and obtain a target subject data set;

[0039] Step S240: performing subject extraction and knowledge reasoning processing on the target subject data set, performing knowledge association based on the processing results, and constructing the pipe network knowledge graph.

[0040] Specifically, the collected multi-dimensional data of the gas pipeline network is identified and judged based on the established data format and length normative standards, and the relevant data that meets the above requirements, that is, structured data, is extracted as the first data set; if any of the remaining data meets any of the requirements, it is regarded as semi-structured data, otherwise it is unstructured data, and the semi-structured data and the unstructured data are regarded as the second data set. For the first data set, data attribution integration is performed for different data format types to complete data fusion as the fused data; for the second data set, where entities include subjects and objects, data relationships are determined based on the association definition between subjects, objects and attributes, where attributes are predicates. For the second data set, the concrete information of attributes, relationships and entities of multiple data information is extracted respectively as the extracted data to extract the subject semantic information. The fused data and the extracted data are valid data that are determined by information identification based on the adaptive processing method for the data pattern, so as to improve the energy efficiency of data analysis.

[0041] Furthermore, the data processing module is constructed. For example, sample data that conforms to the data processing mechanism can be obtained by conducting a big data survey, and a module execution mechanism can be constructed by conducting module training. The data processing module is a functional execution module. The fused data and the extracted data are input into the data processing module, and data integration and target parameter elimination are performed by identifying the associated data corresponding to the target to determine the complete associated data set of the target subject, and the target subject data set is obtained. The target subject data set includes the corresponding data sets of multiple target subjects. Subject extraction is performed on the target subject data set respectively, and the correlation influence analysis between subjects is performed, and possible derivative data is determined to determine the processing results. Knowledge association is performed on the processing results to determine a complete knowledge system as the pipeline network knowledge graph. The pipeline network knowledge graph is a visual display of the complete architecture and operation association information of the pipeline network, based on which the mutual influence information can be directly extracted.

[0042] Step S300: monitoring the gas pipeline network through data monitoring equipment to obtain pipeline network monitoring data;

[0043] Furthermore, the gas network is monitored by a data monitoring device to obtain network monitoring data. Step S300 of this application further includes:

[0044] Step S310: monitoring parameters of connected devices in the gas pipeline network through operation monitoring equipment to obtain device operation parameters;

[0045] Step S320: monitoring gas leakage data of pipelines in the gas network using gas monitoring equipment to obtain gas monitoring data;

[0046] Step S330: Based on the data monitoring equipment index parameters and the monitoring database, the equipment operating parameters and gas monitoring data are judged for data format integrity, monitoring range, and data credibility, and the monitoring data that meets the judgment requirements is used as the pipeline network monitoring data.

[0047] Specifically, the data monitoring equipment includes the operation monitoring equipment and the gas monitoring equipment, which are auxiliary equipment for collecting the real-time operation status of the pipeline network. There are differences in their layout locations and execution functions, such as sensing equipment, image acquisition devices, etc. The operation monitoring equipment is deployed at the device connection nodes of multiple transmission nodes in the pipeline network, and the gas monitoring equipment is deployed at the pipeline transmission nodes. The deployment density is proportional to the risk level of the node. Based on the operation monitoring equipment, real-time operation monitoring of the pipeline network connection equipment is performed, and the monitoring data is marked with the device source and monitoring time as the equipment operation parameters. Based on the gas monitoring equipment, gas leakage data monitoring of pipeline transmission is performed. For example, judgment can be made based on gas concentration and diffusion range to obtain the gas monitoring data.

[0048] Furthermore, due to limitations such as the monitoring environment, equipment aging, signal interference, and network quality, the monitoring data may be abnormal, requiring a pre-screening analysis of the data. The data monitoring equipment indicators and the monitoring database are used as standards for measuring the status of the monitoring data. The data format integrity, monitoring range, and data credibility are used as data evaluation directions. The equipment operating parameters and the gas monitoring data are proofread and evaluated in multiple dimensions to see if there are abnormalities such as data format anomalies, missing data, and insufficient character string length. For example, if the equipment monitoring range is 100 and the data obtained is 130, it is abnormal data. The credibility of the data depends on the equipment monitoring range, which is not the recognized conventional data range. The accuracy of the data affects the final analysis results. Screen the monitoring data that meets the above-mentioned monitoring requirements as the pipeline network monitoring data to avoid result deviations based on abnormal data analysis.

