A gas pipeline safety monitoring method based on the Internet of Things

Abstract

The present invention provides a gas pipeline safety monitoring method based on the Internet of Things, which belongs to the field of gas pipeline safety monitoring, involves gas pipeline network burst analysis, uses GIS technology to build a gas pipeline network information system, and realizes real-time monitoring of gas pipeline network temperature, pressure, flow and other operating parameters through a three-layer structure. According to intelligent leak detection technology and a rapid response mechanism when a burst occurs, gas leaks are quickly detected and valves and pressure regulators are closed to notify affected users. The present invention improves the level of gas pipeline network management and services, and at the same time uses a SCADA system for data collection and monitoring control, overcomes the shortcoming that simple GIS is difficult to monitor the operating status of the gas pipeline network, improves the response speed and efficiency to gas pipeline network bursts, reduces potential risks, and ensures public safety.

Description

Technical Field

[0001] The invention relates to a gas pipeline safety monitoring method based on the Internet of Things, and belongs to the field of gas pipeline safety monitoring. Background Art

[0002] With the rapid growth of China's economy, the proportion of gas use in industry, commerce and residents' lives has continued to rise. New and existing gas pipeline networks are becoming larger and larger, and their distribution is becoming more and more widespread. As an important urban infrastructure and the key to economic and social development, it is particularly important to manage the gas pipeline network intelligently. In order to improve management efficiency, gas companies have successively established a variety of information systems including supervisory control and data acquisition (SCADA) systems, geographic information systems (GIS) and pipeline inspection systems, all of which have achieved good results. However, these information constructions are often explored by the companies themselves and driven by business needs. Each system is often built independently at different times, resulting in relative isolation between systems and forming the so-called "data islands".

[0003] As enterprises continue to grow and develop, the requirements for business process control are becoming increasingly stringent, and the construction and management of enterprise information systems are facing new challenges. These challenges are mainly reflected in: the independent operation of each business subsystem, insufficient data sharing, and decentralized processes, which make it impossible to effectively conduct closed-loop tracking and management of abnormalities, accidents, and operations. In addition, although enterprises have a large amount of statistical data, they lack in-depth data mining, analysis, and intelligent decision-making support capabilities. This situation restricts the ability of enterprises to discover potential laws and patterns from accumulated business knowledge and data, and fails to provide effective decision-making assistance for business leaders.

[0004] For example, the patent with publication number CN112729723A discloses an intelligent gas remote monitoring management method, system, electronic device and computer storage medium based on the Internet of Things and artificial intelligence. The invention obtains the gas output of each branch gas pipeline in the household, calculates the total gas output of each branch gas pipeline in the household, analyzes and determines whether there is a gas leak in the branch gas pipeline in the household, and obtains the gas intake of each branch gas pipeline if there is a gas leak, compares and counts the branch gas pipelines with gas leaks, detects the gas flow of each section of the sub-pipeline in each branch gas pipeline with gas leaks, compares the gas flow of each section of the sub-pipeline in each branch gas pipeline with gas leaks with the adjacent sub-pipeline, counts the position number of the sub-pipeline with problems in each branch gas pipeline, and displays them, and notifies relevant personnel to perform corresponding maintenance and processing, thereby ensuring the safe operation of gas and the safety of users' lives and property. It can detect the point where the fault occurs, but does not consider timeliness.

[0005] Gas pipeline monitoring plays a vital role in ensuring public safety, preventing environmental pollution, maintaining the stability of energy supply, and reducing economic losses. By monitoring the operating status of gas pipelines in real time, leaks, corrosion or other potential safety hazards can be discovered in time, so that preventive measures can be taken to avoid possible explosions or fire accidents. In addition, gas pipeline monitoring can also help improve energy efficiency and ensure the continuity of gas supply, which is of immeasurable value in ensuring the quality of life of residents and supporting economic development. Therefore, there is an urgent need for a gas pipeline safety monitoring method based on the Internet of Things that can automatically detect and quickly repair. Summary of the invention

[0006] The present invention aims to provide a gas pipeline safety monitoring method based on the Internet of Things. The system uses GIS technology to build a gas pipeline network information system, improves the level of gas pipeline network management and service, and uses the SCADA system for data collection and monitoring control. The invention can improve the speed and efficiency of emergency response to gas pipeline bursts, reduce potential risks, and ensure public safety.

[0007] To achieve the above object, the present invention is implemented by adopting the following technical solutions.

