Gas pipe network monitoring method and system

Abstract

The invention provides a gas pipe network monitoring method and system, and belongs to the technical field of pipe network monitoring, and the method comprises the steps: determining a target health state of a gas pipe network based on a state-time query table; the target health state is the health state of the gas pipe network in a first time period; the state-time query table comprises a plurality of one-to-one correspondence mapping relations between the health states of the gas pipe network and target time intervals; inputting the collected target monitoring data of the gas pipe network in the first time period and the target health state into a gas pipe network fault analysis model to obtain a fault analysis result of the gas pipe network; the gas pipe network fault analysis model is a model obtained by training a multi-layer sensor neural network model based on the health state and monitoring data of the gas pipe network in a second time period. According to the gas pipe network monitoring method and system provided by the invention, the accuracy of fault monitoring analysis of the gas pipe network can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of pipeline network monitoring, and more specifically, relates to a method and system for monitoring a gas pipeline network. Background Art

[0002] As an important part of urban infrastructure, the gas pipeline network undertakes the key task of transporting energy such as natural gas and liquefied petroleum gas. The core of the gas pipeline network monitoring technology lies in real-time collection, transmission, and analysis of pipeline network operation data to achieve comprehensive perception and intelligent management of the pipeline network status. With the acceleration of urbanization and the growth of energy demand, the scale and complexity of the gas pipeline network are constantly increasing, and traditional monitoring methods are difficult to meet the requirements for the safe and efficient operation of modern pipeline networks.

[0003] With the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, the monitoring of gas pipeline networks is gradually developing towards intelligence and automation. Modern monitoring systems usually use distributed sensor networks to achieve real-time monitoring of pipeline network operation parameters. However, the existing technology still has the problem of low accuracy in monitoring and analyzing gas pipeline network failures. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a method and system for monitoring a gas pipeline network to improve the accuracy of monitoring and analyzing gas pipeline network failures.

[0005] In the first aspect of the embodiments of the present disclosure, a method for monitoring a gas pipeline network is provided, including: Determining the target health status of the gas pipeline network based on a state-time query table; the target health status is the health status of the gas pipeline network within a first time period; the state-time query table includes a mapping relationship between the health status of the gas pipeline network and the target time interval that are in one-to-one correspondence; Inputting the target monitoring data of the gas pipeline network within the first time period and the target health status into a gas pipeline network failure analysis model to obtain a failure analysis result of the gas pipeline network; The gas pipeline network failure analysis model is a model obtained by training a multi-layer perceptron neural network model based on the health status and monitoring data of the gas pipeline network within a second time period.

[0006] In the second aspect of the embodiments of the present disclosure, a system for monitoring a gas pipeline network is provided, including: A health status module for determining the target health status of the gas pipeline network based on a state-time query table; the target health status is the health status of the gas pipeline network within a first time period; the state-time query table includes a mapping relationship between the health status of the gas pipeline network and the target time interval that are in one-to-one correspondence; A fault monitoring module, configured to input the target monitoring data and the target health status of the gas pipeline network collected in the first time period into a gas pipeline network fault analysis model to obtain a fault analysis result of the gas pipeline network; A model training module, where the gas pipeline network fault analysis model is a model obtained by training a multi-layer perceptron neural network model based on the health status and monitoring data of the gas pipeline network in the second time period.

[0007] In a third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned gas pipeline network monitoring method are implemented.

[0008] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned gas pipeline network monitoring method are implemented.

[0009] The beneficial effects of the gas pipeline network monitoring method and system provided by the embodiments of the present disclosure are as follows: On the one hand, by constructing a status-time query table, the target health status of the gas pipeline network in a specific time period can be quickly and accurately located, providing a basis for subsequent fault analysis and improving the timeliness of monitoring.

[0010] On the other hand, the gas pipeline network fault analysis model, which utilizes the high fitting ability of the multi-layer perceptron neural network, can deeply explore the complex relationships between data, thereby realizing the accurate analysis of gas pipeline network faults. By jointly inputting the target monitoring data and the target health status into the gas pipeline network fault analysis model trained with historical data, this method differentiates and analyzes faults in combination with the health status of the pipeline network, significantly improving the accuracy of fault monitoring and analysis compared with traditional means. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic flowchart of a gas pipeline network monitoring method provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of a gas pipeline network monitoring system provided by an embodiment of the present disclosure; Figure 3Schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0013] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0014] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0015] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a gas pipeline network monitoring method provided by an embodiment of the present disclosure. The method may include S101 to S103.