[0049] Step S400: inputting the pipe network monitoring data into the pipe network knowledge graph, performing relevant data analysis and extraction, and constructing an analysis data relationship network;

[0050] Step S500: constructing an accident assessment model based on the analysis data relationship network, and obtaining accident assessment information according to the pipeline network monitoring data and the accident assessment model;

[0051] Specifically, the pipeline network monitoring data is valid data after collection and processing. The pipeline network monitoring data is input into the pipeline network knowledge graph, and data positioning is performed in the pipeline network knowledge graph to determine the successfully mapped graph nodes, and the connection relationship and derivative relationship between the nodes are extracted to determine a complete monitoring data system as the analysis data relationship network. Furthermore, based on the analysis data relationship network, the accident assessment model is constructed by performing data structure conversion and logical analysis, that is, a functional model for predicting the occurrence of accident events. The pipeline network monitoring data is input into the accident assessment model, and data analysis and corresponding relationship point mapping are performed to perform logical inference to determine the inevitability of the accident. The inference result is used as the accident assessment information. The accident assessment information is an actual operation matching assessment result with a realistic basis. Based on the accident assessment information, an abnormal early warning and alert for pipeline network operation is performed.

[0052] Furthermore, if Figure 3 As shown, based on the analysis data relationship network, an accident assessment model is constructed. Step S500 of this application also includes:

[0053] Step S510: determining the top event of the accident based on the analysis data relationship network;

[0054] Step S520: performing data structure conversion on the analysis data relationship network based on the top event of the accident to construct an accident tree relationship network;

[0055] Step S530: performing accident factor analysis and determining the logical relationship of accident factors according to the accident tree relationship network;

[0056] Step S540: Based on the accident tree relationship network, perform minimum event segmentation of accident factor combinations according to accident factors and their logical relationships;

[0057] Step S550: Based on the minimum cut set principle, the accident factor combination is segmented into minimum events and the accident factor logical relationship to construct the accident assessment model.

[0058] Specifically, based on the analysis data relationship network, multiple types of safety accident events are determined, including three types: major safety accidents, large safety accidents and general safety accidents, as the accident top events. The matching landing points of the data components of the accident top events in the analysis data relationship network are determined, and the accident tree relationship network is generated by performing data structure conversion. The accident tree relationship network is consistent with the accident top events. By converting the accident tree relationship network, the accident logic system can be directly identified and extracted. Based on the accident tree relationship network, the two types of basic events, basic management and on-site management of gas pipelines, are used as accident factors. The structured data of basic management and the unstructured data of on-site management, such as on-site management videos, are extracted to determine the relative mutual influence relationship as the accident factor logical relationship. Further, based on the accident tree relationship network, the accident factors and the accident factor logical relationships, minimum event segmentation is performed, and the segmentation standard is the possible basic events. Based on the minimum cut set principle, that is, when the minimum cut set involves multiple basic events of basic management and on-site management, it indicates that the corresponding top event is bound to occur. Based on this, a logical execution mechanism is constructed to generate the accident assessment model. Based on the accident assessment model, accurate and objective assessment and analysis of safety accidents can be carried out.

[0059] Step S600: Perform a global analysis of the gas pipeline network based on the accident assessment information and the pipeline network knowledge graph to determine global warning information for the pipeline network.

[0060] Furthermore, based on the accident assessment information and the pipeline network knowledge graph, a global analysis of the gas pipeline network is performed to determine global pipeline network warning information. Step S600 of this application also includes:

[0061] Step S610-1: Determine the accident transmission node, accident assessment probability, and accident assessment level based on the accident assessment information;

[0062] Step S620-1: Using the accident transmission node and the accident assessment level as knowledge screening conditions, inputting them into the pipeline network knowledge graph, performing a global node impact analysis on the gas pipeline network, and obtaining a global node accident impact coefficient for the pipeline network;

[0063] Step S630-1: determining the global node accident probability based on the pipeline network global node accident impact coefficient and the accident assessment probability;

[0064] Step S640-1: Perform warning threshold judgment analysis based on the global node accident probability to obtain the global warning information of the pipeline network.

