Seabed oil and gas pipeline leakage risk assessment and early warning method, electronic device and storage medium

Abstract

The invention relates to the technical field of submarine oil and gas pipeline leakage risk assessment, in particular to a submarine oil and gas pipeline leakage risk assessment and early warning method, an electronic device and a storage medium. The submarine oil and gas pipeline leakage risk assessment and early warning method comprises the following steps: acquiring first monitoring data through a sensor network deployed on a submarine oil and gas pipeline, determining a leakage section through the first monitoring data, and acquiring second monitoring data through a buoy sensor network deployed on the sea surface; constructing a feature vector and a deep neural network model, inputting the first monitoring data into the deep neural network model, and outputting first simulation leakage data; the method comprises the steps of constructing a pipeline physical model through design parameters and environmental conditions of submarine oil and gas pipelines; based on the first simulation leakage data and a pipeline physical model, second simulation leakage data are obtained through computational fluid dynamics (CFD) simulation; correcting the deep neural network model until the difference between the second monitoring data and the second simulated leakage data is within a set difference value by comparing the difference between the second monitoring data and the second simulated leakage data; constructing an offshore gas disaster analysis model by taking the simulated oil and gas leakage area as a boundary to obtain combustible gas cloud space distribution data; and calculating a comprehensive disaster risk index according to the combustible gas cloud space distribution data, and dividing risk grades according to the comprehensive disaster risk index for early warning. According to the method, the leakage point can be accurately identified, and intelligent risk early warning and evaluation are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of subsea oil and gas pipeline leakage risk assessment, and particularly relates to a subsea oil and gas pipeline leakage risk assessment and early warning method, an electronic device, and a storage medium. Background Art

[0002] In recent years, as an important infrastructure for the development and transportation of offshore oil and gas resources, the safety of subsea oil and gas pipelines has attracted much attention. Due to the complex and harsh subsea environment, the long-term operation of pipelines is extremely vulnerable to factors such as corrosion, mechanical damage, and natural disasters, thus increasing the leakage risk.

[0003] Traditional monitoring and assessment methods usually rely on single-sensor technology or manual inspections, which are not only inefficient but also difficult to achieve real-time and accurate risk early warning. The rapid development of digital twin technology has provided a new solution for the safety monitoring of subsea oil and gas pipelines. By establishing a virtual model consistent with the physical object, digital twin technology can integrate multi-source data, monitor the pipeline operation status in real time, and predict and evaluate potential risks. In addition, by combining computational fluid dynamics simulation and deep learning technology, the diffusion behavior of oil and gas leakage and its impact on the marine ecosystem and platform facilities can be comprehensively analyzed, providing a reliable basis for risk decision-making.

[0004] However, the current engineering application of digital twin technology in the field of subsea pipeline safety still faces challenges. On the one hand, the existing technology layout shows the characteristics of "emphasizing prevention and neglecting emergency", mainly focusing on the life prediction and operation and maintenance of subsea pipelines, and there is no detailed and comprehensive risk assessment and prevention and control technology for underwater gas leakage.

[0005] For example, the patent application with the application number CN202410205310.0 has constructed a pipeline leakage diffusion model and explored the inhibition mechanism, but due to experimental conditions and simplified assumptions, it has not yet formed an engineering solution.

[0006] The patent application with the application number CN202410190590.2 focuses on life prediction and operation and maintenance optimization, but has not established a disaster chain assessment system after leakage.

[0007] Although the sensing device developed in the patent application with the application number CN202010934690.3 has improved the data acquisition ability, it lacks the inversion and evaluation of the leakage process.

[0008] On the other hand, existing research on leaked gas mainly focuses on the analysis of dissolution and phase change mechanisms during the migration of underwater gas plumes, but there is insufficient research on key risk parameters such as gas floating time, plume horizontal migration distance, and sea surface diffusion radius. To address this technical gap, it is urgent to construct a digital twin system based on a set of evaluation of the diffusion path of leaked gas and the deflagration risk threshold to provide a quantitative basis for the setting of explosion-proof zones and the dynamic dispatching of rescue forces on offshore platforms. Summary of the Invention

[0009] The purpose of the present invention is to provide a method, an electronic device, and a storage medium for evaluating and warning the leakage risk of subsea oil and gas pipelines to solve the problems mentioned in the above background technology.

