A 3D-based oil pipeline life prediction system

Abstract

This invention discloses a 3D-based oil pipeline life prediction system, relating to the field of pipeline life detection technology. It includes: a contour reconstruction module S11, used to acquire three-dimensional point cloud image data of the oil pipeline shell surface under actual operating conditions, and perform surface contour reconstruction processing based on the three-dimensional point cloud image data to extract spatial geometric structure data containing local deformation defect areas; a force-thermal coupling analysis module S12, used to construct a finite element analysis mesh based on the spatial geometric structure data, and load operating condition data into the corresponding mesh nodes to generate a force-thermal coupling stress field, wherein the operating condition data includes periodic internal working pressure values, temperature field data along the pipeline, and axial disturbance stress tensor; and a feature extraction module S13, used to calculate the equivalent stress distribution values ​​of the defect area nodes based on the force-thermal coupling stress field. This invention achieves accurate quantification of fatigue damage evolution in defect areas.

Description

Technical Field

[0001] This invention relates to the field of pipeline life detection technology, and specifically to a 3D-based oil pipeline life prediction system. Background Technology

[0002] Oil pipelines operate under complex conditions of long-term high pressure, high temperature and alternating loads. Their outer shell structure is prone to local deformation defects. Stress concentration in defect areas will accelerate the cumulative evolution of material fatigue damage, directly affecting the overall load-bearing capacity and service life of the pipeline. Therefore, accurate identification and life prediction of defect areas have become key links to ensure the safe operation of pipelines.

[0003] Existing oil pipeline life prediction systems typically rely on non-destructive testing methods such as ultrasonic testing, magnetic particle testing, or eddy current testing to obtain defect size information, and combine them with empirical degradation models to estimate life. These systems have the advantages of being simple to implement and having low computational cost in terms of defect size acquisition and macroscopic life trend judgment, and can provide preliminary reference for pipeline maintenance.

[0004] However, such systems lack the reconstruction and quantitative description of the real spatial geometry of the defect area, making it difficult to accurately apply boundary constraints in finite element calculations. They also fail to fully consider the stress response characteristics under the coupling of multiple physics fields in actual operating conditions, resulting in deviations between the stress distribution simulation and damage evolution analysis results and the actual situation.

[0005] Based on this, three shortcomings can be identified in the existing system:

[0006] (1) The spatial contour of the defect area cannot be realistically reconstructed at the geometric level, causing the boundary condition setting of the finite element analysis to deviate from the actual situation;

[0007] (2) The multi-physics field coupled stress distribution state of the defect area under actual operating conditions lacks accurate characterization, resulting in insufficient identification accuracy of high stress nodes;

[0008] (3) The calculation of fatigue damage evolution does not incorporate the correlation between stress changes over time and spatial location, making it impossible to reliably estimate the lifespan of high-risk node clusters. Summary of the Invention

[0009] To address the aforementioned technical problems, this invention provides an oil pipeline life prediction system based on 3D technology.

[0010] A 3D-based oil pipeline life prediction system, the system comprising:

[0011] Contour Reconstruction Module S11: Used to acquire three-dimensional point cloud image data of the outer shell surface of an oil pipeline in actual operating environment, and perform surface contour reconstruction processing based on the three-dimensional point cloud image data to extract spatial geometric structure data containing local deformation defect areas.

[0012] Mechanical-thermal coupling analysis module S12: is used to construct a finite element analysis mesh based on spatial geometric structure data, and load the operating condition data into the corresponding mesh nodes to generate a mechanical-thermal coupling stress field. The operating condition data includes periodic internal working pressure values, temperature field data along the line, and axial disturbance stress tensor.

[0013] Feature extraction module S13: used to calculate the equivalent stress distribution value of nodes in the defect region based on the force-thermal coupling stress field, and extract fatigue damage evolution parameters of the stress concentration region by combining spatial geometric structure data to form damage evolution feature data;

[0014] Life assessment module S14: This module is used to calculate the minimum remaining bearing period value by inputting damage evolution characteristic data into the life degradation prediction model, and compare the minimum remaining bearing period value with a preset safety threshold to generate the life assessment result of the oil pipeline.

[0015] Furthermore, the steps for extracting spatial geometric structure data containing regions with localized deformation defects are as follows:

[0016] S111, perform structural segmentation operation using the spatial location data of all points in the three-dimensional point cloud image data of the oil pipeline outer shell surface to generate a set of spatial region segments;

[0017] S112, perform boundary mutation analysis based on the distribution density of boundary points of each segment in the spatial region segment set to generate a mutation boundary set;

[0018] S113, Perform spatial aggregation operation based on the mutation boundary set to generate a set of anomalous region fragments;

[0019] S114, Perform spatial structure construction processing based on the set of abnormal region fragments to generate spatial geometric structure data containing local deformation defect regions.

