Method, apparatus, medium, and product for evaluating pipe stretch load capacity

Abstract

The present application relates to the technical field of pipeline safety, and discloses a pipeline tensile bearing capacity evaluation method, device, medium and product, comprising: acquiring multiple influence factors of the tensile bearing capacity of a pipeline for pipeline corrosion in a defective pipeline; determining coupling difficulty information of the multiple influence factors and influence degree information on the tensile bearing capacity; dividing the multiple influence factors into multiple type influence factor sets based on the coupling difficulty information; determining the influence law corresponding to each influence factor based on finite element simulation and the influence degree information of the multiple influence factors; generating a preliminary data set according to at least one type of influence factor set and the corresponding influence law through finite element simulation; and generating an evaluation model according to machine learning and the preliminary data set. The present application improves the accuracy of the evaluation of the tensile bearing capacity of the pipeline.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipeline safety, in particular to a pipeline tensile bearing capacity evaluation method, device, medium and product. BACKGROUND

[0002] Metal loss defects often occur in areas where the pipeline coating is damaged. Local thinning caused by external corrosion will cause a significant decrease in strain capacity. Traditional methods for evaluating and maintaining these metal loss defects are developed under the assumption that the hoop stress is much larger than the axial stress, i.e., the hoop stress is considered to be the main driving force for potential failure. In geological disaster areas, soil movement such as landslides, geological subsidence, frost heaving and thawing will cause the oil and gas pipeline to bear large axial stress / strain. Under such external conditions, the traditional stress-based evaluation method is usually no longer applicable, and strain-based evaluation is needed. It is necessary to study the tensile bearing capacity of pipelines with metal loss defects under axial strain conditions for large-diameter high-grade pipelines. Therefore, how to improve the evaluation accuracy of the tensile bearing capacity of the pipeline is a technical problem to be solved at present. SUMMARY

[0003] The purpose of the present application is to provide a pipeline tensile bearing capacity evaluation method, device, medium and product, which can improve the accuracy of pipeline bearing capacity evaluation.

[0004] In a first aspect, the present application provides a pipeline tensile bearing capacity evaluation method, comprising: obtaining a plurality of influence factors of the tensile bearing capacity of a pipeline with defects for pipeline corrosion;

[0005] determining coupling difficulty information and influence degree information of the tensile bearing capacity of the plurality of influence factors;

[0006] dividing the plurality of influence factors into a plurality of type influence factor sets based on the coupling difficulty information; the coupling difficulty of influence factor sets of different types is different;

[0007] determining the influence law corresponding to each influence factor based on finite element simulation and the influence degree information of the plurality of influence factors;

[0008] generating a preliminary data set according to at least one type of influence factor set and the corresponding influence law through finite element simulation;

[0009] generating an evaluation model according to machine learning and the preliminary data set, the evaluation model being used to predict the tensile bearing capacity of a pipeline to be evaluated.

[0010] In one possible implementation, the plurality of influence factors includes at least one of the following: defect length, defect width, defect depth, yield strength ratio, internal pressure, pipe diameter, and wall thickness.

[0011] In a possible implementation, the generating, by the finite element simulation, of the preliminary data set according to the at least one type of influence factor set and the corresponding influence law includes:

[0012] The preliminary data set is generated by the finite element simulation based on the at least one type of influence factor set, the influence law corresponding to each influence factor, and the data generation mode corresponding to each type of influence factor set.

[0013] In a possible implementation, the multiple types of influence factor sets include a first type of influence factor set, the coupling difficulty of the first type of influence factor set is greater than that of the remaining types of influence factor sets, and in a case where the at least one type of influence factor set includes the first type of influence factor set,

[0014] The generating, based on the at least one type of influence factor set, the influence law corresponding to each influence factor, and the data generation mode corresponding to each type of influence factor set, of the preliminary data set includes:

[0015] At least one influence factor in the first type of influence factor set is selected as a variable in turn, the remaining influence factors in the first type of influence factor set remain unchanged, and the preliminary data set is generated based on machine learning and the influence law of the at least one influence factor.

[0016] In a possible implementation, the multiple types of influence factor sets include a second type of influence factor set, in a case where the at least one type of influence factor set includes the second type of influence factor set,

[0017] The generating, based on the at least one type of influence factor set, the influence law corresponding to each influence factor, and the data generation mode corresponding to each type of influence factor set, of the preliminary data set includes:

[0018] The preliminary data set is generated based on a normalization mode and the influence law of the at least one influence factor.

