An intelligent gas pipeline network monitoring method and system

Abstract

The present invention relates to the field of gas pipeline monitoring, and in particular to an intelligent gas pipeline network monitoring method and system thereof, comprising acquiring pipeline network data information, establishing a pipeline network integrity level identification neural network model, using the acquired historical pipeline network data information as a training sample, and inputting it into the pipeline network integrity level identification neural network model; defining the pipeline network pressure according to the judgment of the integrity of the pipeline network; calculating the pipeline network pressure adjustment parameter in combination with the pipeline network related data information; adjusting the preset pipeline network pressure according to the pipeline network pressure adjustment parameter; calculating the maintenance frequency of the gas pipeline network system according to the output result of the pipeline network integrity level identification neural network model; establishing a pipeline network health monitoring model through the adjusted pipeline network pressure situation, and realizing the monitoring of the operating status of the gas pipeline network system.

Description

Technical Field

[0001] The present invention relates to the field of gas pipeline monitoring, and in particular to an intelligent gas pipeline network monitoring method and system. Background Art

[0002] In industrial production and infrastructure operations, pipeline systems play a vital role, including the transportation of liquids, gases and other substances. However, the operation of pipeline systems is affected by many factors, such as aging, wear, corrosion, external force damage, etc. These problems may cause pipeline leaks, explosions or other serious accidents, posing huge risks to personnel safety and the environment. Traditional pipeline monitoring methods usually rely on manual or simple tools, which are inefficient, costly, and have safety hazards.

[0003] With the development of artificial intelligence technology, the use of machine learning and other technologies for gas pipeline monitoring has become a major advancement, but the existing technology still has the following problems: it is impossible to effectively and objectively distinguish different pipeline conditions; thus, the key parameters for analysis cannot be obtained; the basic modeling recognition accuracy is not high and the adaptability is poor; and there is no adjustment of parameters through multiple influencing factors.

[0004] Therefore, there is a need for an intelligent gas pipeline network monitoring method and system. Summary of the invention

[0005] The present invention provides an intelligent gas pipeline network monitoring method and system, which aims to monitor and analyze the status of the pipeline system in real time, discover abnormal conditions and potential risks; improve maintenance efficiency, reduce labor costs, and reduce monitoring blind spots; predict the occurrence of pipeline problems, provide early warnings and suggestions, and help operators take timely measures; and effectively monitor the safety, reliability, and sustainable operation of the pipeline system.

[0006] The technical solution of the present invention is specifically as follows:

[0007] An intelligent gas pipeline network monitoring method comprises the following steps:

[0008] Step S1. Obtain gas pipeline network data information, establish a pipeline network integrity level recognition neural network model, use the obtained historical pipeline network data information as training samples, and input it into the pipeline network integrity level recognition neural network model;

[0009] Step S2. Based on the judgment of the integrity of the pipeline network, define the pipeline network pressure; and calculate the pipeline network pressure adjustment parameters in combination with the relevant data information of the pipeline network;

[0010] Step S3. According to the network pressure adjustment parameter, adjust the preset network pressure; according to the output result of the network integrity level identification neural network model, calculate the maintenance frequency of the gas network system ;

[0011] Step S4: Establish a pipeline health monitoring model based on the adjusted pipeline pressure to monitor the operating status of the gas pipeline system.

[0012] Further, step S1 specifically includes:

[0013] The pipeline network integrity level recognition neural network model includes an input layer, a recognition layer, a deep analysis layer, and an output layer;

[0014] It is defined that the preprocessed pipeline network related data information has a total of X features, in which the input layer and the analysis layer transmit feature information through the fully connected layer, and the pipeline network data is identified and analyzed in the recognition layer. The specific process is as follows:

[0015] ;

[0016] in, Represents the input of the recognition layer; Represents the connection weight between the input layer and the recognition layer; Represents the first Characteristic data information, ; represents the bias of the recognition layer; Represents the output of the recognition layer; represents the first recognition coefficient; represents the second identification coefficient; Indicates the total duration of the selected historical pipe network data; Indicates The priority level of each sensor; Indicates the number of deployed sensors.