[0020] Furthermore, the steps for performing spatial structure construction processing based on the set of abnormal region fragments are as follows:

[0021] S114.1, Perform boundary closure construction operation through the spatial connection relationship between each boundary point in the abnormal region fragment set to generate a closed boundary structure set;

[0022] S114.2, Perform surface fitting processing based on the boundary contour points of each structure in the closed boundary structure set to generate a fitted contour set;

[0023] S114.3, Perform a geometric unit encapsulation operation based on the fitted contour set to generate spatial geometric structure data containing local deformation defect regions.

[0024] Furthermore, the steps for loading operational data into the corresponding mesh nodes to generate a force-thermal coupled stress field are as follows:

[0025] S121 generates a set of finite element analysis mesh nodes by performing node generation operations on the three-dimensional boundary structure in the spatial geometric structure data;

[0026] S122, based on the periodic internal working pressure value, performs the mesh inner surface node loading operation to generate an internal pressure loading node set;

[0027] S123, perform interpolation and expansion processing based on the temperature field data along the line to generate a set of thermal field loading nodes;

[0028] S124 performs boundary node mapping processing through axial perturbation stress tensor, and generates a force-thermal coupled stress field by combining the set of internal pressure loading nodes and the set of thermal field loading nodes.

[0029] Furthermore, the steps for performing boundary node mapping using the axial perturbation stress tensor are as follows:

[0030] S124.1, based on the coordinates of the boundary nodes in the finite element analysis mesh node set, perform node matching processing to generate a set of perturbation loading node indices;

[0031] S124.2, Tensor assignment operation is performed through the perturbation loading node index set to generate the boundary stress loading matrix;

[0032] S124.3 performs boundary stress input operation based on the boundary stress loading matrix to generate a force-thermal coupled stress field containing perturbation tensors.

[0033] Furthermore, the steps for extracting fatigue damage evolution parameters in stress concentration regions are as follows:

[0034] S131, Stress peak extraction is performed based on the equivalent stress distribution values ​​of each grid node in the mechanical-thermal coupled stress field to generate a set of high-stress nodes;

[0035] S132 generates a set of stress concentration regions by performing structural region matching processing between the set of high-stress nodes and spatial geometric data.

[0036] S133: Perform fatigue change calculations based on the historical stress changes of each node in the stress concentration region set, and generate a set of fatigue evolution segments.

[0037] Furthermore, the step of performing fatigue change calculation based on the historical stress changes of each node in the stress concentration region set is as follows:

[0038] S133.1, performs peak-valley identification operation by analyzing the equivalent stress sequence of each node in the stress concentration region set to generate a set of stress cycle change segments;

[0039] S133.2, Perform interval stress amplitude calculation processing based on the set of stress cycle change segments to generate a set of fatigue evolution segments;

[0040] S134 generates fatigue damage evolution parameters based on the cumulative execution time and weight superposition of the fatigue evolution fragment set.

[0041] Furthermore, the steps for inputting damage evolution characteristic data into the lifespan degradation prediction model to calculate the minimum remaining bearing capacity period are as follows:

[0042] S141, normalization processing is performed on the fatigue damage evolution parameters in the damage evolution feature data to generate a standardized damage feature matrix;

[0043] S142, based on the standardized damage feature matrix, call the life degradation prediction model to perform prediction inference operations and generate a set of remaining bearing cycles;

[0044] S143, Perform a minimum value filtering operation based on the minimum cycle value in the set of remaining load-bearing cycles to generate the minimum remaining load-bearing cycle value.

[0045] Furthermore, the logic for comparing the minimum remaining load-bearing period value with a preset safety threshold to generate the oil pipeline life assessment result is as follows:

[0046] S144, By performing a difference comparison between the minimum remaining load-bearing cycle value and the preset safety threshold, a remaining safety factor value is generated;

[0047] S145, perform risk level classification processing based on the remaining safety factor value to generate a lifespan level information set;

[0048] S146, based on the matching and processing of the defect area locations in the life grade information set and the spatial geometric structure data, the life assessment results of the oil pipeline are generated.

[0049] Furthermore, the steps for generating the lifetime rating information set are as follows:

[0050] S145.1, Perform interval mapping operation based on the remaining safety factor values ​​to assign each value to the preset risk level boundary interval and generate an initial risk level distribution set;

[0051] S145.2, perform boundary fusion processing on the transition areas between adjacent risk levels in the initial risk level distribution set to generate a continuous risk level partition set;

[0052] S145.3, Perform a level coding mapping operation based on the continuous level partition set to generate a lifespan level information set.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0054] This invention reconstructs spatial geometric structure data based on three-dimensional point cloud image data of the outer surface of an oil pipeline, thereby enabling precise positioning and structured representation of the spatial range containing local deformation defects, thus improving the integrity of the geometric morphological features of the defect area and enhancing the accuracy of spatial boundary constraints in the mechanical analysis process.

