Oil and gas pipeline leakage monitoring method based on SCADA

Abstract

The invention discloses an oil and gas pipeline leakage monitoring method based on SCADA, and relates to the technical field of safety monitoring, and the method comprises the following steps: S1, building an SCADA data preprocessing model; s2, establishing a leakage feature extraction model; s3, performing leakage state identification through the leakage detection classification model; s4, positioning a leakage point; s5, calculating the leakage rate; s6, evaluating a risk level based on the leakage risk evaluation model; s7, performing real-time early warning, and dynamically adjusting the early warning level; and S8, making an emergency scheme. According to the oil and gas pipeline leakage monitoring method, the influence of environmental noise and operation disturbance can be effectively removed by establishing a plurality of models, the accuracy of leakage feature extraction is ensured, and high precision and dynamic adaptability of leakage positioning and rate estimation are realized. Compared with a traditional method, the method has the advantages that the sensitivity and accuracy of leakage detection are remarkably improved, and monitoring parameters can be dynamically adjusted in a complex environment.

Description

Technical Field

[0001] The present invention relates to the technical field of safety monitoring, and in particular to a SCADA-based oil and gas pipeline leakage monitoring method. Background Art

[0002] With the large-scale installation and operation of oil and gas pipelines worldwide, pipeline leakage has become a significant threat to energy security and environmental protection. Existing leak detection methods based on SCADA (Supervisory Control and Data Acquisition) systems have been widely used. These methods typically rely on real-time monitoring of parameters such as pressure, flow, and temperature, and determine leakage status through fixed thresholds, empirical formula calculations, or signal feature extraction.

[0003] However, faced with complex pipeline conditions and changing environmental factors, existing methods still have many shortcomings in terms of accuracy and reliability. Most traditional leakage monitoring methods use fixed thresholds or discrimination algorithms based on historical experience, which are difficult to cope with changing pipeline conditions. For example, factors such as pressure fluctuations, flow rate changes, and operational disturbances often lead to deviations in monitoring results or even false alarms. Moreover, existing leakage rate estimation models are mostly based on ideal fluid mechanics assumptions and fail to fully consider changes in multiphase flow and medium characteristics, resulting in a significant decrease in accuracy in complex environments. These problems seriously restrict the practicality and accuracy of leakage monitoring, especially in complex terrain or extreme environments, where the false alarm rate remains high and the reliability of leak detection is difficult to guarantee. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides an oil and gas pipeline leakage monitoring method based on SCADA to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides a SCADA-based oil and gas pipeline leakage monitoring method, comprising the following steps: S1. Establish a SCADA data preprocessing model to preprocess the data collected in the SCADA system; S2. Establishing a leakage feature extraction model to extract leakage features based on the pressure gradient change rate and flow rate difference ratio; S3. After extracting the leakage features, the leakage status of the oil and gas pipeline is identified through the leakage detection classification model; S4. After the leakage state is identified, the leakage point is located; S5. After accurately locating the leak point, calculate the leak rate; S6. After obtaining the leakage rate, assess the risk level based on the leakage risk assessment model; S7. Based on the risk level and leakage rate, real-time warning is carried out and the warning level is adjusted dynamically; S8. Develop emergency plans based on early warning results and risk assessment.

[0006] To further optimize the technical solution, in step S1, a SCADA data preprocessing model is established, including: Model construction: Set the collected pressure data as a sequence , the traffic data is a sequence , the signal is decomposed into multiple scales through wavelet transform: ; in, For the Level wavelet coefficients, For 1- Middle wavelet basis functions; Data smoothing: Threshold filtering is performed on the multi-scale wavelet decomposition results using an adaptive threshold method: ; in, Representative The threshold of the wavelet coefficients, For the The standard deviation of the wavelet coefficients; Model output: Get smoothed pressure data and traffic data .

[0007] To further optimize the technical solution, in step S2, a leakage feature extraction model is established, including: Feature construction: The pressure gradient change rate and flow rate difference ratio are used as leakage characteristic quantities; Define the pressure gradient change rate for: ; in, is the smoothed pressure data output from step S1, is the time of pressure change; Defining the flow difference ratio for: ; in, The smoothed traffic data Flow rate data at the pipe inlet, The smoothed traffic data Flow rate data at the pipeline outlet; Feature fusion: Constructing comprehensive leakage characteristics : ; in, and is the weight coefficient, which is optimized by linear regression using historical data.