[0065] Specifically, the pipeline monitoring data is analyzed based on the accident assessment model to determine the accident assessment information. When the accident assessment information is a single accident, the accident assessment information is further analyzed to locate the accident-related information, locate the occurrence node and the impact node of the accident in the transmission node, perform type identification as the accident transmission node, determine the probability of the accident occurrence, as the accident assessment probability, and determine the accident assessment level, for example, whether it is a major safety accident, a large safety accident or a general safety accident. The accident assessment level and the accident transmission node are further used as screening conditions and input into the pipeline knowledge graph for global impact analysis to determine the accident impact degree of each node and determine the node accident impact coefficient. On this basis, a global comprehensive analysis is further performed to determine the comprehensive impact coefficient as the pipeline global node accident impact coefficient. The pipeline global node accident impact coefficient is data for judging the degree of node operation impact caused by the accident.

[0066] Furthermore, the global node accident probability is measured based on the accident impact coefficient of the global node of the pipeline network and the accident assessment probability. For example, a preferred measurement method is set, and the coefficient standard is set to 10. When the global accident impact coefficient of the pipeline network is 9 and the accident assessment probability is 90%, 9 / 10×90% is the global node accident probability. Based on the above probability analysis method, the actual fit of the accident probability determination result can be further improved. The warning threshold is configured, that is, the critical probability for the accident probability warning. When the global node accident probability meets the warning threshold, it indicates that the current accident probability has reached the warning standard. The global warning information of the pipeline network is obtained for early warning and alert for preventive treatment.

[0067] Furthermore, when the accident assessment information includes multiple accidents, step S600 of the present application further includes:

[0068] Step S610-2: Obtaining the laying position of the accident transmission node according to the accident transmission node and the pipe network knowledge graph;

[0069] Step S620-2: Collecting environmental propagation factor information based on the location of the accident transmission node to obtain the location environmental propagation factor;

[0070] Step S630-2: Evaluate the propagation risk level based on the location environment propagation factor and the accident transmission node to determine the risk propagation coefficient;

[0071] Step S640-2: Determine the accident assessment risk coefficient based on the accident assessment probability and the accident assessment level;

[0072] Step S650-2: setting an accident weight coefficient according to the risk propagation coefficient and the accident assessment risk coefficient;

[0073] Step S660-2: Obtain the global early warning information of the pipeline network according to the accident weight coefficient and the global node accident probability corresponding to each accident.

[0074] Specifically, when the accident assessment information includes multiple accidents, the accident node location is determined based on the accident transmission node and the pipeline network knowledge graph. The node where the accident occurred is located, including the derived associated nodes of each node, that is, the transmission nodes with significant influence relationships, as the accident transmission node. The actual location of the accident transmission node is then determined, such as the geographic location of the pipeline or connected equipment, as the location of the accident transmission node. Because real-time environmental conditions can have a certain impact on accidents, such as the influence of wind speed and wind direction on transmission, and the influence of temperature and humidity on gas conditions, these are used as environmental transmission factors, and real-time data collection is performed to determine the location environmental transmission factors.

[0075] Based on the location environmental transmission factor and the accident transmission node, an environmental transmission risk level assessment is performed to determine the risk transmission coefficient. The greater the environmental impact, the higher the risk transmission coefficient. For example, in the case of a gas leak, the higher the wind speed, the wider the impact range, and the higher the risk transmission coefficient. Furthermore, based on the risk transmission coefficient and the accident assessment risk coefficient, multiple accidents are weighted to generate accident weight coefficients for mapping and identifying the multiple accidents. The higher the combined score of the risk transmission coefficient and the accident assessment risk coefficient, the greater the accident weight. A global node accident probability analysis is then performed for each accident. The higher the global node accident probability corresponding to the accident weight coefficient and the corresponding accident, the higher the corresponding global risk, and the higher the warning priority. Based on the warning priority, the multiple accidents are ranked for warnings, and global warning information for the pipeline network is generated. A global, comprehensive risk assessment is performed to improve the completeness and coverage of the warning information.

[0076] Furthermore, the present application also includes step S600, including:

[0077] Step S710: matching emergency plan parameters based on the global warning information of the pipe network to obtain an emergency plan for each transmission node;

[0078] Step S720: Building a linkage prediction chain model for a global emergency plan based on the pipe network knowledge graph and the emergency plans of each transmission node;

[0079] Step S730: performing a global linkage emergency response result prediction based on the linkage prediction chain model to obtain linkage emergency response assessment information;

[0080] Step S740: Confirm the emergency plan of each transmission node according to the linkage emergency assessment information, or make linkage emergency adjustments according to the linkage emergency assessment information and the linkage prediction chain model.