[0017] Further, step S1 specifically includes:

[0018] The recognition result of the recognition layer is transmitted to the deep analysis layer, and the pipeline network integrity level recognition neural network model analyzes and processes the output of the recognition layer; the calculation result of the deep analysis layer is transmitted to the output layer, and the output layer outputs the final pipeline network integrity level result.

[0019] Further, step S2 specifically includes:

[0020] if , it means that the pipe network is in an excellent state, and the initial pipe network pressure is defined as , ;

[0021] if , it means that the pipe network is in good condition, so the initial pipe network pressure is defined as , ;

[0022] if , it means that the pipeline network is in a risky state, so the initial pipeline network pressure is defined as , ;

[0023] in, It represents the fluctuation coefficient of pipeline network integrity; Indicates the pipe network pressure under standard conditions; , , They represent the coefficients corresponding to different conditions of pipeline network integrity; represents the first judgment threshold, Indicates the second judgment threshold.

[0024] Further, the specific process is as follows:

[0025] ;

[0026] in, Indicates the regulating parameter of the pipe network pressure; represents the correction factor; Indicates the number of times blockage or deposits occur; It represents the cost caused by blockage or sedimentation in the jdth network channel; Indicates the flow rate in the pipeline when the pipe network system is working; Indicates the upper limit flow value specified in the pipeline; Indicates the flow rate of liquid or gas in the pipeline; Indicates the flow coefficient of the control valve; Indicates the density of the fluid; Represents the influence function of humidity around the pipe network on the pipe network pressure; Indicates the influence coefficient of humidity around the pipe network; Represents the temperature state variable of the pipe network; represents the vibration amplitude variable of the pipe network; Indicates the state variables of valves and joints; , , Represent the corresponding influence weights respectively.

[0027] Further, step S3 specifically includes:

[0028] The pipeline network pressure adjustment parameter is compared with a predefined comparison parameter of the pipeline network pressure adjustment parameter, and the pipeline network pressure is adjusted according to the comparison result; the predefined first pipeline network pressure adjustment parameter comparison parameter is , the first pipe network pressure regulation parameter comparison parameter is ,and ; The adjusted network pressure is calculated as .

[0029] Further, step S3 specifically includes:

[0030] Defining the output of the neural network model for identifying the integrity of the pipeline network The confidence level is , the range is 1 means intact, 0 means damaged; set the threshold , derived from a large amount of experimental data or expert experience;

[0031] ;

[0032] in, Represents the factor used to adjust the maintenance frequency of the gas network system; Indicates the maintenance frequency of the standard gas network system.

[0033] Further, step S4 specifically includes:

[0034] ;

[0035] in, represents the pipeline network health monitoring model; Indicates the adjusted network pressure result; Represents the maintenance frequency set of the gas network system; A collection representing the wall thickness of a gas pipeline; Indicates the geological environment in which the pipeline network is located; Represents the output of the network health monitoring model.

[0036] An intelligent gas pipe network monitoring system includes the following contents:

[0037] Pipeline network information acquisition and processing module, pipeline network integrity level identification module, pipeline network pressure initialization module, pressure adjustment parameter module, pipeline network pressure determination module, maintenance frequency determination module, pipeline network health monitoring module;

[0038] The pipeline network information acquisition and processing module is used to collect various information of the gas pipeline network through real-time sensors and pre-process the collected data;

[0039] The pipeline network integrity level identification module is used to evaluate the health status of the pipeline network, establish a pipeline network integrity level identification neural network model, identify the integrity level of the pipeline network, and provide background support for determining the initial pressure of the pipeline network;

[0040] The pipeline network pressure initialization module obtains the initial pipeline network pressure according to the output result of the pipeline network integrity level identification neural network model;

[0041] The pressure adjustment parameter module is used to set the pressure adjustment parameters in the pipe network system to ensure that the pipeline operates within a safe range and prevent damage to the pipe network system caused by excessively high or low pressure;

[0042] The pipeline network pressure determination module determines the current pressure state of the gas pipeline network system by real-time monitoring of pipeline network data information and combining pipeline network pressure adjustment parameters;

[0043] The maintenance frequency determination module determines the maintenance frequency according to the actual situation and health status of the gas pipe network system;

[0044] The pipeline health monitoring module establishes a pipeline health monitoring model through the adjusted pipeline pressure and the obtained gas pipeline maintenance frequency, and monitors the health status of the gas pipeline system in real time.