[0019] In a possible implementation, the multiple types of influence factor sets include a third type of influence factor set, in a case where the at least one type of influence factor set includes the third type of influence factor set,

[0020] The generating, based on the at least one type of influence factor set, the influence law corresponding to each influence factor, and the data generation mode corresponding to each type of influence factor set, of the preliminary data set includes:

[0021] fitting an influence law of the at least one influence factor into a formula of a bilinear distribution, and generating the preliminary data set based on the formula of the bilinear distribution and the third type of influence factor set.

[0022] In a possible implementation, the plurality of types of influence factor sets comprises a fourth type of influence factor set, and in a case where the at least one type of influence factor set comprises the fourth type of influence factor set,

[0023] The generating the preliminary data set based on the at least one type of influence factor set, the influence law corresponding to each influence factor, and the data generation manner corresponding to each type of influence factor set comprises:

[0024] Determining, based on the fourth type of influence factor set and the fourth type of influence law, a value of an influence factor in the fourth type of influence factor set as a fixed value, to obtain the preliminary data set.

[0025] In a second aspect, the present application provides a pipeline tensile bearing capacity evaluation device, comprising: an acquisition unit, a determination unit and a processing unit;

[0026] The acquisition unit is configured to acquire a plurality of influence factors of a tensile bearing capacity of a pipeline defect.

[0027] The determination unit is configured to determine coupling difficulty information of the plurality of influence factors and influence degree information on the tensile bearing capacity.

[0028] The processing unit is configured to divide the plurality of influence factors into a plurality of types of influence factor sets based on the coupling difficulty information; and the coupling difficulty of influence factor sets of different types is different.

[0029] The determination unit is further configured to determine an influence law corresponding to each influence factor based on finite element simulation and the influence degree information of the plurality of influence factors.

[0030] The processing unit is further configured to generate a preliminary data set according to at least one type of influence factor set and the corresponding influence law through finite element simulation.

[0031] The processing unit is further configured to generate an evaluation model according to machine learning and the preliminary data set, and the evaluation model is used to predict the tensile bearing capacity of a pipeline to be evaluated.

[0032] In a possible implementation, the plurality of influence factors comprises at least one of the following: defect length, defect width, defect depth, yield strength ratio, internal pressure, pipe diameter, and wall thickness.

[0033] In a possible implementation, the processing unit is specifically configured to:

[0034] The preliminary data set is generated based on the at least one type of influence factor set, the influence law corresponding to each influence factor, and the data generation mode corresponding to each type of influence factor set through finite element simulation.

[0035] In a possible implementation, the processing unit is specifically configured to:

[0036] The at least one influence factor in the first type of influence factor set is selected as a variable in turn, the remaining influence factors in the first type of influence factor set are kept unchanged, and the preliminary data set is generated based on machine learning and the influence law of the at least one influence factor.

[0037] In a possible implementation, the processing unit is specifically configured to:

[0038] The preliminary data set is generated based on the normalization mode and the influence law of the at least one influence factor.

[0039] In a possible implementation, the processing unit is specifically configured to:

[0040] The influence law of the at least one influence factor is fitted into a formula of a bilinear distribution, and the preliminary data set is generated based on the formula of the bilinear distribution and the third type of influence factor set.

[0041] In a possible implementation, the processing unit is specifically configured to:

[0042] Based on the fourth type of influence factor set and the fourth type of influence law, the value of the influence factor in the fourth type of influence factor set is determined as a fixed value, and the preliminary data set is obtained.

[0043] In a third aspect, an electronic device is provided, including a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected with the memory through a bus; when the electronic device is running, the processor executes the computer execution instructions stored in the memory, so that the electronic device executes the pipeline stretch carrying capacity evaluation method in the first aspect.

[0044] The electronic device can be a network device, or a part of the network device, for example, a chip system in the network device. The chip system is used to support the network device to implement the functions involved in the first aspect and any possible implementation manner thereof, for example, to acquire, determine, and send the data and / or information involved in the pipeline stretch carrying capacity evaluation method. The chip system includes a chip, and can also include other discrete devices or circuit structures.

[0045] In a fourth aspect, a computer-readable storage medium is provided, which includes computer-executable instructions that, when executed on a computer, cause the computer to perform the pipeline tensile load carrying capacity evaluation method of the first aspect.

[0046] In a fifth aspect, a computer program product is also provided, which includes computer instructions that, when executed on a pipeline tensile load carrying capacity evaluation apparatus, cause the pipeline tensile load carrying capacity evaluation apparatus to perform the pipeline tensile load carrying capacity evaluation method of the first aspect.

[0047] It should be noted that the above computer instructions can be stored on the computer-readable storage medium in whole or in part. The computer-readable storage medium can be packaged together with the processor of the pipeline tensile load carrying capacity evaluation apparatus or packaged separately from the processor of the pipeline tensile load carrying capacity evaluation apparatus, and the embodiments of the present application do not limit this.

