A digital analysis method and device for raising the integrity of wellhead equipment of a short section

Abstract

The present application relates to artificial intelligence, model fusion technology, and discloses a kind of digital analysis method and device for raising short section wellhead equipment integrity, comprising: obtaining the multi-modal sensing data of raising short section wellhead equipment and generating multi-modal fusion feature set;Build multi-parameter dynamic coupling model, obtain historical time series stress field characteristic sample and extract reduced order basis function matrix, utilize reduced order basis function matrix to carry out dimensionality reduction mapping to full-order system stiffness matrix, update and generate reduced order characteristic stiffness matrix;Based on reduced order characteristic stiffness matrix, perform multi-field coupling iterative calculation, output coupled state characteristic data;Stress concentration space coordinates and comprehensive stress distribution matrix are mapped into three-dimensional digital twin node model to generate integrity evaluation atlas, while based on comprehensive stress distribution matrix and material aging degradation function, calculate safety margin quantitative index.The present application can improve the accuracy and efficiency of wellhead equipment integrity analysis.

Description

Technical Field

[0001] This invention belongs to the fields of artificial intelligence and model fusion technology, and particularly relates to a digital analysis method and device for improving the integrity of short-section wellhead equipment. Background Technology

[0002] In oil and gas extraction engineering, wellhead equipment is the core hub connecting the downhole tubing string to the surface pipeline network. During long-term service, wellhead equipment not only needs to withstand extremely high internal fluid pressure and the enormous axial dynamic and static loads from the suspension of the lower tubing string, but also is constantly exposed to complex corrosive media environments such as highly salinized water and carbon dioxide. As the service life of old wells in oil and gas fields continues to increase, the combined effects of material aging, multiaxial stress, and the highly corrosive environment make wellhead equipment highly susceptible to failure risks such as localized wall thinning, hidden cracks, and thermal stress concentration. Therefore, accurate and real-time structural integrity assessment and safety risk early warning are crucial for ensuring the safety of oil and gas production.

[0003] Currently, the integrity assessment of such high-pressure wellhead equipment mainly relies on periodic offline testing and static theoretical model evaluation, but this has revealed the following significant shortcomings in practical engineering applications: First, at the physical inspection level, existing technologies typically employ single-modal inspection methods, such as conventional ultrasonic testing, to acquire equipment damage data. However, wellhead equipment usually has complex structures such as protective bushings installed inside. Single-modal inspection is highly susceptible to mechanical obstruction by the bushings, creating severe blind spots and resulting in extremely low detection rates for hidden defects beneath the bushings, such as microcracks and localized severe wall thickness losses. This limitation of physical detection methods leads to a lack of completeness and accuracy in the input data for subsequent evaluation models.

[0004] Secondly, at the mechanical evaluation and calculation level, existing technologies generally adopt the traditional full-grid finite element static analysis model. Because the stiffness matrix of a full-order finite element system has an extremely large dimension, a single mechanical solution and evaluation analysis often takes several hours or even longer. This high-latency static analysis mode cannot respond in real time to transient load changes such as wellhead pressure fluctuations and tubing string vibrations, exhibiting severe dynamic response lag, and completely fails to meet the industrial requirements of modern intelligent oil and gas fields for real-time, dynamic monitoring of equipment risks.

[0005] Third, at the model mechanism and systemic level, equipment damage under actual operating conditions is the result of deep coupling of multiple factors. Existing assessment methods typically analyze the material properties of the equipment, material aging and degradation due to long-term service, environmental corrosion rate, and dynamic multiaxial stress distribution in a fragmented and independent manner. Due to the lack of a unified dynamic coupling mathematical model of "corrosion-stress-defect evolution," existing technologies cannot truly quantify the mutually reinforcing and accelerating effects of media corrosion and multiaxial stress concentration at defects. This fragmented single-factor analysis leads to a significant deviation between the calculated safety margin and the actual remaining service life.

[0006] In summary, existing wellhead equipment integrity analysis methods suffer from low accuracy and efficiency under complex operating conditions due to blind spots in single-modal detection, excessive time consumption of static calculation models, and lack of multi-parameter coupling mechanisms. Summary of the Invention

[0007] This invention provides a digital analysis method and apparatus for improving the integrity of short-section wellhead equipment, which can improve the accuracy and efficiency of wellhead equipment integrity analysis.

[0008] To achieve the above objectives, the present invention provides a digital analysis method for improving the integrity of short-section wellhead equipment, comprising: Acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data. Based on the multimodal fusion feature set and operating environment parameters, a multi-parameter dynamic coupling model is constructed. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model. Obtain historical time-series stress field feature samples and extract the reduced-order basis function matrix from the historical time-series stress field feature samples. Use the reduced-order basis function matrix to perform dimension reduction mapping on the preset full-order system stiffness matrix, and update and generate the reduced-order feature stiffness matrix of the corresponding multi-parameter dynamic coupling model. Based on the reduced-order characteristic stiffness matrix, the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model are subjected to multi-field coupled iterative calculation in the spatiotemporal dimension, and the output is coupled state characteristic data containing the spatial coordinates of stress concentration and the comprehensive stress distribution matrix. The spatial coordinates of stress concentration and the comprehensive stress distribution matrix are jointly mapped onto the three-dimensional digital twin node model to generate an integrity evaluation map. At the same time, the safety margin quantification index is calculated based on the comprehensive stress distribution matrix and the material aging degradation function.

