Prediction method for layered strain of composite pipe interface and related equipment

Abstract

The invention relates to the field of machine learning, and discloses a composite pipe interface layering strain prediction method and related equipment, and the method comprises the steps: obtaining geometric parameters, material parameters and contact surface parameters of a base layer and a covering layer in a composite pipe; and inputting the geometric parameters, the material parameters and the contact surface parameters into a pre-trained prediction model to obtain layered strain of the base layer and the covering layer. Therefore, based on the geometrical parameters, material parameters and contact surface parameters of the base layer and the coating layer, the conditions of the base layer and the coating layer in the composite pipe can be comprehensively reflected, and accurate data support is provided for the prediction method. Based on the pre-trained prediction model, the layered strain of the composite pipe interface is accurately predicted, and reference is provided for composite pipe selection under different engineering conditions.

Description

Technical Field

[0001] The present application relates to the field of machine learning, and more specifically, to a method for predicting delamination strain at the interface of a composite pipe and related equipment. Background Art

[0002] During offshore oil and gas production, due to the limitations of underwater production system processing technology, oil and gas often contain high concentrations of corrosive media, resulting in severe corrosion failure risks for oil and gas pipelines. Against this backdrop, offshore metallurgical composite pipes are widely used due to their unique structural advantages. However, when subjected to complex and variable plastic loading processes, interlayer delamination and delamination become key factors affecting the service life and safety of composite pipes.

[0003] However, current methods for predicting delamination strain at the interface of marine metallurgical composite pipes are mostly based on idealized binding constraint models, which cannot truly reflect the complex separation behavior of the composite pipe interface under actual loading conditions. Therefore, it is urgent to develop a method that can accurately predict the delamination strain at the interface of marine metallurgical composite pipes. Summary of the Invention

[0004] In view of this, the present application proposes a method for predicting the delamination strain at the interface of a composite pipe and related equipment, aiming to solve the problem that the current technology cannot accurately predict the delamination strain at the interface of a marine metallurgical composite pipe.

[0005] In a first aspect, the present application provides a method for predicting the delamination strain of the interface of a composite pipe, comprising: obtaining the geometric parameters, material parameters and contact surface parameters of the base layer and the cladding in the composite pipe; inputting the geometric parameters, material parameters and contact surface parameters into a pre-trained prediction model to obtain the delamination strain of the base layer and the cladding.

[0006] In some embodiments, the above method further includes: obtaining first geometric parameters, first material parameters, and first contact surface parameters of the base layer and the cladding layer in the first composite tube; constructing a finite element model based on the first geometric parameters, the first material parameters, and the first contact surface parameters; and performing calculations based on the finite element model to obtain the delamination strains of the base layer and the cladding layer in the first composite tube.

[0007] In some embodiments, a finite element model is constructed based on the first geometric parameter, the first material parameter and the first contact surface parameter, including: determining the node information of the finite element model based on the first geometric parameter, the node information including spatial coordinate information; modeling the base layer entity unit and the coating entity unit based on the node information and the first material parameter; modeling the cohesion unit based on the first contact surface parameter; the cohesion unit is used to simulate the contact surface between the base layer and the coating.

[0008] In some embodiments, calculations are performed based on a finite element model to obtain delamination strains of the base layer and the cladding layer in the first composite tube, including: setting boundary conditions and stress loads of the finite element model to obtain multiple finite element calculation files; the stress load represents the axial tensile stress applied to the finite element model; calculating the finite element calculation files to obtain multiple interface separation distances; and determining the delamination strain based on the multiple interface separation distances.

[0009] In some embodiments, the geometric parameters include the base layer thickness and the coating thickness; the material parameters include at least one of the base layer elastic modulus, the base layer nominal yield strength, the base layer strain hardening index, the coating elastic modulus, the coating nominal yield strength and the coating strain hardening index; the contact surface parameters include at least one of the normal stiffness, normal strength, normal fracture energy, tangential stiffness, tangential strength and tangential fracture energy of the interlayer bonding interface.