[0008] The present invention provides a gas pipeline safety monitoring method based on the Internet of Things, comprising:

[0009] S1: multiple pressure sensors are installed on the gas pipeline. When a leak occurs, the negative pressure wave generated at the leak point propagates to the detection point, causing abnormal pressure at the detection point. The negative pressure wave collected at the detection point is uploaded to the SCADA system via the RTU. The SCADA system extracts the waveform feature data of the negative pressure wave collected at the detection point, inputs the waveform feature data into a pre-built pressure anomaly recognition model, obtains the type of negative pressure wave, and determines the gas pipeline state type according to the negative pressure wave type. The gas pipeline state type includes pipe burst, single-point leakage and multi-point leakage. The SCADA system issues a corresponding alarm according to the gas pipeline state type and transmits the corresponding alarm information to the GIS.

[0010] S2: The GIS sends the corresponding alarm information, and the GPS inspection system uses the shortest path strategy traversal search method to find the valves and pressure regulators that need to be closed and the shortest path for the inspection personnel to arrive at the site according to the location of the on-site inspection personnel, and reports it to the dispatcher;

[0011] S3: The dispatcher confirms whether a pipe burst, single-point leakage or multiple-point leakage occurs based on the upstream and downstream valves of the pipe burst location, the single-point leakage location and the multiple-point leakage location, the detection results of the combustible gas detector in the well, the change of pipeline pressure or the report of the on-site inspection personnel. If confirmed, the process proceeds to step S4, otherwise the process terminates;

[0012] S4: The SCADA sends a closing command to the actuator of the relevant equipment to determine whether there is an actuator that does not respond. If the actuator does not respond, the process goes to step S2 to expand the search and find the valves and pressure regulators that need to be closed; otherwise, the process goes to step S5;

[0013] S5: searching the GIS for user information affected by the gas cut-off;

[0014] S6: Notify affected users via SMS or phone call. End.

[0015] Furthermore, the negative pressure wave types include transient negative pressure waves, gradual negative pressure waves and focused negative pressure waves; the gas pipeline status type corresponding to the negative pressure wave type of transient negative pressure wave is marked as pipe burst; the gas pipeline status type corresponding to the negative pressure wave type of gradual negative pressure wave is marked as single-point leakage; the gas pipeline status type corresponding to the negative pressure wave type of focused negative pressure wave is marked as multi-point leakage.

[0016] Furthermore, the training method of the pressure anomaly recognition model includes:

[0017] Collect m groups of historical data, where m is an integer greater than 1, and the historical data includes waveform characteristic data and negative pressure wave types corresponding to the waveform characteristic data, and numerically number the negative pressure wave types; convert the historical data into a corresponding set of characteristic vectors;

[0018] The historical data is used as the input of the pressure anomaly recognition model, the pressure anomaly recognition model takes the negative pressure wave type numerical number corresponding to each set of waveform feature data as the output, takes the negative pressure wave type numerical number actually corresponding to each set of waveform feature data as the prediction target, and takes minimizing the loss function value of the pressure anomaly recognition model as the training target; the training is stopped when the loss function value of the pressure anomaly recognition model is less than or equal to the preset target loss value; the pressure anomaly recognition model is a support vector machine, a decision tree or a random forest.

[0019] Furthermore, the feature is that: the GIS has the ability to capture, manage, operate and analyze data related to the gas pipeline network space, and is used to manage gas pipeline network graphics, pipelines, and valves; the GIS provides the latest information of the gas pipeline network system at any time to achieve gas pipeline network management, planning and design, operation scheduling and decision-making;

[0020] The GIS data include: pipeline spatial data, including pipeline centerline coordinates, pipeline burial depth, remote sensing images, coordinates and burial depth of important facilities, pipeline crossing conditions and spatial orientation of adjacent facilities; pipeline attribute and environmental data, namely pipeline materials, specifications and models, pipeline facilities; among which, important facilities include tees, elbows, diameter reduction points and thickening points, valves, and pressure regulating stations; adjacent facilities include pipelines, power lines, communication lines, roads and railways, bridges and tunnels, water conservancy facilities, rivers, and lakes; pipeline facilities include valves, elbows, anti-corrosion coatings, cathodic protection, welds, steel pipe information, technical parameters, stray current interference, and pipeline soil corrosion.

[0021] Furthermore, the SCADA system is used to monitor and control the operation of gas pipeline network equipment; the SCADA system monitors the real-time status of each monitoring point in the gas pipeline network, and issues dispatch instructions and gas volume statistics of each monitoring point; the pressure, flow and temperature information of the gas are stored in the database of the SCADA system.