[0055] Furthermore, this invention also constructs a mechanical-thermal coupled stress field by generating a finite element analysis mesh based on spatial geometric structure data and loading periodic internal working pressure values, temperature field data along the line, and axial disturbance stress tensor. This enables multi-physics response characterization of the equivalent stress distribution values ​​of nodes in the defect region, thereby improving the accuracy of identifying high-stress nodes in the defect region and enhancing the reliability of fatigue damage evolution parameter extraction.

[0056] Furthermore, this invention generates a standardized damage feature matrix based on fatigue damage evolution parameters and combines it with a life degradation prediction model to generate a set of remaining bearing cycles, thereby achieving a quantitative assessment of the remaining bearing capacity of nodes in defective areas. This enhances the ability to determine life risk in high-risk node cluster areas, thus improving the integration level of spatial positioning and time estimation of oil pipeline life assessment results.

[0057] In summary, this invention constructs a three-dimensional spatial geometry of the defect region and couples it with operating conditions for force and thermal stress analysis, thereby achieving precise quantification of fatigue damage evolution in the defect region and improving the accuracy of oil pipeline life assessment. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0059] Figure 1 This is a block diagram of an oil pipeline life prediction system based on 3D technology provided in Embodiment 1 of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Please see Figure 1 As shown, this embodiment discloses a 3D-based oil pipeline life prediction system, the system comprising:

[0062] The contour reconstruction module S11 is used to acquire three-dimensional point cloud image data of the outer shell surface of an oil pipeline in actual operating environment, and to perform surface contour reconstruction processing based on the three-dimensional point cloud image data to extract spatial geometric structure data containing local deformation defect areas.

[0063] Specifically, the steps for extracting spatial geometric structure data containing regions with localized deformation defects are as follows:

[0064] S111, perform structural segmentation operation using the spatial location data of all points in the three-dimensional point cloud image data of the oil pipeline outer shell surface to generate a set of spatial region segments;

[0065] In one specific embodiment, the spatial location data of all points in the three-dimensional point cloud image data of the oil pipeline outer shell surface are arranged according to... The axis coordinates are arranged in ascending order and at fixed axial intervals. Using length as the unit, continuous points are divided into several spatial region segments, forming a set of spatial region segments;

[0066] It should be noted that: spatial location data refers to the location of each point. , , The three-dimensional coordinates of the direction are used to determine the precise location of a point in three-dimensional space.

[0067] S112, perform boundary mutation analysis based on the distribution density of boundary points of each segment in the spatial region segment set to generate a mutation boundary set;

[0068] In one specific embodiment, the distribution density of the boundary points in each spatial region segment is calculated by taking the boundary point as the center and a radius of . The number of neighborhood points within a spherical neighborhood is counted and divided by the neighborhood volume to obtain the result.

[0069] Represented as:

[0070]

[0071] In the formula, Boundary point Distribution density, For Centered on, with radius Count the number of neighborhood points within a spherical neighborhood. For radius The volume of a sphere;

[0072]

[0073] It should be noted that: The unit is The specific unit is set based on the diameter of the oil pipeline opening. For example, if... 125 , then it means There are approximately 125 boundary points within a unit volume (1 mm³) around a point;

[0074] S113, Perform spatial aggregation operation based on the mutation boundary set to generate a set of anomalous region fragments;

[0075] In one specific embodiment, the spatial location data of each boundary point in the mutation boundary set is input into a distance clustering algorithm. Boundary points whose Euclidean distance is less than a predetermined distance threshold are classified into the same abnormal region segment, and all abnormal region segments form an abnormal region segment set.

[0076] It should be noted that the distance threshold is set by multiplying the average point spacing of the spatial location data by three, and is used to limit the aggregation range of the mutation region.

[0077] S114, Perform spatial structure construction processing based on the set of abnormal region fragments to generate spatial geometric structure data containing local deformation defect regions;

[0078] Specifically, the steps for performing spatial structure construction processing based on the set of abnormal region fragments are as follows:

[0079] S114.1, Perform boundary closure construction operation through the spatial connection relationship between each boundary point in the abnormal region fragment set to generate a closed boundary structure set;

[0080] In one specific embodiment, the boundary points within each abnormal region segment in the abnormal region segment set are subjected to three-dimensional Delaunay triangulation based on their spatial location data, and the generated triangular mesh surfaces are combined into a set of closed boundary structures.

[0081] It should be noted that when the distance between any two boundary points is greater than the break threshold, no connecting edge is generated to prevent the formation of a pseudo-closed surface through cross-regional connections.

