A pipeline risk identification method and system under geological disasters and external force influences

Abstract

The application discloses a pipeline risk identification method and system under geological disasters and external force influence, and relates to the technical field of pipeline risk identification.The method comprises the following steps: obtaining historical pipeline risk records, wherein M historical pipeline risk events are included; analyzing to obtain a target pipeline risk form group; extracting a first pipeline risk form; obtaining a first historical pipeline risk event; analyzing to obtain first risk information; constructing an intelligent evaluation model; collecting real-time risk index parameters based on preset risk indexes; analyzing real-time displacement evaluation through the intelligent evaluation model; and performing pipeline risk identification and early warning according to the real-time displacement evaluation.The application solves the technical problem of poor safety evaluation effect caused by insufficient understanding of the mechanism of the action of common typical soil movement and external load on pipelines, realizes risk identification and early warning of pipeline damage accidents caused by geological disasters, and thus effectively guarantees the safe operation of pipelines.

Description

Technical Field

[0001] This invention relates to the field of pipeline risk identification technology, and in particular to a method and system for identifying pipeline risks under the influence of geological disasters and external forces. Background Technology

[0002] In recent years, the development of oil and gas pipelines both domestically and internationally has been rapid. As of 2015, there were 3,500 oil and gas pipelines in operation worldwide, with a total length of approximately 1.83 million kilometers. Domestically, the length of long-distance oil and gas pipelines reached 130,000 kilometers. By 2020, the national oil and gas pipeline network is projected to reach 169,000 kilometers; and by 2025, it is expected to reach 240,000 kilometers. To achieve safe and economical oil and gas transportation, the adoption of high-pressure, large-diameter, and high-capacity pipelines in new construction has become a major development trend in pipeline construction both domestically and internationally. With improvements in pipe manufacturing processes and corrosion prevention technologies, the quality of newly constructed pipelines has significantly improved. However, because the circumferential welds are welded on-site, their quality is difficult to guarantee due to limitations in technical capabilities and on-site construction conditions. In recent years, several pipeline circumferential weld failure accidents have occurred both domestically and internationally, causing serious consequences.

[0003] Existing technologies suffer from insufficient understanding of the mechanisms by which common soil movements and external loads affect pipelines, resulting in poor safety assessment outcomes. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for identifying pipeline risks under geological disasters and external forces, in order to address the technical problem that the existing technology lacks sufficient understanding of the mechanism of action of common typical soil movement and external loads on pipelines, resulting in poor safety evaluation.

[0005] In view of the above problems, this application provides a method and system for identifying pipeline risks under the influence of geological disasters and external forces.

[0006] Firstly, this application provides a method for identifying pipeline risks under the influence of geological disasters and external forces. The method includes: acquiring historical pipeline risk records, wherein the historical pipeline risk records include M historical pipeline risk events, where M is an integer greater than 1; analyzing the M historical pipeline risk events to obtain a target pipeline risk form group, wherein the target pipeline risk form group includes N types of pipeline risk forms, 1 < N ≤ M, and N is an integer; extracting a first pipeline risk form from the N types of pipeline risk forms and combining it with the M historical pipeline risk events to obtain a first historical pipeline risk event, wherein the first historical pipeline risk event is a risk event belonging to the first pipeline risk form; analyzing the first historical pipeline risk event to obtain first risk information, wherein the first risk information includes first force information and first displacement information, and the first force information and the first displacement information have a mapping relationship; constructing an intelligent assessment model based on the first force information, the first displacement information and their mapping relationship; collecting real-time risk indicator parameters based on preset risk indicators and analyzing them through the intelligent assessment model to obtain a real-time displacement assessment; and performing pipeline risk identification and early warning based on the real-time displacement assessment.

[0007] Secondly, this application also provides a pipeline risk identification system under geological disasters and external force influences, used to execute a pipeline risk identification method under geological disasters and external force influences as described in the first aspect. The system includes: a historical record acquisition module, used to acquire historical pipeline risk records, wherein the historical pipeline risk records include M historical pipeline risk events, where M is an integer greater than 1; a risk form acquisition module, used to analyze the M historical pipeline risk events to obtain a target pipeline risk form group, wherein the target pipeline risk form group includes N pipeline risk forms, 1 < N ≤ M, and N is an integer; and a risk event acquisition module, used to extract a first pipeline risk form from the N pipeline risk forms and combine it with the M historical pipeline risk events to obtain a first historical pipeline risk event. The system includes: a first historical pipeline risk event, which is a risk event belonging to the first pipeline risk type; a risk event analysis module, which analyzes the first historical pipeline risk event to obtain first risk information, wherein the first risk information includes first force information and first displacement information, and the first force information and the first displacement information have a mapping relationship; an evaluation model construction module, which constructs an intelligent evaluation model based on the first force information, the first displacement information and their mapping relationship; a real-time displacement evaluation acquisition module, which collects real-time risk indicator parameters based on preset risk indicators and analyzes them through the intelligent evaluation model to obtain a real-time displacement evaluation; and a pipeline risk identification and early warning module, which performs pipeline risk identification and early warning based on the real-time displacement evaluation.

[0008] Thirdly, this application also provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the steps of any of the methods in the first aspect described above.

