A pipeline leakage alarm method and device based on CO2 phase state

Abstract

The application provides a pipeline leakage alarm method and device based on CO2 phase state. The method acquires real-time pressure time series data and temperature time series data of CO2 in the pipeline and a space-time temperature field matrix output by a distributed optical fiber temperature measurement system arranged along the pipeline; according to the pressure time series data and the temperature time series data, real-time target phase state and corresponding phase state conversion trend parameters are determined by referring to a pre-stored CO2 phase state diagram; target feature parameters related to the target phase state are extracted from the space-time temperature field matrix; a leakage risk index is determined based on the deviation of the short-time fluctuation amplitude of each target feature parameter from the long-time baseline value, and a leakage alarm is triggered according to the comparison result of the leakage risk index and a preset threshold. The method makes the alarm condition highly consistent with the actual leakage thermal characteristics, and significantly reduces the false positive rate during the phase conversion period.

Description

Technical Field

[0001] This application relates to the field of pipeline transportation safety monitoring technology, and more specifically, to a pipeline leakage alarm method and device based on the CO2 phase. Background Technology

[0002] With the advancement of global carbon neutrality goals, CO2 capture, utilization, and storage (CCUS) technologies have developed rapidly, and pipeline transportation has become the main mode of large-scale CO2 transport. Because CO2 is asphyxiating and operates under high pressure in some conditions, pipeline leaks can cause not only economic losses but also potential casualties and environmental accidents. Therefore, real-time and accurate leak monitoring of CO2 pipelines is of great significance.

[0003] In existing technologies, distributed fiber optic temperature sensing (DTS) technology is widely used for continuous monitoring of the temperature field along pipelines. Its basic principle is as follows: when a pipeline leaks, heat exchange between the leaking medium and the surrounding environment causes abnormal local temperature changes. Characteristic parameters such as the rate of temperature change, minimum temperature value, radius of the low-temperature zone, and duration are extracted from the fiber optic temperature sensing data and compared with pre-set fixed thresholds. When the characteristic parameters exceed the threshold, a leak alarm is triggered. This method has been successfully applied in single-phase medium pipelines such as natural gas and oil.

[0004] However, CO2 has unique physical properties and can exist in various phases during pipeline transportation, such as gaseous, liquid (dense phase), or supercritical, depending on pressure and temperature changes. Existing technologies use fixed thresholds for judgment, ignoring the fundamental impact of phase changes on leakage thermal characteristics. This results in the same set of characteristic parameter thresholds being unable to match leakage thermal characteristics under different phases. Summary of the Invention

[0005] The purpose of this application is to provide a pipeline leakage alarm method and device based on CO2 phase state, which solves the technical problem of false alarms or missed alarms due to CO2 phase state changes. Compared with the prior art, the method focuses on the temperature drop rate threshold for supercritical state leakage and on the low temperature zone radius threshold for liquid state leakage, making the alarm conditions highly consistent with the actual leakage thermal characteristics and significantly reducing the false alarm rate during the phase transition period.

[0006] Firstly, a pipeline leakage alarm method based on the CO2 phase is provided, which may include: Real-time acquisition of CO2 pressure time-series data, temperature time-series data, and spatiotemporal temperature field matrix output by a distributed fiber optic temperature measurement system deployed along the pipeline; Based on the pressure time series data and the temperature time series data, the target phase state and corresponding phase transition trend parameters are determined in real time by referring to the pre-stored CO2 phase state diagram. Extract target feature parameters related to the target phase state from the spatiotemporal temperature field matrix; Based on the deviation between the short-term fluctuation amplitude of each target characteristic parameter and the long-term baseline value, a leakage risk index is determined, and a leakage alarm is triggered based on the comparison result between the leakage risk index and the preset threshold.

[0007] In one possible implementation, the phase transition trend parameters include: the minimum dimensionless distance from the current pressure-temperature state point to the nearest phase boundary on the CO2 phase diagram, and the ratio of the pressure change rate to the temperature change rate.