[0082] S114.2, Perform surface fitting processing based on the boundary contour points of each structure in the closed boundary structure set to generate a fitted contour set;

[0083] In one specific embodiment, the coordinates of the boundary contour points of each structure in the set of closed boundary structures are input into the B-spline fitting algorithm to generate a continuous surface and form a set of fitted contours.

[0084] It should be noted that the order of the B-spline surface is adaptively set according to the number of boundary contour points to ensure that the fitted surface is smooth and strictly covers the closed boundary range.

[0085] S114.3, Perform a geometric unit encapsulation operation based on the fitted contour set to generate spatial geometric structure data containing local deformation defect regions;

[0086] In one specific embodiment, the surfaces in the fitted contour set are converted into three-dimensional voxel structural units, and a complete set of three-dimensional geometric units is generated through voxel merging and meshing. All geometric units are then combined into spatial geometric structure data.

[0087] It should be noted that the side length of the voxelization unit is set according to the average point spacing of the 3D point cloud image data of the oil pipeline shell surface in order to maintain the accuracy of the geometric shape of the defect area.

[0088] The mechanical-thermal coupling analysis module S12 is used to construct a finite element analysis mesh based on spatial geometric structure data and load the operating condition data into the corresponding mesh nodes to generate a mechanical-thermal coupling stress field. The operating condition data includes periodic internal working pressure values, temperature field data along the line, and axial disturbance stress tensor.

[0089] Specifically, the steps for loading operational data into the corresponding mesh nodes to generate a force-thermal coupled stress field are as follows:

[0090] S121 generates a set of finite element analysis mesh nodes by performing node generation operations on the three-dimensional boundary structure in the spatial geometric structure data;

[0091] In one specific embodiment, all surfaces constituting the boundary in the spatial geometric structure data are divided into patches. Each patch is further divided according to a set mesh subdivision density h. Finite element nodes are established at the intersection of the subdivided patches and combined to form a set of finite element analysis mesh nodes.

[0092] It should be noted that the mesh density h is set based on the minimum feature size of the defect region in the spatial geometric data to ensure that the mesh nodes can completely cover the boundary of the defect region.

[0093] S122, based on the periodic internal working pressure value, performs the mesh inner surface node loading operation to generate an internal pressure loading node set;

[0094] In one specific embodiment, the coordinates of all nodes located on the inner wall of the pipe are extracted from the finite element analysis mesh node set. The stress area of ​​each node is calculated according to the node surface area distribution. The periodic internal working pressure value is multiplied by the stress area of ​​the node to obtain the node load. The loaded nodes are marked as the internal pressure loading node set.

[0095] It should be noted that the load-bearing area of ​​each node is equally distributed according to the area of ​​the surrounding elements to ensure uniform load distribution.

[0096] S123, perform interpolation and expansion processing based on the temperature field data along the line to generate a set of thermal field loading nodes;

[0097] In a specific embodiment, the temperature values ​​of each known temperature measurement location in the temperature field data along the line are matched with the spatial coordinates of all nodes in the finite element analysis mesh node set. The temperature values ​​of the unmeasured nodes are calculated based on the three-dimensional inverse distance weighted interpolation method to form a complete node temperature distribution. All nodes and their corresponding temperature values ​​are then combined into a thermal field loading node set.

[0098] It should be noted that the weighting coefficients of the inverse distance weighted interpolation are the inverse square of the distance between each temperature measurement point and the target node, in order to ensure that temperature measurement points that are closer to each other have a greater impact.

[0099] S124 performs boundary node mapping processing through axial perturbation stress tensor, and generates a force-thermal coupled stress field by combining the set of internal pressure loading nodes and the set of thermal field loading nodes.

[0100] Specifically, the steps for performing boundary node mapping using the axial perturbation stress tensor are as follows:

[0101] S124.1, based on the coordinates of the boundary nodes in the finite element analysis mesh node set, perform node matching processing to generate a set of perturbation loading node indices;

[0102] In a specific embodiment, the coordinates of all nodes located at the shell boundary in the finite element analysis mesh node set are compared one by one with the defined node coordinates in the axial perturbation stress tensor. Under the condition that the Euclidean distance is less than the set matching tolerance ε, the corresponding index is established, and the node numbers that meet the conditions are recorded as the perturbation loading node index set.

[0103] It should be noted that: matching tolerance The average node spacing is set to 0.5 times to control matching accuracy and avoid cross-region matching.

[0104] S124.2, Tensor assignment operation is performed through the perturbation loading node index set to generate the boundary stress loading matrix;

[0105] In a specific embodiment, the stress components of each defined node in the axial disturbance stress tensor are assigned to the corresponding finite element nodes in the disturbance loading node index set according to their indexes, and rows are constructed according to node numbers and columns are constructed according to stress component types to form a boundary stress loading matrix.