[0009] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The technical solution provided in this application acquires historical pipeline risk records, including M historical pipeline risk events. It analyzes these records to obtain a target pipeline risk pattern group, extracts the first pipeline risk pattern, obtains the first historical pipeline risk event, analyzes the first risk information, constructs an intelligent assessment model, collects real-time risk indicator parameters based on preset risk indicators, and analyzes the real-time displacement assessment through the intelligent assessment model. Based on the real-time displacement assessment, it performs pipeline risk identification and early warning. This application uses grey relational analysis to calculate the sensitivity of pipeline mechanical response indicators and their influencing factors, achieving risk identification and early warning for pipeline damage accidents caused by geological disasters, thereby effectively ensuring the safe operation of pipelines.

[0012] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0014] Figure 1 A flowchart illustrating a pipeline risk identification method under geological disasters and external force influences, provided as an embodiment of this application;

[0015] Figure 2 This is a flowchart illustrating the process of obtaining a target pipeline risk form group in a pipeline risk identification method under geological disasters and external force influences, provided in an embodiment of this application.

[0016] Figure 3 This application provides a schematic diagram of the structure of a pipeline risk identification system under geological disasters and external force influences, as an embodiment of the present application.

[0017] Figure 4 This is an internal structural diagram of a computer device according to an embodiment of this application.

[0018] Explanation of reference numerals in the attached diagram: Historical record acquisition module 10, Risk form acquisition module 20, Risk event acquisition module 30, Risk event analysis module 40, Assessment model construction module 50, Real-time displacement assessment acquisition module 60, Pipeline risk identification and early warning module 70. Detailed Implementation

[0019] This application provides a method and system for identifying pipeline risks under geological disasters and external forces, in order to address the technical problem that the existing technology lacks sufficient understanding of the mechanisms by which common typical soil movements and external loads affect pipelines, resulting in poor safety evaluation.

[0020] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0021] Example 1

[0022] like Figure 1 As shown, this application provides a method for identifying pipeline risks under the influence of geological disasters and external forces, the method comprising:

[0023] Step S100: Obtain historical pipeline risk records, wherein the historical pipeline risk records include M historical pipeline risk events, where M is an integer greater than 1;

[0024] Specifically, statistics show that from 2011 to 2018, a total of 15 circumferential weld failure accidents occurred, including 8 involving X70 steel pipes and 7 involving X80 steel pipes. In one gas pipeline, within less than a year, two pipeline rupture and explosion accidents occurred on the same section, causing serious casualties and property damage, attracting widespread public attention. By searching and retrieving historical pipeline risk events through the internet, for example, setting the historical timeframe to 10 years, all historical pipeline risk events within the past 10 years are retrieved, and a historical pipeline risk record is constructed based on all these events.

[0025] Step S200: Analyze the M historical pipeline risk events to obtain the target pipeline risk form group, wherein the target pipeline risk form group includes N types of pipeline risk, 1 < N ≤ M, and N is an integer;

[0026] Furthermore, such as Figure 2 As shown, step S200 of this application further includes:

[0027] Step S210: Extract the target historical pipeline risk events from the M historical pipeline risk events, and obtain the target historical pipeline risk form; and

[0028] Step S220: Construct a candidate pipeline risk form group based on the target historical pipeline risk form;

[0029] Step S230: Count the number of target risks in the target historical pipeline risk form; and

[0030] Step S240: Sort the candidate pipeline risk form group in descending order of the number of target risks to obtain the candidate pipeline risk form sequence;

[0031] Step S250: Determine the target pipeline risk form group based on the candidate pipeline risk form sequence.

[0032] Specifically, the K-means algorithm (K-means is the most commonly used clustering algorithm based on Euclidean distance, which believes that the closer two targets are, the greater their similarity) is used to cluster M historical pipeline risk events. The specific steps are as follows: select k initial samples as initial cluster centers, calculate the distance from each sample x in the M historical pipeline risk events to the k cluster centers and assign it to the class corresponding to the nearest cluster center, recalculate the cluster center for each class, and iterate until the maximum number of iterations is reached. For example, the maximum number of iterations is set to M times. The resulting multiple classes are used as multiple historical pipeline risk forms, and multiple samples in a class are multiple historical pipeline risk events corresponding to a historical pipeline risk form.

[0033] Multiple historical pipeline risk patterns are grouped into candidate pipeline risk pattern groups. The number of risk occurrences for each historical pipeline risk pattern is counted, i.e., the number of occurrences of multiple historical pipeline risk events within that pattern. A higher number of risk occurrences indicates a higher frequency of occurrence of that historical pipeline risk pattern in historical events. Within the candidate pipeline risk pattern group, multiple historical pipeline risk patterns are sorted from highest to lowest based on their corresponding number of risk occurrences; that is, the higher the number of risk occurrences, the higher the ranking, indicating a higher frequency of occurrence of the corresponding risk. The top-ranked candidate pipeline risk patterns are selected as typical examples, i.e., pipeline risk patterns that occur frequently in history, resulting in the target pipeline risk pattern group. For example, mining subsidence, floods (debris flows), landslides, and faults are the most common geological hazards in pipeline engineering. When pipelines pass through urban or industrial areas, it is inevitable that roads, buildings, and ground deposits will encroach on the pipelines. Typical geological hazards and external force impacts are specifically categorized as: landslides, frozen soil, mining subsidence, and heavy vehicle crushing, etc. Among them, landslides, frozen soil, mining subsidence, and heavy vehicle compaction are each considered as a type of pipeline risk, and multiple types of pipeline risks constitute the target pipeline risk group.

