Method for quickly identifying topological structure change of gas pipe network

Abstract

The invention provides a method for quickly identifying topological structure change of a gas pipe network. The method comprises the following steps: acquiring data of gas pressure, flow and temperature; modeling the topological structure of the gas pipe network based on the data of gas pressure, flow and temperature; the method comprises the following steps: judging data of gas pressure, flow and temperature through a real-time data monitoring system, and performing feature extraction on historical data and real-time data of an abnormal pipe section and related areas around the abnormal pipe section after judging that the abnormal pipe section is abnormal; embedding a hydraulic equilibrium constraint in the fitness function; performing optimization search on the topological structure of the gas pipe network based on a genetic algorithm; and identifying and adjusting the topological structure of the gas pipe network according to the optimization result of the genetic algorithm. According to the method, the operation characteristics of the gas pipe network under different working conditions are researched, and a basis is provided for optimization design, operation management and accident prevention and treatment of the pipe network.

Description

Technical Field

[0001] This application relates to the field of gas pipeline network monitoring and management technology, specifically to a method for rapidly identifying changes in the topology of a gas pipeline network. Background Technology

[0002] A gas pipeline network is a complex transmission system composed of numerous interconnected pipes, valves, pressure regulators, and other components. Its primary function is to transport natural gas from gas sources (such as natural gas gate stations and storage and distribution stations) to various users (residential, commercial, and industrial). In actual operation, the topology of the pipeline network can change due to various factors. When a valve in the pipeline network is closed, the previously connected pipeline is severed, and the gas can no longer be transported through that path.

[0003] Currently, many gas pipeline networks rely primarily on manual inspections and simple sensors to monitor their operational status. Manual inspections are inefficient and cannot provide real-time updates on network dynamics. Existing sensors typically monitor only local parameters (such as pressure and flow rate) and have low sensitivity to topological changes, failing to promptly detect topological shifts caused by events like valve closures or pipeline leaks. When topological changes are detected, existing responses are often fragmented and unsystematic. For example, after a valve closure, adjustments to other valve openings and gas supply rely mainly on manual experience; this method is imprecise and struggles to quickly restore the network to normal operation. In handling pipeline leaks, effective emergency adjustment strategies are lacking to minimize impact on users and damage to the network. Traditional methods, such as relying solely on physical or data-driven models, struggle to balance accuracy and real-time performance. While physical models are accurate, they require extensive computation under complex real-world conditions, hindering rapid response. Data-driven models, while capable of handling complex nonlinear relationships, demand high-quality and high-quantity data and lack a deep understanding of the physical laws governing gas pipeline networks. In terms of emergency adjustments, there is a lack of effective algorithms for rapid optimization of pipeline network topology to cope with emergencies. Summary of the Invention

[0004] This application provides a method for quickly identifying changes in the topology of a gas pipeline network, which can effectively solve the above-mentioned problems.

[0005] The specific technical solution of this embodiment is as follows:

[0006] This application provides a method for quickly identifying changes in the topology of a gas pipeline network, including the following steps:

[0007] Acquire data on gas pressure, flow rate, and temperature;

[0008] The topology of the gas pipeline network is modeled based on data of gas pressure, flow rate and temperature.

[0009] The system uses a real-time data monitoring system to assess gas pressure, flow rate, and temperature. Once an anomaly is identified, features are extracted from historical and real-time data of the abnormal pipe section and its surrounding areas.

[0010] Embed hydraulic balance constraints in the fitness function;

[0011] The topology of the gas pipeline network is optimized and searched based on a genetic algorithm.

[0012] Based on the optimization results of the genetic algorithm, the topology of the gas pipeline network is identified and adjusted.

[0013] In some embodiments, in the step of optimizing the topology of the gas pipeline network based on the genetic algorithm, the genetic algorithm selection operation adopts the tournament selection method, which selects excellent individuals to enter the breeding pool by comparing the fitness values ​​of individuals.

[0014] The crossover operation uses a combination of single-point crossover and multi-point crossover, while the mutation operation uses bit-flip mutation on the binary code part. During the evolution of the genetic algorithm, the convergence speed and optimization effect of the algorithm are controlled by setting the number of iterations, population size, crossover probability, and mutation probability.

[0015] In some embodiments, the steps of acquiring gas pressure, flow rate and temperature data further include: performing preliminary clearing and verification on the collected data, and performing standardization, normalization and missing data completion operations on the data.