[0048] The descriptions of the second aspect, the third aspect, the fourth aspect and the fifth aspect in the present application can refer to the detailed description of the first aspect.

[0049] In the embodiments of the present application, the name of the above-mentioned pipeline tensile load carrying capacity evaluation apparatus does not constitute a limitation on the device or functional module itself, and in actual implementation, these devices or functional modules can appear with other names. For example, the receiving unit can also be referred to as a receiving module, a receiver, etc. As long as the functions of each device or functional module are similar to those of the present application, they belong to the scope of the claims of the present application and equivalent technologies thereof.

[0050] Compared with the prior art, the beneficial effects of the present application are that multiple influence factors of the tensile load carrying capacity of the pipeline for corrosion in the defective pipeline can be obtained. These influence factors will affect the tensile load carrying capacity of the pipeline for corrosion. Then, the coupling difficulty information and the influence degree information of the tensile load carrying capacity of the multiple influence factors can be determined, and the multiple influence factors are divided into multiple type influence factor sets based on the coupling difficulty information. Different types of influence factor sets correspond to different coupling difficulties. Subsequently, the influence law corresponding to each influence factor can be determined based on the finite element simulation and the influence degree information of the multiple influence factors. Subsequently, a preliminary data set can be generated according to at least one type of influence factor set and the corresponding influence law through finite element simulation, and an evaluation model can be generated according to machine learning and the preliminary data set. The evaluation model is used to predict the tensile load carrying capacity of the pipeline to be evaluated; different types of influence factor sets correspond to different prediction modes.

[0051] The plurality of influence factors can be divided into influence factor sets with different coupling difficulties based on the coupling difficulty. A preliminary data set can be generated according to the influence law of the influence factors and the influence factor sets. Then, the tensile bearing capacity of the pipeline to be evaluated can be predicted according to machine learning. In this way, the tensile bearing capacity can be evaluated according to the coupling of the plurality of influence factors, so that the generated evaluation model can be more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0053] Figure 1 is an architectural block diagram of a pipeline tensile bearing capacity evaluation system provided by the present application;

[0054] Figure 2 is a hardware structure schematic diagram of an electronic device 101 provided by the present application;

[0055] Figure 3 is a flowchart of a pipeline tensile bearing capacity evaluation method provided by the present application;

[0056] Figure 4 is a flowchart of another pipeline tensile bearing capacity evaluation method provided by the present application;

[0057] Figure 5 is a flowchart of another pipeline tensile bearing capacity evaluation method provided by the present application;

[0058] Figure 6 is a flowchart of another pipeline tensile bearing capacity evaluation method provided by the present application;

[0059] Figure 7 is a flowchart of another pipeline tensile bearing capacity evaluation method provided by the present application;

[0060] Figure 8 is a flowchart of another pipeline tensile bearing capacity evaluation method provided by the present application;

[0061] Figure 9 is a structural schematic diagram of a pipeline tensile bearing capacity evaluation device provided by the present application. DETAILED DESCRIPTION

[0062] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure can be embodied in various forms without being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0063] It should be noted that the words "exemplary" and "for example" are used herein to mean "an example of." Any embodiment or design scheme described herein as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or design schemes. Rather, the use of the words "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0064] In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second", etc. are used to distinguish the same or similar items with basically the same function and role, and those skilled in the art can understand that the words "first", "second", etc. are not intended to limit the quantity and execution order.

[0065] Metal loss defects often occur in areas where the pipeline coating is damaged. Local thinning of the pipeline due to external corrosion will cause a significant decrease in strain capacity. The traditional method of evaluating and maintaining these metal loss defects is developed under the assumption that the hoop stress is much greater than the axial stress, i.e., the hoop stress is considered to be the main driving force for potential failure. In geological disaster areas, soil movement such as landslides, geological subsidence, frost heaving and thawing will cause the oil and gas pipeline to bear large axial stress / strain. Under such external conditions, the traditional stress-based evaluation method is usually no longer applicable, and strain-based evaluation is needed. It is necessary to study the tensile bearing capacity of large-diameter high-grade pipeline containing metal loss defects under axial strain conditions. Therefore, how to improve the evaluation accuracy of the tensile bearing capacity of the pipeline is a technical problem to be solved at present.