[0009] To address the aforementioned problems, the present invention also provides a digital analysis device for improving the integrity of short-section wellhead equipment, the device comprising: The multimodal sensing data fusion module is used to acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data and infrared thermal imaging data. The dynamic coupling reduction calculation module is used to construct a multi-parameter dynamic coupling model based on a multi-modal fusion feature set and operating environment parameters. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model. It acquires historical time-series stress field feature samples and extracts the reduced-order basis function matrix from the historical time-series stress field feature samples. It uses the reduced-order basis function matrix to perform dimensionality reduction mapping on the preset full-order system stiffness matrix and updates and generates the reduced-order feature stiffness matrix of the corresponding multi-parameter dynamic coupling model. Based on the reduced-order feature stiffness matrix, it performs multi-field coupling iterative calculations of the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model in the spatiotemporal dimension, and outputs coupling state feature data containing spatial coordinates of stress concentration and a comprehensive stress distribution matrix. The safety early warning module is used to map the spatial coordinates of stress concentration and the comprehensive stress distribution matrix to the three-dimensional digital twin node model to generate an integrity evaluation map. At the same time, it calculates the safety margin quantification index based on the comprehensive stress distribution matrix and the material aging degradation function.

[0010] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the aforementioned digital analysis method for improving the integrity of the short section wellhead equipment.

[0011] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the aforementioned digital analysis method for improving the integrity of raised section wellhead equipment.

[0012] This invention acquires multimodal sensing data from raised-section wellhead equipment and generates a multimodal fusion feature set based on this data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data. By complementing multimodal features, the limitations of single-modal detection are eliminated, improving the comprehensiveness of data acquisition. Furthermore, based on the multimodal fusion feature set and operating environment parameters, a multi-parameter dynamic coupling model is constructed. This model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model, enabling multi-factor joint analysis and improving the accuracy of wellhead equipment integrity analysis under complex operating conditions. Additionally, historical time-series stress field feature samples are acquired, and reduced-order basis function matrices are extracted from these samples. These reduced-order basis function matrices are then used to reduce the dimensionality of the preset full-order system stiffness matrix, updating and generating corresponding multi-parameter dynamic coupling features. The reduced-order characteristic stiffness matrix of the parameter dynamic coupling model can reduce the computational scale and improve the real-time performance of wellhead equipment integrity analysis under complex operating conditions. Furthermore, based on the reduced-order characteristic stiffness matrix, multi-field coupled iterative calculations of the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model in the spatiotemporal dimension are performed, outputting coupled state characteristic data including stress concentration spatial coordinates and a comprehensive stress distribution matrix. This enables rapid cyclic calculation of multi-physics coupling states over time, improving the timeliness of dynamic response. Finally, the stress concentration spatial coordinates and the comprehensive stress distribution matrix are jointly mapped onto a three-dimensional digital twin node model to generate an integrity evaluation map. Simultaneously, safety margin quantification indicators are calculated based on the comprehensive stress distribution matrix and material aging degradation function, improving the accuracy and efficiency of wellhead equipment integrity analysis under complex operating conditions and enabling full lifecycle early warning for wellhead equipment under complex operating conditions. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating a digital analysis method for improving the integrity of raised short-section wellhead equipment according to an embodiment of the present invention. Figure 2 This is a functional block diagram of a digital analysis device for improving the integrity of short-section wellhead equipment according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the electronic device used to implement the digital analysis method for improving the integrity of short-section wellhead equipment, as provided in an embodiment of the present invention.

[0014] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0015] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0016] This application provides a digital analysis method for improving the integrity of short-section wellhead equipment. The executing entity of this digital analysis method for improving the integrity of short-section wellhead equipment includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the digital analysis method for improving the integrity of short-section wellhead equipment can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0017] Reference Figure 1 The diagram shown is a flowchart illustrating a digital analysis method for the integrity of raised-section wellhead equipment according to an embodiment of the present invention. In this embodiment, the digital analysis method for the integrity of raised-section wellhead equipment includes: S1. Acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data.

[0018] Understandably, ultrasonic testing data refers to signal data collected by utilizing the changes in acoustic reflection and transmission physical properties generated when ultrasonic waves propagate in the material medium of a target component, which characterize the internal physical structure state of the component. In this embodiment of the invention, ultrasonic testing data is used to extract structural wall thickness characteristics, wall thickness loss characteristics, and detect continuous physical parameters inside the material.

[0019] Understandably, eddy current detection data refers to signal data that characterizes the physical integrity of the shallow surface layer of a component by measuring the induced eddy current distortion signal excited by an alternating magnetic field on the surface and near the surface of a conductive material, based on the principle of electromagnetic induction. In this embodiment of the invention, the eddy current detection data is used to extract the geometric size characteristics of surface microcracks, the morphological characteristics of surface corrosion defects, and the conductivity distribution parameters near the surface.

[0020] It is understood that infrared thermal imaging data refers to signal data that characterizes the local or overall thermodynamic and stress state of a component by capturing the distribution of infrared radiation energy on the surface of a target component and mapping it into temperature gradient field differences. In this embodiment of the invention, the infrared thermal imaging data is used to extract the local thermal stress concentration characteristics and thermal stress field gradient distribution parameters generated by the structure under complex dynamic loads.