[0008] Further optimize the technical solution, in step S3, the leakage detection classification model adopts a probabilistic classification model based on Bayesian inference, assuming that the leakage state is L=1 and the non-leakage state is L=0, based on the comprehensive leakage feature quantity Calculate the probability of leakage: ; in, For a given comprehensive leakage characteristic The probability of leakage under L=1, that is, the posterior probability of leakage; is the comprehensive leakage characteristic observed under the leakage state L=1 The probability distribution of , i.e., the likelihood function; is the prior probability of the leakage state, that is, the probability of leakage occurring when no characteristic quantity is observed; is the comprehensive leakage characteristic The prior distribution of represents the probability distribution of the feature quantity in all states.

[0009] To further optimize this technical solution, in the leakage detection classification model, the conditional probability is calculated by maximum likelihood estimation, then the likelihood function The calculation formula is as follows: ; in, and is the comprehensive leakage characteristic quantity under leakage state The mean and variance of A threshold is also set in the leak detection classification model , if the posterior probability of leakage , it is judged as leakage, otherwise it is not leakage.

[0010] To further optimize the technical solution, in step S5, the leakage rate of the leakage point is calculated according to the Bernoulli equation and the flow characteristics of the leakage orifice: ; in, is the leakage rate (unit: m³ / s); is the flow coefficient; is the leakage orifice area (unit: m²); is the density of oil and gas fluid (unit: kg / m³); and are the pressures before and after the leakage point (unit: Pa).

[0011] To further optimize this technical solution, when calculating the leakage rate: The density of oil and gas fluid changes significantly with the density of oil and gas mixture, so a temperature compensation coefficient is introduced. , then the density of oil and gas fluid is The correction formula is as follows: ; in, is the standard density; is the temperature change; Correct the flow coefficient through historical leakage event data and area ; Get the leak rate , used as input for subsequent leakage risk assessment model.

[0012] Further optimizing the technical solution, in step S6, the leakage risk assessment model is based on the leakage rate As input to the model, complete the risk assessment calculation; The leakage risk assessment model includes the classification of risk levels and the calculation of the impact radius of the leaked substance in the environment: Risk level classification: by defining risk assessment indicators and classifying risk levels based on risk assessment indicators; The impact radius is calculated based on the diffusion model to calculate the diffusion radius of the leaked substance in the environment.

[0013] Further optimizing this technical solution, the risk assessment indicator is defined as the risk level , the risk level The calculation formula is as follows: ; in, is the leakage rate output in step S5; is the environmental sensitivity coefficient; is the environmental exposure function, defined as: ; in, is the exposure factor, and are model parameters; Set the risk level threshold, the minimum threshold is , the maximum threshold is , according to the risk level Risk level classification: Low risk: ; Medium risk: ; High risk: .

[0014] Further optimize this technical solution, the diffusion radius of the leaked substance in the environment The calculation formula is: ; Where, is the leakage duration, is the diffusion coefficient.

[0015] In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of a SCADA-based oil and gas pipeline leakage monitoring method as described in the first aspect of the present invention are implemented.

[0016] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of a SCADA-based oil and gas pipeline leakage monitoring method as described in the first aspect of the present invention are implemented.

[0017] Compared with the existing technology, the present invention provides a SCADA-based oil and gas pipeline leakage monitoring method, which belongs to the field of machine learning and deep learning technology and has the following beneficial effects: This SCADA-based oil and gas pipeline leak monitoring method, by establishing multiple models, effectively removes the effects of environmental noise and operational disturbances, ensuring the accuracy of leak feature extraction and achieving high-precision and dynamic adaptability in leak location and rate estimation. Compared to traditional methods, this method not only significantly improves the sensitivity and accuracy of leak detection, but also dynamically adjusts monitoring parameters in complex environments, reducing false positives and missed alarms. It has high practical value and potential for engineering application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a flow chart of a SCADA-based oil and gas pipeline leakage monitoring method proposed in the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it constitute a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1: Reference Figure 1 , which is the first embodiment of the present invention, provides a SCADA-based oil and gas pipeline leakage monitoring method, comprising the following steps: S1. Establish a SCADA data preprocessing model to preprocess the data collected in the SCADA system.