[0016] S101: Determine the target health status of the gas pipeline network based on the status-time query table. The target health status is the health status of the gas pipeline network during the first time period. The status-time query table includes a mapping relationship between the health status of the gas pipeline network and the target time interval that corresponds one by one.

[0017] In this embodiment, the status-time query table further includes the latest health detection time and the corresponding health status of different gas pipelines. The health status of the gas pipeline network may include good, average, and dangerous, or first level, second level, and third level, etc. For different health status types, the corresponding target time intervals are different. The target time interval refers to the time period during which the target health status is maintained. After exceeding this target time interval, the health status of the pipeline network needs to be detected again and the health status needs to be updated. The health status stability period corresponding to each health status type can be determined through historical data. For example, a good health status corresponds to half a year, and a dangerous health status corresponds to one month. This health status stability period is used as the target time interval corresponding to each health status type.

[0018] The first time period is the time period for monitoring the pipeline network. The operation data information of the gas pipeline network during the first time period can be collected as the data to be analyzed. The target health status refers to the operation health status of the gas pipeline network during the first time period, such as good or average, etc.

[0019] In this embodiment, the health status of the gas pipeline network can be calculated based on the pressure stability parameter, flow parameter, pipeline material related parameter, and accessory equipment operation parameter of the pipeline. Different health statuses may correspond to different ideal ranges of operation parameters, such as the pressure fluctuation value range.

[0020] Exemplarily, during the winter heating period, the first time period is the first week of December. According to the status-time query table, the time of the latest health detection of the pipeline to be monitored is October 20th, and the health status is average. According to the status-time query table, the target time interval corresponding to the average health status type is three months, that is, the deadline is January 20th of the following year. Since the first time period is within this range, the target health status is determined to be average. The normal range of the pipeline network pressure fluctuation corresponding to the average health status is ±5%. If it is monitored that the pressure fluctuation of a certain section of the pipeline network exceeds ±5% and the flow rate is abnormal, an alarm will be sent to the staff in a timely manner and corresponding measures will be taken to ensure the safe and stable operation of the gas pipeline network during the heating season.

[0021] S102: Input the target monitoring data and target health status of the gas pipeline network during the first time period into the gas pipeline network fault analysis model to obtain the fault analysis result of the gas pipeline network.

[0022] In this embodiment, the gas pipeline network fault analysis model processes and analyzes the input target monitoring data, extracts relevant pressure characteristics, flow characteristics, etc., and analyzes and compares the extracted data characteristics with the ideal parameters corresponding to the target health status to determine whether it is abnormal. If it is abnormal, the fault type and fault location will be further determined.

[0023] If it is monitored that the pressure exceeds the allowable range of the target health status and the flow rate is abnormal, the model makes a comprehensive judgment through internal algorithms. For example, if the pressure drops and the flow rate increases abnormally, it may indicate a pipeline leak. If the pressure fluctuates greatly and the operating parameters of the auxiliary equipment are abnormal, it may be that the equipment failure affects the pressure regulation, and finally the fault analysis result is output.

[0024] Exemplarily, on December 18th, the monitoring data shows that the medium-pressure pipeline network pressure in a certain area drops suddenly from the basically stable 0.3 MPa to 0.25 MPa, and the flow rate suddenly rises from 200 m³ / h to 250 m³ / h. At this time, the target health status corresponding to this pipeline network is good, and under the good health status, the pressure should be stable at 0.28 - 0.32 MPa, and the flow rate is between 180 - 220 m³ / h.

[0025] Input these target monitoring data and target health status into the gas pipeline network fault analysis model. The gas pipeline network fault analysis model extracts the pressure characteristics and flow characteristics, compares them with the ideal parameters of the target health status, and determines it to be abnormal. After further analysis, the fault type is determined to be the risk of pipeline leakage. Based on this fault analysis result, the maintenance personnel quickly carry out control and investigation to ensure the safe operation of the pipeline network.

