Working condition analysis method and system for gas pipeline

Abstract

The invention discloses a working condition analysis method and system for a gas pipeline, and the method comprises the following steps: collecting the real-time data of a to-be-detected gas pipeline, including the starting pressure, terminal pressure, flow and temperature of the gas pipeline; inputting the real-time data into the pipeline analysis model, and outputting an analysis result; obtaining the working condition of the gas pipeline according to analysis results. According to the method, the corresponding pipeline analysis model is constructed for each gas pipeline to output the change of the pipeline efficiency and the friction resistance coefficient, and the related threshold value is set to warn and remind the pipeline operation, so that the working condition monitoring accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pipelines, and in particular to a method and system for analyzing operating conditions of a gas transmission pipeline. Background Art

[0002] Pipeline efficiency is an important indicator for measuring the operating status of natural gas pipelines and is also a reference for pipeline cleaning operations. Currently, the methods for calculating pipeline efficiency at stations include using the Weimos formula for wet gas and the Panhandle formula for dry gas.

[0003] However, in actual use, the pipeline efficiency may be too high (over 100%) or too low (very low) in some complex pipelines. In this case, the pipeline efficiency cannot be fully used as the basis for judging other working conditions such as pipeline cleaning operations, thereby reducing the accuracy of pipeline working condition monitoring. Summary of the invention

[0004] In view of the technical problem of low accuracy of pipeline operating condition monitoring in the prior art, the present invention discloses a method and system for analyzing the operating conditions of a gas transmission pipeline, which extracts data features from the operating data of the natural gas pipeline, infers changes in pipeline efficiency and friction coefficient, and sets relevant thresholds to issue alarm reminders for pipeline operation, thereby improving the accuracy of operating condition monitoring.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A method for analyzing working conditions of a gas pipeline comprises the following steps:

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

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

[0009] The working conditions of the gas pipeline are obtained based on the analysis results.

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

[0011] Collect historical data of the gas pipeline to be inspected from the server;

[0012] The initial pipeline analysis model is constructed by combining the DNN deep neural network model and the decision tree model;

[0013] Based on the historical data of the gas pipeline to be inspected, the model parameters of the initial pipeline analysis model are determined by the gradient descent method;

[0014] The initial pipeline analysis model is initialized by using the 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, terminal pressure, flow rate, and temperature of the gas pipeline; the output historical data includes pipeline efficiency and friction coefficient.

[0016] Preferably, the starting point pressure and the end point 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 comprises an input layer, a hidden layer and an output layer connected in sequence;

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

[0019] Hidden layer, used to mine the mapping relationship of various features in the data of the gas pipeline to be detected, including n unit layers {α 21 , α 22 , α 23 ,...,α 2n};

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

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

[0022] 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 Y i , X i and Y i Respectively represent the input data and output data of the i-th time period;

[0023] According to the input data X i Get the corresponding invisible feature data P i ;

[0024] The invisible feature data P i As input, the output is Y i As an output, a loss function of the initial pipeline analysis model is determined;

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

[0026] Preferably, the invisible feature data P i Including gas pipeline mass flow, pipeline inner diameter, starting pressure, end pressure, length, area, temperature, density, elevation difference, and service life.

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

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

[0029] (2) When the pipeline transportation efficiency decreases and the friction coefficient increases, it is judged that the number of hydrates inside the pipeline increases and the pipeline cleaning operation is required;

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

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

[0032] Firstly, the real-time data is preprocessed by using sliding average filtering and limiting filtering;

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

[0034] The present invention also provides a working condition analysis system for a gas pipeline, comprising a user management unit, a permission management unit, a data acquisition unit, a pipeline analysis model building unit, an analysis unit and an alarm unit; wherein,

[0035] User management unit, used for account registration and login;

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

[0037] A data acquisition unit, used for receiving pipeline data from the outside;

[0038] A pipeline analysis model building unit, used to build a pipeline analysis model and output analysis results according to the received pipeline data;

[0039] An analysis unit is used to determine whether the change amplitude exceeds a threshold value according to the analysis result, and if not, continue the detection and analysis, and if so, send an alarm message to the alarm unit;

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

[0041] In summary, due to the adoption of the above technical solution, compared with the prior art, the present invention has at least the following beneficial effects:

[0042] The present invention extracts data features from each natural gas pipeline operation data, outputs changes in pipeline efficiency and friction coefficient through a correspondingly constructed pipeline analysis model, and sets relevant thresholds to issue pipeline operation alarms, thereby improving the accuracy of operating condition monitoring.