[0045] Beneficial effects: 1. The present invention analyzes the pipeline data by establishing a pipeline integrity level identification neural network model, which can realize real-time monitoring of the gas pipeline status. Through intelligent pipeline integrity identification, gas pipeline problems can be discovered in time and measures can be taken; automated pipeline integrity identification reduces reliance on subjective judgment of personnel and improves the objectivity and accuracy of judgment; based on the output results of the neural network model, more data-driven decisions can be made to improve the efficiency and scientificity of gas pipeline monitoring and management; accurately formulate inspection and maintenance plans to improve maintenance efficiency.

[0046] 2. The present invention defines the pipeline network pressure correction parameters based on the judgment of the integrity of the pipeline network in order to consider the actual state of the gas pipeline network in actual operation and accurately calculate the pressure of the pipeline network. The integrity of the pipeline network is usually affected by factors such as corrosion, wear, and damage, which can cause the actual pressure of the pipeline network to deviate from the pressure under the ideal state. By calculating the correction parameters, abnormal conditions of the gas pipeline network can be discovered in time and necessary maintenance and repairs can be carried out, thereby extending the service life of the gas pipeline network system and ensuring the safe and stable operation of the pipeline system. When calculating the pipeline network pressure correction parameters, combined with the relevant data information of the gas pipeline network, a correction parameter can be obtained for subsequent correction of the pipeline network pressure to make it closer to the actual situation, thereby accurately evaluating the operating status and safety of the gas pipeline network and preventing accidents.

[0047] 3. The present invention can ensure that the gas pipe network system operates within a safe range by adjusting the pipe network pressure according to the pipe network pressure adjustment parameters, avoiding problems caused by excessively high or low pressure, such as leakage, explosion, etc. By calculating the maintenance frequency of the gas pipe network system through the output results of the pipe network integrity level recognition neural network model, a more effective management plan can be formulated according to the actual status of the pipe network, potential problems can be discovered and maintained in time, the possibility of failure can be reduced, and the reliability and safety of the gas pipe network system can be improved. A reasonable maintenance frequency can improve work efficiency, reduce maintenance costs, and reduce production losses caused by failures.

[0048] 4. The present invention can help predict possible problems in the gas pipeline network system by establishing a health monitoring model, so as to take preventive measures, reduce the possibility of accidents, and improve the safety and reliability of the system; carry out targeted maintenance and care based on the output results of the model, avoid unnecessary repairs and replacements, reduce maintenance costs, and improve the sustainability of the pipeline system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of an intelligent gas pipe network monitoring method of the present invention;

[0050] Figure 2 This is a module diagram of an intelligent gas pipe network monitoring system of the present invention. DETAILED DESCRIPTION

[0051] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] Refer to the attached Figure 1 This embodiment provides an intelligent gas pipeline network monitoring method, comprising the following steps:

[0053] S1. Use high-resolution cameras and sensors to collect all-round data on the gas pipeline network, including but not limited to images, temperature, pressure, humidity, concentration of corrosive gas types, pipeline structure, material, length, diameter and other information data. Pre-process the collected data, including image denoising and data standardization, to improve the accuracy of subsequent processing.

[0054] According to the acquired gas pipeline network related data information, a pipeline network integrity level identification neural network model is established. The acquired historical pipeline network data information is used as a training sample and input into the pipeline network integrity level identification neural network model. The pipeline network integrity level identification neural network model includes an input layer, a recognition layer, a deep analysis layer, and an output layer.

[0055] The pre-processed gas network-related data information has a total of X features. The input layer and the analysis layer transmit feature information through the fully connected layer, and the network data is identified and analyzed in the recognition layer. The specific process is as follows:

[0056] ;

[0057] in, Represents the input of the recognition layer; Represents the connection weight between the input layer and the recognition layer; Represents the first Characteristic data information, ; represents the bias of the recognition layer; Represents the output of the recognition layer; represents the first recognition coefficient; represents the second identification coefficient; Indicates the total duration of the selected historical gas network data; Indicates The priority level of each sensor; Indicates the number of deployed sensors.