[0081] Specifically, risk processing is performed based on the global early warning information of the pipeline network, and multiple universal emergency plans corresponding to the mapping are retrieved. The emergency plan parameters are adjusted according to the global early warning information of the pipeline network as the emergency plan for each transmission node. Further, based on the pipeline network knowledge graph, the node positioning and layout of the emergency plan for each transmission node are performed, and a linkage prediction chain model of the global emergency plan is generated. Based on the linkage prediction chain model, the execution effect of the complete adjustment plan is predicted to determine whether the risk event can be resolved, and the linkage emergency assessment information is generated. At the same time, the plan execution instruction or the plan adjustment instruction is additional output information. When the plan execution instruction is output, it indicates that the emergency assessment result of the plan is qualified, and it is confirmed that the current operation control is based on the emergency plan for each transmission node; when the plan adjustment instruction is output, it indicates that the current plan cannot solve the risk event, and the plan is further adjusted based on the relationship between the equipment to improve the actual adaptability of the plan, and the operation control is performed based on the adjusted plan.

[0082] Example 2

[0083] Based on the same inventive concept as the gas pipeline accident disaster monitoring and management method based on knowledge graph in the above embodiment, Figure 4 As shown, this application provides a gas pipeline accident disaster monitoring and management system based on a knowledge graph, the system comprising:

[0084] The data acquisition module 11 is used to collect data on the gas transmission, connection equipment, transmission nodes, and laying locations of the gas pipeline network to obtain multi-dimensional data of the gas pipeline network;

[0085] A graph construction module 12, the graph construction module 12 is used to construct a pipeline network knowledge graph based on the multi-dimensional data of the gas pipeline network;

[0086] A data monitoring module 13 is used to monitor the gas pipeline network through data monitoring equipment to obtain pipeline network monitoring data;

[0087] A relationship network construction module 14 is used to input the pipe network monitoring data into the pipe network knowledge graph, perform relevant data analysis and extraction, and construct an analysis data relationship network;

[0088] An accident assessment module 15 is configured to construct an accident assessment model based on the analysis data relationship network, and obtain accident assessment information based on the pipe network monitoring data and the accident assessment model;

[0089] The pipeline network early warning module 16 is used to perform a global analysis of the gas pipeline network based on the accident assessment information and the pipeline network knowledge graph, and determine the global early warning information of the pipeline network.

[0090] Furthermore, the system also includes:

[0091] a data classification module, the data classification module being configured to identify and classify data types based on the multidimensional data of the gas pipeline network to determine a first data set and a second data set, wherein the first data set is structured data and the second data set is semi-structured data or unstructured data;

[0092] A data processing module, configured to perform knowledge fusion on the first data set to obtain fused data, and extract attributes, relationships, and entities from the second data set to obtain extracted data;

[0093] A target subject data set acquisition module, wherein the target subject data set acquisition module is used to input the fused data and the extracted data into a data processing module to eliminate target parameters and obtain a target subject data set;

[0094] A knowledge graph construction module is used to perform subject extraction and knowledge reasoning processing on the target subject data set, perform knowledge association based on the processing results, and construct the pipeline network knowledge graph.

[0095] Furthermore, the system further comprises:

[0096] An equipment operation parameter monitoring module is used to monitor parameters of connected equipment in the gas pipeline network through operation monitoring equipment to obtain equipment operation parameters;

[0097] A gas leakage data monitoring module is used to monitor gas leakage data of pipelines in the gas network through gas monitoring equipment to obtain gas monitoring data;

[0098] The data identification module is used to identify the data format integrity, monitoring range, and data credibility of the equipment operating parameters and gas monitoring data based on the data monitoring equipment index parameters and the monitoring database, and use the monitoring data that meets the identification requirements as the pipeline network monitoring data.

[0099] Furthermore, the system further comprises:

[0100] A top event determination module, the top event determination module is used to determine the top event of the accident based on the analysis data relationship network;

[0101] A relationship network construction module, the relationship network construction module is used to perform data structure conversion on the analysis data relationship network based on the top event of the accident to construct an accident tree relationship network;

[0102] An association analysis module, the association analysis module is used to perform accident factor analysis and determine the logical relationship of accident factors based on the accident tree relationship network;

[0103] An event segmentation module, wherein the event segmentation module is used to perform minimum event segmentation of accident factor combinations based on the accident tree relationship network and according to accident factors and their logical relationships;

[0104] The accident assessment model construction module is used to construct the accident assessment model based on the minimum cut set principle, according to the combination of accident factors to split the minimum event and the logical relationship of accident factors.