[0016] In some embodiments, the step of modeling the topology of the gas pipeline network includes modeling the connection relationships and location information of pipes, valves, pressure regulators, and meters.

[0017] Based on the obtained model, an association matrix of the pipeline network is constructed, where the rows and columns of the matrix represent different pipe segments and nodes, respectively; and the valve status in the pipeline network is encoded in binary, and the continuous parameters of the pipe segments are encoded in real numbers.

[0018] In some embodiments, hydraulic balance constraints are embedded in the fitness function so that the generated topology conforms to the basic laws of fluid mechanics. In the process, the fitness function for multi-objective optimization is constructed with the goal of minimizing the number of valve operations, minimizing the adjustment range of pipe segment parameters, and achieving optimal hydraulic balance of the pipe network.

[0019] In some embodiments, in the step of optimizing the topology of the gas pipeline network based on the genetic algorithm, a chromosome is formed by the valve state encoding vector and the pipe segment parameter encoding vector. The length of the chromosome is the sum of the number of valves and the number of pipe segments. Each chromosome represents a possible pipeline network topology adjustment scheme, where the binary part represents the valve's on / off state and the real part represents the pipe segment parameter adjustment.

[0020] Compared with the prior art, the embodiments of this application have the following beneficial effects:

[0021] By simulating different operating conditions on the constructed gas pipeline network, including leakage, valve closure, and new user access, corresponding pressure and flow data were collected. The collected data underwent preliminary cleaning and verification, including data standardization, normalization, and missing data completion. The parameter variation patterns when the pipeline network topology changes were analyzed. The study of the operational characteristics of the gas pipeline network under different operating conditions provides a basis for the optimized design, operation management, and accident prevention and handling of the pipeline network. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a method for rapidly identifying changes in the topology of a gas pipeline network, provided in some embodiments of this application.

[0024] Figure 2 This is a schematic diagram of the gas pipeline network topology in a method for rapidly identifying changes in the topology of a gas pipeline network provided in some embodiments of this application;

[0025] Figure 3 These are simulation diagrams of pipeline structures provided in some embodiments of this application. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] "A and / or B" includes the following three combinations: A only, B only, and a combination of A and B.

[0029] The use of "applies to" or "configured to" in this application implies open and inclusive language, which does not exclude the applicability to or configuration to devices performing additional tasks or steps. Additionally, the use of "based on" implies openness and inclusivity, because processes, steps, calculations, or other actions "based on" one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0030] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0031] This application provides a method for quickly identifying changes in the topology of a gas pipeline network, including the following steps:

[0032] Acquire data on gas pressure, flow rate, and temperature;

[0033] The topology of the gas pipeline network is modeled based on data of gas pressure, flow rate and temperature.

[0034] The system uses a real-time data monitoring system to assess gas pressure, flow rate, and temperature. Once an anomaly is identified, features are extracted from historical and real-time data of the abnormal pipe section and its surrounding areas.

[0035] Embed hydraulic balance constraints in the fitness function;

[0036] The topology of the gas pipeline network is optimized and searched based on a genetic algorithm.

[0037] Based on the optimization results of the genetic algorithm, the topology of the gas pipeline network is identified and adjusted.

[0038] In some embodiments, in the step of optimizing the topology of the gas pipeline network based on the genetic algorithm, the genetic algorithm selection operation adopts the tournament selection method, which selects excellent individuals to enter the breeding pool by comparing the fitness values ​​of individuals.

[0039] The crossover operation uses a combination of single-point crossover and multi-point crossover, while the mutation operation uses bit-flip mutation on the binary code part. During the evolution of the genetic algorithm, the convergence speed and optimization effect of the algorithm are controlled by setting the number of iterations, population size, crossover probability, and mutation probability.

[0040] In some embodiments, the steps of acquiring gas pressure, flow rate and temperature data further include: performing preliminary clearing and verification on the collected data, and performing standardization, normalization and missing data completion operations on the data.

[0041] In some embodiments, the step of modeling the topology of the gas pipeline network includes modeling the connection relationships and location information of pipes, valves, pressure regulators, and meters.

[0042] Based on the obtained model, an association matrix of the pipeline network is constructed, where the rows and columns of the matrix represent different pipe segments and nodes, respectively; and the valve status in the pipeline network is encoded in binary, and the continuous parameters of the pipe segments are encoded in real numbers.