[0024] In oil and gas pipeline leak monitoring, the real-time data collected by SCADA systems is subject to significant noise and instability. Therefore, SCADA data preprocessing is necessary before leak monitoring. De-noising and data smoothing operations make the data valuable for analysis. This data preprocessing model lays the foundation for subsequent leak feature extraction.

[0025] Establish a SCADA data preprocessing model, including: Model construction: In order to eliminate data noise and mutation points, an improved wavelet transform method is used. The collected pressure data is set as a sequence , the traffic data is a sequence , the signal is decomposed into multiple scales through wavelet transform: ; in, For the Level wavelet coefficients, For 1- Middle wavelet basis functions; Data smoothing: Threshold filtering is performed on the multi-scale wavelet decomposition results using an adaptive threshold method: ; in, Representative The threshold of the wavelet coefficients, For the The standard deviation of the wavelet coefficients; Model output: Get smoothed pressure data and traffic data , providing input data for subsequent feature extraction models.

[0026] S2. Establish a leakage feature extraction model to extract leakage features.

[0027] After completing the SCADA data preprocessing, leakage features need to be extracted to identify leakage and non-leakage states.

[0028] Establish a leakage feature extraction model, including: Feature construction: The pressure gradient change rate and flow rate difference ratio are used as leakage characteristic quantities; Defining the pressure gradient change rate for: ; in, is the smoothed pressure data output from step S1, is the time of pressure change; Defining the flow difference ratio for: ; in, The smoothed traffic data Flow rate data at the pipe inlet, The smoothed traffic data Flow rate data at the pipeline outlet; Feature fusion: Constructing comprehensive leakage characteristics : ; in, and is the weight coefficient, which is optimized by linear regression using historical data.

[0029] Compared to traditional methods that simply analyze SCADA data directly, this model significantly enhances robustness to various interference signals. In oil and gas pipeline leak monitoring, environmental noise, pressure fluctuations, and operational disturbances often lead to high false alarm rates. This method effectively removes high-frequency noise and low-frequency trend terms through multi-scale feature extraction using a wavelet decomposition model, thereby ensuring accurate feature extraction.

[0030] S3. After extracting the leakage features, the leakage status is identified through the leakage detection classification model.

[0031] After extracting the leak features, a classification model is needed to identify the leak status. The model should have a high recognition rate and a low false alarm rate to ensure the accuracy of leak monitoring.

[0032] Traditional methods often rely on fixed thresholds or empirical formulas, which often fail to adapt to complex pipeline conditions. This step employs a leakage feature extraction model based on Bayesian discriminant theory, which updates leak probabilities in real time and exhibits strong adaptability when using small samples or when prior information is insufficient. Especially in the case of multivariate coupling, the Bayesian approach can integrate features from multiple sources, reducing false positives.

[0033] The leakage detection classification model adopts a probabilistic classification model based on Bayesian inference, assuming that the leakage state is L=1 and the non-leakage state is L=0. Calculate the probability of leakage: ; in, For a given comprehensive leakage characteristic The probability of leakage under L=1, that is, the posterior probability of leakage; is the comprehensive leakage characteristic observed under the leakage state L=1 The probability distribution of , i.e., the likelihood function; is the prior probability of the leakage state, that is, the probability of leakage occurring when no characteristic quantity is observed; is the comprehensive leakage characteristic The prior distribution of represents the probability distribution of the feature quantity in all states.

[0034] In the leakage detection classification model, the conditional probability is calculated by maximum likelihood estimation, so the likelihood function The calculation formula is as follows: ; in, and is the comprehensive leakage characteristic quantity under leakage state The mean and variance of A threshold is also set in the leak detection classification model , if the posterior probability of leakage , it is judged as leakage, otherwise it is not leakage.

[0035] S4. After the leakage state is identified, the leakage point is located.

[0036] In this embodiment, a leakage point distance model is established based on the sound wave propagation characteristics and pressure attenuation principle. Assume that the distance between the leakage point and the sensor is , then the propagation time of leakage sound wave is: ; in, is the propagation speed of sound waves. Combined with the time difference of arrival (TDOA) of sound waves, the coordinates of the leakage point can be further calculated.

[0037] Compared to traditional leak location methods based on pressure gradients or flow rate differences, this step introduces a model based on acoustic wave propagation, effectively addressing positioning errors caused by signal attenuation in complex terrain. This provides an accurate leak location, which, combined with the SCADA visualization platform, is labeled and displayed as an alarm. Based on the location results, maintenance personnel can quickly reach the leak site, reducing response time and environmental damage.

