Natural gas pipeline monitoring and positioning system and method based on optical fiber acoustic wave technology

Abstract

The application discloses a natural gas pipeline monitoring and positioning system and method based on an optical fiber acoustic wave technology, belongs to the technical field of pipeline monitoring, and comprises a management system module, a communication optical cable module, a DAS system module, a SCADA system module and a big data processing system module. The DAS system module identifies the position of an acoustic wave signal, is connected with the big data processing system module, the big data processing system module is connected with the SCADA system, and the management system module is connected with the DAS system module and the big data processing system module. The application combines a traditional acoustic wave monitoring and positioning method with a big data processing method, judges whether a pipeline is blocked or has a water accumulation problem and positions the pipeline through acoustic wave information received by an optical fiber along the pipeline, reduces a false alarm rate, improves the performance of the whole system, and solves problems in the prior art.

Description

Technical Field

[0001] This invention relates to a natural gas pipeline monitoring and positioning system and method based on fiber optic acoustic wave technology, and more particularly to a natural gas pipeline blockage or water accumulation positioning system and method based on distributed fiber optic acoustic wave sensing technology, belonging to the field of pipeline monitoring technology. Background Technology

[0002] Natural gas pipelines are a crucial mode of natural gas transportation. Compared to other methods, pipeline transport offers relatively high economic efficiency and safety. However, due to variations in the quality and characteristics of natural gas, and the complex climate conditions across my country, pipelines are prone to blockages or water accumulation during transport. These blockages can be caused by factors such as hydrate buildup, impurities, and ice. Blockages or water accumulation severely impact pipeline efficiency, and troubleshooting them requires significant human and material resources. Accurate identification and location of blockages or water accumulation in their early stages allow for effective remediation, preventing them from compromising pipeline safety. Therefore, it is essential to develop a real-time, reliable, and accurate method for locating blockages or water accumulation in natural gas pipelines. By introducing real-time positioning technology, the location of pipeline blockages or water accumulation can be accurately determined, providing data support for operation and management companies to formulate unblocking solutions, avoiding complete pipeline blockages, and ensuring that pipelines remain in a stable operating state in the long term.

[0003] In recent years, with the rapid development of distributed optical fiber acoustic sensing (DAS) technology, a new method has been provided for real-time monitoring and location of blockages or water accumulation in natural gas pipelines. DAS technology offers numerous advantages, including long monitoring distances and simple structures, enabling real-time pipeline monitoring without causing damage or impact to the pipeline. The distributed optical fiber acoustic sensing (DAS) system is based on Φ-OTDR technology. It primarily obtains the target of distributed acoustic signal detection by analyzing the phase signal of the Rayleigh scattering light back through an optical fiber. By analyzing changes in the phase and amplitude of the acoustic signal, the intensity information can be enhanced, allowing for quantitative measurement of the acoustic signal. When blockages or water accumulation occur in natural gas pipelines, the cross-sectional area of ​​the natural gas flow channel decreases, resulting in throttling and ultimately generating flow noise. By using DAS technology to collect and analyze this noise information, real-time monitoring and location of blockages or water accumulation can be achieved.

[0004] However, during the use of DAS technology for monitoring and locating blockages or water accumulation in natural gas pipelines, noise may be generated due to pipeline operation and the surrounding environment. This noise has complex and diverse basic characteristics, which may lead to false alarms during the use of DAS technology. According to the current DAS system, it is difficult to achieve high signal-to-noise ratio and low false alarm rate for monitoring and locating blockages or water accumulation in natural gas pipelines. This is an important problem that urgently needs to be solved in this field. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention aims to provide a natural gas pipeline monitoring and positioning system and method based on fiber optic acoustic wave technology, thereby solving the problems existing in the prior art.