[0021] Specifically, multimodal sensing data of the raised short-section wellhead equipment is acquired, and a multimodal fusion feature set is generated based on the multimodal sensing data, including: Ultrasonic test data is characterized as structural wall thickness loss. Eddy current detection data is characterized as surface crack geometric size features; Infrared thermal imaging data is characterized as thermal stress field gradient features; The attention mechanism mapping network assigns feature weights to the structural wall thickness loss feature, surface crack geometry feature, and thermal stress field gradient feature, and merges them to generate a multimodal fusion feature set.

[0022] Understandably, attention mechanism mapping networks refer to deep learning network models built on self-attention or cross-attention algorithms, used to dynamically evaluate and assign weights to the correlation between multi-source input data.

[0023] Understandably, in this embodiment of the invention, the attention mechanism mapping network calculates the relative importance of structural wall thickness loss features, surface crack geometry features, and thermal stress field gradient features in characterizing the current damage state of the component through an internal feature correlation matrix, and generates adaptive weight coefficients for different input dimensions accordingly. The adaptive weight coefficients are used to weight each feature, thereby strengthening the key feature responses that are highly correlated with the current defect state and suppressing redundant modal background noise data. Finally, the weighted single-modal features are aggregated in the feature space to output the multimodal fusion feature set that integrates the component's internal structure, shallow physical morphology, and thermodynamic stress state information.

[0024] For example, multimodal sensing data of the raised short section wellhead equipment is acquired, and a multimodal fusion feature set is generated based on the multimodal sensing data. This can be achieved using the following implementation steps: The multimodal data fusion step is implemented using the following formula: ; Ultrasonic testing modal data is used to detect defects such as cracks and delamination inside materials.

[0025] Eddy current testing modal data is sensitive to defects in conductive materials such as surface and near-surface cracks and corrosion.

[0026] Infrared thermal imaging modal data reflects the internal structure or damage of materials through temperature field differences.

[0027] Attention mechanism: It can automatically learn and assign weights to highlight the most critical information for defect detection and suppress noise.

[0028] The multimodal fusion feature set integrates complementary information from three detection methods, making it more robust and accurate than single-modal detection.

[0029] S2. Based on the multimodal fusion feature set and operating environment parameters, a multi-parameter dynamic coupling model is constructed. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model.

[0030] Understandably, operating environment parameters refer to the physical and chemical media conditions of the target component under actual service conditions. For example, the operating environment parameters mainly include the chemical composition concentration of the environmental medium, acidity and alkalinity parameters, partial pressure parameters of specific corrosive gases, and thermodynamic temperature parameters, which are used to objectively characterize the input conditions for the external service environment to cause corrosion and physicochemical effects on the component's material.

[0031] Understandably, the corrosion rate sub-model refers to a mathematical function model that characterizes the evolution of bulk material loss under specific chemical media and thermodynamic boundary conditions. In this embodiment of the invention, the corrosion rate sub-model uses the structural wall thickness characteristics in the multimodal fusion feature set as the initial benchmark, combines the chemical medium component concentration term and thermodynamic temperature parameter in the operating environment parameters to construct an instantaneous corrosion rate function, and outputs the cumulative wall thickness loss characteristic characterizing the degradation state of the component's physical material through integration in the time dimension. This characteristic is then used as the dynamic geometric boundary input for subsequent stress calculations.

[0032] Understandably, the multi-directional stress sub-model refers to a three-dimensional tensor distribution model that characterizes the internal mechanical response state of a component under the combined action of complex mechanical loads and fluid pressure. In this embodiment of the invention, the multi-directional stress sub-model constructs an axial stress characteristic equation by extracting the dynamic loads generated by the column gravity and external mechanical vibration, constructs a circumferential stress characteristic equation based on the internal fluid pressure load and the cumulative wall thickness loss characteristics transmitted by the corrosion rate sub-model, constructs a radial stress characteristic equation by combining geometric structural parameters, and then combines the stress characteristic equations in the three directions into a tensor simulcast to form a comprehensive stress distribution function that characterizes the full-time-domain loading state of the component.

[0033] Understandably, the defect evolution sub-model refers to a geometrical expansion mathematical model that characterizes the development of microscopic mechanical damage inside or on the surface of a component into macroscopic failure under the combined action of alternating loads and environmental media. In this embodiment of the invention, the defect evolution sub-model uses the surface crack geometric size characteristics in the multimodal fusion feature set as the initial defect parameter, extracts the stress intensity factor fluctuation range parameter based on the stress distribution characteristics output by the multi-directional stress sub-model, and couples it with the intrinsic yield strength parameter of the material and the additional stress term induced by the environmental media to establish a differential equation for crack propagation rate to describe the dynamic changes in damage geometry.

[0034] Specifically, the construction of the corrosion rate sub-model includes: Extract the chemical medium component concentration and thermodynamic temperature parameters from the operating environment parameters; The instantaneous corrosion rate function is constructed by inputting the chemical medium composition concentration term and the thermodynamic temperature parameter into the Arrhenius fundamental equation. The instantaneous corrosion rate function is piecewise linearly integrated over time, and a corrosion acceleration correction factor for the bushing shielded area is introduced to map the cumulative wall thickness loss characteristics and pass them to the multi-directional stress sub-model.