[0105] Furthermore, the system further comprises:

[0106] An accident parameter determination module, configured to determine an accident transmission node, an accident assessment probability, and an accident assessment level based on the accident assessment information;

[0107] An influence coefficient acquisition module is used to use the accident transmission node and the accident assessment level as knowledge screening conditions, input the pipeline network knowledge graph, perform global node impact analysis on the gas pipeline network, and obtain the global node accident impact coefficient of the pipeline network;

[0108] An accident probability determination module, configured to determine a global node accident probability based on the pipeline network global node accident impact coefficient and the accident assessment probability;

[0109] The warning threshold judgment module is used to perform warning threshold judgment analysis based on the global node accident probability to obtain the global warning information of the pipeline network.

[0110] Furthermore, the system further comprises:

[0111] A location acquisition module, configured to obtain a laying location of an accident transmission node based on the accident transmission node and the pipe network knowledge graph;

[0112] An information collection module, configured to collect information on environmental propagation factors based on the locations of the accident transmission nodes, and obtain location environmental propagation factors;

[0113] A risk level assessment module, configured to assess the level of transmission risk based on the location environment transmission factor and the accident transmission node, and determine a risk transmission coefficient;

[0114] A risk coefficient determination module, configured to determine an accident assessment risk coefficient based on the accident assessment probability and the accident assessment level;

[0115] A root weight coefficient setting module, the weight coefficient setting module is used to set an accident weight coefficient according to the risk propagation coefficient and the accident assessment risk coefficient;

[0116] The early warning information acquisition module is used to obtain the global early warning information of the pipeline network based on the accident weight coefficient and the global node accident probability corresponding to each accident.

[0117] Furthermore, the system further comprises:

[0118] A solution matching module is used to match emergency solution parameters according to the global warning information of the pipeline network to obtain an emergency solution for each transmission node;

[0119] A model building module, the model building module is used to build a linkage prediction chain model of the global emergency plan based on the pipeline network knowledge graph and the emergency plans of each transmission node;

[0120] A result prediction module, which is used to perform global linkage emergency result prediction based on the linkage prediction chain model to obtain linkage emergency assessment information;

[0121] A scheme confirmation and adjustment module is used to confirm the emergency scheme of each transmission node according to the linkage emergency assessment information, or to make linkage emergency adjustments according to the linkage emergency assessment information and the linkage prediction chain model.

[0122] Through the above detailed description of the gas pipeline accident disaster monitoring and management method based on the knowledge graph in this specification, those skilled in the art can clearly understand the gas pipeline accident disaster monitoring and management method and system based on the knowledge graph in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0123] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A gas pipeline accident and disaster monitoring and management method based on knowledge graph, characterized by: The method comprises: Collect data on gas transmission, connection equipment, transmission nodes, and laying locations of the gas pipeline network to obtain multi-dimensional data of the gas pipeline network; Constructing a pipeline network knowledge graph based on the multi-dimensional data of the gas pipeline network; Monitor the gas pipeline network through data monitoring equipment to obtain pipeline network monitoring data; Inputting the pipe network monitoring data into the pipe network knowledge graph, performing relevant data analysis and extraction, and constructing an analysis data relationship network; Based on the analysis data relationship network, an accident assessment model is constructed, and accident assessment information is obtained according to the pipeline network monitoring data and the accident assessment model; Performing a global analysis of the gas pipeline network based on the accident assessment information and the pipeline network knowledge graph to determine global early warning information for the pipeline network; The step of constructing an accident assessment model based on the analysis data relationship network includes: Determining the top event of the accident based on the analysis data relationship network; Performing data structure conversion on the analysis data relationship network based on the top events of the accident to construct an accident tree relationship network; Perform accident factor analysis and determine the logical relationship of accident factors based on the accident tree relationship network; Based on the accident tree relationship network, the accident factor combination minimum event segmentation is performed according to the accident factors and the accident factor logical relationships; Based on the minimum cut set principle, the accident assessment model is constructed by dividing the minimum events according to the combination of accident factors and the logical relationship of accident factors; Based on the accident assessment information and the pipeline network knowledge graph, a global analysis of the gas pipeline network is performed to determine global pipeline network warning information, including: Determine the accident transmission node, accident assessment probability, and accident assessment level based on the accident assessment information; The accident transmission node and the accident assessment level are used as knowledge screening conditions, input into the pipeline network knowledge graph, and a global node impact analysis of the gas pipeline network is performed to obtain a global node accident impact coefficient of the pipeline network; Determining the global node accident probability based on the pipeline network global node accident impact coefficient and the accident assessment probability; Performing early warning threshold judgment analysis based on the global node accident probability to obtain the global early warning information of the pipeline network; According to the global early warning information of the pipeline network, emergency plan parameters are matched to obtain emergency plans for each transmission node; Based on the pipe network knowledge graph and the emergency plans of each transmission node, a linkage prediction chain model of the global emergency plan is established; According to the linkage prediction chain model, a global linkage emergency result prediction is performed to obtain linkage emergency assessment information; According to the linkage emergency assessment information, the emergency plan of each transmission node is confirmed, or the linkage emergency adjustment is performed according to the linkage emergency assessment information and the linkage prediction chain model.