[0022] Furthermore, the GIS establishes a data sharing platform with other systems to utilize the data of other systems to achieve intelligence; the data sources of the data sharing platform include Oracle, DB2, Microsoft SQL Server, Microsoft Access, and MySQL database systems.

[0023] Furthermore, the data sharing platform is imported into the data sharing platform by using URL management, JDBC connection and connection pool management technology; the source database is reintegrated by defining operation rules, filtering rules and mapping rules, and the integrated data can be read and used by each business subsystem at any time; the data sharing between the business subsystems is achieved by automated or manual methods.

[0024] Furthermore, it also includes: the SCADA system determines the associated monitoring points in the gas pipeline through the GIS; when a gas pipeline bursts, a single-point leak or a multi-point leak occurs, the associated monitoring points will bypass the monitoring center and communicate directly with each other, and remotely and automatically close the corresponding valves in the pipeline.

[0025] Furthermore, it also includes: the GPS inspection system supervises and manages the inspection personnel and vehicle dispatch management to ensure that the inspection personnel conduct inspections according to predefined patrol routes, locations and times, and provides the inspection personnel with the shortest path navigation calculated by the shortest path strategy when abnormal events occur; the GPS inspection system conducts full dynamic management of the inspection personnel, and uploads information on hidden dangers and accidents during the inspection process in real time; the data involved in the database of the GPS inspection system include: daily patrols, shadow protection operations, stray interference, third-party sabotage, emergency rescue, hidden danger detection and assessment, and risk assessment.

[0026] Furthermore, the shortest path strategy process is as follows:

[0027] Step 1: Input the starting node and the target node into the algorithm, and put the starting node into an open table; an open table is used to store all available nodes;

[0028] Step 2: Select the node with the lowest cost from the open table; the cost of a node consists of two parts: the spatial distance from the node to the target node and the actual distance from the node to the starting node;

[0029] Step 3: If the selected node is the target node, the path from the start node to the target node is found and the search ends; otherwise, the process continues to Step 4 to continue expanding the node;

[0030] Step 4: Find the nodes adjacent to the selected node, calculate their costs, and then transfer the selected node from the open table to the closed table, which is used to store all explored nodes. The management principles for adjacent nodes are as follows: (1) If the adjacent node is already in the open table and the cost of the adjacent node is lower than the node in the open table, update the cost of the corresponding node in the open table. (2) If the adjacent node is in the closed table, it means that the adjacent node has been explored and is discarded. (3) If the adjacent node is neither in the open table nor in the closed table, put the adjacent node and its cost together in the open table. After the above judgment is completed, return to Step 2 to continue searching.

[0031] Beneficial effects: The present invention uses GIS technology to construct a gas pipeline network information system, and realizes real-time monitoring of gas pipeline network operating parameters such as temperature, pressure, and flow through a three-layer structure. Based on intelligent leak detection technology and a rapid response mechanism when a pipe burst occurs, gas leaks are quickly detected and valves and pressure regulators are closed to notify affected users. The present invention improves the level of gas pipeline network management and services, and at the same time uses a SCADA system for data collection and monitoring control, overcoming the shortcoming that simple GIS is difficult to monitor the operating status of the gas pipeline network, improving the response speed and efficiency to gas pipeline network bursts, reducing potential risks, and ensuring public safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 Shown is a flow chart of a gas pipeline safety monitoring method based on the Internet of Things;

[0033] Figure 2 The figure shows a schematic diagram of the architecture of a gas pipeline safety monitoring system based on the Internet of Things;

[0034] Figure 3 Shown is a schematic diagram of the implementation process of data sharing;

[0035] Figure 4 Shown is a schematic diagram of the specific process of the intelligent closing valve. DETAILED DESCRIPTION

[0036] It should be noted that:

[0037] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0038] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0039] Example 1

[0040] This embodiment introduces a gas pipeline safety monitoring method based on the Internet of Things. Figure 1 , the specific steps include:

[0041] S1: multiple pressure sensors are installed on the gas pipeline. When a leak occurs, the negative pressure wave generated by the leak point propagates to the detection point, causing the pressure at the detection point to be abnormal. The negative pressure wave collected by the detection point is uploaded to the SCADA system via the RTU. The SCADA system extracts the waveform feature data of the negative pressure wave collected by the detection point, inputs the waveform feature data into the pre-built pressure anomaly recognition model, obtains the type of negative pressure wave, and determines the gas pipeline state type according to the negative pressure wave type. The gas pipeline state type includes pipe burst, single-point leakage and multi-point leakage. The SCADA system makes corresponding alarms according to the gas pipeline state type and transmits the corresponding alarm information to the GIS, that is, generates corresponding alarm information according to pipe burst, single-point leakage and multi-point leakage. The alarm information includes the hazard level of maintenance for different gas pipeline state types, the tools and materials required for maintenance, and the number of people required for maintenance. Among them, the hazard level of pipe burst, multi-point leakage and single-point leakage and the number of people required for maintenance are reduced in turn, which is convenient for the dispatching center to dispatch corresponding maintenance resources to handle corresponding leaks according to different gas pipeline state types.

[0042] At the same time, users in different ranges can be evacuated in a targeted and scientific manner according to the different gas pipeline status types to reduce the scope of panic impact; among them, the evacuation ranges of pipe burst, multi-point leakage and single-point leakage are reduced in turn.

[0043] The negative pressure wave types include transient negative pressure waves, progressive negative pressure waves and focused negative pressure waves;

[0044] When a pipeline bursts suddenly, a transient negative pressure wave will be generated. The characteristics of this negative pressure wave are steep waveform, fast propagation speed, strong fluctuation and limited propagation distance; when there is a small single-point leakage hole in the pipeline, a gradual negative pressure wave will be generated. The characteristics of this negative pressure wave are relatively flat waveform, slow propagation speed, relatively weak fluctuation and long propagation distance; when there are multiple leakage points on the pipeline, multiple negative pressure waves will be generated, and these negative pressure waves will focus to form a focused negative pressure wave; the characteristic of this negative pressure wave is that the waveform propagation distance is short;

[0045] Secondly, the waveform characteristic data corresponding to the specific negative pressure wave type will change, such as waveform amplitude, waveform duration, waveform frequency, waveform rise time, waveform fall time, and waveform period; for example, the waveform characteristic data characteristics of the focused negative pressure wave are as follows:

[0046] The waveform amplitude will increase as the waveform is focused, because the energy density is high in the focused area; the waveform duration is relatively short; the waveform frequency of the focused negative pressure wave is higher, because the nonlinear characteristics and focusing effect cause the frequency of the waveform to increase; the waveform rise time is shorter, because the waveform can quickly reach the peak in the focused area; the waveform fall time is shorter, because the waveform can quickly fall back from the peak in the focused area; the waveform period is shorter, because the focusing effect enables the waveform to complete a period in a shorter time.

[0047] The training method of the pressure anomaly recognition model includes:

[0048] Collecting m groups of historical data, the historical data including waveform characteristic data and negative pressure wave types corresponding to the waveform characteristic data, and numerically numbering the negative pressure wave types; converting the historical data into a corresponding set of characteristic vectors;

[0049] The historical data is used as the input of the pressure anomaly recognition model. The pressure anomaly recognition model uses the negative pressure wave type numerical number corresponding to each set of waveform feature data as output, the negative pressure wave type numerical number actually corresponding to each set of waveform feature data as the prediction target, and minimizing the loss function value of the pressure anomaly recognition model as the training target; training is stopped when the loss function value of the pressure anomaly recognition model is less than or equal to the preset target loss value; the pressure anomaly recognition model is a support vector machine (SVM), a decision tree, and a random forest.

[0050] Loss function formula

[0051] MSE is the loss function value of the pressure anomaly recognition model, x is the feature vector group number; m is the number of feature vector groups; y is the number of feature vector groups; x is the numerical number of the predicted negative pressure wave type corresponding to the x-th group of waveform characteristic data, The numerical number of the actual negative pressure wave type corresponding to the x-th group of waveform characteristic data.

[0052] S2: GIS sends the corresponding alarm information. At the same time, according to the location of the on-site inspection personnel, it uses the shortest path strategy traversal search method to find the valves and pressure regulators that need to be closed and the shortest path for the inspection personnel to arrive at the site, and reports it to the dispatcher.

[0053] S3: The dispatcher confirms whether a pipe burst, single-point leakage or multiple-point leakage has occurred based on the upstream and downstream valves of the pipe burst location, the single-point leakage location and the multiple-point leakage location, the test results of the combustible gas detector in the well, the change in pipeline pressure or the report of the on-site inspection personnel. If confirmed, proceed to step S4, otherwise terminate the program.