[0010] The technical solution adopted by the present invention to solve its technical problems is as follows: A method for evaluating and warning the leakage risk of subsea oil and gas pipelines, the method for evaluating and warning the leakage risk of subsea oil and gas pipelines includes the following steps:

[0011] S1. Obtain first monitoring data through a sensor network deployed on the subsea oil and gas pipeline, determine the leakage section through the first monitoring data, and obtain second monitoring data through a buoy sensor network deployed on the sea surface;

[0012] S2. Construct a feature vector and a deep neural network model, input the first monitoring data into the deep neural network model, and output first simulated leakage data, where the first simulated leakage data includes a simulated leakage point, a simulated leakage direction, and a simulated leakage scale;

[0013] S3. Construct a pipeline physical model based on the design parameters and environmental conditions of the subsea oil and gas pipeline;

[0014] S4. Based on the first simulated leakage data and the pipeline physical model, obtain second simulated leakage data through computational fluid dynamics (CFD) simulation, where the second simulated leakage data includes a simulated leakage volume, the time for the simulated oil and gas to float to the sea surface, and the simulated oil and gas leakage area;

[0015] S5. By comparing the differences between the second monitoring data and the second simulated leakage data, correct the deep neural network model until the differences between the second monitoring data and the second simulated leakage data are within a set difference value;

[0016] S6. With the simulated oil and gas leakage area as the boundary, construct an offshore gas disaster analysis model to obtain flammable gas cloud spatial distribution data, where the flammable gas cloud spatial distribution data includes the distribution, height, length, coverage area, spatial volume of the flammable gas cloud space, and the dangerous area formed on the offshore platform;

[0017] S7. Calculate the comprehensive disaster risk index based on the flammable gas cloud spatial distribution data, and divide the risk levels according to the comprehensive disaster risk index for early warning.

[0018] Preferably, in step S1, the sensor network includes flexible and stretchable strain sensors and pressure sensors; the first monitoring data includes pipeline stress and strain data and pipeline internal pressure data; the second monitoring data includes marine environment data and oil and gas leakage areas.

[0019] Preferably, in step S1, the method for determining the leakage section is as follows: a number of groups of sensor networks are arranged at intervals on the subsea oil and gas pipeline, and the suspected leakage section is determined according to the obtained pipeline internal pressure data; the pipeline stress and strain data obtained by the flexible and stretchable strain sensors in the same group as the pressure sensors on the pipeline where the suspected leakage section is located are used to verify the suspected leakage section.

[0020] Preferably, step S2 includes the following steps:

[0021] S21. By acquiring the sensor network data under different leakage conditions and normal operating states of the subsea oil and gas pipeline, several feature vectors are extracted to form a feature vector set.

[0022] The feature vector set includes the pipeline internal pressure change rate, stress change amplitude, and stress-strain correlation features.

[0023] S22. Use the feature vector set to train a deep neural network model, and perform repeated training and optimization.

[0024] S23. Input the first monitoring data into the deep neural network model to output the first simulated leakage data.

[0025] Preferably, in step S4, the computational fluid dynamics CFD simulation divides the computational domain into a leakage orifice module, a regular module, and a gas migration path module.

[0026] The leakage orifice module uses tetrahedral meshes of geometric shapes, and the size of the tetrahedral meshes gradually increases from the center of the simulated leakage point to the surrounding areas.

[0027] The regular module uses hexahedral meshes, and the size of the hexahedral meshes remains unchanged.

[0028] The gas migration path module uses encrypted meshes. In the direction of the ocean current, the size of the encrypted meshes gradually decreases, and in the vertical direction, the size of the encrypted meshes gradually decreases from the middle to both sides.

[0029] Preferably, in step S5, the set difference value is less than or equal to 5%.

[0030] Preferably, step S6 is specifically as follows: Based on the simulated oil and gas leakage area, a three-dimensional grid model, i.e., an offshore gas disaster analysis model, is established; using the computational fluid dynamics CFD simulation, the spatial distribution data of the combustible gas cloud is obtained.