[0026] S103: The gas pipeline network fault analysis model is a model obtained by training a multi-layer perceptron neural network model based on the health status and monitoring data of the gas pipeline network during the second time period.

[0027] In this embodiment, the gas pipeline network fault analysis model can identify abnormal data or states during the operation of the gas pipeline network and locate the fault types. The monitoring data can include pressure, flow rate, temperature, gas concentration, etc. The second time period refers to the time range of historical data used for training the model, which can cover different working conditions, seasons, and environmental conditions to ensure that the model has generalization ability. The multi-layer perceptron neural network model learns complex features of the input data through multi-layer non-linear transformations.

[0028] Exemplarily, the monitoring data and corresponding healthy state labels for the second time period are extracted from the historical database. The data is processed for missing values and outliers, and the data is normalized using Z-score. The input layer of the model receives the processed monitoring data and the target healthy state. The monitoring data includes the operation monitoring data and healthy state of pipelines in different parts, and the monitoring data is separated according to the healthy state. The hidden layer can learn the data features of pipelines in different healthy states through non-linear activation functions respectively, and can calculate the correlations between features such as pressure change rate, flow peak value, temperature change trend, etc. and various types of faults. For example, the correlation between a sudden pressure drop and leakage is identified. Under different healthy states, the correlation characteristics between the occurrence of pipeline faults and the operation monitoring data are different. The output layer predicts the fault type.

[0029] It can be concluded from the above that in this embodiment, the state-time query table effectively manages the healthy state of the gas pipeline network and its validity period, ensuring the timeliness and accuracy of the pipeline network's healthy state. Using the target healthy state as a benchmark and combining the real-time collected pipeline network operation data, it can specifically identify fault risks, improve the accuracy and efficiency of identifying abnormal situations during the operation of the pipeline network, and effectively prevent potential safety hazards.

[0030] The introduction of the gas pipeline network fault analysis model further improves the accuracy and efficiency of fault identification. This model is constructed based on a multi-layer perceptron neural network, and through training to learn complex features in historical data, it realizes accurate judgment and location of the pipeline network fault types, and improves the response speed of fault handling.

[0031] This embodiment also fully considers the correlation characteristics between the occurrence of pipeline network faults and the operation monitoring data under different healthy states, enabling the model to maintain a high generalization ability under different working conditions, seasons, and environmental conditions. Through continuous monitoring and analysis of the pipeline network operation data, this method can continuously optimize the fault analysis model and improve its prediction performance, providing a strong guarantee for the long-term safe and stable operation of the gas pipeline network.

[0032] In an embodiment of the present disclosure, a gas pipeline network monitoring method further includes: Determine the health status of the gas pipeline network according to the first health detection result, where the first health detection result is the result obtained by performing health detection on the pipelines of the gas pipeline network at the first detection frequency.

[0033] Determine the target time interval corresponding to the health status based on the status-time query table.

[0034] Starting from the time node when health detection is performed on the pipelines of the gas pipeline network, obtain the pipeline usage frequency and environmental precipitation within the future target time interval.

[0035] Adjust the first detection frequency based on the pipeline usage frequency and environmental precipitation to obtain the second detection frequency.

[0036] Update the health status of the gas pipeline network according to the second health detection result, where the second health detection result is the result obtained by performing health detection on the pipelines of the gas pipeline network at the second detection frequency.

[0037] In this embodiment, adjusting the first detection frequency based on the pipeline usage frequency and environmental precipitation to obtain the second detection frequency includes: If the pipeline usage frequency is less than the usage frequency threshold and the environmental precipitation is less than the precipitation threshold, then adjust the first detection frequency based on the first step length to obtain the second detection frequency.

[0038] If the pipeline usage frequency is greater than or equal to the usage frequency threshold and the environmental precipitation is less than the precipitation threshold, then use the first detection frequency as the second detection frequency.

[0039] In this embodiment, adjusting the first detection frequency based on the pipeline usage frequency and environmental precipitation to obtain the second detection frequency includes: If the environmental precipitation is greater than or equal to the precipitation threshold and the pipeline usage frequency is greater than or equal to the usage frequency threshold, then adjust the first detection frequency based on the second step length to obtain the second detection frequency.