[0058] The recognition results of the recognition layer are passed to the deep analysis layer. The model further analyzes and processes the output of the recognition layer to help the model more accurately improve the performance of the pipeline network integrity level recognition task, making it more intelligent and accurate in evaluating the status of the gas pipeline network. The specific process is as follows:

[0059] ;

[0060] in, Represents the input of the deep analysis layer; Represents the connection weight between the recognition layer and the deep analysis layer; represents the bias of the deep analysis layer; Represents the output of the deep analysis layer; Indicates the pipe network parameter information in the sensor; Indicates the deviation of the current gas network parameter information before and after transmission; Represents the learning factor.

[0061] The calculation results of the deep analysis layer are transferred to the output layer, which outputs the final network integrity level results. The specific process is as follows:

[0062] ;

[0063] in, Represents the calculation result of the output layer; represents the weight of the output layer; Represents the bias of the output layer. Then calculate the error between the model output and the actual pipeline network integrity result, optimize the model parameters according to existing technologies, such as the gradient descent method, so that the error is within the qualified range, and complete the training of the pipeline network integrity level identification neural network. Through the pipeline network integrity level identification neural network model, the category of the current pipeline integrity can be obtained intelligently.

[0064] The present invention analyzes pipeline data by establishing a pipeline integrity level identification neural network model, thereby realizing real-time monitoring of the gas pipeline network status. Through intelligent pipeline network integrity identification, gas pipeline network problems can be discovered in time and measures can be taken; automated pipeline network integrity identification reduces reliance on subjective judgment of personnel and improves the objectivity and accuracy of judgment; based on the output results of the neural network model, more data-driven decisions can be made to improve the efficiency and scientificity of gas pipeline network monitoring and management; and inspection and maintenance plans can be accurately formulated to improve maintenance efficiency.

[0065] S2. Based on the judgment of the integrity of the gas pipeline network, the gas pipeline network pressure is defined as ; At the same time, the gas pipeline network pressure regulation parameters are calculated based on the flow rate in the pipeline network, the surrounding environment of the pipeline, the temperature, etc.

[0066] Based on the judgment of the integrity of the pipeline network, the pipeline network pressure is pre-determined to be ,in, represents the first judgment threshold, Represents the second judgment threshold, which is obtained through expert experience and a large number of experiments.

[0067] if , it means that the gas network is in excellent condition, that is, the pipeline structure is intact, there is no sign of damage or corrosion, there is no leakage, and the pressure is stable; then the initial network pressure is defined as , ;

[0068] if , it means that the gas network is in good condition, that is, there is no obvious damage on the pipeline surface, there may be slight corrosion or surface scratches, which are within the normal range and do not affect the normal operation of the pipeline; then the initial network pressure is defined as , ;

[0069] if , it means that the gas pipeline network is in a risky state, that is, the pipeline structure has certain defects or damage, there is a certain degree of corrosion, wear or local damage, there are certain safety hazards, and timely repair and maintenance are required; the initial pipeline network pressure is defined as , ;

[0070] in, It represents the fluctuation coefficient of pipeline network integrity; Indicates the pipe network pressure under standard conditions; , , They respectively represent the corresponding coefficients under different conditions of gas pipeline network integrity.

[0071] According to the flow rate in the gas pipeline network, the humidity and temperature around the pipeline network, etc., the pipeline network pressure adjustment parameters are calculated. The specific process is as follows:

[0072] ;

[0073] in, Indicates the regulating parameter of the pipe network pressure; represents the correction factor; Indicates the number of times blockage or sedimentation occurs; It represents the cost caused by blockage or sedimentation in the jdth pipe network; represents the time step of the recording; Indicates the flow rate in the pipeline when the pipe network system is working; Indicates the upper limit flow value specified in the pipeline; Indicates the flow rate of liquid or gas in a pipe; Indicates the flow coefficient of the control valve; Indicates the density of the fluid; Represents the function of the influence of humidity around the pipe network on the pipe pressure; Indicates the influence coefficient of humidity around the pipe network; Represents the temperature state variable of the pipe network; represents the vibration amplitude variable of the pipe network; Indicates the state variables of valves and joints; , , Represent the corresponding influence weights respectively.