[0035] Understandably, the chemical medium concentration term refers to a physical parameter characterizing the content of key chemical substances in the fluid environment that participate in or promote the electrochemical corrosion reaction of materials. For example, in the embodiments of the present invention, the chemical medium concentration term includes the partial pressure characteristic variable of dissolved corrosive gases (such as the partial pressure of carbon dioxide) and the concentration characteristic variable of corrosive anions (such as the chloride ion concentration term).

[0036] Understandably, thermodynamic temperature parameter refers to the fundamental physical quantity of the macroscopic thermodynamic state of the operating environment of the target component, and is a key variable of the degree of activity of the thermal motion of microscopic particles in the reaction system.

[0037] Understandably, the Arrhenius fundamental equation refers to the basic kinetic equation in physical chemistry theory used to describe the relationship between the chemical reaction rate and the absolute temperature of the system. For example, in the embodiments of this invention, the Arrhenius fundamental equation combines thermodynamic temperature parameters with the ideal gas constant to construct a temperature effect term, and couples and multiplies it with the chemical medium component concentration term to establish a mathematical expression that objectively reflects the evolution law of the material micro-corrosion process caused by the dynamic changes of external environment thermodynamic and chemical conditions, thereby generating an instantaneous corrosion rate function.

[0038] For example, the corrosion rate sub-model is constructed using the following implementation steps: Step 1, Basic corrosion rate formula: ;in, ; ; Arrhenius fundamental equation; R: gas constant; T: thermodynamic temperature; The effect of carbon dioxide partial pressure; The effect of chloride ion concentration; .

[0039] Step 2, Calculation of dynamic corrosion amount: ; The cumulative corrosion amount at time t; : Time accumulation (the sum of the process from the start of corrosion (τ=0) to the current moment (τ=t); Instantaneous corrosion rate.

[0040] Specifically, the construction of the multi-directional stress sub-model includes: Obtain the axial weight load of the tubular column and the additional dynamic load during operation, and superimpose them to construct the characteristic equation of axial stress. Obtain the fluid pressure load inside the structure, and construct the circumferential stress characteristic equation by combining the cumulative wall thickness loss characteristics output by the corrosion rate sub-model. A radial stress characteristic equation is constructed by combining the internal fluid pressure load of the structure with the internal and external radial geometric features of the structure. By combining the characteristic equations of axial stress, circumferential stress, and radial stress using tensors, a comprehensive stress distribution function in the entire time domain is constructed.

[0041] Understandably, axial tubing weight load refers to the static tensile or compressive force physical quantity generated by the lower tubing structure (such as tubing string, casing string, etc.) connected to the end of the target component due to its own weight along the longitudinal axis of the target component.

[0042] Understandably, operational additional dynamic loads refer to the additional mechanical parameters that fluctuate at high frequency over time, induced by dynamic conditions such as transient impacts of internal fluid media, alternating vibrations of mechanical equipment, or unsteady motions of tubular systems during actual service or production operations of the target component.

[0043] Understandably, the internal and external radial geometric features of a structure refer to the dimensional parameters that characterize the radial distribution of the physical boundaries of the inner cavity and the outer surface of the target component body on a cross section perpendicular to its longitudinal axis. In the embodiments of the present invention, the internal and external radial geometric features of the structure specifically cover the internal cross-sectional radius variables and the external cross-sectional radius variables of the component, which serve as the basic geometric boundary data for defining the spatial scale of the stress application area and the pipe wall thickness. They are coupled with the internal fluid pressure load of the structure to derive and construct the radial stress characteristic equation.

[0044] Understandably, the internal fluid pressure load of a structure refers to the normal expansion force parameter exerted on the inner wall surface of a component by a fluid medium (such as a high-pressure oil-gas-water mixture) that flows or is closed within the cavity of the target component.

[0045] For example, the construction of a multi-directional stress sub-model can be achieved by the following implementation steps: Step 1, Axial stress (including dynamic load): ; Loads related to the tubing string (such as tubing and casing) (e.g., the weight of the tubing string itself). Dynamic loads on the tubing (such as additional forces caused by fluid impact and vibration); Internal pressure; The inner radius of the structure; Outer radius; Initial wall thickness; Wall thickness loss; ; Circumferential stress (including corrosion defects): ; ; The circumferential stress of a pipeline is a key stress indicator for judging material fatigue and failure. Internal pressure, usually expressed in MPa or psi; The inner radius of the pipe; Remaining wall thickness. Radial stress: ; Internal pressure; The inner radius of the pipe; : Outer radius of the pipe.

[0046] Step 2, Calculation of maximum combined stress: ; Axial stress; Circumferential / circumferential stress; Radial stress; Superimposed infrared thermal stress field; The elastic modulus of a material; ΔT: Coefficient of linear expansion of the material; ΔT: Temperature change (ΔT=T) final -T initial ).

[0047] Specifically, the construction of the defect evolution sub-model includes: The surface crack geometry features extracted from multimodal sensing data are set as initial defect parameters; The stress intensity factor fluctuation range parameter is extracted based on the stress distribution characteristics output by the multi-directional stress sub-model. By coupling the stress intensity factor fluctuation range parameter, the intrinsic yield strength parameter of the material, and the additional stress term of the corrosive environment, a differential equation for crack propagation rate is established. The critical defect size reference value of the structure is calculated by integrating the initial defect parameters using the calculus equation of crack propagation rate.