[0008] In one possible implementation, the minimum dimensionless distance is calculated by taking the minimum Euclidean distance between the current pressure and temperature state point and the discrete points of each phase boundary on the pressure-temperature two-dimensional plane of the CO2 phase diagram, and then dividing the minimum value by the length of the diagonal formed by the preset pressure range and temperature range. The ratio of the pressure change rate to the temperature change rate is obtained as follows: least squares linear fitting is performed on the pressure data and temperature data of the most recent N consecutive sampling points to obtain the slope of the pressure change over time as the pressure change rate and the slope of the temperature change over time as the temperature change rate. Then the ratio of the pressure change rate to the temperature change rate is calculated. N is a fixed integer between 5 and 10.

[0009] In one possible implementation, the target feature parameters are extracted from the spatiotemporal temperature field matrix, including: Extract the set of feature parameters related to leakage from the spatiotemporal temperature field matrix; Select target feature parameters related to the target phase from the set of feature parameters.

[0010] In one possible implementation, the target characteristic parameters associated with this target phase state include: When the target phase is a supercritical state, the target characteristic parameters are the rate of temperature change and the duration of low temperature. When the target phase is liquid, the target characteristic parameters are the spatial radius of the low-temperature region and the lowest temperature value; When the target phase is gaseous, the target characteristic parameter is only the duration of low temperature.

[0011] In one possible implementation, the leakage risk index is determined based on the deviation of the calculated short-term fluctuation amplitude of each target characteristic parameter from the long-term baseline value, including: The deviation between the short-term fluctuation amplitude and the long-term baseline value of each target characteristic parameter is calculated as follows: The arithmetic mean of the target feature parameter within a short time window preceding its current time is taken as the short-term fluctuation amplitude; and the moving median of the target feature parameter during a leak-free period within a long time window is taken as the long-term baseline value. The deviation of the target characteristic parameter is obtained by dividing the absolute value of the difference between the short-term fluctuation amplitude and the long-term baseline value by the sum of the long-term baseline value and a zero constant. Based on the calculated deviation of each target characteristic parameter, the leakage risk index is obtained by weighting and summing according to the preset corresponding phase weights.

[0012] In one possible implementation, a leakage alarm is triggered based on a comparison between a leakage risk index and a preset threshold, including: The minimum dimensionless distance in the phase transition trend parameters is compared with a preset transition zone threshold. If the minimum dimensionless distance is less than the transition zone threshold, a nonlinear decay factor is introduced to correct the leakage risk index, and the corrected leakage risk index is used as the comparison index. The index to be compared is compared with a preset threshold: if the index to be compared is greater than the preset threshold, a leakage alarm is triggered.

[0013] Secondly, a pipeline leakage alarm device based on the CO2 phase is provided, which may include: The acquisition unit is used to acquire in real time the pressure time series data and temperature time series data of CO2 in the pipeline, as well as the spatiotemporal temperature field matrix output by the distributed optical fiber temperature measurement system arranged along the pipeline. The determination unit is used to determine the target phase and corresponding phase transition trend parameters in real time by comparing the pressure time series data and the temperature time series data with the pre-stored CO2 phase state diagram. The extraction unit is used to extract target feature parameters related to the target phase from the spatiotemporal temperature field matrix; The determination unit is also used to determine the leakage risk index based on the deviation between the short-term fluctuation amplitude of each target characteristic parameter and the long-term baseline value. The triggering unit is used to trigger a leakage alarm based on the comparison result between the leakage risk index and the preset threshold.

[0014] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0015] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0016] This application provides a pipeline leakage alarm method and device based on CO2 phase state. The method acquires real-time pressure and temperature time-series data of CO2 within the pipeline, as well as the spatiotemporal temperature field matrix output by a distributed fiber optic temperature measurement system arranged along the pipeline. Based on the pressure and temperature time-series data, and by comparing with a pre-stored CO2 phase state diagram, the target phase state and corresponding phase transition trend parameters are determined in real time. Target characteristic parameters related to the target phase state are extracted from the spatiotemporal temperature field matrix. Based on the deviation between the short-term fluctuation amplitude and the long-term baseline value of each calculated target characteristic parameter, a leakage risk index is determined. A leakage alarm is triggered based on the comparison result of the leakage risk index and a preset threshold. This method solves the technical problem of false alarms or missed alarms due to CO2 phase state changes. Compared with existing technologies, it focuses on the temperature drop rate threshold for supercritical state leakage and the low-temperature zone radius threshold for liquid state leakage, making the alarm conditions highly consistent with the actual leakage thermodynamic characteristics and significantly reducing the false alarm rate during the phase transition period. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic flowchart illustrating a pipeline leakage alarm method based on the CO2 phase state provided in this application embodiment; Figure 2 A schematic diagram of a pipeline leakage alarm device based on the CO2 phase state provided in this application embodiment; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art. The terms "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The terms "comprising" or "including," etc., mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but does not exclude other elements or objects. The terms "connection," "coupled," or "linked," etc., are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0020] The pipeline leakage alarm method based on the CO2 phase provided in this application is applied in a pipeline leakage alarm system, which may include the following components: Pressure sensor: Installed at three sections in the upstream, midstream and downstream of the pipeline, with three high-precision pressure transmitters evenly distributed circumferentially in each section, with a range of 0 to 20 MPa, an accuracy of ±0.1%FS, and a sampling frequency of 2 Hz.