[0106] It should be noted that each row in the boundary stress loading matrix corresponds to a boundary node, and each column stores the boundary nodes sequentially. , , The disturbance stress components in the three directions;

[0107] S124.3, performs boundary stress input operation based on boundary stress loading matrix to generate a force-thermal coupled stress field containing perturbation tensor;

[0108] In a specific embodiment, the stress components of each node in the boundary stress loading matrix are input into the boundary load module of the finite element analysis solver, and the nodal loads and temperature loads of the internal pressure loading node set and the thermal field loading node set are input together. The mechanical-thermal coupled stress field containing the perturbation tensor is obtained through finite element solution.

[0109] It should be noted that during the solution process, a coupled thermo-structural solution type is used, where temperature loads and force loads are applied simultaneously to account for their mutual influence.

[0110] The feature extraction module S13 is used to calculate the equivalent stress distribution value of the nodes in the defect region based on the force-thermal coupling stress field, and to extract the fatigue damage evolution parameters of the stress concentration region by combining the spatial geometric structure data to form damage evolution feature data.

[0111] Specifically, the steps for extracting fatigue damage evolution parameters in stress concentration regions are as follows:

[0112] S131, Stress peak extraction is performed based on the equivalent stress distribution values ​​of each grid node in the mechanical-thermal coupled stress field to generate a set of high-stress nodes;

[0113] In a specific embodiment, the equivalent stress distribution values ​​of all finite element mesh nodes in the force-thermal coupled stress field are arranged in order of node number. The equivalent stress distribution value of each node is extracted, and the average value of the equivalent stress distribution values ​​of the adjacent nodes is calculated. Nodes whose own equivalent stress distribution value is more than twice the average value of their adjacent nodes are marked as peak nodes. A set of high-stress nodes is constructed based on all peak nodes.

[0114] It should be noted that adjacent nodes are determined by the topological relationship of finite element elements, and the neighboring nodes of each node are all nodes that share the same element with it.

[0115] S132 generates a set of stress concentration regions by performing structural region matching processing between the set of high-stress nodes and spatial geometric data.

[0116] In one specific embodiment, the three-dimensional spatial coordinates of each node in the high-stress node set are compared with the coordinates of the geometric unit nodes in the spatial geometric structure data to determine spatial overlap. High-stress nodes located in the same geometric unit are classified into the same stress concentration region, and all stress concentration regions are combined into a stress concentration region set.

[0117] It should be noted that: spatial overlap determination is achieved through the inclusion detection of three-dimensional points to mesh voxels, which is used to ensure that the spatial positions of high-stress nodes and defect areas correspond; three-dimensional points are nodes in the set of high-stress nodes; mesh voxels are the smallest cubic units used to represent volume elements in three-dimensional space. In this embodiment, it is a three-dimensional solid mesh unit formed after the spatial geometric structure data has been voxelized. Each mesh voxel occupies a cubic space area to represent the three-dimensional geometric boundary range of the defect area.

[0118] S133, perform fatigue change calculations based on the historical stress changes of each node in the stress concentration region set, and generate a set of fatigue evolution segments;

[0119] Specifically, the step of performing fatigue change calculation based on the historical stress changes of each node in the stress concentration region set is as follows:

[0120] S133.1, performs peak-valley identification operation by analyzing the equivalent stress sequence of each node in the stress concentration region set to generate a set of stress cycle change segments;

[0121] In a specific embodiment, the time-series sampling equivalent stress distribution values ​​of each node in the stress concentration region set are used to form a time series. The time series is traversed through three adjacent sampling points. When the value component of the middle point is greater than the value components of the two points before and after it is marked as a peak point, and when it is less than the value components of the two points before and after it is marked as a valley point, the segment between adjacent peak points and valley points is defined as a set of stress cycle change segments.

[0122] It should be noted that the time interval of the duration sampling is synchronized with the mechanical-thermal coupled stress field to ensure the continuity of the time series.

[0123] S133.2, Perform interval stress amplitude calculation processing based on the set of stress cycle change segments to generate a set of fatigue evolution segments;

[0124] In a specific embodiment, the difference between the numerical components of the equivalent stress distribution value at the peak point and the valley point of each segment in the stress cycle variation segment set is taken as the stress amplitude of that segment.

[0125] Represented as:

[0126]

[0127] In the formula, For the first The stress amplitude of each stress cycle segment. For the first The equivalent stress distribution value at the peak point in each stress cycle variation segment This represents the equivalent stress distribution value at the valley point in a stress cycle variation segment;

[0128] The segments with stress amplitudes greater than a set fatigue threshold are extracted as a set of fatigue evolution segments;

[0129] It should be noted that the fatigue threshold is determined based on the fatigue limit value in the material's SN curve and is used to screen for sections with fatigue risk.