[0048] Understandably, the stress intensity factor fluctuation range parameter refers to a mechanical characteristic parameter in fracture mechanics used to characterize the amplitude of the alternating strength of the stress field at the tip of a microcrack in a component.

[0049] It is understandable that the intrinsic yield strength parameter of a material refers to the inherent critical stress physical quantity that the base metal material of the target component can withstand before macroscopic plastic deformation occurs.

[0050] Understandably, the additional stress term in a corrosive environment refers to the extra microscopic driving stress induced in the local area at the crack tip when a component is in a specific corrosive or brittle fluid medium, due to the penetration of the chemical medium into the material lattice or the occurrence of interfacial physicochemical reactions.

[0051] Understandably, the differential equation for crack propagation rate is a mathematical model constructed based on the principles of fracture fatigue dynamics, used to describe the dynamic growth of the geometric length of a material crack as a function of the number of alternating load cycles or continuous time steps.

[0052] For example, the construction of the defect evolution sub-model can be achieved by the following implementation steps: Step 1, Crack propagation rate: C and m: Material constants, experimentally determined, related to the fatigue properties of the material itself. If the structure has bushings for shielding, increasing the C value by 30% compensates for the abnormally high crack propagation rate caused by geometric constraints, thus avoiding underestimation of lifespan. ΔK: Stress intensity factor range, ΔK = K max -K min , is the core mechanical parameter that drives crack propagation; Additional stress in a hydrogen sulfide environment; in a dry, hydrogen sulfide-free neutral / alkaline environment, the material does not exhibit hydrogen-induced embrittlement or accelerated stress corrosion, and crack propagation is dominated solely by mechanical fatigue; correction factor. Change to 1; Yield strength of the material Step 2, Remaining Life Prediction: ; Remaining life refers to the time or number of load cycles from the current state until structural failure.

[0053] Initial defect size, i.e., the length of the currently detected crack or defect.

[0054] Critical defect size: When a crack extends to this size, the structure will fracture or fail.

[0055] Crack propagation rate, which is the increment (da) of crack length in each load cycle (dN).

[0056] The change in stress or load, where the integral variable can be time, cycle number, or stress spectrum, depending on the engineering scenario.

[0057] S3. Obtain historical time-series stress field feature samples and extract the reduced-order basis function matrix from the historical time-series stress field feature samples. Use the reduced-order basis function matrix to perform dimensionality reduction mapping on the preset full-order system stiffness matrix, and update and generate the reduced-order characteristic stiffness matrix of the corresponding multi-parameter dynamic coupling model.

[0058] Understandably, historical time-series stress field characteristic samples refer to a set of discretized three-dimensional data that characterizes the continuous evolution of the internal mechanical distribution state of a target component over time under specific service cycles or typical working conditions in the past.

[0059] Understandably, a reduced-order basis function matrix refers to a low-dimensional projection transformation operator used to characterize the dominant characteristic components of a high-dimensional dynamical system in a mathematical vector space. It contains a set of mutually independent and representative orthogonal or non-orthogonal basis vectors, which are used to construct a reduced-order subspace that can approximately restore the original high-dimensional mechanical response state with lower degrees of freedom, thus enabling the compression of the computational scale of the finite element model.

[0060] Understandably, the full-order system stiffness matrix refers to the coefficient matrix of the generalized stiffness equation, which is constructed based on the original finite element physical mesh nodes and is used to fully describe the constitutive physical relationship between all degrees of freedom of the target component mechanical system in the undimension-reduced state. The full-order system stiffness matrix contains the complete geometric constraints and material constitutive information of the component in the original high-dimensional space. As the original mechanical model, which is computationally expensive to solve directly, it is also the benchmark object to be processed when performing spatial projection and dimension reduction mapping operations.

[0061] It is understandable that the reduced-order characteristic stiffness matrix refers to the low-dimensional equivalent generalized stiffness matrix of the system that is reconstructed by spatial projection and dimensional compression operations on the stiffness matrix of the full-order system through the reduced-order basis function matrix.

[0062] Specifically, the pre-defined full-order system stiffness matrix is ​​dimensionally reduced using the reduced-order basis function matrix, and the corresponding reduced-order characteristic stiffness matrix of the multi-parameter dynamic coupling model is updated and generated, including: A reduced-order basis function matrix is ​​constructed by extracting historical temporal stress field feature samples using a convolutional neural network model. The full-order system stiffness matrix is ​​multiplied by the reduced-order basis function matrix to generate a reduced-order characteristic stiffness matrix. Based on the reduced-order characteristic stiffness matrix, multi-field time-series coupling solution is performed on the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model within a preset discrete time step.

[0063] Understandably, a Convolutional Neural Network (CNN) model refers to a deep learning network that possesses the characteristics of local receptive field weight sharing and spatial translation invariance.

[0064] For example, obtaining historical time-series stress field feature samples and extracting the reduced-order basis function matrix from the historical time-series stress field feature samples, and using the reduced-order basis function matrix to perform dimensionality reduction mapping on the preset full-order system stiffness matrix, updating and generating the reduced-order characteristic stiffness matrix of the corresponding multi-parameter dynamic coupling model, can be achieved using the following implementation steps: Finite element reduced-order model: ; The full-order finite element stiffness matrix (or generalized stiffness / system matrix) typically has very large dimensions (N×N, where N is the number of degrees of freedom), making direct solution very costly.