[0021] Temperature sensor: Installed in the same position as the pressure sensor, using a Pt100 platinum resistance temperature sensor, with a range of -20℃ to 80℃, an accuracy of ±0.1℃, and a sampling frequency of 2Hz.

[0022] Distributed Fiber Optic Temperature Measurement System (DTS): A multimode optical fiber is laid close to the outer wall of the pipe, with a spatial resolution of 0.5 meters and a temporal resolution of 0.5 seconds, outputting a spatiotemporal temperature field matrix. ,in The coordinates are the spatial coordinates along the pipeline (0.5 meters apart). This represents the sampling time (interval of 0.5 seconds). Matrix elements. Indicates the first The spatial point at the th The temperature value at that moment.

[0023] Data acquisition and processing unit: Includes an industrial computer, a synchronous data acquisition card, and storage devices. Analog signals from pressure and temperature sensors are converted into digital signals by the data acquisition card and synchronized with the temperature data output by the DTS via a precise GPS clock. All data is then aggregated and processed by the industrial computer using algorithms.

[0024] The system executes the following steps in sequence: Baseline acquisition: Under conditions of no pipeline leakage and stable operation, pressure, temperature and DTS data are continuously acquired for 30 minutes to calculate the long-term baseline value, preset temperature difference threshold, preset temperature threshold and adaptive threshold initialization.

[0025] Leakage simulation: Leakage events in different phases were simulated at different locations along the pipeline (100m, 250m, and 400m from the starting point). By adjusting the pipeline pressure and temperature, CO2 was brought to three states: supercritical (12MPa, 35℃), liquid (8MPa, 10℃), and gaseous (5MPa, 5℃). Each leak point was controlled by a solenoid valve, and the leakage lasted for 30 seconds.

[0026] Data acquisition and processing: Real-time acquisition of all sensor data, online leak detection according to the pipeline leak alarm method based on CO2 phase provided in this application, and recording of alarm trigger time, alarm level and alarm evidence.

[0027] Performance evaluation: Statistics on alarm accuracy, false alarm rate, false alarm rate, and response delay under various conditions.

[0028] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0029] Figure 1 This is a schematic flowchart illustrating a pipeline leakage alarm method based on the CO2 phase, provided as an embodiment of this application. Figure 1 As shown, the method may include: Step S110: Real-time acquisition of CO2 pressure time-series data, temperature time-series data, and spatiotemporal temperature field matrix output by the distributed fiber optic temperature measurement system arranged along the pipeline.

[0030] In practice, the pressure sensor and temperature sensor synchronously collect data at a preset sampling frequency (e.g., 2Hz), with each sampling moment... A set of pressure values ​​were obtained. and temperature value To suppress sensor noise, the pressure values ​​at the three cross-sections are averaged to obtain the current pipeline pressure. Similarly, the temperature values ​​at the same location are averaged. The collected pressure time-series data is denoted as follows: Temperature time series data are denoted as .

[0031] The distributed fiber optic temperature measurement system outputs a spatiotemporal temperature field matrix according to a preset spatial resolution (e.g., 0.5 meters) and a preset temporal resolution (e.g., 0.5 seconds). This matrix is ​​a two-dimensional array, where each row corresponds to a spatial point (total...). (points), column corresponding to sampling times. For example, This represents the temperature value at 100 seconds, 50 meters from the starting point.

[0032] Step S120: Based on the pressure time series data and the temperature time series data, determine the target phase state and the corresponding phase transition trend parameters in real time by referring to the pre-stored CO2 phase state diagram.