[0040] If the environmental precipitation is greater than or equal to the precipitation threshold and the pipeline usage frequency is less than the usage frequency threshold, then adjust the first detection frequency based on the frequency update formula to obtain the second detection frequency.

[0041] In this embodiment, the first detection frequency is the initially set health detection time interval of the gas pipeline network and serves as the reference frequency. The pipeline usage frequency refers to the flow rate or usage times of gas in the pipeline per unit time, reflecting the load level of the pipeline, and can be calculated by integrating the flow rate values within different unit times. The environmental precipitation refers to the cumulative precipitation in the area where the gas pipeline network is located within the target time interval, and the environmental precipitation will affect the external environment of the pipeline, such as soil humidity and corrosion risk. The usage frequency threshold and the precipitation threshold are respectively the critical values for judging whether the pipeline usage frequency or precipitation triggers the adjustment of the detection frequency. The first step length and the second step length are both preset step lengths for adjusting the detection frequency.

[0042] In this embodiment, the frequency update formula is:

[0043]

[0044] Wherein, represents the second detection frequency, represents the first detection frequency, α represents the adjustment coefficient (0 < α ≤ 1), which is used to control the influence weight of precipitation on the detection frequency, P represents the cumulative environmental precipitation within the future target time interval, represents the precipitation threshold, represents the maximum precipitation reference value, represents the minimum detection frequency.

[0045] In this embodiment, when the precipitation exceeds the threshold ( ), the pipeline corrosion risk is positively correlated with the precipitation, and the precipitation can be converted into a risk factor through normalization processing The detection frequency decreases linearly with the risk factor. The constraint conditions ensure that the adjusted frequency is within a reasonable range, that is, not lower than the minimum detection frequency, to avoid over-detection.

[0046] Exemplarily, based on the first detection frequency, a comprehensive detection of the pipeline network is carried out to obtain data such as pressure, flow rate, and corrosion, and the health status is evaluated. Through the state-time query table, the target time interval corresponding to the current health status is determined. Starting from the detection time point, the pipeline usage frequency and environmental precipitation within the future target time interval are predicted. The first detection frequency is adjusted according to different conditions to obtain the second detection frequency: Condition 1: If the pipeline usage frequency is low (the pipeline usage frequency is less than the usage frequency threshold) and the environmental precipitation is small (the environmental precipitation is less than the precipitation threshold), it indicates that both the pipeline load and the external environment impact are small. At this time, the first detection frequency is adjusted based on the first step length, the detection interval is appropriately extended, and the detection cost is reduced.

[0047] Condition 2: If the pipeline usage frequency is high (the pipeline usage frequency is greater than or equal to the usage frequency threshold) but the environmental precipitation is low (the environmental precipitation is less than the precipitation threshold), it indicates that the pipeline load is normal. Maintain the first detection frequency to ensure that problems caused by high-load usage can be detected in a timely manner.

[0048] Condition 3: If the precipitation is large and the pipeline usage frequency is high, it indicates that the pipeline is greatly affected by internal and external factors. Adjust the first detection frequency based on the second step length, shorten the detection interval, and strengthen the detection.

[0049] Condition 4: If the precipitation is large but the pipeline usage frequency is low, adjust the first detection frequency using the frequency update formula, taking into account the external impact of precipitation on the pipeline and the pipeline's own load. Finally, continue the detection and update the health status at the adjusted second detection frequency to achieve dynamic and reasonable monitoring.

[0050] Re-detect according to the second detection frequency, update the health status, and loop the above process.

[0051] In this embodiment, by dynamically adjusting the detection frequency, the detection cost and monitoring requirements are effectively balanced. The detection interval is flexibly adjusted according to the pipeline usage frequency and environmental precipitation, which not only ensures the safety of the pipe network under high load and harsh environment, but also avoids over-detection under low load and good weather. Through precise prediction and intelligent adjustment, this embodiment realizes the optimal allocation of detection resources and improves the monitoring efficiency. At the same time, based on the dynamic update of the health status, the real-time operation status of the pipe network is ensured, providing strong support for fault prevention and emergency handling, and further ensuring the safe and stable operation of the gas pipeline network.