[0038] S5. After accurately locating the leak point, calculate the leak rate.

[0039] According to the Bernoulli equation and the flow characteristics of the leakage orifice, the leakage rate of the leakage point is calculated: ; in, is the leakage rate (unit: m³ / s); is the flow coefficient; is the leakage orifice area (unit: m²); is the density of oil and gas fluid (unit: kg / m³); and are the pressures before and after the leakage point (unit: Pa).

[0040] The leak rate is calculated when: The density of oil and gas fluid changes significantly with the density of oil and gas mixture, so a temperature compensation coefficient is introduced. , then the density of oil and gas fluid is The correction formula is as follows: ; in, is the standard density; is the temperature change; Correct the flow coefficient through historical leakage event data and area ; Get the leak rate , used as input for subsequent leakage risk assessment model.

[0041] Traditional leak rate estimation generally uses fixed coefficient formulas, which are difficult to handle with varying leak diameters and fluid properties. This step introduces density correction and adaptive optimization of the flow coefficient, enabling the model to flexibly address leak characteristics in different scenarios. This model demonstrates high reliability, particularly in multiphase and mixed media conditions.

[0042] Output leak rate This can be directly used as a parameter for leak intensity assessment and emergency response. Comparative analysis with historical leak events further verifies the accuracy of the estimate. The rate estimate can also serve as an important input variable in leak risk assessment models, supporting subsequent decision-making and optimization.

[0043] S6. After obtaining the leakage rate, the risk level is assessed based on the leakage risk assessment model.

[0044] Leakage risk assessment model based on leakage rate As input to the model, complete the risk assessment calculation; The leakage risk assessment model includes the classification of risk levels and the calculation of the impact radius of the leaked substance in the environment: Risk level classification: by defining risk assessment indicators and classifying risk levels based on risk assessment indicators; The impact radius is calculated based on the diffusion model to calculate the diffusion radius of the leaked substance in the environment.

[0045] The risk assessment indicator is defined as the risk level , the risk level The calculation formula is as follows: ; in, is the leakage rate output in step S5; is the environmental sensitivity coefficient; is the environmental exposure function, defined as: ; in, is the exposure factor, and are model parameters; Set the risk level threshold, the minimum threshold is , the maximum threshold is , according to the risk level Risk level classification: Low risk: ; Medium risk: ; High risk: .

[0046] The diffusion radius of the leaked substance in the environment The calculation formula is: ; Where, is the leakage duration, is the diffusion coefficient.

[0047] The output risk level and the impact radius of the leaked material in the environment provide a quantitative basis for leak warning and emergency response. Based on the assessment results, operations and maintenance personnel can make quick decisions and develop appropriate emergency response strategies to minimize the environmental and economic losses caused by the leak.

[0048] Compared to single-factor assessments based solely on leak rate or environmental sensitivity, the integrated risk assessment model in this step combines leak rate, environmental characteristics, and exposure factors to provide a comprehensive analysis of potential hazards. The risk level output by the model dynamically responds to changes in external conditions, such as wind speed and terrain characteristics, ensuring high real-time performance and accuracy.

[0049] S7. Provide real-time warning based on risk level and leakage rate, and dynamically adjust the warning level.

[0050] To further enhance the responsiveness and intelligence of oil and gas pipeline leak monitoring systems, this step builds on the previous leak risk assessment model by proposing a real-time early warning mechanism and enabling dynamic adjustment of warning levels. Traditional leak warning systems generally employ static grading rules, triggering a specific level of alarm once the leak probability or rate exceeds a fixed threshold. However, this approach lacks comprehensive consideration of factors such as changing environmental conditions, leak evolution speed, and geographically sensitive locations, leading to frequent false alarms and missed alerts, reducing the effectiveness and operability of the early warning system.

[0051] The steps of the present invention fully integrate the leakage rate estimation results and leakage risk level Combined with time-varying trends in leak characteristics, the warning level can automatically upgrade or downgrade as the leak progresses. For example, if the leak rate continues to increase over a short period of time and the risk level is in a highly sensitive area, the warning index will rise exponentially, triggering a higher warning level, achieving a high degree of coupling between warning timeliness and response level.

