A method and system for operating condition analysis of a gas transmission pipeline

Abstract

This invention discloses a method and system for analyzing the operating conditions of gas transmission pipelines, comprising the following steps: collecting real-time data of the gas transmission pipeline to be monitored, including the starting pressure, ending pressure, flow rate, and temperature of the pipeline; inputting the real-time data into a pipeline analysis model and outputting the analysis results; and obtaining the operating conditions of the gas transmission pipeline based on the analysis results. This invention improves the accuracy of operating condition monitoring by constructing a corresponding pipeline analysis model for each gas transmission pipeline, outputting changes in pipeline efficiency and friction coefficient, and setting relevant thresholds to provide alarms and reminders for pipeline operation.

Description

Technical Field

[0001] This invention relates to the field of pipeline technology, and in particular to a method and system for analyzing the operating conditions of gas pipelines. Background Technology

[0002] Pipeline efficiency is an important indicator of the operational status of natural gas pipelines and a reference for pipeline cleaning operations. Currently, the methods for calculating pipeline efficiency at gas stations include the Vemos formula for wet gas and the Panhand formula for dry gas.

[0003] However, in actual use, some complex pipelines may have excessively high (over 100%) or excessively low (very low) pipeline transport efficiency. In such cases, pipeline transport efficiency cannot be used as the sole basis for judging other operating conditions such as pipeline cleaning, thereby reducing the accuracy of pipeline operating condition monitoring. Summary of the Invention

[0004] To address the technical problem of low accuracy in pipeline condition monitoring in existing technologies, this invention discloses a method and system for analyzing the operating conditions of gas pipelines. By extracting data features from natural gas pipeline operation data, the changes in pipeline efficiency and friction coefficient are deduced, and relevant thresholds are set to issue alarms and reminders for pipeline operation, thereby improving the accuracy of operating condition monitoring.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for analyzing the operating conditions of gas pipelines includes the following steps:

[0007] Collect real-time data of the gas pipeline to be tested, including the starting pressure, ending pressure, flow rate, and temperature of the gas pipeline;

[0008] Input real-time data into the pipeline analysis model and output analysis results;

[0009] The operating conditions of the gas pipeline were obtained based on the analysis results.

[0010] Preferably, the construction of the pipeline analysis model includes:

[0011] Historical data of the gas pipeline to be tested is collected from the server;

[0012] An initial pipeline analysis model was constructed by combining a deep neural network (DNN) model with a decision tree model.

[0013] Based on historical data of the gas pipeline to be tested, the model parameters for initializing the pipeline analysis model are determined using the gradient descent method.

[0014] The initial pipeline analysis model is initialized using these model parameters to obtain the pipeline analysis model.

[0015] Preferably, the historical data of the gas pipeline to be tested includes input historical data and output historical data; the input historical data includes the starting pressure, ending pressure, flow rate, and temperature of the gas pipeline; the output historical data includes pipeline efficiency and friction coefficient.

[0016] Preferably, the starting pressure and ending pressure are collected by a pressure sensor; the flow rate is collected by a flow sensor; and the temperature is collected by a temperature sensor.

[0017] Preferably, the initial pipeline analysis model includes an input layer, a hidden layer, and an output layer connected in sequence;

[0018] The input layer, used to receive data from the gas pipeline to be tested, consists of n unit layers {α} 11 α 12 α 13 , ...,α 1n};

[0019] The hidden layer is used to mine the mapping relationships of various features in the data of the gas pipeline to be detected, and includes n unit layers {α}. 21 α 22 α 23 , ...,α 2n};

[0020] The output layer, used to output analysis results, consists of n unit layers {α} 31 α 32 α 33 , ...,α 3n}

[0021] Preferably, the method for determining the model parameters of the initial pipeline analysis model is as follows:

[0022] The historical data of the gas pipeline to be inspected is divided into time periods, and the input data X for each time period is determined. i and the corresponding output data Y i X i and Y i Let represent the input and output data for the i-th time period, respectively.

[0023] Based on input data X i Obtain the corresponding latent feature data P i ;

[0024] The hidden feature data P i As input, the output result Y i As output, determine the loss function of the initial pipeline analysis model;

[0025] Based on at least one determined loss function, the model parameters are determined using stochastic gradient descent.

[0026] Preferably, the stealth feature data P i This includes the mass flow rate of the gas transmission pipeline, pipeline inner diameter, starting pressure, ending pressure, length, area, temperature, density, elevation difference, and service life.