[0043] In some embodiments, hydraulic balance constraints are embedded in the fitness function so that the generated topology conforms to the basic laws of fluid mechanics. In the process, the fitness function for multi-objective optimization is constructed with the goal of minimizing the number of valve operations, minimizing the adjustment range of pipe segment parameters, and achieving optimal hydraulic balance of the pipe network.

[0044] In some embodiments, in the step of optimizing the topology of the gas pipeline network based on the genetic algorithm, a chromosome is formed by the valve state encoding vector and the pipe segment parameter encoding vector. The length of the chromosome is the sum of the number of valves and the number of pipe segments. Each chromosome represents a possible pipeline network topology adjustment scheme, where the binary part represents the valve's on / off state and the real part represents the pipe segment parameter adjustment. Specific implementation examples:

[0046] Step 1: Deploy sensors at key nodes in the gas pipeline network to monitor critical parameters such as gas pressure, flow rate, and temperature in real time. Perform preliminary data processing and verification, including data standardization, normalization, and data completion for missing data.

[0047] Step 2: Perform detailed topology modeling of the gas pipeline network, including the connection relationships and location information of various components such as pipes, valves, pressure regulators, and meters. Based on this model, construct the network's association matrix, where rows and columns represent different pipe segments and nodes, respectively. Use binary encoding for valve status and real-number encoding for continuous parameters of pipe segments, such as pipe diameter, length, and roughness.

[0048] Step 3: Establish a real-time data monitoring system to continuously monitor key parameters of the gas pipeline network. Upon detecting an anomaly, extract features from historical and real-time data of the abnormal pipeline section and its surrounding areas.

[0049] Step 4: Embed hydraulic balance constraints in the fitness function to ensure that the generated topology adjustment scheme conforms to the basic laws of fluid mechanics. A multi-objective optimization fitness function is constructed with the optimization objectives of minimizing valve operations, minimizing pipe segment parameter adjustments, and achieving optimal hydraulic balance in the pipe network.

[0050] Step 5: Utilize a genetic algorithm to optimize the topology of the gas pipeline network. Chromosomes are formed by combining valve status encoding vectors and pipe segment parameter encoding vectors, where the length of a chromosome is the sum of the number of valves and the number of pipe segments. Each chromosome represents a possible pipeline topology adjustment scheme, where the binary part represents the valve's on / off state, and the real part represents the pipe segment parameter adjustment.

[0051] Step Six: In the genetic algorithm, the selection operation uses tournament selection, which selects superior individuals to enter the breeding pool by comparing their fitness values. The crossover operation uses a combination of single-point crossover and multi-point crossover, and the mutation operation uses bit-flip mutation on the binary encoding part. During the evolution of the genetic algorithm, the convergence speed and optimization effect are controlled by setting appropriate parameters such as the number of iterations, population size, crossover probability, and mutation probability.

[0052] Step 7: Based on the optimization results of the genetic algorithm, the topology of the gas pipeline network is identified and adjusted. For identified topology change events such as valve shutdown, pipeline leakage, or new user access, the system automatically generates corresponding adjustment strategies.

[0053] By simulating different operating conditions on the constructed gas pipeline network, including leakage, valve closure, and new user access, corresponding pressure and flow data were collected. The collected data underwent preliminary cleaning and verification, including data standardization, normalization, and missing data completion. The parameter variation patterns when the pipeline network topology changes were analyzed. The study of the operational characteristics of the gas pipeline network under different operating conditions provides a basis for the optimized design, operation management, and accident prevention and handling of the pipeline network.

[0054] A structural model of a natural gas pipeline network was established using TGNET software. Basic data for the simulated pipeline were imported and simulated based on experimental data from the experimental pipeline network. Data sets of pipeline pressure, flow rate, and temperature collected and processed from both simulation and experiments were used for subsequent analysis and optimization. The feasibility of using a genetic algorithm to identify and optimize changes in pipeline topology was preliminarily verified, laying the foundation for future research.

[0055] In this optimization study, a genetic algorithm was chosen as the optimization tool. The genetic algorithm can automatically identify changes in the pipeline network topology, such as valve closures or pipeline leaks. Once a structural change is detected, the algorithm quickly generates corresponding adjustment strategies based on the current pipeline network status and the optimization objective, such as reallocating flow or adjusting valve openings. By continuously adjusting the model parameters and optimization algorithm, the performance of the genetic algorithm is improved, enabling it to better adapt to the complexity and dynamics of changes in the gas pipeline network topology, thereby achieving efficient and reliable pipeline network optimization.