[0006] The natural gas pipeline monitoring and positioning system based on fiber optic acoustic wave technology of the present invention includes a management system module, a communication optical cable module, a DAS system module, a SCADA system module, and a big data processing system module. The communication optical cable module is laid in the natural gas pipeline and is interconnected with the DAS system module. The DAS system module receives acoustic wave signals along the communication optical cable and identifies the location of the acoustic wave signals. The DAS system module is connected to the big data processing system module. After the DAS system module identifies the acoustic wave signals, the big data processing system module issues instructions. The big data processing system module is connected to the SCADA system. After receiving the instructions from the DAS system, the big data processing system module retrieves the natural gas pipeline operation data from the SCADA system, analyzes the data, and determines whether there is a blockage or water accumulation problem. The management system module connects the DAS system module and the big data processing system module.

[0007] Furthermore, the system management module includes a monitoring system, an early warning system, and terminal devices. The monitoring system is connected to the DAS system and the big data processing system. After receiving a blockage or water accumulation signal, it issues an early warning through the early warning system. The early warning system also pushes the blockage or water accumulation location information and the early warning result from the DAS system to the terminal devices for display.

[0008] Furthermore, the SCADA system includes temperature sensors, pressure sensors, and flow sensors. The SCADA system is used to receive and store flow rate, pressure, and temperature parameters along the natural gas pipeline.

[0009] Furthermore, the terminal devices in the management system module include two types: smartphones and laptops. Both types of terminal devices connect to the management system module via a wireless network.

[0010] Furthermore, the DAS system module includes a DAS host, a power supply, and an operating computer. The DAS host is connected to both the power supply and the operating computer. The power supply provides power to the entire DAS system module, and the operating computer controls the parameters of the DAS host.

[0011] Furthermore, the communication optical cable module is an optical cable laid in the same trench as the natural gas pipeline, and the optical cable has 4 cores or more.

[0012] The present invention discloses a method for monitoring and locating natural gas pipelines based on fiber optic acoustic technology, comprising the following steps:

[0013] S1: When there is a blockage or water accumulation in the natural gas pipeline, an abnormal noise occurs as the natural gas medium flows through the blockage or water accumulation. The optical cable along the pipeline is disturbed. The optical cable is connected to the DAS system, and the DAS system monitors and identifies the location of the disturbance.

[0014] S2: The DAS system sends a blockage or water accumulation warning to the big data analysis system and sends a blockage or water accumulation warning and the location information of the blockage or water accumulation to the management system module.

[0015] S3: The big data analysis system receives early warning signals of blockage or water accumulation and retrieves pipeline operation data from the SCADA system to further identify and judge whether blockage or water accumulation has occurred.

[0016] S4: After the big data analysis system identifies a blockage or water accumulation problem, it sends an alert to the management system.

[0017] S5: When the management system module receives an early warning from the big data analysis system, it pushes congestion or water accumulation warning information to the terminal device.

[0018] Furthermore, the specific steps for identification and judgment by the big data analysis system in step S3 include the following:

[0019] S11: The SCADA system will use a combination of wireless and wired networks to connect with temperature sensors, flow sensors, and pressure sensors;

[0020] S12: The SCADA system normalizes the collected data and divides the collected data into two types: pipeline operation data when there are blockages or water accumulation and pipeline operation data when there are no blockages or water accumulation.

[0021] S13: Perform BP neural network data learning on the pipeline operation data when there are no blockages or water accumulation, and receive pipeline operation data when the DAS system issues an early warning when there are blockages or water accumulation. Use the BP neural network to judge the blockage problem and output the recognition result.

[0022] Furthermore, the process of judging the congestion problem using a BP neural network in step S13 specifically includes the following:

[0023] S21: Normalize the data using a normalization algorithm. The normalization formula is as follows:

[0024]

[0025] Where: y is the normalized value of the parameter data; x is the original value of the parameter data; μ is the mean of x; σ is the standard deviation of x; the BP neural network training model is a three-layer network structure. During forward propagation, the input data is processed from the input layer through the hidden layer to the output layer. If the output layer does not obtain the expected output, it will switch to backpropagation, and the network weights and thresholds will be adjusted according to the prediction error, so that the predicted output of the BP neural network will continuously approach the expected output.