[0033] (1) Pre-stored CO2 phase diagram: The phase diagram data of CO2 is pre-stored in the industrial computer, based on pressure. (Unit: MPa) is the vertical axis, and temperature is the horizontal axis. Using the horizontal axis, the phase boundaries (gas-liquid boundary, supercritical-liquid boundary, supercritical-gas boundary) are discretized into a series of coordinate points. In this embodiment, the spacing between discrete points at the phase boundary is 0.1 MPa × 0.1 °C.

[0034] (2) Real-time determination of target phase state: For each sampling time Take the current pressure and temperature Locate the state point on the phase diagram. By determining which phase region the point is located in, the current target phase state can be obtained. .

[0035] (3) Calculate the phase transition trend parameter: The phase transition trend parameter can include two components: minimum dimensionless distance And the ratio of the rate of change of pressure to the rate of change of temperature. .

[0036] 1) For the smallest dimensionless distance This is calculated on the pressure-temperature two-dimensional plane of the CO2 phase diagram, by determining the Euclidean distance between the current pressure and temperature state point and the discrete points of each phase boundary, taking the minimum value, and then dividing this minimum value by the length of the diagonal formed by the preset pressure and temperature ranges. The specific calculation process is as follows: First, calculate the current state point on the pressure-temperature two-dimensional plane. With each phase boundary discrete point To calculate the Euclidean distance, pressure and temperature must first be dimensionlessly normalized to make them dimensionless before the Euclidean distance can be calculated. .

[0037] Secondly, take all minimum value .

[0038] Next, determine the preset pressure measurement range. MPa, temperature measurement range ℃. Calculate the diagonal length of the measurement range. This requires first normalizing the pressure and temperature to make them dimensionless before calculation.

[0039] Finally, calculate the minimum dimensionless distance: This value is dimensionless and ranges from 0 to 1.

[0040] 2) The ratio of the rate of change of pressure to the rate of change of temperature The method for obtaining the pressure and temperature data is as follows: Least squares linear fitting is performed on the pressure and temperature data from the most recent N consecutive sampling points to obtain the slope of pressure change over time as the pressure rate of change, and the slope of temperature change over time as the temperature rate of change. Then, the ratio of the pressure rate of change to the temperature rate of change is calculated; where N is a fixed integer between 5 and 10. The specific calculation process is as follows: First, take the nearest one. Pressure data from consecutive sampling points to The least squares method is used to fit the straight line. To obtain the slope As the rate of change of pressure .

[0041] Secondly, temperature data within the same time window to Similarly, a least-squares linear fit is performed to obtain the temperature change rate. .

[0042] Finally, calculate the ratio: , among which, when When approaching zero, to avoid division by zero exceptions, a setting is set if... ,but (This setting is intended to indicate that the current state is dominated by pressure changes through large numerical values, while preserving the directionality of pressure changes.)

[0043] The above passed Quantify the proximity of the current state point to the phase boundary, by... It reflects the dynamic trend of pressure and temperature changes, providing a basis for whether to activate nonlinear attenuation correction in the future.

[0044] Step S130: Extract target feature parameters related to the target phase from the spatiotemporal temperature field matrix.

[0045] In specific implementation, (1) based on the spatiotemporal temperature field matrix, the following four leakage-related feature parameters are extracted, including: 1) Rate of temperature change For each spatial point Calculate the partial derivative of temperature with respect to time. The central difference method is used for approximation.

[0046] in, The temperature at the next moment. The temperature at the previous moment. The sampling time interval is 0.5 seconds in this embodiment.

[0047] Then, the average value of all spatial points within the suspected leak area is taken. The suspected leak area is defined as a continuous region where the current temperature is lower than the average temperature during historical leak-free periods minus one standard deviation. If no such area exists, the entire pipeline monitoring area is used. Finally: ,in, This is a set of spatial points in the suspected leak area. This is to sum the results of all spatial points within the suspected leak area. A leak-free period refers to a continuous time frame within a historical time window where no alarms are triggered and the system self-check confirms no leaks; its length is fixed between 30 and 120 minutes.

[0048] 2) Minimum temperature value : Take the minimum temperature of all spatial points within the entire pipeline monitoring area at the current moment: .