[0065] : Reduced-order basis function matrix, obtained from historical time-series stress field feature samples by a convolutional neural network (CNN). We learn from it that the dimension is N×r ( (where r is the reduced degree of freedom).

[0066] : The reduced stiffness matrix, with dimensions r×r.

[0067] S4. Based on the reduced-order characteristic stiffness matrix, perform multi-field coupled iterative calculations of the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model in the spatiotemporal dimension, and output coupled state characteristic data including the spatial coordinates of stress concentration and the comprehensive stress distribution matrix.

[0068] S5. Map the spatial coordinates of stress concentration and the comprehensive stress distribution matrix together into the three-dimensional digital twin node model to generate an integrity evaluation map. At the same time, calculate the safety margin quantification index based on the comprehensive stress distribution matrix and the material aging degradation function.

[0069] Understandably, a three-dimensional digital twin node model refers to a discretized virtual mapping model that represents the three-dimensional physical entity of a target component and its internal structural geometric topology. It consists of a discrete grid node network containing absolute and relative spatial coordinate information and can be used as a multi-dimensional physical field for accurate three-dimensional spatial matching, data fusion mapping, and visualization rendering.

[0070] Understandably, the integrity evaluation map refers to the set of multi-dimensional characterization data of the structural health status and its spatial visualization diagram constructed from the current dynamic service status of the target component and the results of multi-physics field coupling calculations.

[0071] Understandably, the material aging degradation function is a mathematical expression model used to describe the decay and degradation evolution of the core mechanical intrinsic properties (such as material yield strength, fatigue limit, etc.) of the matrix metal material of the target component as it accumulates over long-term service time. In the embodiments of this invention, the material aging degradation function uses environmental accumulation quantities such as service time as independent variables to quantify, correct, and dynamically reduce the critical load-bearing capacity threshold of the material, serving as the constitutive physical benchmark input for calculating the current and future true resistance level of the structure.

[0072] Understandably, the safety margin quantification index refers to the evaluation characteristic parameter used to quantify the remaining safe distance between the target component's stress response state and the physical failure boundary or ultimate bearing state under current or predicted dynamic working conditions. In the embodiments of the present invention, the safety margin quantification index is calculated based on the algebraic or calculus function relationship between the key stress extrema extracted from the comprehensive stress distribution matrix and the dynamic resistance threshold output by the material aging degradation function. It serves as a numerical rigid judgment basis for determining the structural integrity risk level of the component and whether a life cycle warning is triggered.

[0073] This invention acquires multimodal sensing data from raised-section wellhead equipment and generates a multimodal fusion feature set based on this data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data. By complementing multimodal features, the limitations of single-modal detection are eliminated, improving the comprehensiveness of data acquisition. Furthermore, based on the multimodal fusion feature set and operating environment parameters, a multi-parameter dynamic coupling model is constructed. This model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model, enabling multi-factor joint analysis and improving the accuracy of wellhead equipment integrity analysis under complex operating conditions. Additionally, historical time-series stress field feature samples are acquired, and reduced-order basis function matrices are extracted from these samples. These reduced-order basis function matrices are then used to reduce the dimensionality of the preset full-order system stiffness matrix, updating and generating corresponding multi-parameter dynamic coupling features. The reduced-order characteristic stiffness matrix of the parameter dynamic coupling model can reduce the computational scale and improve the real-time performance of wellhead equipment integrity analysis under complex operating conditions. Furthermore, based on the reduced-order characteristic stiffness matrix, multi-field coupled iterative calculations of the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model in the spatiotemporal dimension are performed, outputting coupled state characteristic data including stress concentration spatial coordinates and a comprehensive stress distribution matrix. This enables rapid cyclic calculation of multi-physics coupling states over time, improving the timeliness of dynamic response. Finally, the stress concentration spatial coordinates and the comprehensive stress distribution matrix are jointly mapped onto a three-dimensional digital twin node model to generate an integrity evaluation map. Simultaneously, safety margin quantification indicators are calculated based on the comprehensive stress distribution matrix and material aging degradation function, improving the accuracy and efficiency of wellhead equipment integrity analysis under complex operating conditions and enabling full lifecycle early warning for wellhead equipment under complex operating conditions.

[0074] like Figure 2 The diagram shown is a functional block diagram of a digital analysis device for improving the integrity of short-section wellhead equipment according to an embodiment of the present invention.

[0075] The digital analysis device 100 for improving the integrity of short-section wellhead equipment described in this invention can be installed in an electronic device. Depending on the functions implemented, the digital analysis device 100 for improving the integrity of short-section wellhead equipment may include a multimodal sensor data fusion module 101, a dynamic coupling order reduction calculation module 102, and a safety early warning module 103.

[0076] The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0077] In this embodiment, the functions of each module / unit are as follows: The multimodal sensing data fusion module 101 is used to acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data.