[0031] Preferably, in step S7, the mathematical expression for calculating the comprehensive disaster risk index is as follows:

[0032] RiskIndex=α×P avg ×A p +βα×T avg ×A t +γ×R avg ×A r +δ×VC+η×D platform

[0033] In the formula, α, β, γ, δ, and η are weight coefficients, and the sum of α, β, γ, δ, and η is 1; P avg is the average overpressure of the deflagration of the combustible gas cloud; A p is the area affected by the overpressure, that is, the area of the region where the overpressure reaches a certain hazard threshold; T avg is the average temperature of the high-temperature region of the deflagration of the combustible gas cloud; A t is the area affected by the high temperature, that is, the area of the region where the temperature is higher than the threshold temperature that is harmful to the structure and personnel of the offshore platform; R avg is the average intensity of the thermal radiation of the deflagration of the combustible gas cloud; A r is the area affected by the thermal radiation, that is, the area of the region where the thermal radiation intensity reaches the standard for damaging the equipment and personnel of the offshore platform; VC is the volume of the combustible gas cloud space; D platform is the relevant influence factor of the offshore platform.

[0034] An electronic device, the electronic device includes a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete mutual communication through the communication bus;

[0035] The memory is used to store the risk assessment and early warning program for submarine oil and gas pipeline leakage;

[0036] The processor is used to execute the risk assessment and early warning program for submarine oil and gas pipeline leakage. When the risk assessment and early warning program for submarine oil and gas pipeline leakage is executed, the steps of the above-mentioned risk assessment and early warning method for submarine oil and gas pipeline leakage are implemented.

[0037] A computer-readable storage medium stores a risk assessment and early warning program for submarine oil and gas pipeline leakage. When the risk assessment and early warning program for submarine oil and gas pipeline leakage is executed by a processor, the steps of the above-mentioned risk assessment and early warning method for submarine oil and gas pipeline leakage are implemented.

[0038] The beneficial effects of the present invention are:

[0039] 1. The present invention is based on digital twin technology and uses flexible and stretchable strain sensors and pressure sensors to be able to monitor the operating status of subsea oil and gas pipelines in real time, and accurately identify the leakage location, direction and scale through a deep neural network. By constructing a comprehensive disaster risk index and combining it with a dynamic correction mechanism, the accuracy of risk assessment and the reliability of the model are improved, realizing intelligent risk early warning and quantitative assessment of risk levels.

[0040] 2. The present invention covers the entire process from data collection, risk analysis to disaster early warning, not only improving the automation level of risk management, but also enhancing the full-life cycle safety guarantee ability for the operation of subsea oil and gas pipelines, reducing the incidence rate of leakage accidents and their potential hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to the provided drawings.

[0042] Figure 1 It is a schematic diagram of the installation and data transmission of the sensor network and the buoy sensor network of the present invention;

[0043] Figure 2 It is a schematic diagram of the pipeline oil and gas leakage risk assessment and early warning process of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0045] It should be noted that the terms used herein are only for describing the specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0046] The present invention will be further described in conjunction with specific examples. The following embodiments are only for explaining the present invention and do not constitute a limitation to the present invention. The test samples and test procedures used in the following embodiments include the following content (if the specific test conditions are not specified in the embodiments, they are usually in accordance with conventional conditions or the conditions recommended by the reagent company; the reagents, consumables, etc. used in the following embodiments can be obtained from commercial channels without special instructions).

[0047] One of the objectives of the present invention is to provide a method for evaluating and warning the leakage risk of subsea oil and gas pipelines. The method for evaluating and warning the leakage risk of subsea oil and gas pipelines includes the following steps:

[0048] S1. Obtain the first monitoring data through the sensor network deployed on the subsea oil and gas pipeline, determine the leakage section through the first monitoring data, and obtain the second monitoring data through the buoy sensor network deployed on the sea surface;

[0049] S2. Construct a feature vector and a deep neural network model, input the first monitoring data into the deep neural network model, and output the first simulated leakage data. The first simulated leakage data includes the simulated leakage point, the simulated leakage direction, and the simulated leakage scale;

[0050] S3. Construct a pipeline physical model based on the design parameters and environmental conditions of the subsea oil and gas pipeline;