[0026] Furthermore, in step S5, the management system module can only push warning information and blockage or water accumulation location information if it receives warning information from both the DAS system and the big data analysis system simultaneously.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The natural gas pipeline monitoring and positioning system and method based on fiber optic acoustic wave technology described in this invention combines traditional acoustic wave monitoring and positioning methods with big data processing methods. By receiving acoustic wave information from optical fibers along the pipeline, the DAS system determines whether the pipeline is blocked or has water accumulation and locates the problem. The big data analysis system verifies the DAS system's judgment results by retrieving pipeline operating parameter data from the SCADA system. This improves the signal-to-noise ratio of distributed fiber optic acoustic wave sensing technology for locating natural gas pipeline blockages or water accumulation, reduces the false alarm rate, and improves the overall system performance. This makes the distributed fiber optic acoustic wave sensing technology for locating natural gas pipeline blockages or water accumulation more reliable and better suited for monitoring and locating such blockages. It solves the problems existing in the prior art. Attached Figure Description

[0029] Figure 1 This is a connection block diagram of the natural gas pipeline monitoring and positioning system and method based on fiber optic acoustic wave technology of the present invention;

[0030] Figure 2 This is a schematic diagram of a natural gas pipeline blockage or water accumulation in the natural gas pipeline monitoring and positioning system based on fiber optic acoustic wave technology of the present invention;

[0031] Figure 3This is a schematic diagram of the DAS technology for blockage or water accumulation monitoring and positioning in the natural gas pipeline monitoring and positioning system based on fiber optic acoustic wave technology of the present invention.

[0032] Figure 4 This is a flowchart illustrating the overall steps of the natural gas pipeline monitoring and positioning method based on fiber optic acoustic wave technology of the present invention.

[0033] Figure 5 This is a flowchart of the big data analysis system used in the natural gas pipeline monitoring and positioning method based on fiber optic acoustic wave technology of the present invention. Detailed Implementation

[0034] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0035] Example 1:

[0036] like Figure 1 As shown, the natural gas pipeline monitoring and positioning system based on fiber optic acoustic wave technology of the present invention includes a management system module, a communication optical cable module, a DAS system module, a SCADA system module, and a big data processing system module. The communication optical cable module is laid in the natural gas pipeline and is interconnected with the DAS system module. The DAS system module receives acoustic wave signals along the communication optical cable and identifies the location of the acoustic wave signals. The DAS system module is connected to the big data processing system module. After the DAS system module identifies the acoustic wave signals, the big data processing system module issues instructions. The big data processing system module is connected to the SCADA system. After receiving the instructions from the DAS system, the big data processing system module retrieves the natural gas pipeline operation data from the SCADA system, analyzes the data, and determines whether there is a blockage or water accumulation problem. The management system module connects the DAS system module and the big data processing system module.

[0037] In the above embodiments, such as Figure 2-3 As shown, when a blockage or water accumulation occurs in a natural gas pipeline, abnormal flow will occur at the location of the blockage or water accumulation. The natural gas flowing in the pipeline will rub against the blockage or water accumulation, thus producing a certain sound. The sound inside the pipeline will cause some disturbance to the optical cable laid outside the pipeline. This disturbance will be transmitted to the DAS device. By using the DAS device for analysis, the blockage or water accumulation problem and its location can be determined.

[0038] In some embodiments of the present invention, the management module includes a monitoring system, an early warning system, and a mobile terminal.

[0039] The monitoring system is connected to the early warning system, and the early warning system is connected to the mobile terminal via a wireless network.

[0040] Among them, mobile terminal devices include smartphones and laptops. Smartphones can only display warning information and information on the location of blockages or water accumulation, while laptops can display and save warning information and information on the location of blockages or water accumulation.