[0049] 3) Spatial radius of the low-temperature zone First, identify the low-temperature zone. Then, set a preset temperature difference threshold. ℃ (This example uses an intermediate value). Calculate the upper limit of the temperature in the low-temperature region: ; All temperatures below A continuous region formed by spatial points is considered a low-temperature region. Calculate the area of ​​this region. (By multiplying the number of discrete points by the area of ​​the pipe segment corresponding to each point, in this embodiment each spatial point represents the area of ​​a cylindrical surface with a length of 0.5 meters and an outer diameter of 219 mm). Then, assuming the low-temperature zone is approximately circular, the radius is calculated: ; 4) Duration of low temperature First, determine the preset temperature threshold. During the leak-free baseline acquisition phase, calculate the historical average temperature of each spatial point. and standard deviation The global average temperature is obtained by taking the average and standard deviation of all spatial points. and global standard deviation Set the preset temperature threshold: ; For each spatial point, when the temperature at that point is continuously below Record the length of the continuous time interval. Take the longest continuous time interval among all spatial points as... .

[0050] (2) Select target characteristic parameters related to the target phase: based on the determined target phase... Select a subset from the four parameters above: like The target characteristic parameters for the supercritical state are: and .

[0051] like Liquid state, target feature parameters are: and .

[0052] like In the gaseous state, the target feature parameters are only: .

[0053] Parameters that are not activated are assigned zero weight in subsequent calculations.

[0054] By selecting different feature combinations based on different phase states, interference from invalid features is avoided, thereby improving the specificity of detection and the signal-to-noise ratio.

[0055] Step S140: Determine the leakage risk index based on the deviation between the short-term fluctuation amplitude and the long-term baseline value of each target characteristic parameter.

[0056] First, calculate the deviation between the short-term fluctuation amplitude of each target feature parameter and the long-term baseline value, specifically including: (1) Take the arithmetic mean of the target feature parameters within a short window preceding the current time as the short-term fluctuation amplitude; specifically: take the current time A previous short window The arithmetic mean of this parameter. Let the number of sampling points within the window be... The short-term fluctuation range Represented as:

[0057] in, For feature parameters In the past The value at each sampling time, where j is the sampling point offset index, ranging from 0 to... Integers.

[0058] (2) Take the moving median of the target characteristic parameter during a leak-free period within a long-term window as the long-term baseline value; specifically: Long-term baseline value : Retrieve a long window from the past The moving median of this parameter during the period without leakage. The system maintains a length of The historical data queue only includes the current data if there were no leaks in the past (i.e., no alarms were triggered). Add to the queue. When the queue is full, remove the oldest data. Then calculate the median of the queue: .

[0059] In the initial stage of system startup, when there is insufficient historical data, the initial values ​​obtained during the baseline acquisition phase are used.

[0060] The length of the short window mentioned above can be a fixed value between 10 seconds and 30 seconds; the length of the long window can be a fixed value between 10 minutes and 60 minutes, and this application does not limit it.

[0061] (3) Calculate the absolute value of the difference between the short-term fluctuation amplitude and the long-term baseline value, divide it by the sum of the long-term baseline value and a zero constant, and obtain the deviation of the target characteristic parameter; specifically: deviation The calculation formula is: ,in To prevent the division by zero small constant, This refers to a specific target characteristic parameter (such as the rate of temperature change, the lowest temperature value, etc.). In this embodiment, we take... .

[0062] (4) Based on the calculated deviation of each target characteristic parameter, a weighted sum is performed according to the preset phase weights to obtain the leakage risk index. Specifically: Preset weights based on the target phase ,satisfy In this embodiment: Supercritical state: , .

[0063] Liquid: , .

[0064] Gaseous state: .

[0065] Leakage Risk Index The calculation is as follows: .

[0066] Furthermore, when the target phase is supercritical and the target characteristic parameters include the rate of temperature change... and duration of low temperature To further improve reliability, the cross-validation factor is calculated. : like (i.e., temperature drops) and (The preset duration is 8 seconds), then .otherwise Then, the leakage risk index was revised to: .

[0067] This cross-validation factor replaces the original one in subsequent steps. .