[0034] Step S300: Extract the first pipeline risk form from the N types of pipeline risk forms, and combine it with the M historical pipeline risk events to obtain the first historical pipeline risk event, wherein the first historical pipeline risk event is a risk event belonging to the first pipeline risk form;

[0035] Specifically, a first pipeline risk form is randomly selected from the N types of pipeline risk forms. According to the aforementioned clustering process, the N types of pipeline risk forms are N categories after clustering M historical pipeline risk events. Each category corresponds to multiple historical pipeline risk events, and the multiple historical pipeline risk events are a part of the M historical pipeline risk events. Based on this correspondence, multiple historical pipeline risk events corresponding to the first pipeline risk form are obtained. The first historical pipeline risk event is randomly selected from the multiple historical pipeline risk events.

[0036] Step S400: Analyze the first historical pipeline risk event to obtain the first risk information, wherein the first risk information includes the first force information and the first displacement information, and the first force information and the first displacement information have a mapping relationship;

[0037] Specifically, the first historical pipeline risk event is a risk event within the target pipeline risk type group, which includes landslides, frozen soil, mining subsidence, and heavy vehicle compaction. Stress analysis of the pipeline under different conditions yields stress information, including the source, magnitude, and direction of the stress. Displacement analysis of the pipeline under different conditions provides displacement information, including the direction and length of displacement. Generally, the direction of stress coincides with the direction of displacement, and the displacement length is determined by the magnitude of the stress.

[0038] Regarding the displacement patterns of landslides, landslides are classified into two modes based on the direction of the sliding force (the force exerted by the soil on the pipeline due to the landslide): longitudinal landslides (the sliding force is along the pipeline axis) and transverse landslides (the sliding force is perpendicular to the pipeline axis). In the longitudinal landslide mode, the pipeline runs parallel to the direction of landslide movement. The pipeline section in the landslide area is subjected to axial friction of the soil and the weight of the pipeline itself. The bottom may also be subjected to soil resistance due to the accumulation of sliding soil. In the transverse landslide mode, the pipeline is perpendicular to the direction of landslide movement. The pipeline in the landslide area is subjected to the transverse impact of the landslide body, while the pipeline outside the landslide area is subjected to the transverse resistance of the site soil. The pipeline undergoes transverse bending deformation. Large-scale landslides are very likely to cause the pipeline to break due to excessive transverse deformation.

[0039] Regarding the displacement patterns of frozen soil, frozen soil is a soil medium that is extremely sensitive to temperature. It exhibits rheological properties, and its long-term strength is far lower than its instantaneous strength. Frost heave occurs because water molecules in frozen soil migrate from relatively warmer to relatively colder areas in the form of thin film water. The volume increase caused by the freezing of this migrating water is significant. This volume expansion of the soil pushes the pipeline off its original laying path and upwards, resulting in bending deformation. Thawing settlement occurs when external heat input causes the frozen soil to thaw. The soil loses its supporting capacity, and the amount of thawing varies depending on the thawing depth, ice content, and soil particle size. A transition zone exists between the stable and unstable thawing zones. Pipelines buried in this zone experience different supporting forces, leading to differential settlement. Settlement in the seasonally thawing zone is greater than that in the stable zone and the transition zone, causing pipeline deformation.

[0040] Regarding the displacement patterns of mined-out areas, when the mined-out areas expand to a certain extent, the rock strata move to the surface, causing the surface to move, deform, and be damaged. The forms of surface movement can be divided into two categories: continuous movement and deformation, which refers to the formation of surface movement basins within the movement range, where the surface moves and deforms, and the continuity of the surface is generally maintained; and discontinuous damage, which refers to the formation of steps and collapse pits due to cracks on the surface, causing the surface to lose its original continuity.

[0041] In the case of displacement caused by heavy vehicles, when a pipeline is subjected to the pressure of heavy vehicles on a highway, the static (dynamic) load of the vehicles will be transferred to the pipeline through the road surface or soil layer, and a large additional stress will be generated in the pipeline.

[0042] Step S500: Construct an intelligent evaluation model based on the first force information, the first displacement information, and their mapping relationship;

[0043] Furthermore, step S500 of this application also includes:

[0044] Step S510: The first force information includes the first force direction and the first force magnitude;

[0045] Step S520: Use the first force direction, the first force magnitude, and the first displacement information as training data to train the intelligent evaluation model.

[0046] Specifically, by performing a stress analysis on the pipeline in the first historical pipeline risk event, we can obtain multiple forces acting on the pipeline, which are the loads on the pipeline. In addition to the internal pressure borne by the pipeline, the loads may also be caused by the movement of the surrounding soil, such as landslides, settlement, earthquakes, etc. In addition, during the construction of the pipeline, non-standard assembly and welding can also generate significant additional loads, such as the local bending stress caused by misalignment and skew joints, as well as the additional loads generated by strong assembly of weld joints.