2. The method according to claim 1, wherein Based on the multi-dimensional data of the gas pipeline network, a pipeline network knowledge graph is constructed, including: Identifying and classifying data types according to the multidimensional data of the gas pipeline network to determine a first data set and a second data set, wherein the first data set is structured data and the second data set is semi-structured data or unstructured data; Performing knowledge fusion of the knowledge base based on the first data set to obtain fused data, and extracting attributes, relationships, and entities from the second data set to obtain extracted data; Inputting the fused data and the extracted data into a data processing module to eliminate target parameters and obtain a target subject data set; The target subject data set is subjected to subject extraction and knowledge reasoning processing, and knowledge association is performed based on the processing results to construct the pipe network knowledge graph.

3. The method according to claim 1, wherein The gas network is monitored through data monitoring equipment to obtain network monitoring data, including: Monitor the parameters of the connected equipment in the gas pipeline network through operation monitoring equipment to obtain equipment operating parameters; Monitor gas leakage data in the gas pipeline network through gas monitoring equipment to obtain gas monitoring data; Based on the data monitoring equipment index parameters and the monitoring database, the equipment operating parameters and gas monitoring data are judged for data format integrity, monitoring range, and data credibility, and the monitoring data that meets the judgment requirements is used as the pipeline network monitoring data.

4. The method according to claim 1, wherein When the accident assessment information includes multiple accidents, the method includes: Obtaining the laying position of the accident transmission node according to the accident transmission node and the pipe network knowledge graph; According to the location of the accident transmission node, environmental propagation factor information is collected to obtain the location environmental propagation factor; Performing a propagation risk level assessment based on the location environment propagation factor and the accident transmission node to determine a risk propagation coefficient; Determine the accident assessment risk coefficient based on the accident assessment probability and accident assessment level; Setting an accident weight coefficient according to the risk propagation coefficient and the accident assessment risk coefficient; The global early warning information of the pipeline network is obtained according to the accident weight coefficient and the global node accident probability corresponding to each accident.

5. The gas pipeline accident and disaster monitoring and management system based on knowledge graph is characterized by: The system is used to perform the method according to any one of claims 1 to 4, and the system includes: A data acquisition module is used to collect data on the gas pipeline network, including transmission gas, connection equipment, transmission nodes, and laying locations, to obtain multi-dimensional data of the gas pipeline network; A graph construction module, the graph construction module is used to construct a pipeline network knowledge graph based on the multi-dimensional data of the gas pipeline network; A data monitoring module, which is used to monitor the gas pipeline network through data monitoring equipment to obtain pipeline network monitoring data; A relationship network construction module, which is used to input the pipeline network monitoring data into the pipeline network knowledge graph, perform relevant data analysis and extraction, and construct an analysis data relationship network; An accident assessment module, configured to construct an accident assessment model based on the analysis data relationship network, and obtain accident assessment information based on the pipe network monitoring data and the accident assessment model; The pipeline network early warning module is used to perform a global analysis of the gas pipeline network based on the accident assessment information and the pipeline network knowledge graph, and determine the global early warning information of the pipeline network.

Images