[0041] The monitoring system is responsible for monitoring the identification results of blockage or water accumulation problems in the DAS system and the big data analysis system. After the two systems simultaneously identify the ice blockage problem, the early warning system issues a blockage or water accumulation warning and the location information of the blockage or water accumulation. The warning and the location information of the blockage or water accumulation will be displayed on the mobile terminal device.

[0042] In the above embodiments, the diversification of push platforms facilitates the acquisition of pipe blockage or water accumulation warning information and blockage or water accumulation location information anytime and anywhere.

[0043] It should be noted that the early warning system can push early warning information and blockage or water accumulation location information to multiple smartphones and laptops.

[0044] In some embodiments of the present invention, the communication optical cable module is an optical cable laid in the same trench as the natural gas.

[0045] In this embodiment, the optical cable laid in the same trench as the natural gas pipeline also serves to transmit video and central control information. Therefore, the optical cable has four or more cores to ensure that a backup optical cable is available for locating blockages or water accumulation in the natural gas pipeline. The optical cable loss is <0.2dB / km.

[0046] It should be noted that the optical cable needs to be spliced ​​with the DAS system. The optical cable not only plays the role of receiving sound wave information, but also undertakes the role of transmitting sound wave information.

[0047] In some embodiments of the present invention, the DAS system module includes a DAS host, a power supply, and an operating computer.

[0048] Among them, the distributed acoustic sensing (DAS) system is based on Φ-OTDR technology. It mainly obtains the target of distributed acoustic signal detection by the phase signal of the Rayleigh scattering light back of the optical fiber. By improving the acoustic intensity information through the changes in the phase and amplitude of the acoustic signal, quantitative measurement of the acoustic signal can be performed.

[0049] Preferably, the DAS host is connected to a communication-grade optical fiber, which can be either single-mode or multimode. When a blockage or water accumulation occurs in the pipe, the medium inside the pipe will generate a frictional acoustic signal with the blockage or water. This acoustic signal is transmitted to the location of the communication optical cable outside the pipe, causing a slight change in the refractive index and length of the optical fiber. The phase and intensity of the signal transmitted within the optical fiber will also change. Since the phase change in the optical fiber caused by the acoustic signal is relatively small, the DAS system will use a highly coherent pulsed light source. Interference will occur between Rayleigh scattering signals within the pulse width region. When the phase changes at a certain location in the optical fiber, the intensity of the coherent Rayleigh scattering signal at that location will also change. By monitoring the intensity change of the coherent Rayleigh scattering light signal before and after the acoustic signal is generated, the acoustic event can be detected and located, and the blockage or water accumulation event can be identified and its location determined.

[0050] Preferably, the DAS system uses four indicators—phase, amplitude, sound intensity, and sound frequency—to quantitatively evaluate the sound signal.

[0051] Preferably, since the DAS system identifies the location of blockages or water accumulation using fiber optic distance rather than pipe distance, pipe calibration is required to convert the fiber optic distance to pipe distance. During pipe calibration, a hammer is used to strike each marker post along the pipe line to identify the fiber optic distance between each marker post and the pipe's starting point. The distances between each marker post and between each marker post and the pipe's starting point are known values. Based on the fiber optic distances obtained from the hammering and the actual pipe distance, the conversion between pipe distance and fiber optic distance can be achieved.

[0052] For example, there are two marker posts, A and B, along a pipeline. Marker post A is near the pipeline's starting point, and marker post B is near the pipeline's ending point. Point C is a blockage point, located between marker posts A and B. The pipeline distance between marker post A and the pipeline's starting point is 1200m. After tapping with a hammer, it is found that the fiber optic distance between marker post A and the pipeline's starting point is 1300m. The pipeline distance between marker posts A and B is 1500m. After tapping with a hammer, it is found that the fiber optic distance between marker post A and the pipeline's starting point is 1900m. The total pipeline distance between marker posts A and B is 1500m - 1200m = 300m. The total fiber optic distance between marker posts A and B is 1900m - 1300m = 600m. The fiber optic distance to the blockage point C is 1400m. Therefore, the fiber optic distance between the blockage point C and marker post A is 1400m - 1300m = 100m. The pipeline distance between the blockage point C and marker post A is calculated as follows:

[0053]

[0054] Where: a' is the pipeline distance between blockage point C and marker post A, a is the fiber optic distance between blockage point C and marker post A, c is the pipeline distance between marker posts A and B, and b is the fiber optic distance between marker posts A and B. Calculations show that the pipeline distance between blockage point C and marker post A is 100m × (300m / 600m) = 50m, and the pipeline distance between blockage point C and the pipeline starting point = pipeline distance between marker post A and the pipeline starting point + pipeline distance between blockage point C and marker post A = 1200m + 50m = 1250m.

[0055] In some embodiments of the invention, the SCADA system module includes temperature sensors, flow sensors, pressure sensors, and a SCADA system platform along the pipeline. The temperature sensors, flow sensors, and pressure sensors will be installed along the pipeline. The SCADA system platform will connect to the temperature sensors, flow sensors, and pressure sensors using a combination of wireless and wired networks.

[0056] The data collected by the SCADA system can be divided into two types: pipeline operation data when there are blockages or water accumulation, and pipeline operation data when there are no blockages or water accumulation.

[0057] It should be noted that the SCADA system only plays a role in data acquisition and storage.

[0058] Example 2:

[0059] like Figure 4 As shown, the natural gas pipeline monitoring and positioning method based on fiber optic acoustic wave technology of the present invention includes the following steps:

[0060] When there is a blockage or water accumulation in the pipes;

[0061] Abnormal noises will occur as natural gas flows through blockages or water accumulation, and the optical cables along the pipeline will be disturbed. The optical cables are connected to the DAS system, which monitors and identifies the location of the disturbance.

[0062] The DAS system sends blockage or water accumulation warning information to the big data analysis system and sends blockage or water accumulation warning information and location information of the blockage or water accumulation to the management system.

[0063] The big data analysis system receives early warning signals of blockage or water accumulation and retrieves pipeline operation data from the SCADA system to further identify and judge whether blockage or water accumulation has occurred.

[0064] Once the big data analytics system identifies a blockage or water accumulation problem, it sends an alert to the management system.

[0065] When the management system receives warnings from both the DAS system and the big data analysis system, it will push out warnings about blockages or water accumulation.

[0066] like Figure 5 As shown, the further identification and judgment steps of the big data analysis system specifically include the following:

[0067] The SCADA system will use a combination of wireless and wired networks to connect with temperature sensors, flow sensors, and pressure sensors;

[0068] The SCADA system normalizes the collected data and divides it into two types: pipeline operation data when there are blockages or water accumulation and pipeline operation data when there are no blockages or water accumulation.

[0069] The system performs BP neural network data learning on the pipeline operation data collected when there are no blockages or water accumulation. For pipeline operation data with blockages or water accumulation, it receives pipeline operation data when the DAS system issues an early warning, uses the BP neural network to judge the blockage problem, and outputs the recognition result.

[0070] The process of using a BP neural network to determine congestion issues specifically includes the following:

[0071] The data is normalized using a normalization algorithm. The normalization formula is as follows:

[0072]

[0073] Where: y is the normalized value of the parameter data; x is the original value of the parameter data; μ is the mean of x; σ is the standard deviation of x;

[0074] The BP neural network training model is a three-layer network structure. During the forward propagation process, the input data is processed from the input layer through the hidden layer to the output layer. If the output layer does not obtain the expected output, it will switch to backpropagation. The network weights and thresholds are adjusted according to the prediction error, so that the predicted output of the BP neural network continuously approaches the expected output.

[0075] For example, under normal operating conditions of a certain pipeline, a total of 1243 sets of pipeline operating flow, operating pressure, and operating temperature data were collected. The data ranges of operating flow, operating pressure, and operating temperature at points A and B under normal operating conditions are shown in Table 1.

[0076] Table 1. Data range of the locations of points A and B under normal pipeline operation conditions.