[0047] Based on a feedforward neural network, an intelligent evaluation model is constructed. The input data of the intelligent evaluation model includes the force direction and magnitude, and the output data includes displacement information. Construction data is obtained according to the first force direction, the first force magnitude, and the first displacement information. The construction data is randomly divided into a training set, a validation set, and a test set according to a certain ratio, and the divided training set, validation set, and test set are labeled. For example, the preferred ratio in this application is 8:1:1. The training set is used to train the model, i.e., to determine the model's weights and biases—these are the learning parameters. The validation set is used to validate each model after training multiple models on the training set, and the model accuracy is recorded to select the best-performing model and its corresponding parameters. The test set is used only once, i.e., when evaluating the final model after training is complete. It does not participate in the learning parameter process or the hyperparameter selection process, but is only used for model evaluation. Based on machine learning, the model is trained under supervision using a training set, validated using a validation set, and evaluated using a test set. The hyperparameters are continuously adjusted until the accuracy meets the preset requirements, and the intelligent evaluation model is output. For example, the preset accuracy requirement is set to 98%.

[0048] Furthermore, prior to step S520 of this application, the following are also included:

[0049] Step S520-1: Obtain the first historical risk pipeline of the first historical pipeline risk event;

[0050] Step S520-2: Determine whether the first historical risk pipeline is an onshore pipeline;

[0051] Step S520-3: If yes, obtain the first ground activity information; and

[0052] Step S520-4: Adjust the first force information based on the first ground activity information.

[0053] Specifically, the pipeline involved in the first historical pipeline risk event is identified as the first historical risk pipeline. For onshore pipelines, longitudinal strain is often related to ground activities, such as seismic activity, slope instability, frost heave, and mine subsidence. The first ground activity is identified based on these ground activities. Taking seismic activity as an example, the hazards of earthquakes to long-distance oil and gas pipelines include direct and secondary hazards. Direct hazards include surface displacement and rupture caused by earthquakes, and seismic waves subjecting the pipeline to strong compression or tension, which may cause the pipeline to break, snap, or buckle. Furthermore, earthquake-induced soil liquefaction can cause the pipeline foundation soil to subside, resulting in the pipeline being suspended or unevenly settled, further increasing the axial tensile force of the pipeline and threatening pipeline safety. Indirect hazards include earthquakes causing site failure, leading to landslides, rock collapses, rock cracks, and deep soil landslides, which may cause oil and gas pipeline ruptures and power supply interruptions.

[0054] An evaluation model is set up based on the actual situation, and the changes at the critical point are determined. Simultaneously, the strain baseline is calculated. For example, an IMU (inertial motion unit, a combination of accelerometer and gyroscope sensors used to detect acceleration and angular velocity to represent motion and intensity) can provide the centerline information of the pipeline. Successful operation of the IMU can provide vertical displacement information of the pipeline and convert its analysis into "bending strain." A soil interaction model or pipeline-soil interaction model is created. This type of model begins with an estimation of ground or soil motion, which is transferred to the pipeline through pipeline-soil interaction. There are many types of models for estimating the strain experienced by the pipeline. Direct measurement, using strain gauges, is widely used in areas where high strain may occur. Measurement data is transmitted via fiber optic cable, and this method can provide strain data for a long section of pipeline. Using the above methods, first ground activity information is obtained. This first ground activity information includes the direction and magnitude of the force exerted on the pipeline by the first ground activity. The direction and magnitude of this force are superimposed with the magnitude and direction of the force in the first force information to adjust the first force information.

[0055] Furthermore, following step 520-1 of this application, it also includes:

[0056] Step S520-11: Determine whether the first historical risk pipeline is a marine pipeline;

[0057] Step S520-12: If yes, obtain the first pipeline laying and operation information; and

[0058] Step S520-13: Adjust the first stress information based on the first pipeline laying and operation information;

[0059] Specifically, for offshore pipelines, the greatest longitudinal strain occurs during pipeline laying and certain operational conditions, with the longitudinal strain range from 0.1% to 2%. Offshore pipelines are directly affected by ocean waves. Therefore, firstly, it is necessary to investigate the occurrence cycle, duration, direction, wave height, wavelength, and frequency of ocean waves in different seasons within the sea area. Wave recorders can be used for wave surveying. Secondly, water flow affects the safety and stability of the pipeline. Measuring the vertical distribution and direction of seawater flow velocity along the route allows for calculation of pipeline stability and vibration. Underwater, pipelines are subjected to various forces, especially the forces of water flow, including horizontal thrust and uplift. Vertically, the pipeline can only be stable when its weight exceeds the uplift and buoyancy forces. When pipelines are laid exposed on an uneven seabed, water flow over the suspended sections can easily cause vibrations and even breakage. Measuring the seawater flow velocity at the seabed allows for the calculation of the maximum permissible length of the suspended section. By detecting ocean waves and water flow, the first pipeline laying and operation information is obtained. The first pipeline laying and operation information includes the magnitude and direction of the force exerted by seawater on the first historical risk pipeline. The direction and magnitude of this force are superimposed with the magnitude and direction of the force in the first force information, and the first force information is adjusted.