[0052] In an embodiment of the present disclosure, the target monitoring data and target health status of the gas pipeline network in the first time period are input into the gas pipeline network fault analysis model to obtain the fault analysis result of the gas pipeline network, including: Input the target monitoring data and target health status of the gas pipeline network in the first time period into the gas pipeline network fault analysis model.

[0053] The gas pipeline network fault analysis model is used to determine the fault warning threshold based on the target health status.

[0054] Obtain the fault analysis result of the gas pipeline network based on the target monitoring data and the fault warning threshold.

[0055] In this embodiment, determining the fault warning threshold based on the target health status includes: If the target health status is the first-level health status, determine the fault warning threshold as the first fault warning threshold.

[0056] If the target health status is the first-level health status, determine the fault warning threshold as the second fault warning threshold.

[0057] The health assessment score of the gas pipeline network corresponding to the first-level health state is greater than that of the second-level health state.

[0058] The first fault warning threshold is lower than the second fault warning threshold.

[0059] In this embodiment, the fault warning threshold is the critical value for judging possible faults in the gas pipeline network. The fault warning threshold can include a pressure fluctuation range threshold, a temperature range threshold, etc. The first-level health state indicates that the gas pipeline network is in a stable operation state. The parameters associated with the first-level health state can include a relatively high health assessment score and a specific range of operation and environmental monitoring data. The second-level health state refers to a relatively poorer pipeline network health condition compared to the first-level health state, indicating that there are potential risks in the pipeline network. The health assessment score and the monitoring data range are different from those of the first-level health state.

[0060] In this embodiment, the better the health state (such as the first-level health state), the greater the range of changes that can be tolerated or the stronger the tolerance to abnormal situations. Therefore, the corresponding first fault warning threshold is relatively high. While for a poorer health state (such as the second-level health state), the range of changes that can be tolerated is smaller or the tolerance to abnormal situations is poorer, and the corresponding second fault warning threshold is relatively low. For example, the first fault warning threshold is a pressure fluctuation range of ±8%, while the second fault warning threshold is a pressure fluctuation range of ±5%.

[0061] In this embodiment, the gas pipeline network fault analysis model first sets the fault warning threshold according to the target health state. The received target monitoring data is compared and analyzed with the fault warning threshold. If the monitoring data exceeds the threshold, it is marked as abnormal data, and then the abnormal data is analyzed based on the fault-related features learned from historical data to determine the fault type and thus obtain the fault analysis result.

[0062] Exemplarily, it is monitored that the pressure fluctuation of a medium-pressure pipeline in area A reaches +9% (exceeding the threshold), and at the same time, the flow rate increases abnormally by 15%. The fault analysis model determines that the pressure fluctuation exceeds the ±8% threshold of the first-level health state and marks it as abnormal data. The fault analysis model learns from historical data that when the pressure fluctuation > 8% and the flow rate surges, there is a 75% probability of pipeline leakage and a 25% probability of regulator failure. Based on this data feature, the fault analysis result is output: "Suspected pipeline leakage, high risk level".

[0063] This embodiment effectively improves the accuracy of fault warning by accurately setting the fault warning threshold and adjusting the threshold range according to the differences in the health state of the pipeline network. The fault analysis model can monitor and analyze the pipeline network data in real time, identify abnormalities in a timely manner and determine the fault type, reducing the risk of faults occurring.

[0064] In one embodiment of the present disclosure, the health status of the gas pipeline network includes a primary health status and a secondary health status. The health assessment score of the gas pipeline network corresponding to the primary health status is greater than that of the secondary health status. The monitoring data includes operation monitoring data and environmental monitoring data.

[0065] Training the multi-layer perceptron neural network model based on the health status and monitoring data of the gas pipeline network in the second time period includes: Dividing the operation monitoring data and environmental monitoring data of the gas pipeline network in the second time period based on the health status of the gas pipeline network to obtain first operation monitoring data and first environmental monitoring data corresponding to the primary health status, and second operation monitoring data and second environmental monitoring data corresponding to the secondary health status.

[0066] Training the multi-layer perceptron neural network model based on the first operation monitoring data and the first environmental monitoring data to obtain an intermediate multi-layer perceptron neural network model.

[0067] Training the intermediate multi-layer perceptron neural network model based on the second operation monitoring data and the second environmental monitoring data.