[0051] S4. Based on the first simulated leakage data and the pipeline physical model, obtain the second simulated leakage data through computational fluid dynamics (CFD) simulation. The second simulated leakage data includes the simulated leakage volume, the time for the simulated oil and gas to float to the sea surface, and the simulated oil and gas leakage area. The simulated oil and gas leakage area includes the spill position of the simulated oil and gas on the sea surface and the affected area formed by the simulated oil and gas on the sea surface;

[0052] S5. By comparing the differences between the second monitoring data and the second simulated leakage data, correct the deep neural network model until the differences between the second monitoring data and the second simulated leakage data are within the set difference value;

[0053] S6. Construct an offshore gas disaster analysis model with the simulated oil and gas leakage area as the boundary to obtain the spatial distribution data of the combustible gas cloud. The spatial distribution data of the combustible gas cloud includes the distribution, height, length, coverage area, spatial volume of the combustible gas cloud space, and the dangerous area formed on the offshore platform;

[0054] S7. Calculate the comprehensive disaster risk index according to the spatial distribution data of the combustible gas cloud, and divide the risk levels according to the comprehensive disaster risk index for early warning.

[0055] Such as Figure 1As shown, the sensor network includes flexible and stretchable strain sensors and pressure sensors. The sensor network realizes data transmission through underwater acoustic communication, and transmits the first monitoring data, that is, pipeline stress and strain data and pipeline internal pressure data, to the offshore platform. The abnormal fluctuations can be identified through the pipeline internal pressure data to assist in judging the leakage location and leakage rate; a buoy sensor network is arranged on the sea surface, and the buoy sensor network continuously monitors the target offshore pipeline and transmits the second monitoring data, that is, marine environment data and oil and gas leakage area, to the offshore platform.

[0056] The above sensors adopt a permanent magnet power generation and battery power supply mode to ensure long-term stable operation.

[0057] In step S1, several groups of sensor networks are set at equal intervals. Through the pipeline internal pressure data transmitted in real time, the suspected leakage section is determined; the pipeline stress and strain data obtained by the flexible and stretchable strain sensors in the same group as the pressure sensors on the pipeline where the suspected leakage section is located are used to verify the suspected leakage section.

[0058] In this embodiment, on a 10-kilometer-long and 0.8-meter-diameter submarine oil and gas pipeline, a group of sensor networks is deployed every 100 meters. The pressure sensor can maintain stable pressure monitoring during normal pipeline operation. Once a leakage occurs, the pressure near the leakage point will decrease. When it is monitored that the pressure has an abnormal change of 0.1 - 0.3 MPa within a certain period of time, and the pressure of a certain section of the pipeline drops by more than the set threshold of 0.2 MPa within a short time, while the pressures of other surrounding sensors do not have similar fluctuations, it is determined that this section of the submarine oil and gas pipeline is a suspected leakage section. At this time, combined with the data of the flexible and stretchable strain sensors, if the strain data corresponding to the pressure abnormal change area also fluctuates significantly, it can be initially determined that the leakage point is near the pressure and strain abnormal area, thereby determining the location of the leakage section.

[0059] In this embodiment, step S2 includes the following steps:

[0060] S21. By obtaining the sensor network data under different leakage conditions (determined by numerical simulation) and normal operation states of the submarine oil and gas pipeline, several feature vectors are extracted to form a feature vector set. The feature vector set includes the pipeline internal pressure change rate, stress change amplitude, and stress-strain correlation feature;

[0061] S22. Use the feature vector set to train a deep neural network model, and perform repeated training and optimization;

[0062] S23. Input the first monitoring data into the deep neural network model and output the first simulated leakage data.

[0063] The numerical simulation method is as follows: Based on the actual pipeline parameters, a pipeline-seawater coupling model is established. Unstructured grid division technology is used to perform local encryption on the pipeline wall and leakage hole area to ensure the accuracy of the leakage port vortex and pressure wave propagation. A constant flow boundary is set at the inlet end, and the outlet end is a pressure outlet. The leakage aperture gradient, leakage direction, leakage position and leakage duration are defined as control variables. The transient SST k-ω turbulence model is used to solve the oil and gas mixed flow in the pipeline, and the sensor network data of different leakage conditions (determined by numerical simulation) and normal operation of the submarine oil and gas pipeline are obtained.