[0068] In some embodiments, the lengths of the short-time window and the long-time window are not fixed values, but are dynamically adjusted according to the target phase state: When the target phase is supercritical, the short time window is 10 seconds and the long time window is 20 minutes. When the target phase is liquid, the short time window is 20 seconds and the long time window is 40 minutes. When the target phase is gaseous, the short-time window is 30 seconds and the long-time window is 60 minutes. Furthermore, when the ratio of pressure change rate to temperature change rate in the phase transition trend parameter exceeds a preset threshold, the short-term window is temporarily shortened to half its original value to enhance the response sensitivity to rapid transient processes. The thermodynamic response rate of CO2 varies in different phases, with the supercritical state responding fastest and the gaseous state slowest. A fixed window would result in a sluggish response in the supercritical state or noise sensitivity in the gaseous state. Adaptively adjusting the window length according to the phase state and temporarily shortening it during drastic pressure-temperature changes ensures both steady-state noise immunity and improved rapid detection of transient leaks.

[0069] Step S150: Trigger a leakage alarm based on the comparison result between the leakage risk index and the preset threshold.

[0070] In practice, the minimum dimensionless distance in the phase transition trend parameter is compared with the preset transition zone threshold. If the minimum dimensionless distance is greater than or equal to the transition zone threshold, the leakage risk index remains unchanged and is denoted as the index to be compared. If the minimum dimensionless distance is less than the threshold of the transition zone, a nonlinear decay factor is introduced to correct the leakage risk index, and the corrected leakage risk index is used as the comparison index. The comparison index is compared with a preset threshold: if the comparison index is greater than the preset threshold, a leakage alarm is triggered; if the comparison index is less than or equal to the preset threshold, a leakage alarm is not triggered.

[0071] Corresponding to the above method, this application also provides a pipeline leakage alarm device based on the CO2 phase state, such as... Figure 2 As shown, the device includes: The acquisition unit 210 is used to acquire in real time the pressure time series data and temperature time series data of CO2 in the pipeline, as well as the spatiotemporal temperature field matrix output by the distributed optical fiber temperature measurement system arranged along the pipeline. The determination unit 220 is used to determine the target phase state and the corresponding phase state transition trend parameters in real time by referring to the pre-stored CO2 phase state diagram based on the pressure time series data and the temperature time series data. Extraction unit 230 is used to extract target feature parameters related to the target phase state from the spatiotemporal temperature field matrix; The determination unit 220 is also used to determine the leakage risk index based on the deviation between the short-term fluctuation amplitude of each target characteristic parameter and the long-term baseline value. Triggering unit 240 is used to trigger a leakage alarm based on the comparison result between the leakage risk index and the preset threshold.

[0072] The functions of each functional unit of the pipeline leakage alarm device based on CO2 phase provided in the above embodiments of this application can be implemented through the above methods and steps. Therefore, the specific working process and beneficial effects of each unit in the pipeline leakage alarm device based on CO2 phase provided in the embodiments of this application will not be repeated here.

[0073] This application also provides an electronic device, such as... Figure 3 As shown, it includes a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340.

[0074] Memory 330 is used to store computer programs; When the processor 310 executes the program stored in the memory 330, it performs the following steps: Real-time acquisition of CO2 pressure time-series data, temperature time-series data, and spatiotemporal temperature field matrix output by a distributed fiber optic temperature measurement system deployed along the pipeline; Based on the pressure time series data and the temperature time series data, the target phase state and corresponding phase transition trend parameters are determined in real time by referring to the pre-stored CO2 phase state diagram. Extract target feature parameters related to the target phase state from the spatiotemporal temperature field matrix; Based on the deviation between the short-term fluctuation amplitude of each target characteristic parameter and the long-term baseline value, a leakage risk index is determined, and a leakage alarm is triggered based on the comparison result between the leakage risk index and the preset threshold.

[0075] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0076] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0077] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0078] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be 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, or discrete hardware components.

[0079] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 1 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0080] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform any of the pipeline leakage alarm methods based on the CO2 phase described in the above embodiments.

[0081] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the pipeline leakage alarm methods based on the CO2 phase described in the above embodiments.

[0082] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.

[0087] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the claims in this application and their equivalents, then this application also intends to include these modifications and variations.