[0052] The warning output includes real-time warning levels (e.g., Level III Warning, Level II Warning, Level I Severe Warning), as well as trend indicators (continuously rising, maintaining, or declining), which are accessed and dynamically visualized on the SCADA monitoring interface. Integrating the spatial distribution capabilities of the GIS system, the warning levels can also be used to visually represent the leakage risk status of different areas within the geographic interface using colors and icons, enhancing the spatial judgment capabilities of dispatchers. Based on the current warning level, leakage trends, and risk maps, operations and maintenance personnel can quickly determine whether to enter the emergency response phase and select appropriate resource and personnel dispatch plans.

[0053] It enhances the active perception capability and intelligent decision-making support level of the traditional SCADA system, realizes the transformation from "data monitoring to risk-driven intelligent response", and is a key link in building the intelligent and digital transformation of future pipeline systems.

[0054] S8. Develop emergency plans based on early warning results and risk assessment.

[0055] Failure to quickly develop a scientifically sound emergency response strategy after a high-level leak warning significantly increases the risk of the accident escalating, potentially leading to severe economic losses and environmental pollution. Traditional emergency response methods often rely on manual judgment and fixed strategy tables, often based on preset response rule sets. These methods lack the ability to dynamically adapt to complex emergencies and are unable to meet the actual emergency needs of varying geographic conditions, leak types, and resource constraints.

[0056] This step proposes an intelligent emergency response strategy optimization mechanism, which fully integrates the warning level, leakage severity, and spatial risk distribution information output by the previous step, and combines multi-dimensional information such as resource allocation, emergency response capabilities, and geographical traffic conditions in the actual operating environment.

[0057] Specifically, the system intelligently generates a series of emergency response strategies based on the current pipeline leak's location, intensity, risk level, and the geographic sensitivity of the area. These strategies include, but are not limited to, the dynamic allocation of emergency supplies (such as leak-proofing devices, explosion-proof equipment, and emergency lighting), the rapid dispatch of specialized technicians and maintenance personnel, traffic diversion and blockade decisions along the pipeline, risk isolation and control at key nodes, and mechanisms for activating government or community liaisons. The system assesses the current state of available resources and the feasibility of response paths in real time, avoiding the problems of delayed response, resource misallocation, and chaotic responses often associated with traditional approaches.

[0058] Furthermore, by integrating with existing GIS platforms and SCADA systems, optimal response paths and strategic steps can be visualized, clearly indicating the required actions, estimated response times, and target control effects at each node, facilitating global scheduling and task assignment by the command center. The system also supports case learning based on historical leak accident data, prioritizing previously successful response paths in similar scenarios to enhance the intelligence and accuracy of responses.

[0059] The emergency response process will no longer be a simple rule-based process of manual judgment. Instead, it will be an intelligent, closed-loop decision-making system based on real-time data, multi-source information integration, risk evolution prediction, and resource linkage management. This approach will not only significantly shorten emergency response times, but also minimize environmental pollution and economic losses, enhancing the overall risk resilience of the entire oil and gas pipeline system in the face of emergencies.

[0060] Example 2: This embodiment also provides a computer device, which is suitable for a SCADA-based oil and gas pipeline leakage monitoring method, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement a SCADA-based oil and gas pipeline leakage monitoring method proposed in the above embodiment.

[0061] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for monitoring oil and gas pipeline leakage based on SCADA as proposed in the above embodiment is implemented.

[0062] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0063] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0064] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0065] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0066] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A SCADA-based oil and gas pipeline leakage monitoring method, characterized in that: The following steps are involved: S1. Establish a SCADA data preprocessing model to preprocess the data collected in the SCADA system; S2. Establishing a leakage feature extraction model to extract leakage features based on the pressure gradient change rate and flow rate difference ratio; S3. After extracting the leakage features, the leakage status of the oil and gas pipeline is identified through the leakage detection classification model; S4. After the leakage state is identified, the leakage point is located; S5. After accurately locating the leak point, calculate the leak rate; S6. After obtaining the leakage rate, assess the risk level based on the leakage risk assessment model; S7. Provide real-time warning based on risk level and leakage rate, and dynamically adjust the warning level.