[0066] In this regard, an embodiment of the present application can obtain a plurality of influence factors of the pipeline corrosion tensile bearing capacity in the defective pipeline. These influence factors will affect the tensile bearing capacity of the pipeline for corrosion. Then, the coupling difficulty information and the influence degree information of the tensile bearing capacity of the plurality of influence factors can be determined, and the plurality of influence factors can be divided into a plurality of type influence factor sets based on the coupling difficulty information. Different types of influence factor sets correspond to different coupling difficulties. Then, the influence law corresponding to each influence factor can be determined based on the finite element simulation and the influence degree information of the plurality of influence factors. Subsequently, a preliminary data set can be generated according to at least one type of influence factor set and the corresponding influence law through finite element simulation, and an evaluation model can be generated according to machine learning and the preliminary data set. The evaluation model is used to predict the tensile bearing capacity of the pipeline to be evaluated; different types of influence factor sets correspond to different prediction modes.

[0067] The plurality of influence factors can be divided into influence factor sets with different coupling difficulties based on the coupling difficulty. And a preliminary data set can be generated according to the influence law of the influence factor and the influence factor set. Then, the tensile bearing capacity of the pipeline to be evaluated can be predicted according to machine learning. In this way, the tensile bearing capacity can be evaluated according to the coupling of the plurality of influence factors together, so that the generated evaluation model can be more accurate.

[0068] Figure 1 is an architecture block diagram of a pipeline tensile bearing capacity evaluation system provided by the present application. As shown in Figure 1 , the pipeline tensile bearing capacity evaluation system comprises an electronic device 101 and a data storage device 102.

[0069] The electronic device 101 and the data storage device 102 are communicatively connected. Optionally, the electronic device 101 and the data storage device 102 can be the same device, or can be different devices, which is not limited here.

[0070] In the embodiment of the present application, the data storage device 102 can store data of the defective pipeline, for example, a plurality of influencing factors. The electronic device 101 can obtain the plurality of influencing factors from the data storage device 102. Then, the electronic device 101 can determine coupling difficulty information of the plurality of influencing factors and influence degree information on the tensile bearing capacity, and divide the plurality of influencing factors into a plurality of type of influencing factor sets based on the coupling difficulty information. Different types of influencing factor sets correspond to different coupling difficulties. Then, the electronic device 101 can determine the influence law corresponding to each influencing factor based on the finite element simulation and the influence degree information of the plurality of influencing factors. Subsequently, the electronic device 101 can generate a preliminary data set according to at least one type of influencing factor set and the corresponding influence law through finite element simulation, and generate an evaluation model according to machine learning and the preliminary data set. The evaluation model is used to predict the tensile bearing capacity of the pipeline to be evaluated.

[0071] In a possible implementation, the electronic device 101 can be a terminal, a server, or other electronic device, which is not limited in the embodiment of the present application.

[0072] Optionally, the terminal can be a device that provides voice and / or data connectivity to users, handheld devices with wireless connection capability, or other processing devices connected to a wireless modem. The terminal can communicate with one or more core networks through a radio access network (RAN). The terminal can be a mobile terminal, such as a mobile phone (or called "cellular" phone) and a computer with a mobile terminal, and can also be a portable, pocket, handheld, built-in, or vehicle-mounted mobile device that exchanges voice and / or data with a radio access network, such as a mobile phone, tablet computer, notebook computer, netbook, personal digital assistant (PDA).

[0073] Optionally, the server can be a server in a server cluster (composed of multiple servers), a chip in the server, a system on chip in the server, or implemented through a virtual machine (VM) deployed on a physical machine, which is not limited in the embodiment of the present application.

[0074] Figure 2 FIG. 1 is a schematic diagram of a hardware structure of an electronic device 101 provided by the present application. The electronic device 101 can include a processor 202, which is used to execute application program codes, thereby realizing the pipeline tensile bearing capacity evaluation method in the present application.

[0075] The processor 202 can be a central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the embodiments.

[0076] As shown in Figure 2 The electronic device 101 can further include a memory 203. The memory 203 is configured to store application program codes for implementing the embodiments, and the processor 202 is configured to control the execution of the application program codes.

[0077] The memory 203 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magneto-optical disk, a magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory 203 can exist independently and be connected to the processor 202 through the bus 204. The memory 203 can also be integrated with the processor 202.

[0078] As shown in Figure 2 The electronic device 101 can further include a communication interface 201. The communication interface 201, the processor 202, and the memory 203 can be coupled to each other, for example, through the bus 204. The communication interface 201 is configured to interact with other devices, for example, to support information interaction between multiple modules and other devices.

[0079] It should be noted that the structure of the electronic device 101 shown in Figure 2 The structure of the electronic device 101 shown in the embodiments does not limit the electronic device 101, and the module can include more or fewer components than those shown in the figure, or combine some components, or arrange different components. Figure 2

[0080] In actual implementation, the functions of the electronic device 101 can be implemented by​Figure 2 The processor 202 shown invokes program code in the memory 203 to implement.

[0081] The pipeline tensile bearing capacity evaluation method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0082] As Figure 3 shown, the pipeline tensile bearing capacity evaluation method comprises:

[0083] S301, obtaining a plurality of influence factors of the tensile bearing capacity of the pipeline corrosion in the defective pipeline.