[0130] S134, Based on the cumulative execution time and weight superposition processing of the fatigue evolution fragment set, fatigue damage evolution parameters are generated;

[0131] In a specific embodiment, the stress amplitude of each segment in the fatigue evolution segment set is multiplied by the corresponding duration to obtain the fatigue damage value of each segment. The fatigue damage values ​​of all segments are superimposed in the order of duration and normalized by combining the weighting coefficient of the stress amplitude to obtain the fatigue damage evolution parameters.

[0132] Represented as:

[0133]

[0134] In the formula, For fatigue damage evolution parameters, For the first The stress amplitude of each fatigue evolution segment. For the first The duration of each fatigue evolution segment. This represents the number of fatigue evolution segments contained in the fatigue evolution segment set.

[0135] It should be noted that: fatigue damage evolution parameters The unit is the square of the stress, specifically... , The square of the stress amplitude is used as a weight to enhance the contribution of high-amplitude segments to fatigue damage evolution parameters.

[0136] The life assessment module S14 is used to calculate the minimum remaining bearing period value by inputting damage evolution characteristic data into the life degradation prediction model, and compare the minimum remaining bearing period value with the preset safety threshold to generate the life assessment result of the oil pipeline.

[0137] Specifically, the steps for inputting damage evolution characteristic data into the lifespan degradation prediction model to calculate the minimum remaining bearing capacity period are as follows:

[0138] S141, normalization processing is performed on the fatigue damage evolution parameters in the damage evolution feature data to generate a standardized damage feature matrix;

[0139] The values ​​of all nodes in the fatigue damage evolution parameters are normalized by dividing them by their global maximum value to generate standardized damage values.

[0140] Represented as:

[0141]

[0142] In the formula, For the first Standardized damage values ​​for each node. For the first Fatigue damage evolution parameters of each node, This is the maximum value among all node fatigue damage evolution parameters;

[0143] The standardized damage values ​​are arranged by node number to form a standardized damage feature matrix;

[0144] It should be noted that the damage values ​​of all nodes after standardization are limited to the range of [0,1].

[0145] S142, based on the standardized damage feature matrix, call the life degradation prediction model to perform prediction inference operations and generate a set of remaining bearing cycles;

[0146] In one specific embodiment, the standardized damage feature matrix is ​​input into the life degradation prediction model row by row, and the corresponding remaining bearing period value is output for each node. The predicted remaining bearing period values ​​are then combined into a set of remaining bearing periods according to the node number.

[0147] It should be noted that the lifespan degradation prediction model is a pre-trained deep regression network used to learn the nonlinear mapping relationship between the standardized damage feature matrix and the remaining bearing period.

[0148] S143, Perform a minimum value filtering operation based on the minimum cycle value in the set of remaining load-bearing cycles to generate the minimum remaining load-bearing cycle value;

[0149] In one specific embodiment, the remaining bearer cycle values ​​of all nodes in the remaining bearer cycle set are traversed, and the item with the smallest value is extracted as the minimum remaining bearer cycle value.

[0150]

[0151] In the formula, This is the minimum remaining load-bearing period value. From The smallest value is selected from the remaining carrying capacity period values ​​of each node.

[0152] Specifically, the logic for comparing the minimum remaining load-bearing period value with a preset safety threshold to generate the oil pipeline life assessment result is as follows:

[0153] S144, By performing a difference comparison between the minimum remaining load-bearing cycle value and the preset safety threshold, a remaining safety factor value is generated;

[0154] In one specific embodiment, the difference between the minimum remaining load period value and the preset safety threshold is calculated, and the difference is divided by the preset safety threshold to obtain the remaining safety coefficient value.

[0155] Represented as:

[0156]

[0157] In the formula, This represents the remaining safety factor value. The preset safety threshold;

[0158] It should be noted that the remaining safety factor value is used to measure the safety margin of the remaining bearing capacity of the weakest node relative to the safety benchmark. The preset safety threshold is calibrated based on the analysis of historical experimental data.

[0159] S145, perform risk level classification processing based on the remaining safety factor value to generate a lifespan level information set;

[0160] Specifically, the steps for generating the lifetime rating information set are as follows:

[0161] S145.1, Perform interval mapping operation based on the remaining safety factor values ​​to assign each value to the preset risk level boundary interval and generate an initial risk level distribution set;

[0162] In one specific embodiment, it is based on a predetermined low-risk preset risk level range, a medium-risk preset risk level range, and a high-risk preset risk level range;

[0163] The remaining safety factor values ​​of all nodes are divided into initial risk levels according to their magnitude. The initial risk levels include low risk level, medium risk level and high risk level.