[0064] The transient SST k-omega turbulence model (Transient Shear Stress Transport k-omegaTurbulenceModel) is a high-precision turbulence simulation method widely used in computational fluid dynamics (CFD) and is suitable for simulation analysis of complex flows (such as separated flows, strong pressure gradient flows, transient flows, etc.). Its core idea is to combine the advantages of the k-ω model (high accuracy near the wall) and the k-ε model (good free flow stability) and introduce the shear stress transport (SST) correction term to achieve the simulation of turbulent boundary layers and separated flows.

[0065] The model architecture of this deep neural network model includes multiple hidden layers. Each hidden layer adopts an appropriate number of neurons and activation function combination to enhance the model's nonlinear fitting and generalization capabilities. Through repeated training and optimization, the model can accurately learn the complex mapping relationship between the leakage location, direction and scale and the feature vector.

[0066] In actual positioning, in addition to using traditional linear interpolation or spline interpolation methods to analyze the pressure data change trends of adjacent sensors in detail and infer the location of the leakage point based on its rules, the first monitoring data collected in real time is input into the trained deep neural network model. After comprehensive analysis and processing, the model outputs more accurate first simulated leakage data to determine the leakage point, the direction of the leakage (such as forward or reverse along the axis of the pipeline, or a certain azimuth direction relative to the pipeline) and the approximate scale (such as estimating the level range of leakage based on the degree of change in pressure and strain).

[0067] In step S3, a pipeline physical model is constructed according to the design parameters and environmental conditions of the submarine oil and gas pipeline.

[0068] In this embodiment, oil and gas leakage is detected in a specific area of the subsea oil and gas pipeline. Through preliminary exploration and analysis of the first monitoring data, the leakage point is located at 1.5 kilometers of the pipeline mileage. The water depth in this area is about 70m, and the seabed topography presents a gentle slope with a slope of about 5°. According to the actual data collected, a physical model for this leakage area is established. The pipeline model is constructed according to the actual shape and size to simulate the pipeline breakage at the leakage point.

[0069] In step S4, the computational fluid dynamics (CFD) simulation divides the computational domain into a leakage orifice module, a regular module, and a gas migration path module.

[0070] The leakage orifice module adopts tetrahedral meshes of geometric shapes, and the sizes of the tetrahedral meshes gradually increase from the center of the simulated leakage point to the surrounding areas.

[0071] The regular module adopts hexahedral meshes, and the sizes of the hexahedral meshes remain unchanged.

[0072] The gas migration path module adopts encrypted meshes. In the sea current direction, the sizes of the encrypted meshes gradually decrease, and in the vertical direction, the sizes of the encrypted meshes gradually decrease from the middle to both sides.

[0073] In this embodiment, the leakage orifice module adopts tetrahedral meshes with strong adaptability to geometric shapes. The mesh sizes gradually increase from the center of the leakage orifice to the periphery, and the minimum mesh size is 0.10m to capture the initial injection and diffusion behaviors of oil and gas at the leakage orifice. Within 10m from the leakage orifice, the mesh sizes are kept below 0.5m, and as the distance increases, the mesh sizes gradually transition to 0.5m. The surrounding regular module adopts hexahedral meshes with a mesh size of 2m, which can better simulate the fluid flow in the surrounding areas while ensuring the calculation efficiency. For the gas migration path module, key encryption is carried out according to the sea current direction and the oil and gas diffusion trend. In the sea current direction, the encrypted area extends 20m along the flow direction with a width of 10m, and the mesh size is reduced to 0.2m to ensure that the migration process of gas under the action of the sea current can be accurately simulated. In the vertical direction, from the seabed to the sea surface, stratified encryption is carried out within the range of 0 - 30m according to the possible diffusion height of oil and gas. The areas near the seabed and the sea surface have finer meshes, and the middle area is relatively coarser.

[0074] The basic principle of the above-mentioned computational fluid dynamics (CFD) is the coupled model of the volume of fluid (VOF) and the Euler-Lagrange discrete phase model (DPM). The VOF model assumes that the fluids in the computational domain are interpenetrating continuous phases, and the distribution of different phases is measured by the volume fraction. The DPM model regards the gas as bubble particles moving in the continuous water phase, and solves the motion trajectory of the bubbles by integrating the differential equation of particle force in the Lagrangian coordinate system. Taking water and air as the continuous phases and the leaked gas as the discrete phase, the motion of the continuous phase is simulated, and the discrete phase model is used to track the motion trajectory of the bubble particles in the continuous phase, so as to track the motion trajectory of the bubble particles.