[0056] Optimizing pipeline network topology using a genetic algorithm involves embedding hydraulic balance constraints into the fitness function. A multi-objective optimization fitness function is constructed, aiming to minimize valve operations, reduce pipe segment parameter adjustments, and achieve optimal pipeline hydraulic balance. The genetic algorithm topology optimization process is described below. Figure 1 The population size is denoted as M.

[0057] The pipeline structure of the pipeline network monitoring experimental platform was simulated using TGNET software. Figure 3 The basic attribute data of the experimental pipeline network and the monitoring data of pipeline operation were substituted into the simulation model, and the simulation operation data were verified using the experimentally collected data. After verification, the updated pipeline network model was simulated again to obtain the operating status data of the medium-pressure gas distribution pipeline network under different operating conditions.

[0058] China Jiliang University Gas Pipeline Network Experimental Platform Figure 2As shown, each control point has a pressure transmitter measuring point, which can process the pressure signal at the control point, as well as the flow data at the air inlet and each load point, into a system (simulated SCADA system) to realize real-time monitoring and data acquisition of the simulated pipeline network operation.

[0059] Based on the gas pipeline network experimental platform of China Jiliang University, a simulation model of the gas pipeline network was established using the offline fluid simulation software Pipeline Studio, as follows: Figure 3 .

[0060] 1. Leakage simulation: Adjust the opening of the leakage ball valve to different openings such as 10, 20, and 30, and at the same time adjust the pressure of the air source point to three pressure levels of 0.1MPa, 0.2MPa, and 0.3MPa, in order to simulate different degrees of leakage.

[0061] 2. Valve shut-off simulation: Simulate the operation by changing the opening and closing states of valves 1 and 2, including different combinations of fully open and closed states, such as valve 1 open and valve 2 closed; valve 1 closed and valve 2 open; valves 1 and 2 closed at the same time, etc. At the same time, the gas source pressure has two different pressure levels: 0.1MPa and 0.2MPa.

[0062] 3. New User Onboarding Simulation: This mainly involves adjusting the gas consumption of new users, with gas consumption values ​​ranging from 1m³ / s. 3 / h、3m 3 / h、5m 3 The gas supply point pressures were also set to three different levels ( / h) and 0.1MPa, 0.2MPa, and 0.3MPa, respectively, to simulate the connection of new users with different gas loads.

[0063] Equipment Inspection and Commissioning: Carefully inspect the entire pipeline system and all connections to ensure they are properly sealed and leak-free. Check that valves open and close correctly, sensors are installed in the correct positions, and the data acquisition system is functioning properly. Commission the gas supply equipment to ensure it can output stable gas pressure and flow.

[0064] Initial parameter settings: Open all valves to bring the pipeline network into normal operating condition. Record the flow rate of each pipeline and the pressure at each monitoring point at this time as initial operating condition data.

[0065] Operating condition simulation phase

[0066] (1) Leakage condition simulation

[0067] Simulation method: Select a pipe in the pipeline network, simulate the leakage point with a ball valve, and adjust the leakage size by adjusting the opening of the ball valve.

[0068] Data Acquisition: Immediately after the leak occurs, start collecting flow data from each pipeline and pressure data from each monitoring point, record continuously for a period of time, observe the changes in pressure and flow over time, and the changes in flow and pressure in the pipelines upstream and downstream of the leak point.

[0069] (2) Simulation of valve shut-off condition

[0070] Simulation method: Perform shut-off operations on valves 1 and 2 separately. First, slowly close valve 1 and observe the changes in pressure and flow in the pipeline system; then restore valve 1 to its normal open state, and slowly close valve 2. Then close valves 1 and 2 simultaneously, and perform the same observation and data collection.

[0071] Data acquisition: During the valve shut-off process, the flow rate of each pipeline and the pressure changes at each monitoring point are recorded in real time, with a focus on sudden changes in pressure and flow rate in the pipelines before and after the valve and the impact range on the entire pipeline network.

[0072] (3) Simulation of new user access conditions

[0073] Simulation method: Add a simulated user branch pipe at a suitable location in the pipeline network (such as near the end of Pipe 4). Install a flow regulating device on the branch pipe to simulate the connection of new users with different gas consumption. Adjust the flow rate of the branch pipe to gradually increase the gas consumption of the new users, simulating the situation where new users start using gas and gradually increase their gas load.