[0010] In a second aspect, a model training method is provided, comprising: obtaining training data, the training data comprising: geometric parameters, material parameters, contact surface parameters of a base layer and a cladding layer in a plurality of composite tubes, and a first layered strain corresponding to the composite tube; inputting the training data into an initial model to obtain a second layered strain output by the initial model; and adjusting the parameters of the initial model based on the first layered strain and the second layered strain.

[0011] In a third aspect, a device for predicting the delamination strain of a composite pipe interface is provided, comprising: an acquisition unit and a processing unit; the acquisition unit is used to obtain geometric parameters, material parameters, and contact surface parameters of a base layer and a cladding layer in the composite pipe; and the processing unit is used to input the geometric parameters, material parameters, and contact surface parameters into a pre-trained prediction model to obtain the delamination strain of the base layer and the cladding layer.

[0012] In a fourth aspect, an electronic device is provided, comprising a memory and a processor; the memory is used to store computer-executable instructions, and the processor is connected to the memory via a bus; when the electronic device is running, the processor executes the computer-executable instructions stored in the memory, so that the electronic device executes any one of the methods provided in the first aspect or the second aspect.

[0013] In a fifth aspect, a computer-readable storage medium is provided, which includes computer-executable instructions. When the computer-executable instructions are run on a computer, the computer is caused to execute any one of the methods provided in the first aspect or the second aspect.

[0014] In a sixth aspect, a computer program product is provided, which includes: computer execution instructions, which, when the computer execution instructions are run on an electronic device, enable the electronic device to execute any one of the methods provided in the first or second aspect above.

[0015] It should be noted that the above-mentioned computer-executable instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the electronic device or separately from the processor of the electronic device, and this embodiment of the application is not limited to this.

[0016] The description of the third, fourth, fifth and sixth aspects of this application may refer to the detailed description of the first or second aspect.

[0017] In the embodiments of this application, the name of the device for predicting composite pipe interface delamination strain does not limit the device or function itself. In actual implementation, these devices or functional modules may be referred to by other names. For example, the processing unit may also be referred to as a processing module, a processor, etc. As long as the functions of each device or functional module are similar to those of this application, they are within the scope of the claims of this application and their equivalents.

[0018] This application obtains the geometric parameters, material parameters, and contact surface parameters of the base layer and cladding in the composite pipe, and then inputs these geometric parameters, material parameters, and contact surface parameters into a pre-trained prediction model to obtain the delamination strain of the base layer and cladding. In this way, based on the geometric parameters, material parameters, and contact surface parameters of the base layer and cladding, the conditions of the base layer and cladding in the composite pipe can be comprehensively reflected, providing accurate data support for the prediction method. Based on the pre-trained prediction model, the delamination strain of the composite pipe interface is accurately predicted, providing a reference for the selection of composite pipes in different engineering situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application;

[0021] Figure 2 A schematic flow chart of a method for predicting delamination strain at a composite pipe interface provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the delamination phenomenon between the base layer and the cladding layer during a tensile test of a composite pipe provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of simulating the delamination phenomenon of the base layer and the covering layer by a finite element model provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of a process for calculating layered strain using a finite element model provided in an embodiment of the present application;

[0025] Figure 6 A flowchart of a model training method provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of a neural network model provided in an embodiment of the present application;

[0027] Figure 8 A schematic structural diagram of a device for predicting interfacial delamination strain of a composite pipe provided in an embodiment of the present application;

[0028] Figure 9 A schematic diagram of the structure of a model training device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0030] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "back," "inner," "outer," and the like, indicating directions or positional relationships, are based on the directions or relative positional relationships shown in the accompanying drawings and are intended solely to facilitate the description of this application and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific direction, be constructed, or operate in a specific direction. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned directionality descriptions may be flexibly set in actual application, provided that the relative positional relationships shown in the accompanying drawings are met.

[0031] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0032] In the embodiments of the present application, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of other identical elements in the process, article, or device comprising the element.