[0078] The dynamic coupling reduction calculation module 102 is used to construct a multi-parameter dynamic coupling model based on a multi-modal fusion feature set and operating environment parameters. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model. It acquires historical time-series stress field feature samples and extracts the reduced-order basis function matrix from the historical time-series stress field feature samples. It uses the reduced-order basis function matrix to perform dimensionality reduction mapping on the preset full-order system stiffness matrix and updates and generates the reduced-order feature stiffness matrix of the corresponding multi-parameter dynamic coupling model. Based on the reduced-order feature stiffness matrix, it performs multi-field coupling iterative calculations of the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model in the spatiotemporal dimension and outputs coupling state feature data containing spatial coordinates of stress concentration and a comprehensive stress distribution matrix.

[0079] The safety early warning module 103 is used to map the stress concentration spatial coordinates and the comprehensive stress distribution matrix to the three-dimensional digital twin node model to generate an integrity evaluation map, and at the same time calculate the safety margin quantification index based on the comprehensive stress distribution matrix and the material aging degradation function.

[0080] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a digital analysis method to improve the integrity of short-section wellhead equipment, according to an embodiment of the present invention.

[0081] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a digital analysis method program for improving the integrity of short-section wellhead equipment.

[0082] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a digital analysis method program to improve the integrity of short-section wellhead equipment), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0083] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of a digital analysis method program for improving the integrity of short-section wellhead equipment, but also to temporarily store data that has been output or will be output.

[0084] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0085] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0086] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0087] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0088] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0089] The memory 11 in the electronic device stores a digital analysis method program for improving the integrity of short-section wellhead equipment. This program is a combination of multiple instructions, which, when run in the processor 10, can achieve the following: Acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data. Based on the multimodal fusion feature set and operating environment parameters, a multi-parameter dynamic coupling model is constructed. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model. Obtain historical time-series stress field feature samples and extract the reduced-order basis function matrix from the historical time-series stress field feature samples. Use the reduced-order basis function matrix to perform dimension reduction mapping on the preset full-order system stiffness matrix, and update and generate the reduced-order feature stiffness matrix of the corresponding multi-parameter dynamic coupling model. Based on the reduced-order characteristic stiffness matrix, the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model are subjected to multi-field coupled iterative calculation in the spatiotemporal dimension, and the output is coupled state characteristic data containing the spatial coordinates of stress concentration and the comprehensive stress distribution matrix. The spatial coordinates of stress concentration and the comprehensive stress distribution matrix are jointly mapped onto the three-dimensional digital twin node model to generate an integrity evaluation map. At the same time, the safety margin quantification index is calculated based on the comprehensive stress distribution matrix and the material aging degradation function.

[0090] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0091] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0092] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data. Based on the multimodal fusion feature set and operating environment parameters, a multi-parameter dynamic coupling model is constructed. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model. Obtain historical time-series stress field feature samples and extract the reduced-order basis function matrix from the historical time-series stress field feature samples. Use the reduced-order basis function matrix to perform dimension reduction mapping on the preset full-order system stiffness matrix, and update and generate the reduced-order feature stiffness matrix of the corresponding multi-parameter dynamic coupling model. Based on the reduced-order characteristic stiffness matrix, the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model are subjected to multi-field coupled iterative calculation in the spatiotemporal dimension, and the output is coupled state characteristic data containing the spatial coordinates of stress concentration and the comprehensive stress distribution matrix. The spatial coordinates of stress concentration and the comprehensive stress distribution matrix are jointly mapped onto the three-dimensional digital twin node model to generate an integrity evaluation map. At the same time, the safety margin quantification index is calculated based on the comprehensive stress distribution matrix and the material aging degradation function.

[0093] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0094] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0095] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0096] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0097] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0098] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0099] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0100] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0101] Finally, 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 it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A digital analysis method for improving the integrity of short-section wellhead equipment, characterized in that, The method includes: Acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data, and infrared thermal imaging data. Based on the multimodal fusion feature set and operating environment parameters, a multi-parameter dynamic coupling model is constructed. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model. Obtain historical time-series stress field feature samples and extract the reduced-order basis function matrix from the historical time-series stress field feature samples. Use the reduced-order basis function matrix to perform dimension reduction mapping on the preset full-order system stiffness matrix, and update and generate the reduced-order feature stiffness matrix of the corresponding multi-parameter dynamic coupling model. Based on the reduced-order characteristic stiffness matrix, the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model are subjected to multi-field coupled iterative calculation in the spatiotemporal dimension, and the output is coupled state characteristic data containing the spatial coordinates of stress concentration and the comprehensive stress distribution matrix. The spatial coordinates of stress concentration and the comprehensive stress distribution matrix are jointly mapped onto the three-dimensional digital twin node model to generate an integrity evaluation map. At the same time, the safety margin quantification index is calculated based on the comprehensive stress distribution matrix and the material aging degradation function.

2. The digital analysis method for improving the integrity of short-section wellhead equipment as described in claim 1, characterized in that, The process of acquiring multimodal sensing data from the lift-up sub wellhead equipment and generating a multimodal fusion feature set based on the multimodal sensing data includes: Ultrasonic test data is characterized as structural wall thickness loss. Eddy current detection data is characterized as surface crack geometric size features; Infrared thermal imaging data is characterized as thermal stress field gradient features; The attention mechanism mapping network assigns feature weights to the structural wall thickness loss feature, surface crack geometry feature, and thermal stress field gradient feature, and merges them to generate a multimodal fusion feature set.