[0074] The present invention defines the pipeline network pressure correction parameter based on the judgment of the integrity of the pipeline network in order to consider the actual state of the gas pipeline network in actual operation and accurately calculate the pressure of the pipeline network. The integrity of the pipeline network is usually affected by factors such as corrosion, wear, damage, etc., which will cause the actual pressure of the pipeline network to deviate from the pressure under the ideal state. By calculating the correction parameters, abnormal conditions of the gas pipeline network can be discovered in time and necessary maintenance and repair can be carried out, thereby extending the service life of the gas pipeline network system and ensuring the safe and stable operation of the pipeline system. When calculating the pipeline network pressure correction parameters, combined with the relevant data information of the gas pipeline network, a correction parameter can be obtained for subsequent correction of the pipeline network pressure to make it closer to the actual situation, thereby accurately evaluating the operating status and safety of the gas pipeline network and preventing accidents.

[0075] S3. Adjust the pipeline network pressure according to the pipeline network pressure regulation parameters; calculate the maintenance frequency of the gas pipeline network system according to the output results of the pipeline network integrity level identification neural network model.

[0076] In the embodiment of the present invention, the pipeline network pressure adjustment parameter is compared with a predefined comparison parameter of the pipeline network pressure adjustment parameter, and the pipeline network pressure is adjusted according to the comparison result; specifically, the predefined first pipeline network pressure adjustment parameter comparison parameter is , the first pipe network pressure regulation parameter comparison parameter is ,and ; The specific process is as follows:

[0077] if , then the adjusted network pressure is set to , ;

[0078] if , then the adjusted network pressure is set to , ;

[0079] if , then the adjusted network pressure is set to , ;

[0080] in, represents the first setting adjustment parameter; represents the second setting adjustment parameter; Indicates that the third adjustment coefficient is not set.

[0081] Calculate the maintenance frequency of the gas network system based on the output of the neural network model for network integrity identification ; The specific process is as follows:

[0082] Output results of the neural network model for assuming pipeline network integrity level identification The confidence level is , the range is 1 indicates intact, and 0 indicates damaged. In the embodiment of the present invention, the threshold is set , derived from a large amount of experimental data or expert experience;

[0083] ;

[0084] in, Represents the factor used to adjust the maintenance frequency of the gas network system; Indicates the maintenance frequency of the standard gas network system.

[0085] The present invention can ensure that the gas pipe network system operates within a safe range by adjusting the pipe network pressure according to the pipe network pressure adjustment parameter, and avoid problems caused by excessively high or low pressure, such as leakage, explosion, etc. By calculating the maintenance frequency of the gas pipe network system through the output result of the pipe network integrity level recognition neural network model, a more effective management plan can be formulated according to the actual state of the pipe network, potential problems can be discovered and maintained in time, the possibility of failure can be reduced, and the reliability and safety of the gas pipe network system can be improved. A reasonable maintenance frequency can improve work efficiency, reduce maintenance costs, and reduce production losses caused by failures.

[0086] S4. Establish a pipeline health monitoring model based on the adjusted pipeline pressure and the obtained gas pipeline system maintenance frequency , to manage the operating status of the gas pipeline network system, improve the safety, reliability and efficiency of the pipeline network system, help operators respond to changes in the operating status of the gas pipeline network in a timely manner, prevent potential risks, and ensure the normal operation of the pipeline system. The specific process is as follows:

[0087] ;

[0088] in, Indicates the adjusted network pressure result; Represents the maintenance frequency set of the gas network system; A collection representing the wall thickness of a gas pipeline; Indicates the address environment of the pipe network, etc. Represents the output of the network health monitoring model.

[0089] ;

[0090] in, Indicates that within a certain period of time The status score of the pipeline network obtained during the first maintenance; Indicates the difference between the pipe wall thickness and the ideal state; Indicates the impact of the environment in which the pipeline network is located on the normal operation of the gas pipeline network system; Represents the health test factor.