[0033] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0034] In the field of offshore oil and gas extraction, due to the limitations of underwater production system processing technology, oil and gas often contain high concentrations of corrosive media such as H2S and CO2, which poses a serious risk of corrosion failure in oil and gas pipelines. Against this backdrop, marine metallurgical composite pipes are widely used due to their unique structural advantages. The base material of such pipes is typically made of high-strength and relatively cost-effective materials, such as X65 steel, to ensure the overall structural strength and load-bearing capacity of the pipe. The cladding is constructed of materials with excellent corrosion resistance, such as 625 alloy. This combination of X65 steel and 625 alloy is a widely used marine metallurgical composite pipe, providing an economical and efficient solution to the corrosion problem of submarine pipelines.

[0035] However, the interfacial properties of marine metallurgical composite pipes significantly impact the stability and durability of their overall structure. Especially when subjected to complex and variable plastic loading conditions, delamination and delamination at the interlayer interface become key factors affecting the service life and safety of the composite pipes. Despite the unique advantages of marine metallurgical composite pipes in deep-sea oil and gas production, research on their interfacial mechanical properties is relatively scarce, especially for marine metallurgical composite pipes made of such specialized materials.

[0036] During pipeline design and analysis, interfaces are often simplified into an idealized bound constraint model, assuming that the base and cladding maintain identical deformation under all conditions. While this simplified approach reduces computational complexity to a certain extent, it fails to truly reflect the complex separation behavior of interfaces under actual loading conditions. More importantly, it ignores the specific effects of various conditions, such as the base and cladding material ratio, on interface performance.

[0037] With the growing demand for composite pipes in harsh deepwater conditions, in-depth research into the true separation behavior and mechanical mechanisms of marine metallurgical composite pipe interfaces has become increasingly urgent. Delamination strain, a key indicator for evaluating the rationality of pipeline design, warrants significant attention and consideration.

[0038] Therefore, a method for predicting the interface delamination strain of composite pipes is urgently needed to overcome the limitations of existing technologies. This method accurately predicts the interface delamination strain of marine metallurgical composite pipes and provides a scientific basis and technical support for the design, manufacturing and safety assessment of actual composite pipes.

[0039] In this case, an embodiment of the present application provides a method for predicting the delamination strain of the composite pipe interface, including: obtaining geometric parameters, material parameters and contact surface parameters of the base layer and the coating in the composite pipe; inputting the geometric parameters, material parameters and contact surface parameters into a pre-trained prediction model to obtain the delamination strain of the base layer and the coating.

[0040] As can be seen from the above, this application obtains the geometric parameters, material parameters, and contact surface parameters of the base layer and cladding in the composite pipe, and then inputs the geometric parameters, material parameters, and contact surface parameters into a pre-trained prediction model to obtain the delamination strain of the base layer and cladding. In this way, based on the geometric parameters, material parameters, and contact surface parameters of the base layer and cladding, the situation of the base layer and cladding in the composite pipe can be comprehensively reflected, providing accurate data support for the prediction method. Based on the pre-trained prediction model, the delamination strain of the composite pipe interface is accurately predicted, and a reference is provided for the selection of composite pipes in different engineering situations.

[0041] like Figure 1 FIG. 1 is a schematic diagram of a hardware structure of an electronic device provided in an embodiment of the present application, wherein the electronic device includes a processor 11, a memory 12, a communication interface 13, and a bus 14. The processor 11, the memory 12, and the communication interface 13 may be connected via the bus 14.

[0042] The processor 11 is the control center of the electronic device and can be a single processor or a collective term for multiple processing elements. For example, the processor 11 can be a general-purpose central processing unit (CPU) or other general-purpose processor. The general-purpose processor can be a microprocessor or any conventional processor.

[0043] As an embodiment, the processor 11 may include one or more CPUs, such as Figure 1 CPU 0 and CPU 1 are shown in Figure 1.

[0044] The memory 12 may 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 magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0045] In one possible implementation, memory 12 may exist independently of processor 11 and may be connected to processor 11 via bus 14 to store instructions or program code. When processor 11 calls and executes the instructions or program code stored in memory 12, the method for predicting composite pipe interface delamination strain provided in the following embodiments of this application can be implemented.

[0046] In another possible implementation, the memory 12 may also be integrated with the processor 11 .