[0054] S4: SCADA sends a closing command to the actuators of the relevant equipment to determine whether there are any actuators that have not responded. If the actuator has not responded, it goes to step S2 to expand the search and find other valves and pressure regulators that need to be closed; otherwise, it goes to step S5.

[0055] S5: Search for user information affected by gas cut-off in GIS.

[0056] S6: The affected users are notified via SMS or phone call, and the process ends.

[0057] Example 2

[0058] The gas pipeline safety monitoring method based on the Internet of Things of the present invention is implemented through a gas pipeline safety monitoring system. The architecture of the gas pipeline safety monitoring system is as follows: Figure 2 As shown. The system platform is developed based on Python, and it integrates a variety of core technologies, including plug-in bus, message bus, multi-node cluster management, unified address management and access object addressing service, message routing between plug-ins, object-oriented memory database, and synchronization and persistence of memory database. These technologies together form the foundation of the platform, enabling it to run cross-platform on different hardware environments (such as rack servers or PC servers), operating systems (including Unix, Linux or Windows), database systems (such as MySQL, SQL Server, etc.) and EJB / WEB containers (such as WebLogic, WebSphere, JBOSS, etc.), adapting to the needs of distributed environments.

[0059] From the perspective of software architecture, the system platform consists of multiple layers, including basic technology components, communication components, platform infrastructure components and business middleware from the bottom to the top. This hierarchical design not only clearly divides the functional modules of the platform, but also facilitates technical integration and functional expansion between different layers to meet the needs of various business applications.

[0060] On this basis, the platform provides secondary development interfaces for protocol plug-ins and business plug-ins, as well as SOA service call interfaces that provide open services for third-party systems. After the corresponding protocol plug-ins and business components are developed on the platform, access management, communication management, interconnection, information interaction and data exchange platforms can be provided for external integrated systems (including terminals). Intelligent processing of system information and data is carried out, coordinating each integrated system for mutual operation and linkage control, and providing new services based on the integration of each integrated system for connected terminals.

[0061] The data layer forms the core foundation of the unified spatial data analysis platform. It is compatible with a variety of popular database types, including Oracle, DB2, Microsoft SQL Server, Microsoft Access, and MySQL. This layer provides the necessary support for the data sharing function on the platform, covering the spatial location information and related attribute data of the gas pipeline network. Data from multiple systems are collected here, mainly including geographic information systems (GIS), supervisory control and data acquisition systems (SCADA), and global positioning system (GPS) detection equipment. The integration of these data provides a solid foundation for in-depth analysis and decision-making.

[0062] GIS has the ability to capture, manage, operate and analyze data related to the spatial data of the gas pipeline network, and can comprehensively and accurately manage gas pipeline network graphics, pipelines, valves and other key facilities. It can provide the latest information of the gas pipeline network system at any time for gas pipeline network management, planning and design, operation scheduling and decision-making, and provide an open and highly scalable information infrastructure platform for enterprises. GIS data mainly includes the following:

[0063] Pipeline spatial data, namely, pipeline centerline coordinates, pipeline burial depth, remote sensing images, coordinates and burial depth of important facilities (such as tees, elbows, reducers and thickening points, valves, and pressure regulating stations), pipeline crossing conditions, and the spatial orientation of adjacent facilities (such as pipelines, power lines, communication lines, roads and railways, bridges and tunnels, water conservancy facilities, rivers, and lakes); pipeline attribute and environmental data, namely, pipeline materials, specifications and models, pipeline facilities (valves, elbows, anti-corrosion coatings, cathodic protection, welds, steel pipe information, technical parameters, stray current interference, pipeline soil corrosion, etc.).

[0064] The SCADA system is used to monitor and control the operation of gas pipeline network equipment to ensure safe, reliable, stable, efficient and economical gas transmission. It monitors the real-time status of each monitoring point in the gas pipeline network and issues dispatch instructions and gas volume statistics at each monitoring point. The pressure, flow, temperature and other information of the gas are stored in the database of the SCADA system.

[0065] The GPS inspection system can supervise and manage inspection personnel and vehicle dispatch management to ensure that inspection personnel can accurately conduct inspections according to predefined patrol routes, locations and times, and provide inspection personnel with the shortest path navigation calculated by the shortest path strategy when abnormal events occur. The system not only realizes the full dynamic management of inspection personnel, but also realizes the real-time upload of hidden dangers, accidents and other event information during the inspection process, thereby minimizing accident hazards, achieving early control of accidents, and ensuring the safe operation of lines and equipment. The database of the GPS inspection system involves data including daily patrols, shadow protection operations, stray interference, third-party sabotage, emergency rescue, hidden danger detection and evaluation, risk assessment, etc.