[0027] Preferably, the operating condition of the gas pipeline is determined as follows:

[0028] (1) When pipeline efficiency decreases and friction coefficient changes steadily, it is judged as a risk of leakage;

[0029] (2) When the pipeline efficiency decreases and the friction coefficient increases, it is determined that there is an increase in hydrates inside the pipeline, and pipeline cleaning is required.

[0030] (3) When the pipeline efficiency fluctuates irregularly and the friction coefficient is stable, it is judged that there is a process change or production adjustment.

[0031] Preferably, before the real-time data is input into the pipeline analysis model, it further includes:

[0032] First, two methods, moving average filtering and amplitude limiting filtering, are used to preprocess the real-time data;

[0033] Secondly, supplementary assignment is used to fill in the missing or incomplete items in the real-time data.

[0034] This invention also provides a condition analysis system for gas pipelines, including a user management unit, an access control unit, a data acquisition unit, a pipeline analysis model construction unit, an analysis unit, and an alarm unit; wherein,

[0035] The user management unit is used for account registration and login;

[0036] The permissions management unit is used to assign different permissions to different accounts;

[0037] The data acquisition unit is used to receive pipeline data from external sources;

[0038] The pipeline analysis model building unit is used to build pipeline analysis models and output analysis results based on the received pipeline data.

[0039] The analysis unit is used to determine whether the change exceeds the threshold based on the analysis results. If not, it continues to detect and analyze; if so, it sends an alarm message to the alarm unit.

[0040] The alarm unit is used to send alarm signals and simultaneously push alarm information to the terminal of the corresponding staff member.

[0041] In summary, by adopting the above technical solution, the present invention has at least the following beneficial effects compared with the prior art:

[0042] This invention improves the accuracy of operating condition monitoring by extracting data features from the operating data of each natural gas pipeline, outputting changes in pipeline efficiency and friction coefficient through a corresponding pipeline analysis model, and setting relevant thresholds to issue alarms for pipeline operation.

[0043] This invention enables individual detection of pipelines in different environments by modeling each pipeline separately, allowing for more specific data analysis and improved accuracy. Attached image description:

[0044] Figure 1 This is a schematic diagram of an operational condition analysis method for a gas transmission pipeline according to an exemplary embodiment of the present invention.

[0045] Figure 2 This is a schematic diagram of a pipeline analysis model structure according to an exemplary embodiment of the present invention.

[0046] Figure 3 This is a schematic diagram of a condition analysis system for a gas pipeline according to an exemplary embodiment of the present invention. Detailed Implementation

[0047] The present invention will be further described in detail below with reference to embodiments and specific implementation methods. However, it should not be construed that the scope of the above-mentioned subject matter of the present invention is limited to the following embodiments, and all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0048] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0049] like Figure 1 As shown, this invention provides a method for analyzing the operating conditions of gas pipelines, specifically including the following steps:

[0050] S1: Collect historical data of the gas pipeline to be tested from the server (station control system).

[0051] In this embodiment, the historical data of the gas pipeline to be tested includes input data and output data. The input data includes starting pressure, ending pressure, flow rate, temperature, etc., and the output data includes pipeline efficiency, friction coefficient, etc.

[0052] In this embodiment, the starting pressure and ending pressure can be collected by a pressure sensor; the flow rate can be collected by a flow sensor; the temperature can be collected by a temperature sensor; and the pipeline efficiency and friction coefficient are known data obtained through expert calculation.

[0053] S2: Train the initial pipeline analysis model based on the historical data of the gas pipeline to be tested to obtain the pipeline analysis model.

[0054] S2-1: An initial pipeline analysis model is constructed by combining a DNN deep neural network model with a decision tree model.

[0055] In this embodiment, as Figure 2 As shown, the initial pipeline analysis model includes an input layer, a hidden layer, and an output layer connected in sequence.

[0056] The input layer, used to receive data from the gas pipeline to be tested, consists of n unit layers {α} 11 α 12 α 13 , ...,α 1n};

[0057] The hidden layer is used to mine the mapping relationships of various features in the data of the gas pipeline to be detected, and includes n unit layers {α}. 21 α 22 α 23 , ...,α 2n};

[0058] The output layer, used to output analysis results, consists of n unit layers {α} 31 α 32 α 33 , ...,α 3n}

[0059] In this embodiment, each unit layer of the input layer is mapped to each unit layer of the hidden layer, and each unit layer of the hidden layer is mapped to each unit layer of the output layer.

[0060] S2-2: Based on historical data of the gas pipeline to be tested, the model parameters for initializing the pipeline analysis model are determined using the gradient descent method.