[0164] Based on the initial risk level of different nodes, construct a set of initial risk level distributions;

[0165] It should be noted that the preset risk level boundary range is determined according to industry standards. For example, [−1,0) is the preset risk level range for high risk, [0,0.5) is the preset risk level range for medium risk, and [0.5,+∞) is the preset risk level range for low risk.

[0166] S145.2, perform boundary fusion processing on the transition areas between adjacent risk levels in the initial risk level distribution set to generate a continuous risk level partition set;

[0167] In one specific embodiment, a neighborhood search is performed on all nodes in the initial risk level distribution set according to their spatial location. Nodes whose remaining safety factor values ​​are close to the boundary values ​​of the risk level interval are marked as transition nodes, based on the radius around each transition node. The set of spatial neighboring nodes performs neighborhood voting, assigning the initial risk level with the highest proportion in the neighborhood to the transition node, and recombining the initial risk levels of all nodes after the update into a set of continuous level partitions.

[0168] The criteria for determining a transition node are: the absolute value of the difference between the node's remaining safety factor and the nearest risk level boundary value is less than the set fusion threshold.

[0169] The neighborhood voting process is achieved by statistically analyzing the frequency of each initial risk level in the set of neighborhood nodes and taking the mode. It should be noted that this step is used to eliminate locally isolated nodes in the risk level distribution and form spatially continuous level partitions.

[0170] S145.3, Perform a level coding mapping operation based on the continuous level partition set to generate a lifespan level information set;

[0171] In a specific embodiment, the initial risk levels of all nodes in the continuous risk level partition set are read in the order of node number. Based on the initial risk level of each node, an encoding mapping is performed, mapping high risk level to code 1, medium risk level to code 2, low risk level to code 3, and combining node number, node spatial coordinates and corresponding level code to form a lifespan level information set.

[0172] It should be noted that the grade code is a purely numerical label, which is used for subsequent matching and indexing with the spatial location of the defect area in the spatial geometric structure data;

[0173] S146, Based on the matching and processing of the defect area locations in the life level information set and the spatial geometric structure data, the life assessment results of the oil pipeline are generated.

[0174] In one specific embodiment, the spatial coordinates of each node in the life grade information set are matched with the spatial coordinates of the boundary points of the defect area in the spatial geometric structure data. The grade code corresponding to the node located in the defect area is bound to the defect area number. All defect area numbers and their corresponding grade codes are combined into the oil pipeline life assessment result.

[0175] It should be noted that the life assessment results of oil pipelines consist of defect area numbers and corresponding level codes, which are used to indicate the risk level status of the defect area and serve as the final basis for determining the safety of pipeline life.

[0176] Specifically, based on the risk level distribution of defective areas in the oil pipeline life assessment results, and combined with the life level information set and the remaining load-bearing cycle set, the earliest failure area of ​​the pipeline can be determined by identifying high-risk node clusters, and the corresponding remaining load-bearing cycle value can be used as the lower limit of the overall remaining life of the pipeline, so as to realize the spatial positioning and time estimation of pipeline life risk.

[0177] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0178] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0179] The units described as separate components may or may not be physically separate. The components shown as units 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0180] In addition, the functional units 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.

[0181] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0182] The above embodiments are only used to illustrate the technical methods 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 methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A 3D technology based oil pipeline life prediction system characterized by, The system comprises: a contour reconstruction module S11, configured to acquire a three-dimensional point cloud image data of an oil pipeline shell surface in an actual operating environment, and perform surface contour reconstruction processing based on the three-dimensional point cloud image data to extract spatial geometric structure data containing a local deformation defect region; a coupled force-heat analysis module S12, configured to construct a finite element analysis grid according to the spatial geometric structure data, and load operating condition data into corresponding grid nodes to generate a coupled force-heat stress field, wherein the operating condition data comprises a periodic internal working pressure value, an along-line temperature field data, and an axial disturbance stress tensor; the step of loading the operating condition data into the corresponding grid nodes to generate the coupled force-heat stress field comprises: S121, performing a node generation operation through a three-dimensional boundary structure in the spatial geometric structure data to generate a finite element analysis grid node set; S122, performing a grid inner surface node loading operation based on the periodic internal working pressure value to generate an internal pressure loading node set; S123, performing an interpolation expansion processing according to the along-line temperature field data to generate a thermal field loading node set; S124, performing a boundary node mapping processing through the axial disturbance stress tensor, combining the internal pressure loading node set and the thermal field loading node set, and generating the coupled force-heat stress field; the step of performing the boundary node mapping processing through the axial disturbance stress tensor comprises: S124.1, performing a node matching processing based on the axial disturbance stress tensor and the coordinates of the boundary nodes in the finite element analysis grid node set to generate a disturbance loading node index set; S124.2, performing a tensor distribution operation through the disturbance loading node index set to generate a boundary stress loading matrix; S124.3, performing a boundary stress input operation according to the boundary stress loading matrix to generate the coupled force-heat stress field containing the disturbance tensor; a feature extraction module S13, configured to calculate equivalent stress distribution values of defect region nodes based on the coupled force-heat stress field, and extract fatigue damage evolution parameters of a stress concentration region in combination with the spatial geometric structure data to form damage evolution feature data; a life assessment module S14, configured to calculate a minimum residual carrying period value by inputting the damage evolution feature data into a life degradation prediction model, and compare the minimum residual carrying period value with a preset safety threshold to generate an oil pipeline life assessment result.