[0066] Different business systems have different databases, data structures and data types. If a GIS wants to use data from other systems to achieve intelligence, it must establish a data sharing platform. The implementation process of data sharing is as follows: Figure 3 shown.

[0067] The data source covers a variety of database systems, including Oracle, DB2, Microsoft SQL Server, Microsoft Access, MySQL, etc. In the implementation of a specific project, one or more of the above commercial databases may be used. Although these commercial databases provide corresponding Java development driver packages, the process of cross-database development or data migration is still complex. For example, the stored procedures of different commercial databases are different, which requires a set of specific SQL scripts to be customized for each database. This system uses the Hibernate framework and implements a cross-commercial database operation mode by providing the HQL (similar to SQL) language, so that the upper-level plug-in can conveniently carry out cross-database development work by directly assembling HQL statements. In view of the strict requirements of the upper-level plug-in on the data reading and writing speed, it may not be able to meet the requirements if the commercial database is used directly for reading and writing operations. Therefore, the platform specially provides three different modes of memory database services: synchronous persistence, synchronous non-persistence, and asynchronous non-persistence, to adapt to the needs of the upper-level plug-in in different scenarios.

[0068] The data import method is to use URL management, JDBC connection, connection pool management and other technologies to import the source data into the data sharing platform; data integration: by defining operation rules, filtering rules, mapping rules and other rules, the source database data is reintegrated. The integrated data can be read and used by various business subsystems at any time; data use: data sharing between business subsystems is realized. For example, GIS needs to obtain data from the SCADA system. This process can be achieved in two ways. First, the automated method, that is, by setting a scheduled task, using specific commands to automatically obtain SCADA system data at a preset time; second, the manual method, that is, by creating a dedicated button, each click can manually read SCADA system data once.

[0069] Each business subsystem operates independently, but the isolated state of data and the isolation of processes hinder the effective closed-loop tracking of anomalies, accidents, and operational management. Although enterprises have a large amount of data statistics, they lack in-depth data analysis and intelligent decision-making mechanisms. This limits the use of accumulated business knowledge and data to discover the laws and patterns behind the data, and fails to provide effective decision-making support for management. Business integration provides a way to solve these problems.

[0070] GIS displays the layout and attribute information of gas pipeline networks and facilities, which belongs to the static category. The flow, pressure and temperature of the pipeline network belong to dynamic information, which comes from the SCADA system. Traditional GIS fails to include such dynamic information. By realizing data sharing and business process integration, GIS can access this dynamic information, thus providing a basis for pipeline network modeling, data analysis and control.

[0071] After data sharing is realized, GIS has the ability to access the real-time data of the SCADA system. Using the mapping function of GIS, the location of SCADA monitoring points can be accurately marked on the map, and the relevant real-time data can be displayed to facilitate effective scheduling and monitoring. In addition, GIS can also obtain real-time data and images or alarm information provided by the inspection system, quickly locate the specific location on the map, retrieve videos or images of relevant points, mark the alarm situation, and display these data.

[0072] The system is accessed through C / S and B / S modes. The C / S structure is mainly used to implement management functions such as input, modification, editing, updating, location query, retrieval, processing, statistical analysis, drawing, emergency dispatch and report generation of gas network graphics and attribute data. The B / S structure is mainly used to implement the query and retrieval functions of graphics and attribute data. Establishing an analysis model based on various spatial data and importing real-time data from the SCADA system and GPS inspection system into the model will improve the accuracy and real-time performance of the model. The powerful graphic display capability of GIS greatly enhances the visual analysis capability of the model.

[0073] In the SCADA system, certain monitoring points are particularly critical, such as valves and flow monitoring points. This requires the use of GIS to determine the location information of these monitoring points and their connection with the corresponding pipelines. Monitoring points identified as being associated with a specific pipeline will become associated monitoring points for that pipeline. When a pipeline has abnormal conditions such as single-point leakage, multiple-point leakage, pipe burst or other types of accidents, the monitoring center will activate a mechanism that enables these associated monitoring points to communicate directly with each other, bypassing the monitoring center, thereby speeding up the transmission of information. More importantly, this setting allows the remote and automatic closure of related valves in the pipeline through monitoring points, avoiding the need for on-site maintenance personnel to manually intervene to close the valves, and realizing the intelligent automatic closing function of the valves. The specific process of intelligent valve closing is shown in Figure 4 middle.