[0047] The communication interface 13 is used to connect the electronic device to other devices via a communication network, which may be Ethernet, wireless access network, wireless local area network (WLAN), etc. The communication interface 13 may include a receiving unit for receiving data and a sending unit for sending data.

[0048] The bus 14 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, Figure 1 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0049] It should be pointed out that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, except Figure 1In addition to the components shown, the electronic device may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0050] The following is a detailed description of the method for predicting the delamination strain at the composite pipe interface provided by the embodiments of the present application in conjunction with the accompanying drawings.

[0051] Figure 2 The flowchart of a method for predicting delamination strain at a composite pipe interface is shown according to an exemplary embodiment. Exemplarily, the prediction method can be applied to electronic equipment. The method steps include the following S201-S202.

[0052] S201. Obtain geometric parameters, material parameters, and contact surface parameters of the base layer and the cladding layer in the composite pipe.

[0053] For example, the base material in the composite pipe may be X65 steel, and the cladding material may be 625 alloy.

[0054] In one possible implementation, the geometric parameters include the base layer thickness and the coating layer thickness. The material parameters include at least one of the base layer elastic modulus, base layer nominal yield strength, base layer strain hardening exponent, coating layer elastic modulus, coating layer nominal yield strength, and coating layer strain hardening exponent. The contact surface parameters include at least one of the interlayer bonding interface normal stiffness, normal strength, normal fracture energy, tangential stiffness, tangential strength, and tangential fracture energy.

[0055] In some embodiments, the base layer thickness in the geometric parameters is determined based on the pressure, flow rate, and diameter of the medium transported in the composite pipe, while the coating thickness must meet the corrosion protection requirements of the composite pipe. The material parameters of the base layer and coating in the composite pipe are determined based on the materials of the base layer and coating themselves. The contact surface parameters can be determined by shear testing or peel testing to determine the interfacial bonding strength between the base layer and coating.

[0056] S202: Input the geometric parameters, material parameters, and contact surface parameters into a pre-trained prediction model to obtain the delamination strain of the base layer and the cover layer.

[0057] Among them, the delamination strain of the base layer and the cladding is used to characterize the debonding phenomenon at the interface between the base layer and the cladding in the composite pipe caused by interlayer residual stress, guiding defects or external loads.

[0058] It should be noted that the prediction model is pre-trained using a neural network to predict the delamination strain at the composite pipe interface. The specific training process is described below and will not be elaborated here.

[0059] In some embodiments, after obtaining the geometric parameters, material parameters, and contact surface parameters, these parameters are input into the prediction model to obtain the output parameters of the prediction model. The output parameters are the delamination strain of the base layer and the coating, that is, the prediction result of the delamination strain of the composite pipe interface.

[0060] As shown above, after obtaining the geometric, material, and interface parameters of the base and cladding layers in a composite pipe, these parameters are input into a pre-trained prediction model to determine the delamination strains of the base and cladding layers. This comprehensive understanding of the base and cladding layers in the composite pipe, based on their geometric, material, and interface parameters, provides accurate data support for the prediction method. Based on the pre-trained prediction model, the delamination strains at the composite pipe interface are accurately predicted, providing a reference for selecting composite pipes for different engineering scenarios.

[0061] In the embodiment of the present application, when the composite pipe is subjected to a tensile test, delamination may occur between the base layer and the coating layer in the composite pipe. Figure 3 As shown, when the composite pipe is subjected to a tensile test, delamination will occur between the base layer and the cladding layer of the composite pipe after being subjected to a tensile force.

[0062] To simulate this stratification phenomenon, Figure 4 As shown, the present application proposes a method for simulating the delamination phenomenon between the base layer and the cladding layer by using a finite element model, wherein different regions represent forces of different magnitudes or directions on the composite pipe.

[0063] like Figure 5 , which is a schematic diagram of a process for calculating layered strain using a finite element model according to an exemplary embodiment, the method comprises the following steps S501 - S503 .

[0064] S501: Obtain first geometric parameters, first material parameters, and first contact surface parameters of a base layer and a cladding layer in a first composite tube.