[0091] The present invention can help predict possible problems in the gas pipeline network system by establishing a health monitoring model, so as to take preventive measures, reduce the possibility of accidents, and improve the safety and reliability of the system; carry out targeted maintenance and care based on the output results of the model, avoid unnecessary repairs and replacements, reduce maintenance costs, and improve the sustainability of the pipeline system.

[0092] Refer to the attached Figure 2 This embodiment provides an intelligent gas pipeline network monitoring system, including the following contents:

[0093] Pipeline network information acquisition and processing module, pipeline network integrity level identification module, pipeline network pressure initialization module, pressure adjustment parameter module, pipeline network pressure determination module, maintenance frequency determination module, pipeline network health monitoring module;

[0094] The pipeline network information acquisition and processing module is used to collect various information of the gas pipeline network through real-time sensors, including but not limited to images, temperature, pressure, humidity, type and concentration of corrosive gases, pipeline structure, material, length, diameter and other information data; pre-process the collected data, including image denoising, data standardization, etc., to improve the accuracy of subsequent processing;

[0095] The pipeline network integrity level identification module is used to evaluate the health of the gas pipeline network, establish a pipeline network integrity level identification neural network model, identify the integrity level of the pipeline network, help determine whether there are potential problems or risks, and provide background support for determining the initial pressure of the pipeline network;

[0096] The initial network pressure module obtains the initial network pressure according to the output result of the network integrity level identification neural network model;

[0097] The pressure regulation parameter module is used to set the pressure regulation parameters in the gas pipe network system to ensure that the pipeline operates within a safe range and prevent damage to the pipe network system caused by excessively high or low pressure.

[0098] The pipeline network pressure determination module determines the current pressure status of the pipeline network system by real-time monitoring of pipeline data information and combining it with the pipeline network pressure adjustment parameters, so as to detect abnormal conditions or leaks in time.

[0099] Maintenance frequency determination module, which can determine the maintenance frequency according to the actual situation and health status of the gas pipeline network system to ensure the safe and stable operation of the gas system;

[0100] The pipeline health monitoring module establishes a pipeline health monitoring model through the adjusted pipeline pressure conditions and the maintenance frequency of the gas pipeline system. It monitors the health status of the gas pipeline system in real time, detects problems in time and provides early warnings to ensure the safe operation of the pipeline system.

[0101] 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.

[0102] 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.

[0103] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0104] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0105] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. An intelligent gas pipeline network monitoring method, characterized in that: The following steps are involved: Step S1. Obtain gas pipeline network data information, establish a pipeline network integrity level recognition neural network model, use the obtained historical pipeline network data information as training samples, and input it into the pipeline network integrity level recognition neural network model; Step S2. Define the network pressure based on the judgment of the network integrity; and calculate the network pressure adjustment parameters based on the network related data information. ; if , then the initial network pressure is defined as , ;if , then the initial network pressure is defined as , ;if , then the initial network pressure is defined as , ; in, It represents the output result of the neural network model for pipeline network integrity level identification; It represents the fluctuation coefficient of pipeline network integrity; Indicates the pipe network pressure under standard conditions; , , They represent the coefficients corresponding to different conditions of pipeline network integrity; represents the first judgment threshold, represents the second judgment threshold; ； in, represents the correction factor; Indicates the number of times blockage or deposits occur; It represents the cost caused by blockage or sedimentation in the jdth network channel; Indicates the flow rate in the pipeline when the pipe network system is working; Indicates the upper limit flow value specified in the pipeline; Indicates the flow rate of liquid or gas in the pipeline; Indicates the flow coefficient of the control valve; Indicates the density of the fluid; Represents the influence function of humidity around the pipe network on the pipe network pressure; Indicates the influence coefficient of humidity around the pipe network; Represents the temperature state variable of the pipe network; represents the vibration amplitude variable of the pipe network; Indicates the state variables of valves and joints; , , They represent the corresponding influence weights respectively; represents the time step of the recording; Step S3. According to the network pressure adjustment parameter, adjust the preset network pressure; according to the output result of the network integrity level identification neural network model, calculate the maintenance frequency of the gas network system ; Step S4. Establish a pipeline health monitoring model based on the adjusted pipeline pressure and the obtained gas pipeline system maintenance frequency to monitor the operating status of the gas pipeline system.