[0060] Step S600: Collect real-time risk indicator parameters based on preset risk indicators, and obtain real-time displacement assessment through the intelligent assessment model;

[0061] Specifically, a risk indicator set is constructed based on big data. This risk indicator set includes multiple risk indicators. A correlation index between these multiple risk indicators and pipeline risk is calculated. Risk indicators whose correlation index meets a preset threshold are added to a preset risk indicator set. The preset risk indicator set refers to the risk indicator among the multiple risk indicators whose correlation with pipeline risk meets preset requirements. A first preset risk indicator is obtained, and the correlation between this first preset risk indicator and pipeline risk is used as a first correlation degree. Data is collected based on this first preset risk indicator, and the product of the collected data and the first correlation degree is used as a first real-time risk indicator parameter. Polarity data of multiple risk indicators within the preset risk indicator set is collected and calculated to obtain multiple real-time risk indicator parameters. The average of these multiple real-time risk indicator parameters is calculated to obtain the real-time risk indicator parameter, which represents the force exerted on the pipeline by the real-time pipeline risk, including the direction and magnitude of the force. The direction and magnitude of the force are input into the intelligent assessment model. The direction and magnitude of the force are matched with sample data in the model. Based on the mapping relationship between the first force direction, the first force magnitude, and the first displacement information, the displacement information corresponding to the force direction and magnitude is obtained, and this is used as the real-time displacement assessment output.

[0062] Furthermore, prior to step S600 of this application, the following are included:

[0063] Step S600-1: Construct a risk indicator set based on big data, wherein the risk indicator set includes O indicators, where O is an integer greater than 1;

[0064] Step S600-2: Extract the first risk indicator from the risk indicator set; and

[0065] Step S600-3: Use grey relational analysis to obtain the first correlation index between the first risk indicator and the pipeline risk;

[0066] Step S600-4: If the first correlation index meets the preset correlation threshold, add the first risk index to the preset risk index.

[0067] Specifically, analyzing the stress-strain failure mechanism of pipeline circumferential weld failure involves considering the following: Failure mode refers to the external manifestation of material failure at the macroscopic level, such as brittle fracture, ductile fracture, fatigue fracture, creep fracture, and stress corrosion cracking. Failure mechanism, on the other hand, refers to the physical or chemical changes involved in causing material failure, often linked to microscopic material behavior, such as cleavage fracture, dimple fracture, intergranular fracture, and fatigue fracture. Failure modes are categorized as brittle fracture, ductile fracture, fatigue failure, and stress corrosion cracking. The criteria include plastic failure, net section failure, and fracture failure. Evaluation is based on pipeline stress failure. Defects in the circumferential welds of high-strength steel pipelines are a major risk factor. For oil pipelines, cracking of circumferential welds results in large leaks and serious consequences. These defects are often related to geometric deformations such as repair welding (especially internal repair welding), rework, dead joints, connections, mitered joints, and depressions, as well as variations in wall thickness, connections to elbows, and misalignment. Simultaneously, weld impact energy and other toughness indicators may fail to meet standards, indicating poor welding quality and weak points such as weld crack-type defects and non-metallic inclusions. Under the combined effects of original defects, internal pipeline pressure, assembly stress, residual welding stress, bending stress caused by misalignment and mitered joints, and external loads from ground settlement, circumferential welds can crack, often exhibiting brittle cracking.

[0068] Among them, plastic fracture: When a pressure pipeline with a circumferential crack enters yielding at the cross section where the crack is located under the action of bending moment (or simultaneously applied internal pressure and axial force), the pipeline fails. Considering the hardening phenomenon of the pipeline material, it can be considered that the pipeline will only fail when all the stress on the cross section reaches the rheological stress of the material. Net section failure: When the cross section of the pipeline where the crack is located enters yielding, the pipeline fails. Considering the hardening phenomenon of the pipeline material, it can be considered that the pipeline will only fail when all the stress on the cross section reaches the rheological stress of the material. Fracture failure: Fracture mechanics studies the fracture toughness of cracked materials based on a large number of experiments, and studies the laws of crack propagation, instability and crack arrest of cracked components under various working conditions. The three main factors controlling fracture are: crack size and shape, applied stress and fracture toughness of the material.

[0069] Based on the above analysis, multiple risk indicators are obtained and a risk indicator set is constructed. Any risk indicator in the risk indicator set is selected as the first risk indicator.

[0070] Grey relational analysis is a very active branch of grey system theory. Its basic idea is to judge whether the relationship between different sequences is close based on the similarity of the geometric shapes of the sequence curves. The basic idea is to transform the discrete behavior observations of system factors into piecewise continuous broken lines through linear interpolation, and then construct a model to measure the degree of correlation based on the geometric characteristics of the broken lines. The closer the geometric shapes of the broken lines are, the greater the correlation between the corresponding sequences, and vice versa.