[0043] The present invention realizes individual detection of pipelines in different environments by modeling each pipeline separately, and can analyze data more specifically to improve accuracy. Description of the drawings:

[0044] Figure 1 Schematic diagram of a method for analyzing operating conditions of a gas pipeline according to an exemplary embodiment of the present invention.

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

[0046] Figure 3 Schematic diagram of a working condition analysis system for a gas pipeline according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0047] The present invention is further described in detail below in conjunction with the examples and specific implementation methods. However, this should not be understood as the scope of the above subject matter of the present invention being limited to the following examples, and all technologies realized based on the content of the present invention belong to the scope of the present invention.

[0048] In the description of the present invention, it is necessary to understand that the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0049] like Figure 1 As shown, the present invention provides a method for analyzing the working conditions of a gas pipeline, which specifically includes the following steps:

[0050] S1: Collect historical data of the gas pipeline to be inspected 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, end pressure, flow rate, temperature, etc., and the output data includes pipeline efficiency, friction coefficient, etc.

[0052] In this embodiment, the starting pressure and the end 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; the pipeline efficiency and the friction coefficient are known data obtained by expert calculation.

[0053] S2: The constructed initial pipeline analysis model is trained according to the historical data of the gas pipeline to be inspected to obtain a pipeline analysis model.

[0054] S2-1: The initial pipeline analysis model is constructed by combining the DNN deep neural network model and the decision tree model.

[0055] In this embodiment, 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 is used to receive the data of the gas pipeline to be detected from the outside world, including n unit layers {α 11 , α 12 , α 13 ,...,α 1n};

[0057] Hidden layer, used to mine the mapping relationship of various features in the data of the gas pipeline to be detected, including n unit layers {α 21 , α 22 , α 23 ,...,α 2n};

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

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

[0060] S2-2: Based on the historical data of the gas pipeline to be inspected, the model parameters of the initialization pipeline analysis model are determined by 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 Represent the input data and output data of the i-th time period respectively.

[0062] S2-2-2: According to the input data X i Get the corresponding invisible feature P i .

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

[0064] Invisible Features P i Including gas pipeline mass flow, pipeline inner diameter, starting pressure, end pressure, length, area, temperature, density, elevation difference, service life, etc.

[0065] S2-2-3: Set invisible feature P i As input, the output is Y i As an output, a loss function of the initial pipeline analysis model is determined;

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

[0067] S2-2-4: Based on the determined at least one loss function, determine the model parameters by stochastic gradient descent method.

[0068] S2-3: Initializing the initial pipeline analysis model through the model parameters to obtain a determined pipeline analysis model.

[0069] S3: The real-time data of the gas pipeline to be inspected can be collected through OPC and MODBUS protocols, and input into the determined pipeline analysis model, so as to output the analysis results, including pipeline efficiency and friction coefficient.

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

[0071] In this embodiment, before the real-time data of the gas pipeline to be detected is input into the determined pipeline analysis model, the collected real-time data is also cleaned:

[0072] First, the real-time data is preprocessed by using sliding average filtering and limiting filtering to remove interference signals (such as noise signals), thereby reducing interference to the data and reducing the proportion of interference signals in useful signals;

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

[0074] S4: Obtain the gas pipeline operating conditions 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, so a corresponding change curve can be obtained, and different working conditions can be obtained according to the change curve:

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

[0077] (2) Since the gas flow state during gas transmission in the gas pipeline is mostly in the turbulent zone, the pipeline transmission efficiency is reduced and the friction coefficient increases. Considering the possible reasons, the increase of hydrates inside the pipeline requires pipeline cleaning operations;

[0078] (3) If the pipeline efficiency fluctuates irregularly and the friction coefficient is stable, consider the possibility of process switching or production adjustment;

[0079] Based on the above situation, the production status of the pipeline can be judged. When the production status changes beyond the preset threshold, an alarm will be issued and the corresponding management personnel will be notified to confirm and perform related operations.

[0080] In this embodiment, the station personnel make expert judgments on the output results, give correct and incorrect opinions, and supplement the reasons for the fluctuations in pipeline efficiency and friction coefficient. Subsequently, learning and optimization of the model output are carried out based on the expert feedback.

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

[0082] User management unit, used for account registration and login;

[0083] The permission management unit is used to assign different permissions to different accounts, thereby preventing data from being tampered with and improving data security;

[0084] A data acquisition unit, used for receiving pipeline data from the outside;

[0085] A pipeline analysis model building unit, used to build a pipeline analysis model and output analysis results based on received pipeline data;

[0086] The analysis unit is used to determine whether the change amplitude exceeds the threshold value according to the analysis result. If not, continue the detection and analysis. If yes, send an alarm message to the alarm unit for alarm.