2. The intelligent gas pipeline network monitoring method according to claim 1 is characterized in that: The step S1 specifically includes: The pipeline network integrity level recognition neural network model includes an input layer, a recognition layer, a deep analysis layer, and an output layer; It is defined that the preprocessed pipeline network related data information has a total of X features, in which the input layer and the recognition layer transmit feature information through the fully connected layer, and the pipeline network data is recognized and analyzed in the recognition layer. The specific process is as follows: ； in, Represents the input of the recognition layer; Represents the connection weight between the input layer and the recognition layer; Represents the first Characteristic data information, ; represents the bias of the recognition layer; Represents the output of the recognition layer; represents the first recognition coefficient; represents the second identification coefficient; Indicates the total duration of the selected historical pipe network data; Indicates The priority level of each sensor; Indicates the number of deployed sensors.

3. The intelligent gas pipeline network monitoring method according to claim 2 is characterized in that: The step S1 specifically includes: The recognition result of the recognition layer is transmitted to the deep analysis layer, and the pipeline network integrity level recognition neural network model analyzes and processes the output of the recognition layer; the calculation result of the deep analysis layer is transmitted to the output layer, and the output layer outputs the final pipeline network integrity level result.

4. The intelligent gas pipeline network monitoring method according to claim 1 is characterized in that: The step S3 specifically includes: The pipeline network pressure adjustment parameter is compared with a predefined comparison parameter of the pipeline network pressure adjustment parameter, and the pipeline network pressure is adjusted according to the comparison result; the predefined first pipeline network pressure adjustment parameter comparison parameter is , the second pipe network pressure regulation parameter comparison parameter is ,and ; The adjusted network pressure is calculated as .

5. The intelligent gas pipeline network monitoring method according to claim 1 is characterized in that: The step S3 specifically includes: Defining the output of the neural network model for identifying the integrity of the pipeline network The confidence level is , the range is 1 means intact, 0 means damaged; set the threshold , derived from a large amount of experimental data or expert experience; ； in, Represents the factor used to adjust the maintenance frequency of the gas network system; Indicates the maintenance frequency of the standard gas network system.

6. The intelligent gas pipe network monitoring method according to claim 1 is characterized in that: The step S4 specifically includes: ； in, represents the pipeline network health monitoring model; Indicates the adjusted network pressure result; Represents the maintenance frequency set of the gas network system; A collection representing the wall thickness of a gas pipeline; Indicates the geological environment in which the pipeline network is located; Represents the output of the network health monitoring model.

7. An intelligent gas pipe network monitoring system, applied to the intelligent gas pipe network monitoring method according to claim 1, characterized in that: Includes the following: Pipeline network information acquisition and processing module, pipeline network integrity level identification module, pipeline network pressure initialization module, pressure adjustment parameter module, pipeline network pressure determination module, maintenance frequency determination module, pipeline network health monitoring module; The pipeline network information acquisition and processing module is used to collect various information of the gas pipeline network through real-time sensors and pre-process the collected data; The pipeline network integrity level identification module is used to evaluate the health status of the pipeline network, establish a pipeline network integrity level identification neural network model, identify the integrity level of the pipeline network, and provide background support for determining the initial pressure of the pipeline network; The pipeline network pressure initialization module obtains the initial pipeline network pressure according to the output result of the pipeline network integrity level identification neural network model; The pressure adjustment parameter module is used to set the pressure adjustment parameters in the pipe network system to ensure that the pipe network operates within a safe range and prevent damage to the pipe network system caused by excessively high or low pressure; The pipeline network pressure determination module determines the current pressure state of the gas pipeline network system by real-time monitoring of pipeline network data information and combining pipeline network pressure adjustment parameters; The maintenance frequency determination module determines the maintenance frequency according to the actual situation and health status of the gas pipe network system; The pipeline health monitoring module establishes a pipeline health monitoring model through the adjusted pipeline pressure and the obtained gas pipeline maintenance frequency, and monitors the health status of the gas pipeline system in real time.

Images