[0061] S2-2-1: Divide the historical data of the gas pipeline to be tested into time periods, and determine the input data X for each time period. i and the corresponding output data Yi X i and Y i Let represent the input data and output data for the i-th time period, respectively.

[0062] S2-2-2: Based on input data X i Obtain the corresponding latent feature P i .

[0063] In this embodiment, the pipeline efficiency and friction coefficient of the gas transmission pipeline are affected by a variety of hidden features in the pipeline, and changes in each hidden feature will cause changes in the output results.

[0064] Latent Feature P i This includes the mass flow rate of the gas transmission pipeline, pipeline inner diameter, starting pressure, ending pressure, length, area, temperature, density, elevation difference, and service life.

[0065] S2-2-3: The stealth feature P i As input, the output result Y i As output, determine the loss function of the initial pipeline analysis model;

[0066] In this embodiment, the relationship between input and output can be obtained by fitting the existing pipeline efficiency calculation formula.

[0067] S2-2-4: Determine the model parameters using stochastic gradient descent based on at least one determined loss function.

[0068] S2-3: Initialize the initial pipeline analysis model using these model parameters to obtain a defined pipeline analysis model.

[0069] S3: Real-time data of the gas pipeline under test can be collected through OPC and Modbus protocols and input into a defined pipeline analysis model to output analysis results, including pipeline efficiency and friction coefficient.

[0070] In this embodiment, considering the complexity of environmental conditions in different pipelines, the diversity of the impact of different upstream and downstream gas volumes, and the inability to unify correlation parameters, a separate pipeline analysis model is constructed for each gas transmission pipeline to ensure the accuracy of detection.

[0071] In this embodiment, before inputting the real-time data of the gas pipeline to be detected into the determined pipeline analysis model, the method further includes data cleaning of the collected real-time data:

[0072] First, the real-time data is preprocessed using two methods: moving average filtering and amplitude limiting filtering, to remove interference signals (such as noise signals), thereby reducing interference to the data and decreasing the proportion of interference signals in the useful signal.

[0073] Secondly, supplementary assignment is used to fill in missing or incomplete items in the real-time data to ensure data continuity.

[0074] S4: Obtain the operating conditions of the gas pipeline based on the analysis results.

[0075] In this embodiment, when the input data changes, the output analysis results (including pipeline efficiency and friction coefficient) will also change accordingly, thus obtaining the corresponding change curves. Based on the change curves, different operating conditions can be obtained:

[0076] (1) Consider the possibility of leakage risk when the friction coefficient changes steadily as pipeline efficiency decreases;

[0077] (2) Since the gas flow state is mostly in the turbulent region during the gas transmission process, the pipeline cleaning operation is required due to the possible reasons of reduced pipeline efficiency and increased friction coefficient.

[0078] (3) If the pipeline efficiency fluctuates irregularly but the friction coefficient is stable, then it is possible that the process has been reversed or the output has been adjusted.

[0079] Based on the above, the production status of the pipeline can be judged. When the change in production status exceeds the preset threshold, an alarm will be issued and the relevant management personnel will be notified to confirm and carry out relevant operations.

[0080] In this embodiment, the site personnel conduct expert evaluation of the output results, providing correct and incorrect opinions, and supplementing the reasons for the fluctuations in pipeline efficiency and friction coefficient. Subsequently, the model output is learned and optimized based on expert feedback.

[0081] Based on the above-mentioned operating condition analysis method for gas transmission pipelines, such as Figure 3 As shown, the present invention also provides a system for analyzing the operating conditions of gas pipelines, including a user management unit, an access control unit, a data acquisition unit, a pipeline analysis model construction unit, an analysis unit, and an alarm unit.

[0082] The user management unit is used for account registration and login;

[0083] The access control unit is used to assign different permissions to different accounts, thereby preventing data from being tampered with and improving data security.

[0084] The data acquisition unit is used to receive data from the external pipeline;

[0085] The pipeline analysis model building unit is used to build pipeline analysis models and output analysis results based on the received pipeline data.

[0086] The analysis unit is used to determine whether the change exceeds the threshold based on the analysis results. If not, it continues to detect and analyze; if so, it sends an alarm message to the alarm unit to trigger an alarm.

[0087] The alarm unit is used to send alarm signals (audio and visual signals) and simultaneously push alarm information to the terminal of the corresponding staff member, prompting the staff member to check and operate accordingly.

[0088] This application also provides a computer-readable medium storing a method for analyzing the operating conditions of a gas pipeline.