[0074] Data Acquisition: During the process of new user access, flow rate data of each pipeline and pressure data of each monitoring point are continuously collected to analyze the impact of new user access on the pressure distribution and flow transmission of the original pipeline network.

[0075] Experimental End Phase

[0076] All collected data were organized and stored separately according to different operating conditions to ensure data integrity and accuracy. The gas supply equipment was shut off, and each valve was closed sequentially to restore the pipeline system to its initial state. The experimental equipment was cleaned and inspected to ensure it was functioning properly and undamaged.

[0077] Data processing and analysis

[0078] Data processing: The collected raw data undergoes preliminary processing, such as removing outliers and smoothing the data. Then, curves showing the changes in pipeline flow and pressure over time under various operating conditions, as well as curves showing the relationship between pressure and flow at different locations, are plotted to more intuitively observe the data trends.

[0079] Data Analysis: By comparing data curves under different operating conditions, this study analyzes the degree and scope of the impact of leakage, valve closure, and new user access on pipeline pressure and flow. It investigates the changing patterns of pressure loss and flow distribution in the pipeline under various operating conditions to identify key influencing factors. Finally, it summarizes the operational characteristics of the pipeline under different operating conditions, providing a theoretical basis for pipeline optimization design, operation scheduling, and accident early warning based on genetic algorithms.

[0080] This application uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for rapidly identifying changes in the topology of a gas pipeline network, characterized in that, Includes the following steps: Acquire data on gas pressure, flow rate, and temperature; The topology of the gas pipeline network is modeled based on data of gas pressure, flow rate and temperature. The system uses a real-time data monitoring system to assess gas pressure, flow rate, and temperature. Once an anomaly is identified, features are extracted from historical and real-time data of the abnormal pipe section and its surrounding areas. Embed hydraulic balance constraints in the fitness function; The topology of the gas pipeline network is optimized and searched based on a genetic algorithm. Based on the optimization results of the genetic algorithm, the topology of the gas pipeline network is identified and adjusted.

2. The method for rapidly identifying changes in the topology of a gas pipeline network according to claim 1, characterized in that, In the search step of optimizing the topology of the gas pipeline network based on the genetic algorithm, the selection operation of the genetic algorithm adopts the tournament selection method, which selects excellent individuals into the breeding pool by comparing the fitness values ​​of individuals. The crossover operation uses a combination of single-point crossover and multi-point crossover, while the mutation operation uses bit-flip mutation on the binary code part. During the evolution of the genetic algorithm, the convergence speed and optimization effect of the algorithm are controlled by setting the number of iterations, population size, crossover probability, and mutation probability.

3. The method for rapidly identifying changes in the topology of a gas pipeline network according to claim 1, characterized in that, The steps for obtaining gas pressure, flow rate, and temperature data also include: preliminary data clearing and verification, as well as data standardization, normalization, and missing data completion.

4. The method for rapidly identifying changes in the topology of a gas pipeline network according to claim 1, characterized in that, The steps of modeling the topology of the gas pipeline network include the connection relationships and location information of pipes, valves, pressure regulators, and meters. Based on the obtained model, an association matrix of the pipeline network is constructed, where the rows and columns of the matrix represent different pipe segments and nodes, respectively; and the valve status in the pipeline network is encoded in binary, and the continuous parameters of the pipe segments are encoded in real numbers.

5. The method for rapidly identifying changes in the topology of a gas pipeline network according to claim 1, characterized in that, Hydraulic balance constraints are embedded in the fitness function to ensure that the generated topology conforms to the basic laws of fluid mechanics. In the process, the optimization objectives are to minimize the number of valve operations, minimize the adjustment range of pipe segment parameters, and achieve optimal hydraulic balance of the pipe network. A multi-objective optimization fitness function is constructed.

6. The method for rapidly identifying changes in the topology of a gas pipeline network according to claim 1, characterized in that, In the optimization search step of the gas pipeline network topology based on the genetic algorithm, a chromosome is formed by the valve state encoding vector and the pipe segment parameter encoding vector. The length of the chromosome is the sum of the number of valves and the number of pipe segments. Each chromosome represents a possible pipeline network topology adjustment scheme. The binary part represents the valve opening and closing state, and the real part represents the parameter adjustment of the pipe segment.

Images