[0068] In this embodiment, the operation monitoring data may include gas flow rate, pressure, flow velocity, temperature, etc. The environmental monitoring data may include data related to the environment where the gas pipeline network is located, such as precipitation, temperature, humidity, soil pH, etc. The health assessment score can be comprehensively calculated based on indicators such as the corrosion degree of the pipeline, the pressure fluctuation range, and the leakage detection result. The intermediate multi-layer perceptron neural network model is the multi-layer perceptron neural network model obtained after the first round of training based on the first operation monitoring data and the first environmental monitoring data. After training the intermediate multi-layer perceptron neural network model based on the second operation monitoring data and the second environmental monitoring data, a gas pipeline network fault analysis model is obtained.

[0069] In this embodiment, the multi-layer perceptron neural network model is composed of an input layer, a hidden layer, and an output layer, and can be used for tasks such as data classification and prediction. The multi-layer perceptron neural network model performs weighted summation on the input data, and after being processed by an activation function, it is passed layer by layer in the hidden layer and finally outputs a result in the output layer. In the monitoring of the gas pipeline network, it is used to predict the health status of the gas pipeline network according to the monitoring data.

[0070] For gas pipeline networks in different health states, there will be different specific correlation characteristics among their operation monitoring data, environmental monitoring data, and the occurrence of faults. By dividing the data according to the health status and training the model separately, the model can learn these different characteristic patterns. When new monitoring data and health status are input, the model can judge the type and situation of the faults of the gas pipeline network based on the learned knowledge.

[0071] Exemplarily, a corresponding fault warning threshold is set according to the target health state of the gas pipeline network, and the received target monitoring data is compared with the threshold. If the monitoring data exceeds the threshold, it is marked as abnormal data, and then the abnormal data is deeply analyzed by using the fault-related features in the target health state learned from the historical data, so as to determine the fault type and obtain the fault analysis result.

[0072] In this embodiment, by considering the health state of the gas pipeline network to divide the data set, it can more accurately reflect the fault-related features of the pipeline network in different health states and improve the accuracy of fault judgment.

[0073] Corresponding to a gas pipeline network monitoring method in the above embodiment, Figure 2 is a structural block diagram of a gas pipeline network monitoring system provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 This gas pipeline network monitoring system 20 includes: a health state module 21, a fault monitoring module 22, and a model training module 23.

[0074] Among them, the health state module 21 is used to determine the target health state of the gas pipeline network based on the state-time query table. The target health state is the health state of the gas pipeline network in the first time period. The state-time query table includes a mapping relationship between multiple health states of the gas pipeline network and the target time intervals that correspond one by one.

[0075] The fault monitoring module 22 is used to input the target monitoring data and the target health state of the gas pipeline network collected in the first time period into the gas pipeline network fault analysis model to obtain the fault analysis result of the gas pipeline network.

[0076] The model training module 23 is used to train the multi-layer perceptron neural network model based on the health state and monitoring data of the gas pipeline network in the second time period to obtain the gas pipeline network fault analysis model.

[0077] In an embodiment of the present disclosure, a gas pipeline network monitoring system 20 further includes: a health detection module, which is used to determine the health state of the gas pipeline network according to the first health detection result, and the first health detection result is the result obtained by performing a health detection on the pipeline of the gas pipeline network at the first detection frequency.

[0078] Determine the target time interval corresponding to the health state based on the state-time query table.

[0079] Starting from the time node of performing a health detection on the pipeline of the gas pipeline network, obtain the pipeline usage frequency and environmental precipitation within the future target time interval.

[0080] Adjust the first detection frequency based on the pipeline usage frequency and environmental precipitation to obtain the second detection frequency.

[0081] Update the health status of the gas pipeline network according to the second health detection result, where the second health detection result is the result obtained by performing a health detection on the pipelines of the gas pipeline network at the second detection frequency.

[0082] In an embodiment of the present disclosure, the health detection module is specifically configured to, if the pipeline usage frequency is less than the usage frequency threshold and the environmental precipitation is less than the precipitation threshold, adjust the first detection frequency based on the first step length to obtain the second detection frequency.

[0083] If the pipeline usage frequency is greater than or equal to the usage frequency threshold and the environmental precipitation is less than the precipitation threshold, use the first detection frequency as the second detection frequency.