[0065] The first geometric parameters include the thickness of the base layer and the thickness of the cladding layer in the first composite tube. The first material parameters include at least one of the elastic modulus, nominal yield strength, strain hardening exponent of the base layer, elastic modulus, nominal yield strength, and strain hardening exponent of the cladding layer of the first composite tube. The first contact interface parameters include at least one of the normal stiffness, normal strength, normal fracture energy, tangential stiffness, tangential strength, and tangential fracture energy of the interlayer bonding interface between the base layer and the cladding layer in the first composite tube.

[0066] S502: Construct a finite element model based on the first geometric parameter, the first material parameter, and the first contact surface parameter.

[0067] The finite element model is used to simulate the actual interface characteristics between the base layer and the cladding layer in the first composite tube and to simulate the delamination phenomenon between the base layer and the cladding layer under load.

[0068] In one possible implementation, the node information of the finite element model is determined based on the first geometric parameter, and the node information includes spatial coordinate information; based on the node information and the first material parameter, the base layer entity unit and the coating entity unit are modeled; based on the first contact surface parameter, the cohesion unit is modeled; the cohesion unit is used to simulate the contact surface between the base layer and the coating.

[0069] In some embodiments, node numbers and spatial coordinate information are generated according to the first geometric parameters of the first composite tube, thereby constructing nodes of the finite element model.

[0070] Specifically, the finite element model's base and cladding solid elements are constructed based on the node information of the generated finite element model and the first material parameters of the first composite tube. The stress-strain relationship between the base and cladding materials is determined by the Ramberg-Osgood (RO) relationship. By adjusting parameters such as the yield strength and hardening exponent of the base and cladding materials, a large dataset is obtained.

[0071] In some embodiments, the parameters specifically related to describing the stress-strain relationship curve include: elastic modulus of the base material, nominal yield strength of the base, strain hardening index of the base, elastic modulus of the coating material, nominal yield strength of the coating, and strain hardening index of the coating. The stress-strain relationship satisfies the following formula:

[0072]

[0073] Among them, ε represents true strain, E represents elastic modulus, σ represents true stress, and σ y represents the nominal yield strength and n represents the strain hardening exponent.

[0074] In some embodiments, a cohesive zone model (CZM) is used to model a cohesive force unit based on the first contact surface parameter of the first composite tube, wherein the cohesive force unit is used to simulate the contact surface between the base layer and the cladding layer.

[0075] Specifically, a cohesive force unit was embedded into the finite element model of the composite pipe to simulate the progressive debonding process at the contact interface. Combined with tensile shear tests and normal peel tests, the model parameters were calibrated to ensure that the simulation results were consistent with the actual mechanical behavior. Key parameters of the cohesive force model involved include normal stiffness, normal strength, normal fracture energy, tangential stiffness, tangential strength, and tangential fracture energy.

[0076] S503 : Based on calculation of the finite element model, obtain the delamination strains of the base layer and the cladding layer in the first composite pipe.

[0077] In one possible implementation, boundary conditions and stress loads of a finite element model are set to obtain multiple finite element calculation files; the stress load represents the axial tensile stress applied to the finite element model; the finite element calculation files are calculated to obtain multiple interface separation distances; and the delamination strain is determined based on the multiple interface separation distances.

[0078] In some embodiments, stress loads are applied to the finite element model based on actual operating conditions and applied to the model's boundary nodes. Simultaneously, the displacement degrees of freedom at the end of the first composite tube or at a specific interface within the finite element model are restricted to ensure the model's mechanical equilibrium. During the stress application process, the relative displacement distance of the interface nodes is monitored in real time, and the interface separation distance is determined through post-processing. When the interface separation distance exceeds a preset threshold, delamination of the first composite tube is determined, and the corresponding strain value of the first composite tube at this time is extracted as the delamination strain.

[0079] As shown above, by obtaining the first geometric parameters, first material parameters, and first contact surface parameters of the base layer and cladding layer in the first composite tube, constructing a finite element model based on the first geometric parameters, first material parameters, and first contact surface parameters, and calculating the delamination strain of the base layer and cladding layer in the first composite tube based on the finite element model, the delamination strain between the base layer and cladding layer in the first composite tube can be accurately simulated by constructing a finite element model under load.