2. The SCADA-based oil and gas pipeline leakage monitoring method according to claim 1, characterized in that: In step S1, a SCADA data preprocessing model is established, including: Model construction: The collected pressure data is a sequence , the traffic data is a sequence , the signal is decomposed into multiple scales through wavelet transform: ； in, For the Level wavelet coefficients, For 1- Middle wavelet basis functions; Data smoothing: Threshold filtering is performed on the multi-scale wavelet decomposition results using an adaptive threshold method: ； in, Representative The threshold of the wavelet coefficients, For the The standard deviation of the wavelet coefficients; Model output: Get smoothed pressure data and traffic data .

3. The SCADA-based oil and gas pipeline leakage monitoring method according to claim 1, characterized in that: In step S2, a leakage feature extraction model is established, including: Feature construction: The pressure gradient change rate and flow rate difference ratio are used as leakage characteristic quantities; Pressure gradient change rate for: ； in, is the smoothed pressure data output from step S1, is the time of pressure change; Flow difference ratio for: ； in, The smoothed traffic data Flow rate data at the pipe inlet, The smoothed traffic data Flow rate data at the pipeline outlet; Feature fusion: Constructing comprehensive leakage characteristics : ； in, and is the weight coefficient, which is optimized by linear regression using historical data.

4. The oil and gas pipeline leakage monitoring method based on SCADA according to claim 1, characterized in that: In step S3, the leakage detection classification model adopts a probability classification model based on Bayesian inference, with the leakage state as L=1 and the non-leakage state as L=0. Calculate the probability of leakage: ； in, For a given comprehensive leakage characteristic The probability of leakage under L=1, that is, the posterior probability of leakage; is the comprehensive leakage characteristic observed under the leakage state L=1 The probability distribution of , i.e., the likelihood function; is the prior probability of the leakage state, that is, the probability of leakage occurring when no characteristic quantity is observed; is the comprehensive leakage characteristic The prior distribution of represents the probability distribution of the feature quantity in all states.

5. The oil and gas pipeline leakage monitoring method based on SCADA according to claim 4 is characterized in that: In the leakage detection classification model, the conditional probability is calculated by maximum likelihood estimation, so the likelihood function The calculation formula is as follows: ； in, and is the comprehensive leakage characteristic quantity under leakage state The mean and variance of A threshold is also set in the leak detection classification model , if the posterior probability of leakage , it is judged as leakage, otherwise it is not leakage.

6. The oil and gas pipeline leakage monitoring method based on SCADA according to claim 1, characterized in that: In step S5, the leakage rate of the leakage point is calculated according to the Bernoulli equation and the flow characteristics of the leakage orifice: ； in, is the leakage rate; is the flow coefficient; is the leakage orifice area; is the density of oil and gas fluid; and are the pressures before and after the leak point, respectively.

7. The SCADA-based oil and gas pipeline leakage monitoring method according to claim 6, characterized in that: The leak rate is calculated when: The density of oil and gas fluid changes significantly with the density of oil and gas mixture, so a temperature compensation coefficient is introduced. , then the density of oil and gas fluid is The correction formula is as follows: ； in, is the standard density; is the temperature change; Correct the flow coefficient through historical leakage event data and area ; Get the leak rate , used as input for subsequent leakage risk assessment model.

8. The SCADA-based oil and gas pipeline leakage monitoring method according to claim 1, characterized in that: In step S6, the leakage risk assessment model is based on the leakage rate As input to the model, complete the risk assessment calculation; The leakage risk assessment model includes the classification of risk levels and the calculation of the impact radius of the leaked substance in the environment: Risk level classification: by defining risk assessment indicators and classifying risk levels based on risk assessment indicators; The impact radius is calculated based on the diffusion model to calculate the diffusion radius of the leaked substance in the environment.

9. The SCADA-based oil and gas pipeline leakage monitoring method according to claim 8, characterized in that: The risk assessment indicator is defined as the risk level , the risk level The calculation formula is as follows: ； in, is the leakage rate output in step S5; is the environmental sensitivity coefficient; is the environmental exposure function, defined as: ； in, is the exposure factor, and are model parameters; Set the risk level threshold, the minimum threshold is , the maximum threshold is , according to the risk level Risk level classification: Low risk: ; Medium risk: ; High risk: .

10. The oil and gas pipeline leakage monitoring method based on SCADA according to claim 8, characterized in that: The diffusion radius of the leaked substance in the environment The calculation formula is: ； Where, is the leakage duration, is the diffusion coefficient.

Images