[0084] In an embodiment of the present disclosure, the health detection module is further specifically configured to, if the environmental precipitation is greater than or equal to the precipitation threshold and the pipeline usage frequency is greater than or equal to the usage frequency threshold, adjust the first detection frequency based on the second step length to obtain the second detection frequency.

[0085] If the environmental precipitation is greater than or equal to the precipitation threshold and the pipeline usage frequency is less than the usage frequency threshold, adjust the first detection frequency based on the frequency update formula to obtain the second detection frequency.

[0086] In an embodiment of the present disclosure, the fault monitoring module 22 is specifically configured to input the target monitoring data and the target health status of the gas pipeline network collected during the first time period into the gas pipeline network fault analysis model.

[0087] The gas pipeline network fault analysis model is used to determine the fault warning threshold based on the target health status.

[0088] Obtain the fault analysis result of the gas pipeline network based on the target monitoring data and the fault warning threshold.

[0089] In an embodiment of the present disclosure, the fault monitoring module 22 is further specifically configured to, if the target health status is the first-level health status, determine the fault warning threshold as the first fault warning threshold.

[0090] If the target health status is the first-level health status, determine the fault warning threshold as the second fault warning threshold.

[0091] The health assessment score of the gas pipeline network corresponding to the first-level health status is greater than that of the second-level health status.

[0092] The first fault warning threshold is lower than the second fault warning threshold.

[0093] In one embodiment of the present disclosure, the health status of the gas pipeline network includes a primary health status and a secondary health status. The health assessment score of the gas pipeline network corresponding to the primary health status is greater than that of the secondary health status. The monitoring data includes operation monitoring data and environmental monitoring data. The model training module 23 is specifically configured to divide the operation monitoring data and environmental monitoring data of the gas pipeline network in the second time period based on the health status of the gas pipeline network, so as to obtain the first operation monitoring data and the first environmental monitoring data corresponding to the primary health status, and the second operation monitoring data and the second environmental monitoring data corresponding to the secondary health status.

[0094] Train the multi-layer perceptron neural network model based on the first operation monitoring data and the first environmental monitoring data to obtain an intermediate multi-layer perceptron neural network model.

[0095] Train the intermediate multi-layer perceptron neural network model based on the second operation monitoring data and the second environmental monitoring data.

[0096] See Figure 3 , Figure 3 which is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure. As Figure 3 shown, the electronic device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module in the above system embodiments, for example Figure 2 the functions of the modules 21 to 23 shown.

[0097] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0098] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0099] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may further include a non-volatile random access memory. For example, the memory 304 may further store information about the device type.

[0100] In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first embodiment and the second embodiment of a method for monitoring a gas pipeline network provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device 300 described in the embodiments of the present disclosure, which will not be elaborated herein.

[0101] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the above-described method embodiments are implemented. It may also be completed by instructing relevant hardware through the computer program. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-described method embodiments may be implemented. Among them, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0102] A computer-readable storage medium may be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device. Further, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0103] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0104] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0105] In several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection to each other can be an indirect coupling or communication connection through some interfaces or units, and can also be in an electrical, mechanical, or other form of connection.

[0106] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of this disclosure.

[0107] In addition, in each embodiment of the present disclosure, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0108] The above are only the specific implementation manners of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A gas pipeline network monitoring method, characterized in that: include: Determine the target health state of the gas network based on the state-time query table; The target health status is the health status of the gas pipeline network in the first time period; The state-time query table includes a plurality of one-to-one mapping relationships between the health states of the gas pipeline network and the target time intervals; Inputting the target monitoring data of the gas pipeline network collected in the first time period and the target health state into the gas pipeline network fault analysis model to obtain a fault analysis result of the gas pipeline network; The gas pipeline network fault analysis model is a model obtained by training a multi-layer perceptron neural network model based on the health status and monitoring data of the gas pipeline network in the second time period.