[0075] The governing equations of the Eulerian volume-of-fluid model include mass conservation, momentum conservation, and energy conservation:

[0076]

[0077] In the formula, ρ represents the fluid density, t represents time, represents the fluid velocity vector, · represents the divergence operation, p is the pressure, is the viscous stress tensor, is the gravitational acceleration vector. E is the total energy (including internal energy and kinetic energy), k is the thermal conductivity, T is the temperature, and S h is the heat source term.

[0078] In step S5, by comparing the difference between the second monitoring data and the second simulated leakage data, specifically by comparing the differences between the oil and gas leakage area and the simulated oil and gas leakage area, the data error between the two is controlled within 5%, ensuring the rationality and accuracy of the physical model and mesh generation, and providing a basis for subsequent risk assessment and decision support.

[0079] Steps S6 and S7 are the oil and gas leakage assessment and early warning stages of the present invention, and the process is as Figure 2 shown.

[0080] Step S6 is specifically: based on the simulated oil and gas leakage area, a three-dimensional grid model, namely the offshore gas disaster analysis model, is established; using computational fluid dynamics (CFD) simulation, the spatial distribution data of the combustible gas cloud is obtained.

[0081] In this embodiment, the simulated oil and gas diffusion range forms an approximately elliptical area on the sea surface, with the major axis about 100 m and the minor axis about 30 m. Based on this, a three-dimensional grid model is constructed. Using CFD combined with meteorological data (wind speed 5 m / s, wind direction southeast), the dynamic simulation of gas diffusion is carried out to obtain the spatial distribution of the combustible gas cloud, where the length of the combustible gas cloud reaches 300 m, and the height reaches up to 100 m in some areas, and the coverage area is about 12000 m 2 , and the spatial volume is about 5000 m3 。

[0082] In step S7, the mathematical expression for calculating the comprehensive disaster risk index is as follows:

[0083] RiskIndex = α × P avg × A p + β × T avg × A t + γ × R avg × A r + δ × VC + η × D platform

[0084] In the formula, α, β, γ, δ, and η are weight coefficients, and the sum of α, β, γ, δ, and η is 1; P avg is the average overpressure of the deflagration of the combustible gas cloud, and the average value is obtained by monitoring with sensors or numerical simulation calculation within the deflagration area; A p is the area affected by the overpressure, that is, the area of the region where the overpressure reaches a certain hazard threshold; T avg is the average temperature of the high-temperature area of the deflagration of the combustible gas cloud; A t is the high-temperature influence area, that is, the area of the region where the temperature is higher than the threshold temperature that is harmful to the structure and personnel of the offshore platform; R avg is the average intensity of the thermal radiation of the deflagration of the combustible gas cloud; A r is the thermal radiation influence area, that is, the area of the region where the thermal radiation intensity reaches the standard for damaging the equipment and personnel of the offshore platform; VC is the volume of the combustible gas cloud space; D platform is the relevant influence factor of the offshore platform. If the offshore platform is within the direct threat range of the deflagration of the combustible gas cloud and its key equipment and personnel-intensive areas are greatly affected, a higher value is taken.

[0085] In this embodiment, substituting the above combustible gas cloud space distribution data into the mathematical expression for calculating the comprehensive disaster risk index, the average overpressure of the deflagration of the combustible gas cloud is 400 Pa, and the overpressure influence area is 80 / m 2 ; the average temperature is 750 K, and the high-temperature influence area is 60 / m 2 ; the average thermal radiation intensity is 8 kW / m 2 , and the thermal radiation influence area is 100 / m 2 ; the relevant influence factor of the offshore platform is determined to be 0.6 according to its relative position to the combustible gas cloud and the importance of the platform. The weight coefficients are set as α = 0.2, β = 0.15, γ = 0.15, δ = 0.2, η = 0.3, and the calculated comprehensive disaster risk index RiskIndex = 0.2 × 400 × 80 + 0.15 × 750 × 60 + 0.15 × 8 × 100 + 0.2 × 5000 + 0.3 × 0.6 = 14270.18.