3. The digital analysis method for improving the integrity of short-section wellhead equipment as described in claim 1, characterized in that, The construction of the corrosion rate sub-model includes: Extract the chemical medium component concentration and thermodynamic temperature parameters from the operating environment parameters; The instantaneous corrosion rate function is constructed by inputting the chemical medium composition concentration term and the thermodynamic temperature parameter into the Arrhenius fundamental equation. The instantaneous corrosion rate function is piecewise linearly integrated over time, and a corrosion acceleration correction factor for the bushing shielded area is introduced to map the cumulative wall thickness loss characteristics and pass them to the multi-directional stress sub-model.

4. The digital analysis method for improving the integrity of short-section wellhead equipment as described in claim 1, characterized in that, The construction of the multi-directional stress sub-model includes: Obtain the axial weight load of the tubular column and the additional dynamic load during operation, and superimpose them to construct the characteristic equation of axial stress. Obtain the fluid pressure load inside the structure, and construct the circumferential stress characteristic equation by combining the cumulative wall thickness loss characteristics output by the corrosion rate sub-model. A radial stress characteristic equation is constructed by combining the internal fluid pressure load of the structure with the internal and external radial geometric features of the structure. By combining the characteristic equations of axial stress, circumferential stress, and radial stress using tensors, a comprehensive stress distribution function in the entire time domain is constructed.

5. The digital analysis method for improving the integrity of short-section wellhead equipment as described in claim 1, characterized in that, The construction of the defect evolution sub-model includes: The surface crack geometry features extracted from multimodal sensing data are set as initial defect parameters; The stress intensity factor fluctuation range parameter is extracted based on the stress distribution characteristics output by the multi-directional stress sub-model. By coupling the stress intensity factor fluctuation range parameter, the intrinsic yield strength parameter of the material, and the additional stress term of the corrosive environment, a differential equation for crack propagation rate is established. The critical defect size reference value of the structure is calculated by integrating the initial defect parameters using the calculus equation of crack propagation rate.

6. The digital analysis method for improving the integrity of short-section wellhead equipment as described in claim 1, characterized in that, The step of using a reduced-order basis function matrix to perform dimensionality reduction mapping on the preset full-order system stiffness matrix and updating it to generate the reduced-order characteristic stiffness matrix of the corresponding multi-parameter dynamic coupling model includes: A reduced-order basis function matrix is ​​constructed by extracting historical temporal stress field feature samples using a convolutional neural network model. The full-order system stiffness matrix is ​​multiplied by the reduced-order basis function matrix to generate a reduced-order characteristic stiffness matrix. Based on the reduced-order characteristic stiffness matrix, multi-field time-series coupling solution is performed on the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model within a preset discrete time step.

7. The digital analysis method for improving the integrity of short-section wellhead equipment as described in claim 1, characterized in that, The process involves mapping the spatial coordinates of stress concentration and the comprehensive stress distribution matrix onto a three-dimensional digital twin node model to generate an integrity evaluation map. Simultaneously, based on the comprehensive stress distribution matrix and the material aging degradation function, a safety margin quantification index is calculated, including: Extract the initial yield strength base of the structure and the material service attenuation time factor, construct an exponential material aging degradation function, and calculate the current time-series material attenuation yield limit; The ratio of the maximum comprehensive stress threshold in the comprehensive stress distribution matrix to the current time-series material attenuation yield limit is calculated to output a safety margin quantification index. The spatial coordinates of stress concentration and the maximum comprehensive stress threshold are jointly mapped onto the three-dimensional digital twin node model to generate an integrity evaluation map.

8. A digital analysis device for improving the integrity of short-section wellhead equipment, characterized in that, The device can implement the digital analysis method for the integrity of raised short section wellhead equipment as described in any one of claims 1 to 7, and the device includes: The multimodal sensing data fusion module is used to acquire multimodal sensing data of the raised short section wellhead equipment and generate a multimodal fusion feature set based on the multimodal sensing data. The multimodal sensing data includes ultrasonic detection data, eddy current detection data and infrared thermal imaging data. The dynamic coupling reduction calculation module is used to construct a multi-parameter dynamic coupling model based on a multi-modal fusion feature set and operating environment parameters. The multi-parameter dynamic coupling model includes a corrosion rate sub-model, a multi-directional stress sub-model, and a defect evolution sub-model. It acquires historical time-series stress field feature samples and extracts the reduced-order basis function matrix from the historical time-series stress field feature samples. It uses the reduced-order basis function matrix to perform dimensionality reduction mapping on the preset full-order system stiffness matrix and updates and generates the reduced-order feature stiffness matrix of the corresponding multi-parameter dynamic coupling model. Based on the reduced-order feature stiffness matrix, it performs multi-field coupling iterative calculations of the corrosion rate sub-model, multi-directional stress sub-model, and defect evolution sub-model in the spatiotemporal dimension, and outputs coupling state feature data containing spatial coordinates of stress concentration and a comprehensive stress distribution matrix. The safety early warning module is used to map the spatial coordinates of stress concentration and the comprehensive stress distribution matrix to the three-dimensional digital twin node model to generate an integrity evaluation map. At the same time, it calculates the safety margin quantification index based on the comprehensive stress distribution matrix and the material aging degradation function.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the digital analysis method for improving the integrity of the sub-section wellhead equipment as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the digital analysis method for improving the integrity of the raised section wellhead equipment as described in any one of claims 1 to 7.

Images