[0084] S302, determining coupling difficulty information of the plurality of influence factors and influence degree information on the tensile bearing capacity.

[0085] S303, dividing the plurality of influence factors into a plurality of type influence factor sets based on the coupling difficulty information through finite element simulation.

[0086] Among them, the coupling difficulty corresponding to influence factors of different types is different.

[0087] S304, determining the influence law corresponding to each influence factor based on the finite element simulation and the influence degree information of the plurality of influence factors.

[0088] S305, generating a preliminary data set according to at least one type of influence factor set and the corresponding influence law.

[0089] S306, generating an evaluation model according to machine learning and the preliminary data set.

[0090] Among them, the evaluation model is used to predict the tensile bearing capacity of the pipeline to be evaluated.

[0091] In the embodiments of the present application, the defective pipeline can be a pipeline containing a volume type defect, for example, the defect volume in the pipeline is greater than a threshold value. Since the defect of the pipeline affects the tensile bearing capacity of the corrosion, the electronic device can obtain data corresponding to a plurality of influence factors of the defect. Among them, the types of the plurality of influence factors can be preset in advance. Then, the electronic device can determine the coupling difficulty information between the plurality of influence factors, and the influence degree information of each influence factor on the tensile bearing capacity. For example, the length, width, depth, etc. of the defect have less correlation, greater coupling difficulty, and greater influence on the bearing capacity (i.e. tensile bearing capacity).

[0092] Afterwards, the electronic device can divide the plurality of influence factors into a plurality of sets of influence factors of different types based on the coupling difficulty information, that is, into sets of influence factors of different coupling difficulties, and each set of influence factors includes one or more influence factors. In this way, the influence factors in the set of influence factors with more difficult coupling difficulty can be coupled by machine learning or the like, and the influence factors in the set of influence factors with easier coupling difficulty can be coupled by a simpler coupling method.

[0093] In addition, the electronic device can determine the influence law corresponding to each influence factor based on the finite element simulation and the influence degree information of each influence factor. For example, a plurality of sets of simulation data are generated by finite element simulation and data corresponding to a plurality of influence factors, and then the influence law corresponding to each influence factor is determined according to the plurality of sets of simulation data, for example, the smaller the pipe wall, the smaller the tensile load capacity.

[0094] Afterwards, the electronic device generates a preliminary data set according to at least one set of influence factors of different types and the corresponding influence law. Subsequently, the electronic device can determine an evaluation model according to the preliminary data set. In this way, when the pipeline is evaluated subsequently, the load capacity of the pipeline to be evaluated can be generated according to the evaluation model.

[0095] In this way, the establishment of the evaluation model is performed by more comprehensive multiple influence factors and the coupling difficulty between the multiple influence factors. Since the coupling difficulty of the influence factors of different types is different, the evaluation model can be generated according to different prediction methods. In this way, the tensile load capacity can be evaluated according to the coupling of the multiple influence factors, so that the generated evaluation model is more accurate.

[0096] For example, modeling of a batch grid model is performed by a finite element analysis software (for example, ABAQUS), the pipe size is 1422 mm, the pipe wall thickness is 32.1 mm, the pipe length is 10000 mm, the defect is located at the midpoint of the pipe length direction, the defect size includes defect length, defect width and defect depth, the modeling range of the defect length is 32.1-720 mm, the modeling range of the defect width is 72-960 mm, and the modeling range of the defect depth is 3-16 mm.

[0097] Material properties are set by the finite element analysis software, and the material is X80 pipeline steel material with four different yield strengths, and the yield strength of the material is 0.83, 0.88, 0.92 and 0.93.

[0098] Boundary conditions are set by the finite element analysis software, internal pressure is applied to the inner surface of the pipe, rigid constraints are applied to one end of the pipe, displacement load is applied to the other end of the pipe, and the displacement load is 60 mm.

[0099] The maximum load criterion was used to determine the tensile bearing capacity failure criterion for defective pipelines. The time-load relationship at the pipeline end was extracted. When the load reached its maximum value, the pipeline was considered to have failed, and the time at this point was defined as the pipeline failure moment. The time-strain curve at a location three times the pipe diameter from the defect size was also extracted, and the strain value corresponding to the pipeline failure moment was defined as the tensile strain capacity.

[0100] Based on the above pre-processing settings and mesh modeling, the other influencing factors are kept constant, and the three sizes of volumetric defects are used as variables. 500 sets of finite element simulations are performed to analyze the influence of defect size and form a preliminary data set.

[0101] It should be noted that the order of S303 and S304 is not limited.