2. A gas pipeline network monitoring method according to claim 1, characterized in that: Also includes: Determining a health status of the gas pipeline network according to a first health detection result, wherein the first health detection result is a result of performing a health detection on a pipeline of the gas pipeline network at a first detection frequency; Determine the target time interval corresponding to the health state based on the state-time query table; Starting from the time point of health detection of the gas pipeline network, the frequency of pipeline use and environmental precipitation in the future target time interval are obtained; Adjusting the first detection frequency based on the pipeline use frequency and the environmental precipitation to obtain a second detection frequency; The health status of the gas pipeline network is updated according to a second health detection result, where the second health detection result is a result obtained by performing a health detection on pipelines of the gas pipeline network at a second detection frequency.

3. A gas pipeline network monitoring method as claimed in claim 2, characterized in that: The adjusting the first detection frequency based on the pipeline use frequency and the environmental precipitation to obtain the second detection frequency includes: If the pipeline usage frequency is less than the usage frequency threshold, and the environmental precipitation is less than the precipitation threshold, the first detection frequency is adjusted based on the first step length to obtain a second detection frequency; If the pipeline usage frequency is greater than or equal to the usage frequency threshold, and the environmental precipitation is less than the precipitation threshold, the first detection frequency is used as the second detection frequency.

4. A gas pipeline network monitoring method as claimed in claim 3, characterized in that: The adjusting the first detection frequency based on the pipeline use frequency and the environmental precipitation to obtain a second detection frequency also includes: If the environmental precipitation is greater than or equal to the precipitation threshold, and the pipeline usage frequency is greater than or equal to the usage frequency threshold, adjusting the first detection frequency based on a second step length to obtain a second detection frequency; If the environmental precipitation is greater than or equal to the precipitation threshold, and the pipeline usage frequency is less than the usage frequency threshold, the first detection frequency is adjusted based on the frequency update formula to obtain the second detection frequency.

5. A gas pipeline network monitoring method according to claim 1, characterized in that: The target monitoring data of the gas pipeline network collected in the first time period and the target health status are input into the gas pipeline network fault analysis model to obtain the fault analysis result of the gas pipeline network, including: Inputting the collected target monitoring data of the gas pipeline network in the first time period and the target health status into the gas pipeline network fault analysis model; The gas pipeline network fault analysis model is used to determine a fault warning threshold based on the target health state; A fault analysis result of the gas pipeline network is obtained based on the target monitoring data and the fault warning threshold.

6. A gas pipeline network monitoring method as claimed in claim 5, characterized in that: The determining of a fault warning threshold based on the target health state includes: If the target health state is a first-level health state, determining the fault warning threshold to be a first fault warning threshold; If the target health state is a first-level health state, determining the fault warning threshold to be a second fault warning threshold; The health assessment score of the gas pipeline network corresponding to the first-level health status is greater than that of the second-level health status; The first fault warning threshold is lower than the second fault warning threshold.

7. A gas pipeline network monitoring method according to claim 1, characterized in that: The health status of the gas pipeline network includes a primary health status and a secondary health status; the health assessment score of the gas pipeline network corresponding to the primary health status is greater than that of the secondary health status; the monitoring data includes operation monitoring data and environmental monitoring data; The training of the multi-layer perceptron neural network model based on the health status and monitoring data of the gas pipeline network in the second time period includes: Based on the health status of the gas pipeline network, the operation monitoring data and the environmental monitoring data of the gas pipeline network in the second time period are divided to obtain first operation monitoring data and first environmental monitoring data corresponding to the first-level health status, and second operation monitoring data and second environmental monitoring data corresponding to the second-level health status; Training the multi-layer perceptron neural network model based on the first operation monitoring data and the first environment monitoring data to obtain an intermediate multi-layer perceptron neural network model; The intermediate multi-layer perceptron neural network model is trained based on the second operation monitoring data and the second environment monitoring data.

8. A gas pipeline network monitoring system, characterized in that: include: A health status module is used to determine the target health status of the gas network based on a state-time query table; The target health status is the health status of the gas pipeline network in the first time period; The state-time query table includes a plurality of one-to-one mapping relationships between the health states of the gas pipeline network and the target time intervals; A fault monitoring module, used for inputting the target monitoring data of the gas pipeline network and the target health status collected in the first time period into the gas pipeline network fault analysis model to obtain a fault analysis result of the gas pipeline network; The model training module is used for the gas pipeline network fault analysis model, which is a model obtained by training a multi-layer perceptron neural network model based on the health status and monitoring data of the gas pipeline network in the second time period.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images