[0086] In this embodiment, according to the risk level classification standard, a RiskIndex between 8000 and 15000 is considered a medium-level risk, greater than 15000 is a high-level risk, and less than 8000 is a low-level risk. The current RiskIndex value of 14270.18 is determined to be a medium-level risk. An early warning message is immediately sent to surrounding offshore platforms, the coast guard, and relevant emergency management departments through the maritime communication system and satellite communication. The early warning message details that the risk level is medium, and it is expected that the combustible gas cloud may pose a serious threat to the platform within the next 2 hours. It is recommended that the platform immediately activate the emergency plan, including stopping relevant operations, evacuating non-essential personnel to a safe area, preparing fire and explosion-proof equipment, etc. At the same time, passing ships are reminded to stay away from the area to avoid accidents.

[0087] A second object of the present invention is to provide an electronic device, which includes a processor, a memory, a communication interface, and a communication bus. The electronic device can be a notebook computer, a computer mainframe, a portable mainframe, a smart tablet, or other devices with intelligent computing capabilities; the processor can be a CPU or other final execution units with information processing and program running capabilities; the memory can be a memory, a hard disk, a storage card, or other devices with storage and program reading capabilities.

[0088] In this embodiment, the memory is used to store the risk assessment and early warning program for submarine oil and gas pipeline leaks;

[0089] The processor is used to execute the risk assessment and early warning program for submarine oil and gas pipeline leaks. When the risk assessment and early warning program for submarine oil and gas pipeline leaks is executed, it realizes the steps of the risk assessment and early warning method for submarine oil and gas pipeline leaks as described above.

[0090] A third object of the present invention is to provide a computer-readable storage medium. The risk assessment and early warning program for submarine oil and gas pipeline leaks of the present invention can be stored in the computer-readable storage medium. The computer-readable storage medium can be a USB flash drive, a mobile hard disk, an optical disc, or other devices. When the computer executes the risk assessment and early warning program for submarine oil and gas pipeline leaks, it can read the program stored in the computer-readable storage medium and execute any one of the steps in the above-mentioned risk assessment and early warning method for submarine oil and gas pipeline leaks through the processor.

[0091] In this specification, each embodiment is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts between each embodiment can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0092] The above has introduced in detail a method, an electronic device and a storage medium for evaluating and warning the leakage risk of a subsea oil and gas pipeline provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. A method for assessing and warning the risk of submarine oil and gas pipeline leakage, characterized in that: The risk assessment and early warning method for submarine oil and gas pipeline leakage includes the following steps: S1. Obtain first monitoring data through a sensor network deployed on a submarine oil and gas pipeline, determine a leakage section through the first monitoring data, and obtain second monitoring data through a buoy sensor network deployed on the sea surface; S2. Construct a feature vector and a deep neural network model, input the first monitoring data into the deep neural network model, and output first simulated leakage data, where the first simulated leakage data includes a simulated leakage point, a simulated leakage direction, and a simulated leakage scale; S3. Construct a pipeline physical model based on the design parameters and environmental conditions of the submarine oil and gas pipeline; S4. Based on the first simulated leakage data and the pipeline physical model, obtain second simulated leakage data through computational fluid dynamics (CFD) simulation, where the second simulated leakage data includes a simulated leakage amount, a simulated time for oil and gas to float to the sea surface, and a simulated oil and gas leakage area; S5. By comparing the difference between the second monitoring data and the second simulated leakage data, calibrating the deep neural network model until the difference between the second monitoring data and the second simulated leakage data is within a set difference value; S6. Taking the simulated oil and gas leakage area as the boundary, construct an offshore gas disaster analysis model to obtain the flammable gas cloud spatial distribution data, which includes the flammable gas cloud space distribution, height, length, coverage area, spatial volume and the dangerous area formed on the offshore platform; S7. Calculate the comprehensive disaster risk index based on the spatial distribution data of combustible gas clouds, and divide the risk levels according to the comprehensive disaster risk index for early warning.

2. The method for assessing and warning the risk of submarine oil and gas pipeline leakage according to claim 1 is characterized by: In step S1, the sensor network includes a flexible stretchable strain sensor and a pressure sensor; the first monitoring data includes pipeline stress strain data and pipeline internal pressure data; and the second monitoring data includes marine environment data and oil and gas leakage areas.