[0087] The alarm unit is used to send out alarm signals (sound and light signals) and simultaneously push the alarm information to the terminal of the corresponding staff, prompting the staff to perform relevant checks and operations.

[0088] The present application also provides a computer-readable medium, on which is stored a method for analyzing operating conditions of a gas pipeline.

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

[0090] The computer readable medium may be included in the described working condition analysis system for gas pipelines; or may exist independently without being assembled into the system. The computer readable medium carries one or more programs, and when the one or more programs are executed by the system, the system implements the method described in Example 1.

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

Claims

1. A method for analyzing the working conditions of a gas pipeline, characterized in that: The following steps are involved: Collect real-time data of the gas pipeline to be tested, including the starting pressure, end pressure, flow rate, and temperature of the gas pipeline; Input real-time data into pipeline analysis models and output analysis results; The working conditions of the gas pipeline are obtained based on the analysis results.

2. A method for analyzing operating conditions of a gas pipeline according to claim 1, characterized in that: The construction of the pipeline analysis model includes: Collect historical data of the gas pipeline to be inspected from the server; The initial pipeline analysis model is constructed by combining the DNN deep neural network model and the decision tree model; Based on the historical data of the gas pipeline to be inspected, the model parameters of the initial pipeline analysis model are determined by the gradient descent method; The initial pipeline analysis model is initialized by using the model parameters to obtain the pipeline analysis model.

3. A method for analyzing operating conditions of a gas pipeline according to claim 2, characterized in that: 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, terminal pressure, flow rate, and temperature of the gas pipeline; the output historical data includes pipeline efficiency and friction coefficient.

4. A method for analyzing operating conditions of a gas pipeline according to claim 3, characterized in that: The starting point pressure and the end point 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.

5. A method for analyzing operating conditions of a gas pipeline according to 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 is used to receive the data of the gas pipeline to be detected from the outside world, including n unit layers {α 11 , α 12 , α 13 ,...,α 1n }; Hidden layer, used to mine the mapping relationship of various features in the data of the gas pipeline to be detected, including n unit layers {α 21 , α 22 , α 23 ,...,α 2n }; The output layer is used to output the analysis results, including n unit layers {α 31 , α 32 , α 33 ,...,α 3n }.

6. A method for analyzing operating conditions of a gas pipeline according to claim 2, characterized in that: The method for determining the model parameters of the initialization pipeline analysis model is: 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 Y i , X i and Y i Respectively represent the input data and output data of the i-th time period; According to the input data X i Get the corresponding invisible feature data P i ; The invisible feature data P i As input, the output is Y i As an output, a loss function of the initial pipeline analysis model is determined; Based on the determined at least one loss function, model parameters are determined by a stochastic gradient descent method.

7. A method for analyzing operating conditions of a gas pipeline according to claim 6, characterized in that: The invisible feature data P i Including gas pipeline mass flow, pipeline inner diameter, starting pressure, end pressure, length, area, temperature, density, elevation difference, and service life.

8. The method for analyzing the working condition of a gas pipeline according to claim 1, characterized in that: The working condition of the gas pipeline is determined as follows: (1) When the pipeline efficiency decreases and the friction coefficient changes steadily, it is judged as a leakage risk; (2) When the pipeline transportation efficiency decreases and the friction coefficient increases, it is judged that the number of hydrates inside the pipeline increases and the pipeline cleaning operation is required; (3) When the pipeline efficiency fluctuates irregularly and the friction coefficient is stable, it is judged that there is a process reversal or production adjustment.

9. A method for analyzing operating conditions of a gas pipeline according to claim 1, characterized in that: Before the real-time data is input into the pipeline analysis model, it also includes: Firstly, the real-time data is preprocessed by using sliding average filtering and limiting filtering; Secondly, supplementary assignment is used to fill in the missing items in the real-time data.

10. A working condition analysis system for a gas pipeline based on the method according to any one of claims 1 to 9, characterized in that: It includes a user management unit, a permission management unit, a data acquisition unit, a pipeline analysis model building unit, an analysis unit and an alarm unit; wherein, User management unit, used for account registration and login; The permission management unit is used to assign different permissions to different accounts; A data acquisition unit, used for receiving pipeline data from the outside; A pipeline analysis model building unit, used to build a pipeline analysis model and output analysis results according to the received pipeline data; An analysis unit is used to determine whether the change amplitude exceeds a threshold value according to the analysis result, and if not, continue the detection and analysis, and if so, send an alarm message to the alarm unit; The alarm unit is used to send out an alarm signal and simultaneously push the alarm information to the terminal of the corresponding staff.

Images