[0089] Computer-readable media can be computer-readable signal media or computer-readable storage media, or any combination thereof. Computer-readable storage media can be, for example,—but not limited to—electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0090] The computer-readable medium may be included in a condition analysis system for a gas pipeline as described; or it may exist independently and not be assembled into the system. The aforementioned computer-readable medium carries one or more programs that, when executed by a system, cause the system to perform the method described in Example 1.

[0091] Those skilled in the art will understand that the above embodiments are specific examples of implementing the present invention, and in practical applications, various changes in form and detail may be made without departing from the spirit and scope of the present invention.

Claims

1. A method for analyzing the operating conditions of gas pipelines, characterized in that, The use of a working condition analysis system includes the following steps: Collect real-time data of the gas pipeline to be tested, including the starting pressure, ending pressure, flow rate, and temperature of the gas pipeline; Input real-time data into the pipeline analysis model and output analysis results; The operating conditions of the gas pipeline were obtained based on the analysis results; The historical data of the gas pipeline to be tested includes input historical data and output historical data; the input historical data includes the starting pressure, ending pressure, flow rate, and temperature of the gas pipeline; the output historical data includes pipeline efficiency and friction coefficient. When pipeline efficiency decreases and the friction coefficient changes steadily, it is considered a risk of leakage. When pipeline efficiency decreases and friction coefficient increases, it is determined that there is an increase in hydrates inside the pipeline, and pipeline cleaning is required. When pipeline efficiency fluctuates irregularly and the friction coefficient remains stable, it is judged that there is a process change or production adjustment.

2. The operating condition analysis method for gas transmission pipelines as described in claim 1, characterized in that, The construction of the pipeline analysis model includes: Historical data of the gas pipeline to be tested is collected from the server; An initial pipeline analysis model was constructed by combining a deep neural network (DNN) model with a decision tree model. Based on historical data of the gas pipeline to be tested, the model parameters for initializing the pipeline analysis model are determined using the gradient descent method. The initial pipeline analysis model is initialized using these model parameters to obtain the pipeline analysis model.

3. The operating condition analysis method for gas transmission pipelines as described in claim 2, characterized in that, The starting pressure and ending pressure are collected by a pressure sensor; the flow rate is collected by a flow sensor; and the temperature is collected by a temperature sensor.

4. The operating condition analysis method for gas transmission pipelines as described in claim 2, characterized in that, The initial pipeline analysis model includes an input layer, a hidden layer, and an output layer connected in sequence. The input layer, used to receive data from the gas pipeline under test from the outside, consists of n unit layers. ； The hidden layer is used to mine the mapping relationships between various features in the data of the gas pipeline to be detected, and includes n unit layers. ; The output layer, used to output analysis results, consists of n unit layers. .

5. The operating condition analysis method for gas transmission pipelines as described in claim 2, characterized in that, The method for determining the model parameters of the initial pipeline analysis model is as follows: The historical data of the gas pipeline to be inspected is divided into time periods, and the input data for each time period is determined. and the corresponding output data , and Let represent the input and output data for the i-th time period, respectively. Based on the input data Obtain the corresponding hidden feature data ; Hidden feature data As input, output result As output, determine the loss function of the initial pipeline analysis model; Based on at least one determined loss function, the model parameters are determined using stochastic gradient descent.

6. The operating condition analysis method for gas transmission pipelines as described in claim 5, characterized in that, The hidden feature data This includes the mass flow rate of the gas transmission pipeline, pipeline inner diameter, starting pressure, ending pressure, length, area, temperature, density, elevation difference, and service life.

7. The operating condition analysis method for gas transmission pipelines as described in claim 1, characterized in that, Before the real-time data is input into the pipeline analysis model, it also includes: First, two methods, moving average filtering and amplitude limiting filtering, are used to preprocess the real-time data; Secondly, supplementary assignment is used to fill in the missing or incomplete items in the real-time data.

8. A condition analysis system for gas pipelines based on the method of any one of claims 1-7, characterized in that, It includes a user management unit, a permission management unit, a data acquisition unit, a pipeline analysis model construction unit, an analysis unit, and an alarm unit; among which, The user management unit is used for account registration and login; The permissions management unit is used to assign different permissions to different accounts; The data acquisition unit is used to receive pipeline data from external sources; The pipeline analysis model building unit is used to build pipeline analysis models and output analysis results based on the received pipeline data. The analysis unit is used to determine whether the change exceeds the threshold based on the analysis results. If not, it continues to detect and analyze; if so, it sends an alarm message to the alarm unit. The alarm unit is used to send alarm signals and simultaneously push alarm information to the terminal of the corresponding staff member.

Images