3. The method for assessing and warning the risk of submarine oil and gas pipeline leakage according to claim 2 is characterized by: In step S1, the method for determining the leakage section is: several groups of sensor networks are set at intervals on the submarine oil and gas pipeline, and the suspected leakage section is determined based on the obtained internal pressure data of the pipeline; the suspected leakage section is verified by the pipeline stress strain data obtained by the flexible stretchable strain sensor in the same group as the pressure sensor on the pipeline where the suspected leakage section is located.

4. The method for assessing and warning the risk of submarine oil and gas pipeline leakage according to claim 1 is characterized by: Step S2 includes the following steps: S21, by acquiring sensor network data of submarine oil and gas pipelines under different leakage conditions and normal operation conditions, extracting several feature vectors to form a feature vector set, The feature vector set includes the pressure change rate, stress change amplitude and stress-strain correlation characteristics inside the pipeline; S22. Use the feature vector set to train the deep neural network model, and perform repeated training and optimization; S23. Input the first monitoring data into the deep neural network model and output the first simulated leakage data.

5. The method for risk assessment and early warning of submarine oil and gas pipeline leakage according to claim 1 is characterized by: In step S4, the computational fluid dynamics (CFD) simulation divides the calculation domain into a leakage port module, a rule module, and a gas migration path module. The leakage port module uses a geometric tetrahedral grid, and the size of the tetrahedral grid gradually increases from the center of the simulated leakage point to the surrounding areas; The regular module uses a hexahedral mesh, and the size of the hexahedral mesh remains unchanged; The gas migration path module uses an encrypted grid. In the direction of the ocean current, the size of the encrypted grid gradually decreases. In the vertical direction, the size of the encrypted grid gradually decreases from the middle to both sides.

6. The method for assessing and warning the risk of submarine oil and gas pipeline leakage according to claim 1 is characterized by: In step S5, the difference value is set to be less than or equal to 5%.

7. The method for assessing and warning the risk of submarine oil and gas pipeline leakage according to claim 1 is characterized by: Step S6 specifically includes: establishing a three-dimensional grid model, namely, an offshore gas disaster analysis model, based on the simulated oil and gas leakage area; and obtaining the flammable gas cloud spatial distribution data by computational fluid dynamics (CFD) simulation.

8. The method for assessing and warning the risk of submarine oil and gas pipeline leakage according to claim 1 is characterized by: In step S7, the mathematical expression for calculating the comprehensive disaster risk index is as follows: RiskIndex=α×P avg ×A p +β×T avg ×A t +γ×R avg ×A r +δ×VC+η×D platform Where α, β, γ, δ, η are weight coefficients, and the sum of β, γ, δ, η is 1; P avg is the average overpressure of combustible gas cloud explosion; A p is the area affected by overpressure, that is, the area where overpressure reaches a certain hazard threshold; T avg A is the average temperature of the high temperature area of ​​the combustible gas cloud explosion; t is the high temperature affected area, that is, the area where the temperature is higher than the threshold temperature that is harmful to the offshore platform structure and personnel; R avg A is the average intensity of thermal radiation from the deflagration of combustible gas cloud; r is the area affected by thermal radiation, that is, the area where the intensity of thermal radiation reaches the standard of causing damage to offshore platform equipment and personnel; VC is the volume of combustible gas cloud space; D platform It is the influencing factor related to offshore platforms.

9. An electronic device, characterized in that: The electronic device includes a processor, a memory, a communication interface and a communication bus, and the processor, the memory and the communication interface communicate with each other through the communication bus; The memory is used to store the submarine oil and gas pipeline leakage risk assessment and early warning program; The processor is used to execute a submarine oil and gas pipeline leakage risk assessment and early warning program. When the submarine oil and gas pipeline leakage risk assessment and early warning program is executed, the steps of the submarine oil and gas pipeline leakage risk assessment and early warning method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, characterized in that: A submarine oil and gas pipeline leakage risk assessment and early warning program is stored in a computer-readable storage medium. When the submarine oil and gas pipeline leakage risk assessment and early warning program is executed by a processor, the steps of the submarine oil and gas pipeline leakage risk assessment and early warning method according to any one of claims 1 to 8 are implemented.

Images