[0074] Example 3

[0075] The shortest path strategy of the present invention is a node traversal method based on path finding, which determines the shortest path by searching all possible nodes. This can be seen as an extension of Dijkstra's algorithm, but the shortest path strategy achieves better performance by using a heuristic algorithm to guide its search. This feature of completely searching all possible nodes in a certain order and storing them in memory enables the shortest path strategy to generate the optimal path, and its performance is better than most other algorithms.

[0076] The search process of the shortest path strategy is as follows:

[0077] Step 1: Data preparation. Input the start node and target node into the algorithm and put the start node into an open table. An open table is used to store all available nodes.

[0078] Step 2: Select a node. Select the node with the lowest cost from the opened table. The cost of a node consists of two parts: the spatial distance from the node to the target node and the actual distance from the node to the starting node.

[0079] Step3: Check the selected node. If the selected node is the target node, a path from the start node to the target node is found, and the search ends. Otherwise, the process continues to Step4 to continue expanding the node.

[0080] Step 4: Expand the selected node. Find the nodes adjacent to the selected node, calculate their costs, and then transfer the selected node from the open table to the closed table (the closed table is used to store all explored nodes). The management principles for adjacent nodes are as follows: (1) If the adjacent node is already in the open table and the cost of the node is lower than the node in the table, update the cost of the corresponding node in the list. (2) If the adjacent nodes are in the closed table, that is, they have been explored, discard them. (3) If the adjacent nodes are neither in the open table nor in the closed table, put them and their costs together in the open table. After making these judgments, return to Step 2 to continue searching. The following is a specific code for Python to implement the shortest path strategy.

[0081]

[0082]

[0083]

[0084]

[0085] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0089] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A gas pipeline safety monitoring method based on the Internet of Things, characterized in that: include: S1: multiple pressure sensors are installed on the gas pipeline. When a leak occurs, the negative pressure wave generated at the leak point propagates to the detection point, causing abnormal pressure at the detection point. The negative pressure wave collected at the detection point is uploaded to the SCADA system via the RTU. The SCADA system extracts the waveform feature data of the negative pressure wave collected at the detection point, inputs the waveform feature data into a pre-built pressure anomaly recognition model, obtains the type of negative pressure wave, and determines the gas pipeline state type according to the negative pressure wave type. The gas pipeline state type includes pipe burst, single-point leakage and multi-point leakage. The SCADA system issues a corresponding alarm according to the gas pipeline state type and transmits the corresponding alarm information to the GIS. S2: The GIS sends the corresponding alarm information, and the GPS inspection system uses the shortest path strategy traversal search method to find the valves and pressure regulators that need to be closed and the shortest path for the inspection personnel to arrive at the site according to the location of the on-site inspection personnel, and reports it to the dispatcher; S3: The dispatcher confirms whether a pipe burst, single-point leakage or multiple-point leakage occurs based on the upstream and downstream valves of the pipe burst location, the single-point leakage location and the multiple-point leakage location, the detection results of the combustible gas detector in the well, the change of pipeline pressure or the report of the on-site inspection personnel. If confirmed, the process proceeds to step S4, otherwise the process terminates; S4: The SCADA sends a closing command to the actuator of the relevant equipment to determine whether there is an actuator that does not respond. If the actuator does not respond, the process goes to step S2 to expand the search and find the valves and pressure regulators that need to be closed; otherwise, the process goes to step S5; S5: searching the GIS for user information affected by the gas cut-off; S6: Notify the affected users via SMS or phone call, ending; The negative pressure wave types include transient negative pressure waves, gradual negative pressure waves and focused negative pressure waves; the gas pipeline state type corresponding to the negative pressure wave type of transient negative pressure waves is marked as pipe burst; the gas pipeline state type corresponding to the negative pressure wave type of gradual negative pressure waves is marked as single-point leakage; the gas pipeline state type corresponding to the negative pressure wave type of focused negative pressure waves is marked as multi-point leakage; The SCADA system is used to monitor and control the operation of gas pipeline network equipment; the SCADA system monitors the real-time status of each monitoring point in the gas pipeline network, and issues dispatch instructions and gas volume statistics of each monitoring point; the pressure, flow and temperature information of the gas are stored in the database of the SCADA system; The SCADA system determines the associated monitoring points in the gas pipeline through the GIS; when a burst, single-point leakage or multi-point leakage occurs in the gas pipeline, the associated monitoring points will bypass the monitoring center and communicate directly with each other, and remotely and automatically close the corresponding valves in the pipeline; The GPS inspection system supervises and manages the inspection personnel and vehicle dispatch management to ensure that the inspection personnel conduct inspections according to the predefined patrol routes, locations and times, and provides the inspection personnel with the shortest path navigation calculated by the shortest path strategy when an abnormal event occurs; the GPS inspection system conducts full dynamic management of the inspection personnel, and uploads the hidden dangers and accident event information in real time during the inspection process; The data involved in the database of the GPS inspection system include: daily patrols, shadow protection operations, stray interference, third-party sabotage, emergency rescue, hidden danger detection and assessment, and risk assessment.