[0071] Specifically, a reference sequence is constructed based on pipeline risk, representing a data sequence reflecting the system's behavioral characteristics. A comparison sequence is constructed based on the primary risk indicator, representing a data sequence composed of factors influencing the system's behavior. Both the reference and comparison sequences are dimensionless. The so-called degree of correlation is essentially the degree of difference in the geometric shapes of the curves; therefore, the magnitude of the difference between curves can be used as a measure of the degree of correlation. For a reference sequence x0, there are several comparison sequences x1, x2, ... x0. n The correlation coefficient ξ(x) between each comparison series and the reference series at each time point (i.e., each point on the curve). i This can be expressed as the following formula: in, For each comparison sequence x i The absolute difference between each point on the curve and each point on the reference sequence x0 curve is indicated by the subscript i, where i represents the i-th comparison sequence, Δ(min) is the second minimum difference, Δ(max) is the two-level maximum difference, and ρ is the resolution coefficient, which is usually taken as 0.5.

[0072] Since the correlation coefficient represents the degree of correlation between the comparison series and the reference series at various time points (i.e., points on the curve), it has more than one value. Because the information is too scattered to facilitate a comprehensive comparison, it is necessary to aggregate the correlation coefficients at each time point (i.e., points on the curve) into a single value, i.e., to calculate its average, as a quantitative representation of the degree of correlation between the comparison series and the reference series. The correlation degree, r, is... i As shown below: Where, r i To compare the sequence x i The grey relational degree r of the reference sequence x0 i The closer the value is to 1, the better the correlation. The first correlation index is calculated.

[0073] Obtain a preset correlation threshold, for example, set to 0.8. When the first correlation index meets the preset correlation threshold, that is, is greater than 0.8, it means that the correlation between the first correlation index and pipeline risk meets the requirements, and the first risk index is added to the preset risk index.

[0074] Step S700: Perform pipeline risk identification and early warning based on the real-time displacement assessment.

[0075] Specifically, due to the variety, frequency, and intensity of geological disasters, and the extensive coverage of oil and gas pipeline networks traversing areas prone to various geological disasters, pipelines face a severe threat from geological hazards. Under the influence of typical soil movements such as landslides and ground subsidence (mining collapse, karst collapse and melting subsidence), as well as external loads such as heavy vehicle compaction and surcharge, pipelines often experience stress concentration. Welds are prone to stress concentration and are also weak points in pipeline safety. Based on real-time displacement assessment of pipeline circumferential welds under typical geological disasters and other external forces, early warning values ​​are set. When the real-time displacement assessment reaches the early warning value, pipeline risk identification and early warning are initiated. Solving key technical issues such as the mechanism and safety evaluation of common typical soil movements and external loads on pipelines, assessment of circumferential weld failure and service performance, and risk prevention and control technologies will effectively reduce the occurrence of pipeline damage accidents caused by geological disasters, and strongly guarantee the safe operation of pipelines and environmental protection.

[0076] Furthermore, following step S600 of this application, the following are also included:

[0077] Step S610: Based on the preset risk indicators, traverse the M historical pipeline risk events to obtain risk analysis data;

[0078] Step S620: Fit the risk analysis data to obtain a risk fitting formula; and

[0079] Step S630: Obtain the risk fitting result by combining the real-time risk indicator parameters;

[0080] Step S640: Perform pipeline risk identification and early warning based on the risk fitting results and the real-time displacement assessment.

[0081] Specifically, based on the preset risk indicators, the M historical pipeline risk events are traversed to obtain risk analysis data. This risk analysis data is essentially historical data, meaning it is used for fitting. Machine learning methods are used for fitting to obtain a fitting formula for the pipeline mechanical response index. Changes in the pipeline are then measured. For example, features are normalized to eliminate the dimensional influence between data features, making different indicators comparable. The most commonly used method is linear function normalization, which performs a linear transformation on the original data, mapping the result to the range [0,1], achieving proportional scaling of the original data. This is used to fit the risk analysis data, resulting in the following risk fitting formula: Where, x i For the original data, max(x) i min(x) i The maximum and minimum values ​​of the data are used to calculate the real-time risk indicator parameters and obtain the risk fitting result. Based on the risk fitting result and the real-time displacement assessment, the pipeline condition is calculated to achieve a preventative effect.

[0082] In summary, the pipeline risk identification method under geological disasters and external force influences provided in this application has the following technical effects:

[0083] By acquiring historical pipeline risk records, including M historical pipeline risk events, and analyzing them to obtain a target pipeline risk form group, the first pipeline risk form is extracted to obtain the first historical pipeline risk event. This first risk information is then analyzed to construct an intelligent assessment model. Based on preset risk indicators, real-time risk indicator parameters are collected, and real-time displacement assessments are obtained through the intelligent assessment model. Pipeline risk identification and early warning are then performed based on these real-time displacement assessments. This application uses grey relational analysis to calculate the sensitivity of pipeline mechanical response indicators and their influencing factors, achieving risk identification and early warning for pipeline damage accidents caused by geological disasters, thereby effectively ensuring the safe operation of pipelines.

[0084] Example 2

[0085] Based on the same inventive concept as the pipeline risk identification method under geological disasters and external force influences described in the foregoing embodiments, such as Figure 3 As shown, this application provides a pipeline risk identification system under geological disasters and external force influences, the system comprising:

[0086] The historical record acquisition module 10 is used to acquire historical pipeline risk records, wherein the historical pipeline risk records include M historical pipeline risk events, where M is an integer greater than 1;

[0087] Risk form acquisition module 20 is used to analyze the M historical pipeline risk events to obtain a target pipeline risk form group, wherein the target pipeline risk form group includes N types of pipeline risk forms, 1 < N ≤ M, and N is an integer;

[0088] Risk event acquisition module 30 is used to extract the first pipeline risk form from the N types of pipeline risk forms, and combine it with the M historical pipeline risk events to obtain the first historical pipeline risk event, wherein the first historical pipeline risk event is a risk event belonging to the first pipeline risk form.