[0102] In some embodiments, combined Figure 3 ,like Figure 4 As shown, in the above S305, generating a preliminary data set according to at least one type of influencing factor set and the corresponding influencing rules specifically includes:

[0103] S401 . Generate a preliminary data set through finite element simulation based on at least one type of influencing factor set, an influencing law corresponding to each influencing factor, and a data generation method corresponding to each type of influencing factor set.

[0104] Different sets of influencing factors correspond to different data generation methods. For example, sets of influencing factors that are difficult to couple can be coupled using data generation methods such as machine learning. This allows multiple difficult-to-couple influencing factors to be coupled together to create an evaluation model, thereby improving evaluation accuracy.

[0105] In some other embodiments, combined Figure 4 ,like Figure 5 As shown, the multiple types of influencing factor sets include a first type of influencing factor set, and the coupling difficulty of the first type of influencing factor set is greater than the coupling difficulty of the other types of influencing factor sets; when at least one type of influencing factor set includes the first type of influencing factor set, in the above S401, generating the preliminary data set based on the at least one type of influencing factor set, the influence law corresponding to each influencing factor, and the data generation method corresponding to each type of influencing factor set specifically includes:

[0106] S501. Select at least one influencing factor in the first type of influencing factor set as a variable in turn, keep the other influencing factors in the first type of influencing factor set unchanged, and generate a preliminary data set based on machine learning and the influence rule of at least one influencing factor.

[0107] The first type of influencing factor set is the most difficult to couple among the multiple types of influencing factor sets. For example, the first type of influencing factor set may include defect length, defect width, and defect depth. Electronic devices can use defect length as a variable, while keeping defect width and defect depth constant. In this way, finite element simulation can generate multiple data sets with varying defect lengths. Similarly, defect width or defect depth can be used as a variable to generate corresponding data, thus obtaining a preliminary data set.

[0108] Furthermore, due to the difficulty of coupling defect length, depth, and width, traditional coupling methods are incapable of achieving this. Therefore, machine learning can be used to couple the data corresponding to these three influencing factors. This results in a richer preliminary dataset and stronger correlations between the various influencing factors, thereby improving assessment accuracy.

[0109] In some embodiments, combined Figure 4 ,like Figure 6 As shown, the multiple types of influencing factor sets include the second type of influencing factor set. In the case where at least one type of influencing factor set includes the second type of influencing factor set, in the above S401, generating the preliminary data set based on the at least one type of influencing factor set, the influencing rule corresponding to each influencing factor, and the data generation method corresponding to each type of influencing factor set specifically includes:

[0110] S601: Generate a preliminary data set based on a normalization method and an influence rule of at least one influencing factor.

[0111] The coupling difficulty in the second type of influencing factor set is lower than that of the first type of influencing factors. For example, the second type of influencing factor set may include yield ratio, pipe diameter, wall thickness, and internal pressure. Since the coupling difficulty of the influencing factors in the second type of influencing factor set meets the current coupling, that is, the formulated coupling. Therefore, the electronic device can keep the yield ratio and internal pressure unchanged, and use the pipe diameter and wall thickness as variables to generate a preliminary data set using a normalized method. In this way, the preliminary data set can contain data corresponding to both the first type of influencing factor set and the second type of influencing factor set, thereby making the preliminary data set richer and the resulting evaluation model more accurate.

[0112] For example, keeping the yield ratio, pipe diameter, wall thickness and internal pressure unchanged, finite element numerical simulation studies are conducted on the specifications of 1422mm pipe diameter-32.1mm wall thickness, 1219mm-pipe diameter-18.4mm wall thickness and 1422mm pipe diameter-17.8mm wall thickness respectively. After the numerical simulation is completed, post-processing analysis is performed. According to the maximum load criterion, a node at a 90° position of the pipeline that is more than three times the pipe diameter away from the defect size is selected, and the strain corresponding to the maximum failure moment of the node is extracted. The strain is defined as the tensile strain capacity, and the influence of pipe diameter and wall thickness is analyzed. The normalization method is used to couple the two influencing factors of pipe diameter and wall thickness into the generation process of the evaluation model.

[0113] In some embodiments, combined Figure 4 ,like Figure 7 As shown, the multiple types of influencing factor sets include a third type of influencing factor set. When at least one type of influencing factor set includes the third type of influencing factor set, in the above S401, generating a preliminary data set based on the at least one type of influencing factor set, the influencing rule corresponding to each influencing factor, and the data generation method corresponding to each type of influencing factor set specifically includes:

[0114] S701: Fit the influence rule of at least one influencing factor into a bilinear distribution formula, and generate a preliminary data set based on the bilinear distribution formula and a set of influencing factors of the third type.