Claims

1. A pipeline leakage alarm method based on CO2 phase, characterized in that, The method includes: Real-time acquisition of CO2 pressure time-series data, temperature time-series data, and spatiotemporal temperature field matrix output by a distributed fiber optic temperature measurement system deployed along the pipeline; Based on the pressure time series data and the temperature time series data, the target phase state and corresponding phase transition trend parameters are determined in real time by referring to the pre-stored CO2 phase state diagram. Extract target feature parameters related to the target phase state from the spatiotemporal temperature field matrix; Based on the deviation between the short-term fluctuation amplitude of each target characteristic parameter and the long-term baseline value, a leakage risk index is determined, and a leakage alarm is triggered based on the comparison result between the leakage risk index and the preset threshold.

2. The method as described in claim 1, characterized in that, The phase transition trend parameters include: the minimum dimensionless distance from the current pressure and temperature state point to the nearest phase boundary on the CO2 phase diagram, and the ratio of the pressure change rate to the temperature change rate.

3. The method as described in claim 2, characterized in that, The minimum dimensionless distance is calculated on the pressure-temperature two-dimensional plane of the CO2 phase diagram, by taking the minimum Euclidean distance between the current pressure and temperature state point and the discrete points of each phase boundary, and then dividing the minimum value by the length of the diagonal formed by the preset pressure range and temperature range. The ratio of the pressure change rate to the temperature change rate is obtained by performing least squares linear fitting on the pressure data and temperature data of the most recent N consecutive sampling points, respectively, to obtain the slope of the pressure change over time as the pressure change rate and the slope of the temperature change over time as the temperature change rate, and then calculating the ratio of the pressure change rate to the temperature change rate. N is a fixed integer between 5 and 10.

4. The method as described in claim 1, characterized in that, Extract target feature parameters from the spatiotemporal temperature field matrix, including: Extract the set of feature parameters related to leakage from the spatiotemporal temperature field matrix; Select target feature parameters related to the target phase from the set of feature parameters.

5. The method as described in claim 4, characterized in that, The target characteristic parameters associated with this target phase state include: When the target phase is a supercritical state, the target characteristic parameters are the rate of temperature change and the duration of low temperature. When the target phase is liquid, the target characteristic parameters are the spatial radius of the low-temperature region and the lowest temperature value; When the target phase is gaseous, the target characteristic parameter is only the duration of low temperature.

6. The method as described in claim 1, characterized in that, Based on the deviation between the calculated short-term fluctuation amplitude of each target characteristic parameter and the long-term baseline value, a leakage risk index is determined, including: The deviation between the short-term fluctuation amplitude and the long-term baseline value of each target characteristic parameter is calculated as follows: The arithmetic mean of the target feature parameter within a short time window preceding its current time is taken as the short-term fluctuation amplitude; and the moving median of the target feature parameter during a leak-free period within a long time window is taken as the long-term baseline value. The deviation of the target characteristic parameter is obtained by dividing the absolute value of the difference between the short-term fluctuation amplitude and the long-term baseline value by the sum of the long-term baseline value and a zero constant. Based on the calculated deviation of each target characteristic parameter, the leakage risk index is obtained by weighting and summing according to the preset corresponding phase weights.

7. The method as described in claim 2, characterized in that, Leakage alarms are triggered based on the comparison between the leakage risk index and a preset threshold, including: The minimum dimensionless distance in the phase transition trend parameters is compared with a preset transition zone threshold. If the minimum dimensionless distance is less than the transition zone threshold, a nonlinear decay factor is introduced to correct the leakage risk index, and the corrected leakage risk index is used as the comparison index. The index to be compared is compared with a preset threshold: if the index to be compared is greater than the preset threshold, a leakage alarm is triggered.

8. A pipeline leakage alarm device based on the CO2 phase, characterized in that, The device includes: The acquisition unit is used to acquire in real time the pressure time series data and temperature time series data of CO2 in the pipeline, as well as the spatiotemporal temperature field matrix output by the distributed optical fiber temperature measurement system arranged along the pipeline. The determination unit is used to determine the target phase and corresponding phase transition trend parameters in real time by comparing the pressure time series data and the temperature time series data with the pre-stored CO2 phase state diagram. The extraction unit is used to extract target feature parameters related to the target phase from the spatiotemporal temperature field matrix; The determination unit is also used to determine the leakage risk index based on the deviation between the short-term fluctuation amplitude of each target characteristic parameter and the long-term baseline value. The triggering unit is used to trigger a leakage alarm based on the comparison result between the leakage risk index and the preset threshold.

9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images