[0089] Risk event analysis module 40 is used to analyze the first historical pipeline risk event to obtain first risk information, wherein the first risk information includes first force information and first displacement information, and the first force information and the first displacement information have a mapping relationship.

[0090] The evaluation model construction module 50 is used to construct an intelligent evaluation model based on the first force information, the first displacement information and their mapping relationship.

[0091] The real-time displacement assessment acquisition module 60 is used to collect real-time risk indicator parameters based on preset risk indicators and analyze them through the intelligent assessment model to obtain real-time displacement assessment.

[0092] Pipeline risk identification and early warning module 70, which is used to identify and warn of pipeline risks based on the real-time displacement assessment.

[0093] Furthermore, the system also includes:

[0094] The historical risk form acquisition module is used to extract the target historical pipeline risk event from the M historical pipeline risk events and obtain the target historical pipeline risk form; and

[0095] A candidate risk form group construction module is used to construct a candidate pipeline risk form group based on the target historical pipeline risk form.

[0096] The target risk frequency statistics module is used to count the frequency of the target risk in the historical pipeline risk form; and

[0097] The sorting module is used to sort the candidate pipeline risk form group in descending order of the target risk frequency to obtain a candidate pipeline risk form sequence;

[0098] The risk form group determination module is used to determine the target pipeline risk form group based on the candidate pipeline risk form sequence.

[0099] Furthermore, the system also includes:

[0100] The first force information includes the first force direction and the first force magnitude;

[0101] The model training module is used to train the intelligent evaluation model by using the first force direction, the first force magnitude, and the first displacement information as training data.

[0102] Furthermore, the system also includes:

[0103] The first historical risk pipeline acquisition module is used to acquire the first historical risk pipeline of the risk event of the first historical pipeline.

[0104] The onshore pipeline identification module is used to determine whether the first historical risk pipeline is an onshore pipeline;

[0105] The first ground activity information acquisition module is used to acquire first ground activity information if the condition is met; and

[0106] The first force information adjustment module is used to adjust the first force information based on the first ground activity information.

[0107] Furthermore, the system also includes:

[0108] The offshore pipeline identification module is used to determine whether the first historical risk pipeline is an offshore pipeline;

[0109] The first pipeline laying operation information acquisition module is used to acquire, if necessary, the first pipeline laying operation information; and

[0110] The stress information adjustment module is used to adjust the first stress information based on the first pipeline laying and operation information.

[0111] Furthermore, the system also includes:

[0112] The risk indicator set construction module is used to construct a risk indicator set based on big data, wherein the risk indicator set includes O indicators, where O is an integer greater than 1;

[0113] The first risk indicator extraction module is used to extract the first risk indicator from the risk indicator set; and

[0114] The first correlation index acquisition module is used to obtain the first correlation index between the first risk indicator and the pipeline risk using grey relational analysis.

[0115] The first correlation index judgment module is used to add the first risk indicator to the preset risk indicator if the first correlation index meets the preset correlation threshold.

[0116] Furthermore, the system also includes:

[0117] The traversal module is used to traverse the M historical pipeline risk events based on the preset risk indicators to obtain risk analysis data;

[0118] A fitting module is used to fit the risk analysis data to obtain a risk fitting formula; and

[0119] The risk fitting result acquisition module is used to obtain the risk fitting result by combining the real-time risk indicator parameters;

[0120] The identification and early warning module is used to identify and warn of pipeline risks based on the risk fitting results and the real-time displacement assessment.

[0121] Example 3

[0122] Based on the same inventive concept as the pipeline risk identification method under geological disasters and external force influences described in the foregoing embodiments, such as Figure 4 As shown, this application also provides a computer device, which can be a server, and its internal structure diagram can be as follows. Figure 4 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores news data and data such as time decay factors. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps of the method in Embodiment 1.

[0123] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0124] Example 4

[0125] Based on the same inventive concept as the pipeline risk identification method under geological disasters and external force influences in the foregoing embodiments, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method in Embodiment 1.