[0115] The coupling difficulty of the third type of influencing factor set is lower than that of the first type of influencing factors. For example, the third type of influencing factor set may include yield strength ratio, pipe diameter, wall thickness, and internal pressure. Since the coupling difficulty of the influencing factors in the third type of influencing factor set meets the current coupling, that is, the formulated coupling, the electronic device can keep the defect size, internal pressure, pipe diameter, and wall thickness unchanged, and use the yield strength ratio as a variable to generate a preliminary data set in a normalized manner. In this way, the preliminary data set can contain data corresponding to both the first type of influencing factor set and the third type of influencing factor set, thereby enriching the preliminary data set and making the resulting evaluation model more accurate.

[0116] For example, keeping the defect size, pipe diameter, wall thickness, and internal pressure unchanged, the effects of the material properties of X80 pipeline steel with four different yield ratios on the tensile bearing capacity are studied in the numerical simulation of finite element analysis software. The yield ratios of the materials are 0.83, 0.88, 0.92, and 0.93, respectively, and finite element simulation calculations are carried out. After the numerical simulation is completed, post-processing analysis is performed. According to the maximum stress criterion, a node at a position 90° of the pipeline that is more than three times the pipe diameter away from the defect size is selected, and the strain corresponding to the moment of failure of the node is extracted. The strain is defined as the tensile strain capacity. The influence of the material yield ratio on the tensile bearing capacity is analyzed, the law is summarized, and a bilinear distribution formula is fitted, thereby coupling the yield ratio into the determination process of the evaluation model.

[0117] In some embodiments, combined Figure 4 ,like Figure 8 As shown, the multiple types of influencing factor sets include a fourth type of influencing factor set. When at least one type of influencing factor set includes the fourth type of influencing factor set, in the above S401, generating a preliminary data set based on the at least one type of influencing factor set, the influencing rule corresponding to each influencing factor, and the data generation method corresponding to each type of influencing factor set includes:

[0118] S801 : Based on the fourth type of influencing factor set and the fourth type of influencing rules, determine the values ​​of the influencing factors in the fourth type of influencing factor set as fixed values ​​to obtain a preliminary data set.

[0119] The fourth type of influencing factor set presents a relatively low level of coupling difficulty, including, for example, internal pressure. The electronic device can maintain the defect size, pipe diameter, wall thickness, and yield strength ratio constant, perform finite element simulations, and analyze the effects of internal pressure on tensile bearing capacity. Following the numerical simulation, post-processing analysis is performed. Based on the maximum load criterion, a node at a 90-degree angle to the pipe, at least three pipe diameters away from the defect, is selected. The strain corresponding to the failure moment at this node is extracted, and this strain is defined as the tensile strain capacity. The rules are summarized, and the boundary values ​​under the operating conditions are determined. The internal pressure is fixed, thus obtaining a preliminary data set.

[0120] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily appreciate that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0121] In the embodiments of the present application, the pipeline tensile bearing capacity assessment device can be divided into functional modules based on the above-described method examples. For example, each functional module can be divided into corresponding functional modules, or two or more functions can be integrated into a single processing module. The above-mentioned integrated modules can be implemented as hardware or software functional modules. Optionally, the module division in the embodiments of the present application is illustrative and merely represents a logical functional division. In actual implementation, other division methods may be used.

[0122] like Figure 9 , which is a schematic structural diagram of a pipeline tensile bearing capacity evaluation device provided by the present invention. Figure 9 The pipeline tensile bearing capacity evaluation device shown includes: an acquisition unit 901 , a determination unit 902 , and a processing unit 903 .

[0123] An acquisition unit 901 is used to acquire multiple factors affecting the tensile bearing capacity of a defective pipeline for pipeline corrosion;

[0124] A determining unit 902 is configured to determine coupling difficulty information of the plurality of influencing factors and information on the degree of influence on the tensile bearing capacity;

[0125] A processing unit 903 is configured to classify the plurality of influencing factors into a plurality of types of influencing factor sets based on the coupling difficulty information; different types of influencing factor sets correspond to different coupling difficulties;

[0126] The determining unit 902 is further configured to determine an influence rule corresponding to each influencing factor based on the finite element simulation and the influence degree information of the multiple influencing factors;

[0127] The processing unit 903 is further configured to generate a preliminary data set according to at least one type of influencing factor set and corresponding influencing rules through finite element simulation;

[0128] The processing unit 903 is further configured to generate an evaluation model according to machine learning and the preliminary data set, the evaluation model being used to predict the tensile bearing capacity of a pipeline to be evaluated.

[0129] In a possible implementation, the plurality of influence factors include at least one of the following: defect length, defect width, defect depth, yield strength ratio, internal pressure, pipe diameter, and wall thickness.