2. The system for predicting the life of a petroleum pipeline based on 3D technology according to claim 1, wherein, the step of extracting the spatial geometric structure data containing the local deformation defect region comprises: S111, performing a structure segmentation operation through the spatial position data of all points in the three-dimensional point cloud image data of the oil pipeline shell surface to generate a spatial region segment set; S112, performing a boundary mutation analysis processing based on the distribution density of boundary points in each segment in the spatial region segment set to generate a mutation boundary set; S113, performing a spatial aggregation operation according to the mutation boundary set to generate an abnormal region segment set; S114, performing a spatial structure construction processing according to the abnormal region segment set to generate the spatial geometric structure data containing the local deformation defect region.

3. The system for predicting the life of a petroleum pipeline based on 3D technology according to claim 2, characterized in that, the step of performing the spatial structure construction processing according to the abnormal region segment set comprises: S114.1, performing a boundary closure construction operation through the spatial connection relationship between each boundary point in the abnormal area segment set, to generate a closed boundary structure set; S114.2, performing a curve fitting processing based on the boundary contour points of each structure in the closed boundary structure set, to generate a fitted contour set; S114.3, performing a geometric unit packaging operation according to the fitted contour set, to generate a spatial geometric structure data containing a local deformation defect area.

4. The system for predicting the life of a petroleum pipeline based on 3D technology according to claim 3, wherein, The step of extracting the fatigue damage evolution parameter of the stress concentration area is: S131, performing a stress peak extraction processing based on the equivalent stress distribution value of each grid node in the force-thermal coupling stress field, to generate a high stress node set; S132, performing a structure area matching processing through the high stress node set and the spatial geometric structure data, to generate a stress concentration area set; S133, performing a fatigue change calculation according to the time-varying stress of each node in the stress concentration area set, to generate a fatigue evolution segment set.

5. The system for predicting the life of a petroleum pipeline based on 3D technology according to claim 4, wherein, The step of performing a fatigue change calculation according to the time-varying stress of each node in the stress concentration area set is: S133.1, performing a peak-valley identification operation through the equivalent stress sequence of each node in the stress concentration area set, to generate a stress cycle change segment set; S133.2, performing an interval stress amplitude calculation processing based on the stress cycle change segment set, to generate a fatigue evolution segment set; S134, performing a time accumulation and weight superposition processing based on the fatigue evolution segment set, to generate a fatigue damage evolution parameter.

6. The system for predicting the life of a petroleum pipeline based on 3D technology according to claim 5, wherein, The step of inputting the damage evolution feature data into the life degradation prediction model to calculate the minimum residual carrying period value is: S141, performing a normalization processing through the fatigue damage evolution parameter in the damage evolution feature data, to generate a standardized damage feature matrix; S142, calling the life degradation prediction model based on the standardized damage feature matrix to perform a prediction reasoning operation, to generate a residual carrying period set; S143, performing a minimum value screening operation according to the minimum period value in the residual carrying period set, to generate a minimum residual carrying period value.

7. The system for predicting the life of a petroleum pipeline based on 3D technology according to claim 6, wherein The logic for comparing the minimum residual carrying period value with the preset safety threshold to generate the oil pipeline life assessment result is: S144, performing a difference comparison processing through the minimum residual carrying period value and the preset safety threshold, to generate a residual safety coefficient value; S145, performing a risk level division processing based on the residual safety coefficient value, to generate a life level information set; S146, performing a defect area position matching processing based on the life level information set and the spatial geometric structure data, to generate an oil pipeline life assessment result.

8. The system for predicting the life of a petroleum pipeline based on 3D technology according to claim 7, wherein, The step of generating the life level information set is: S145.1, performing an interval mapping operation based on the residual safety coefficient value, to classify each value into a preset risk level boundary interval, to generate an initial risk level distribution set; S145.2, performing a boundary fusion processing through the adjacent level transition area in the initial risk level distribution set, to generate a continuous level partition set; S145.3, performing a level coding mapping operation according to the continuous level partition set, to generate a life level information set.

Images