[0077]

[0078] When the DAS system issues an early warning and identifies a blockage or water accumulation point between points A and B, the operating temperature, flow rate, and pressure data of 1243 sets of pipelines at points A and B are normalized.

[0079] The BP neural network will learn from the normalized data. Then, it will receive operational data from points A and B of the pipeline when the DAS system issues an early warning. After normalizing the data, the BP neural network algorithm will identify whether there is a blockage or water accumulation at the two locations. Assume the flow rate at point A of the pipeline is 1.77 m³ / s. 3 The pressure is 1.73 MPa, the temperature is 20.33℃, and the flow rate at point B in the pipeline is 1.63 m³ / s. 3 The pressure is 1.62 MPa and the temperature is 19.89℃. It is determined that there is a blockage or water accumulation between points A and B in the pipeline.

[0080] To verify the recognition accuracy of the BP neural network algorithm, 103 sets of normal pipeline operation data and 68 sets of pipeline blockage and water accumulation data were mixed and then simultaneously input into the BP neural network algorithm for recognition. The recognition accuracy is shown in the table below:

[0081] Table 2 Recognition Accuracy Table

[0082] Pipeline is operating normally Pipe blockage or water accumulation Number of data sets (groups) 103 68 Number of groups to be identified 96 66 Recognition accuracy (%) 93.20 97.06

[0083] The BP neural network algorithm achieved a recognition rate of up to 96.43% for pipe blockage and water accumulation problems, proving that this type of algorithm has a high accuracy in the field of pipe ice blockage and water accumulation identification.

[0084] The maximum number of training iterations for the BP neural network is set to 10,000, and the learning rate is set to 0.01.

[0085] It should be noted that the BP neural network algorithm first needs to learn from pipeline operation data under the premise of no blockage or water accumulation in order to determine whether there are abnormalities in pipeline operation parameter data when the DAS issues a warning.

[0086] In the above embodiments, the management system can only push early warning information and blockage or water accumulation location information when it simultaneously receives early warning information from the DAS system and the big data analysis system. This reduces the false alarm rate of blockage or water accumulation early warning and makes the natural gas pipeline blockage or water accumulation location method of the entire distributed fiber optic acoustic sensing technology more efficient, reliable and significantly improves performance.

[0087] The natural gas pipeline monitoring and positioning system and method based on fiber optic acoustic wave technology, as described above in conjunction with the accompanying drawings, combines traditional acoustic wave monitoring and positioning methods with big data processing methods. By using acoustic wave information received from optical fibers along the pipeline, the DAS system determines and locates whether the pipeline is blocked or has water accumulation, thus solving the problems encountered in the prior art. However, this invention is not limited to the described embodiments. Variations, modifications, substitutions, and modifications made to the embodiments without departing from the principles and spirit of this invention still fall within the protection scope of this invention.