[0130] In a possible implementation, the processing unit 903 is specifically configured to:

[0131] The preliminary data set is generated based on the at least one type of influence factor set, the influence law corresponding to each influence factor, and the data generation mode corresponding to each type of influence factor set through finite element simulation.

[0132] In a possible implementation, the processing unit 903 is specifically configured to:

[0133] At least one influence factor in the first type of influence factor set is selected as a variable in turn, and the remaining influence factors in the first type of influence factor set are kept unchanged, and the preliminary data set is generated based on machine learning and the influence law of the at least one influence factor.

[0134] In a possible implementation, the processing unit 903 is specifically configured to:

[0135] The preliminary data set is generated based on the normalization mode and the influence law of the at least one influence factor.

[0136] In a possible implementation, the processing unit 903 is specifically configured to:

[0137] The influence law of the at least one influence factor is fitted into a formula of a bilinear distribution, and the preliminary data set is generated based on the formula of the bilinear distribution and the third type of influence factor set.

[0138] In a possible implementation, the processing unit 903 is specifically configured to:

[0139] Based on the fourth type of influence factor set and the fourth type of influence law, the value of an influence factor in the fourth type of influence factor set is determined as a fixed value, and the preliminary data set is obtained.

[0140] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application but not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, and these modifications or equivalent replacements should not make the technical solutions deviate from the spirit and scope of the present application.

[0141] The system provided by the above examples is only illustrated by the division of the above functional modules. In actual application, the above functions can be completed by different functional modules according to needs, that is, the modules or steps in the embodiments of the present application are further decomposed or combined, for example, the modules of the above examples can be combined into one module, or can be further split into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present application are only for distinguishing the respective modules and steps, and should not be considered as improper limitation of the present application.

[0142] Those skilled in the art should be able to understand that the modules and method steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of both. The programs corresponding to the software modules and method steps can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a register, a hard disk, a removable disk, a CD-ROM or any other form of storage medium known in the art. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been described in the above description in general terms. Whether the functions are performed by electronic hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

Claims

1. A method of evaluating the tensile load carrying capacity of a pipe, characterized by, include: Obtain multiple factors affecting the tensile bearing capacity of pipeline corrosion in defective pipelines; Determining coupling difficulty information of the multiple influencing factors and information on the degree of influence on the tensile bearing capacity; Dividing the plurality of influencing factors into a plurality of types of influencing factor sets based on the coupling difficulty information; different types of influencing factor sets correspond to different coupling difficulties; Based on finite element simulation and the influence degree information of multiple influencing factors, determine the influence law corresponding to each influencing factor; generating a preliminary data set through finite element simulation according to at least one type of influencing factor set, corresponding influencing rules, and a data generation method corresponding to each type of influencing factor set; generating an evaluation model based on machine learning and the preliminary data set, wherein the evaluation model is used to predict the tensile bearing capacity of the pipeline to be evaluated; The at least one type of influencing factor set includes a first type of influencing factor set and other types of influencing factor sets, the coupling difficulty of the first type of influencing factor set is greater than the coupling difficulty of the other types of influencing factor sets, and the other types of influencing factor sets include at least one of the following: a second type of influencing factor set, a third type of influencing factor set, and a fourth type of influencing factor set; The data generation method corresponding to the first type of influencing factor set includes: selecting at least one influencing factor in the first type of influencing factor set as a variable in turn, keeping the other influencing factors in the first type of influencing factor set unchanged, and generating the preliminary data set based on machine learning and the influence law of the at least one influencing factor; The data generation method corresponding to the second type of influencing factor set includes: generating the preliminary data set based on a normalization method and an influencing rule of at least one influencing factor of the second type of influencing factor set; The data generation method corresponding to the third type of influencing factor set includes: fitting the influence rule of at least one influencing factor of the third type of influencing factor set to a bilinear distribution formula, and generating the preliminary data set based on the bilinear distribution formula and the third type of influencing factor set; The data generation method corresponding to the fourth type of influencing factor set includes: based on the fourth type of influencing factor set and the fourth type of influencing rules, determining the values ​​of the influencing factors in the fourth type of influencing factor set as fixed values ​​to obtain the preliminary data set.

2. The method of claim 1, wherein, The multiple influencing factors include at least one of the following: defect length, defect width, defect depth, yield strength ratio, internal pressure, pipe diameter, and wall thickness.

3. An electronic device, comprising: include: memory and processor; Memory and processor coupling; The memory is used to store instructions executable by the processor; When the processor executes the instructions, the method according to any one of claims 1 to 2 is performed.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 2.

5. A computer program product, characterised in that, The computer program product comprises computer program instructions which, when executed by a processor, implement the method according to any one of claims 1-2.

Images