2. According to claim 1, a gas pipeline safety monitoring method based on the Internet of Things is characterized by: The training method of the pressure abnormality recognition model includes: Collect m groups of historical data, where m is an integer greater than 1, and the historical data includes waveform characteristic data and negative pressure wave types corresponding to the waveform characteristic data, and numerically number the negative pressure wave types; convert the historical data into a corresponding set of characteristic vectors; The historical data is used as the input of the pressure anomaly recognition model, the pressure anomaly recognition model takes the negative pressure wave type numerical number corresponding to each set of waveform feature data as the output, takes the negative pressure wave type numerical number actually corresponding to each set of waveform feature data as the prediction target, and takes minimizing the loss function value of the pressure anomaly recognition model as the training target; the training is stopped when the loss function value of the pressure anomaly recognition model is less than or equal to the preset target loss value; the pressure anomaly recognition model is a support vector machine, a decision tree or a random forest.

3. According to claim 2, a gas pipeline safety monitoring method based on the Internet of Things is characterized by: The GIS has the ability to capture, manage, operate and analyze data related to the gas pipeline network space, and is used to manage gas pipeline network graphics, pipelines, and valves; the GIS provides the latest information of the gas pipeline network system at any time to achieve gas pipeline network management, planning and design, operation scheduling and decision-making; The GIS data include: pipeline spatial data, including pipeline centerline coordinates, pipeline burial depth, remote sensing images, coordinates and burial depth of important facilities, pipeline crossing conditions and spatial orientation of adjacent facilities; pipeline attribute and environmental data, namely pipeline materials, specifications and models, pipeline facilities; among which, important facilities include tees, elbows, diameter reduction points and thickening points, valves, and pressure regulating stations; adjacent facilities include pipelines, power lines, communication lines, roads and railways, bridges and tunnels, water conservancy facilities, rivers, and lakes; pipeline facilities include valves, elbows, anti-corrosion coatings, cathodic protection, welds, steel pipe information, technical parameters, stray current interference, and pipeline soil corrosion.

4. According to claim 3, a gas pipeline safety monitoring method based on the Internet of Things is characterized by: The GIS establishes a data sharing platform with other systems to utilize the data of other systems to achieve intelligence; the data sources of the data sharing platform include Oracle, DB2, Microsoft SQL Server, Microsoft Access, and MySQL database systems.

5. According to claim 4, a gas pipeline safety monitoring method based on the Internet of Things is characterized by: The data import method of the data sharing platform is to import the source data into the data sharing platform using URL management, JDBC connection, and connection pool management technology; by defining operation rules, filtering rules, and mapping rules, the source database is reintegrated, and the integrated data can be read and used by each business subsystem at any time; the data sharing between the business subsystems is achieved through automated or manual methods.

6. According to the method for gas pipeline safety monitoring based on the Internet of Things according to claim 5, it is characterized in that: The shortest path strategy process is as follows: Step 1: Input the starting node and the target node into the algorithm, and put the starting node into an open table; an open table is used to store all available nodes; Step 2: Select the node with the lowest cost from the open table; The cost of a node consists of two parts: the spatial distance from the node to the target node and the actual distance from the node to the start node; Step 3: If the selected node is the target node, the path from the start node to the target node is found and the search ends; otherwise, the process continues to Step 4 to continue expanding the node; Step 4: Find the nodes adjacent to the selected node, calculate their costs, and then transfer the selected node from the open table to the closed table, which is used to store all explored nodes. The management principles for adjacent nodes are as follows: (1) If the adjacent node is already in the open table and the cost of the adjacent node is lower than the node in the open table, then update the cost of the corresponding node in the open table; (2) If the adjacent node is in the closed table, it means that the adjacent node has been explored and is discarded; (3) If the adjacent node is neither in the open table nor in the closed table, the adjacent node and its cost are placed in the open table together; the above judgment is completed and return to Step 2 to continue searching.

Images