Claims

1. A method for monitoring and locating natural gas pipelines based on fiber optic acoustic technology, characterized in that, This document describes a natural gas pipeline monitoring and positioning system based on fiber optic acoustic wave technology. The system includes a management system module, a communication optical cable module, a DAS (Digital Audio System) module, a SCADA (Supervisory Control and Data Acoustic) system module, and a big data analysis system module. The communication optical cable module is laid within the natural gas pipeline and is interconnected with the DAS system module. The DAS system module receives acoustic signals along the communication optical cable and identifies the location of the acoustic signals. The DAS system module is also connected to the big data analysis system module, sending commands to it after identifying the acoustic signals. The big data analysis system module communicates with the SCADA system module, which collects operational data from the natural gas pipeline. The big data analysis system module determines whether blockages or water accumulation have occurred. The management system module connects the DAS system module and the big data analysis system module. The natural gas pipeline monitoring and location method includes the following steps: S1: When a blockage or water accumulation occurs in a natural gas pipeline, an abnormal sound is generated as the natural gas flows through the blockage or water. The optical cable along the pipeline is disturbed. The optical cable is connected to the DAS system module. The DAS system module detects and locates the acoustic event by monitoring the intensity change of the coherent Rayleigh scattering light signal before and after the acoustic signal is generated, and identifies and determines the location of the blockage or water accumulation event. The DAS system module uses four indicators—phase, amplitude, acoustic intensity, and acoustic frequency—to quantitatively evaluate the acoustic signal. S2: The DAS system module sends a blockage or water accumulation warning to the big data analysis system module and sends a blockage or water accumulation warning and the location information of the blockage or water accumulation to the management system module; S3: The big data analysis system module receives blockage or water accumulation warning signals and retrieves pipeline operation data from the SCADA system module to further identify and determine whether blockage or water accumulation has occurred. Specifically, this includes: S11: The SCADA system module connects to temperature sensors, flow sensors, and pressure sensors using a combination of wireless and wired networks; S12: The SCADA system module normalizes the collected data and divides the collected data into two types: pipeline operation data when there are blockages or water accumulation and pipeline operation data when there are no blockages or water accumulation. S13: Perform BP neural network data learning on the pipeline operation data when there are no blockages or water accumulation, and receive pipeline operation data when the DAS system module issues an early warning when there are blockages or water accumulation. Use the BP neural network to judge the blockage problem and output the recognition result. S4: After the big data analysis system module determines the blockage or water accumulation problem, the big data analysis system module sends an early warning to the management system. S5: When the management system module receives an alert from the big data analysis system module, it pushes a blockage or water accumulation alert to the terminal device. The management system module can only push the alert information and the location information of the blockage or water accumulation if it receives alert information from both the DAS system module and the big data analysis system module at the same time.

2. The natural gas pipeline monitoring and positioning method based on fiber optic acoustic technology according to claim 1, characterized in that: The management system module includes a monitoring system, an early warning system, and terminal devices. The monitoring system is connected to the DAS system module and the big data analysis system module. After receiving a blockage or water accumulation signal, the monitoring system issues an early warning through the early warning system. The early warning system also pushes the blockage or water accumulation location information and the early warning result from the DAS system module to be displayed on the terminal devices.

3. The natural gas pipeline monitoring and positioning method based on fiber optic acoustic technology according to claim 1, characterized in that: The SCADA system module includes a temperature sensor, a pressure sensor, and a flow sensor. The SCADA system module is installed at the natural gas pipeline to receive and store flow rate, pressure, and temperature parameter data along the natural gas pipeline.

4. The natural gas pipeline monitoring and positioning method based on fiber optic acoustic wave technology according to claim 2, characterized in that: The terminal devices in the management system module include two types: smartphones and laptops. Both types of terminal devices are connected to the management system module via a wireless network.

5. The natural gas pipeline monitoring and positioning method based on fiber optic acoustic technology according to claim 1, characterized in that: The DAS system module includes a DAS host, a power supply, and an operating computer. The DAS host is connected to both the power supply and the operating computer. The power supply provides power to the entire DAS system module, and the operating computer controls the parameters of the DAS host.

6. The natural gas pipeline monitoring and positioning method based on fiber optic acoustic technology according to claim 1, characterized in that: The aforementioned communication optical cable module is an optical cable laid in the same trench as the natural gas pipeline, and the optical cable has 4 or more cores.

7. The natural gas pipeline monitoring and positioning method based on fiber optic acoustic technology according to claim 1, characterized in that, The process of judging the congestion problem using a BP neural network in step S13 specifically includes: S21: Normalize the data using a normalization algorithm. The normalization formula is as follows: ， Where: y is the normalized value of the parameter data; x is the original value of the parameter data; μ is the mean of x; σ is the standard deviation of x; the BP neural network training model is a three-layer network structure. During forward propagation, the input data is processed from the input layer through the hidden layer to the output layer. If the output layer does not obtain the expected output, it will switch to backpropagation, and the network weights and thresholds will be adjusted according to the prediction error, so that the predicted output of the BP neural network will continuously approach the expected output.

Images