[0126] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The pipeline risk identification method and specific examples under geological disasters and external force influences in Embodiment 1 are also applicable to the pipeline risk identification system under geological disasters and external force influences in this embodiment. Through the foregoing detailed description of the pipeline risk identification method under geological disasters and external force influences, those skilled in the art can clearly understand the pipeline risk identification system under geological disasters and external force influences in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0127] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying pipeline risks under the influence of geological disasters and external forces, characterized in that, include: Obtain historical pipeline risk records, wherein the historical pipeline risk records include M historical pipeline risk events, where M is an integer greater than 1; The target pipeline risk form group is obtained by analyzing the M historical pipeline risk events, wherein the target pipeline risk form group includes N types of pipeline risk, 1 < N ≤ M, and N is an integer; Extract the first pipeline risk form from the N types of pipeline risk forms, and combine it with the M historical pipeline risk events to obtain the first historical pipeline risk event, wherein the first historical pipeline risk event is a risk event belonging to the first pipeline risk form; The analysis of the first historical pipeline risk event yields the first risk information, wherein the first risk information includes the first force information and the first displacement information, and the first force information and the first displacement information have a mapping relationship. An intelligent evaluation model is constructed based on the first force information, the first displacement information and their mapping relationship, wherein the first force information includes the source of force, the magnitude of force and the direction of force; Real-time risk indicator parameters are collected based on preset risk indicators, and real-time displacement assessment is obtained through analysis by the intelligent assessment model. The categories of preset risk indicators include geometric deformation of pipe circumferential welds, welding quality, and material properties. Pipeline risk identification and early warning are performed based on the real-time displacement assessment. The analysis of the M historical pipeline risk events yields a target pipeline risk form group, including: Extract the target historical pipeline risk events from the M historical pipeline risk events, and obtain the target historical pipeline risk form; and A candidate pipeline risk form group is formed based on the target historical pipeline risk forms; Statistically count the number of target risks in the historical pipeline risk forms mentioned above; and The candidate pipeline risk form groups are sorted in descending order of the number of target risks to obtain a candidate pipeline risk form sequence; The target pipeline risk form group is determined based on the candidate pipeline risk form sequence; The types of risk forms for the target pipeline include: landslides, frozen soil, mining subsidence, and heavy vehicle compaction. The first real-time risk indicator parameter is the product of the data collected based on the first preset risk indicator and the first correlation degree. The real-time risk indicator parameters refer to the forces exerted on the pipeline by real-time pipeline risks, including the direction and magnitude of the forces.

2. The method according to claim 1, characterized in that, The step of constructing an intelligent evaluation model based on the first force information, the first displacement information, and their mapping relationship includes: The first force information includes the first force direction and the first force magnitude; The intelligent evaluation model is trained by using the first force direction, the first force magnitude, and the first displacement information as training data.

3. The method according to claim 2, characterized in that, Before training the intelligent evaluation model using the first force direction, the first force magnitude, and the first displacement information as training data, the method further includes: Obtain the first historical risk pipeline for the first historical pipeline risk event; Determine whether the first historical risk pipeline is an onshore pipeline; If so, obtain first ground activity information; and The first force information is adjusted based on the first ground activity information.

4. The method according to claim 3, characterized in that, After obtaining the first historical risk pipeline of the first historical pipeline risk event, the method further includes: Determine whether the first historical risk pipeline is a marine pipeline; If so, obtain information on the first pipeline's laying and operation; and The first stress information is adjusted based on the first pipeline laying and operation information.

5. The method according to claim 1, characterized in that, Before the process of collecting real-time risk indicator parameters based on preset risk indicators and analyzing them through the intelligent assessment model to obtain a real-time displacement assessment, the following steps are included: A risk indicator set is constructed based on big data, wherein the risk indicator set includes O indicators, where O is an integer greater than 1; Extract the first risk indicator from the risk indicator set; and The first correlation index between the first risk indicator and pipeline risk is obtained by using grey relational analysis. If the first correlation index meets the preset correlation threshold, the first risk indicator is added to the preset risk indicator.

6. The method according to claim 5, characterized in that, After collecting real-time risk indicator parameters based on preset risk indicators and analyzing them through the intelligent assessment model to obtain a real-time displacement assessment, the method further includes: Based on the preset risk indicators, the M historical pipeline risk events are traversed to obtain risk analysis data; The risk fitting formula is obtained by fitting the risk analysis data; and The risk fitting result is obtained by combining the real-time risk indicator parameters; Pipeline risk identification and early warning are performed based on the risk fitting results and the real-time displacement assessment.

7. A pipeline risk identification system under geological disasters and external force influences, characterized in that, The system is used to perform the method according to any one of claims 1 to 6, the system comprising: The historical record acquisition module is used to acquire historical pipeline risk records, wherein the historical pipeline risk records include M historical pipeline risk events, where M is an integer greater than 1; The risk form acquisition module is used to analyze the M historical pipeline risk events to obtain a target pipeline risk form group, wherein the target pipeline risk form group includes N pipeline risk forms, 1 < N ≤ M, and N is an integer; The risk event acquisition module is used to extract the first pipeline risk form from the N types of pipeline risk forms, and combine it with the M historical pipeline risk events to obtain the first historical pipeline risk event, wherein the first historical pipeline risk event is a risk event belonging to the first pipeline risk form. The risk event analysis module is used to analyze the first historical pipeline risk event to obtain the first risk information, wherein the first risk information includes the first force information and the first displacement information, and the first force information and the first displacement information have a mapping relationship. An evaluation model construction module is used to construct an intelligent evaluation model based on the first force information, the first displacement information and their mapping relationship. A real-time displacement assessment acquisition module is used to collect real-time risk indicator parameters based on preset risk indicators and analyze them through the intelligent assessment model to obtain a real-time displacement assessment. A pipeline risk identification and early warning module is used to identify and warn of pipeline risks based on the real-time displacement assessment.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the steps of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of any one of claims 1-6.

Images