[0080] In some embodiments, a finite element model is used to simulate the delamination of the base layer and cladding layer in a composite pipe, thereby obtaining the delamination strains of the base layer and cladding layer. By adjusting parameters such as base layer thickness and cladding thickness, the delamination strains calculated by the finite element model under different parameters are repeatedly obtained to generate multiple data sets. The data sets include the geometric parameters, material parameters, and contact surface parameters of the base layer and cladding layer in the composite pipe, as well as the corresponding delamination strains of the composite pipe.

[0081] like Figure 6 , which is a flow chart of a model training method provided according to an exemplary embodiment, wherein the method steps include S601 - S603 .

[0082] S601 : Acquire training data, where the training data includes: geometric parameters, material parameters, contact surface parameters of a base layer and a cladding layer in a plurality of composite tubes, and first layered strain corresponding to the composite tubes.

[0083] The first layered strain is the layered strain of the base layer and the cladding layer corresponding to the composite pipe obtained through the finite element model.

[0084] In some embodiments, a large number of calculation files and their corresponding layered strain values ​​are used as training data for the model. A certain percentage of samples are used as training data, and the remaining samples are used as test data to train and validate the model. For example, 85% of the training data can be used as the training data set, and 15% of the samples can be used as the test data set.

[0085] In some embodiments, the model input parameters include geometric parameters, material parameters, and interface parameters of the base layer and cladding layer in the composite pipe. Specifically, the base layer thickness, base layer elastic modulus, base layer nominal yield strength, base layer strain hardening exponent, cladding layer thickness, cladding layer elastic modulus, cladding layer nominal yield strength, cladding layer strain hardening exponent, interlayer interface normal stiffness, normal strength, normal fracture energy, tangential stiffness, tangential strength, and tangential fracture energy.

[0086] S602: Input the training data into the initial model to obtain the second layer strain output by the initial model.

[0087] The second delamination strain is the predicted value of the delamination strain of the base layer and the cover layer obtained by the initial model through calculation of the training data.

[0088] In some embodiments, geometric parameters, material parameters, and contact surface parameters of the base layer and the cladding layer in the plurality of composite tubes in the training data are input into the initial model to calculate the second layered strains corresponding to the plurality of composite tubes.

[0089] In some embodiments, the initial model is a neural network model, such as Figure 7 As shown in Figure 1, the neural network consists of an input layer, an output layer, and a hidden layer. The input layer receives the raw input parameters and passes them to the hidden layer. The hidden layer processes the input parameters using neurons and activation functions to capture the characteristics of the data. The output layer outputs the neural network's final prediction results.

[0090] For example, the number of input layer nodes is the number of input parameters, the number of output layer nodes is 1, the number of hidden layers is set to 2, and the initial values ​​of the connection weights, hidden layer bias, hidden layer threshold, and output layer threshold are all set to random numbers. The activation function uses the Sigmoid function, the optimizer uses the Adam optimizer, the maximum number of iterations is 3000, the learning rate is 0.1, and the training target minimum error is set to 0.001.

[0091] S603: Adjust the parameters of the initial model based on the first layer strain and the second layer strain.

[0092] In some embodiments, the parameters of the initial model are adjusted according to the first layer strain and the second layer strain, and retraining is performed until the prediction accuracy of the initial model is higher than a preset value.

[0093] In some embodiments, an initial model is trained based on training data, and the accuracy of the model's predictions is calculated. If the accuracy is lower than a preset value, the training parameters are modified and the model is retrained. If the accuracy is higher than the preset value, a prediction model for the delamination strain at the interface between the base layer and the cladding layer of the composite pipe is obtained.

[0094] 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.

[0095] In the embodiments of the present application, the device for predicting composite pipe interface delamination strain 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 in the form of 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.

[0096] like Figure 8 , which is a schematic structural diagram of a device for predicting the delamination strain of a composite pipe interface provided in an embodiment of the present application. Figure 8 The prediction device shown includes: a first acquisition unit 801 and a first processing unit 802 .

[0097] The first acquisition unit 801 is used to obtain the geometric parameters, material parameters and contact surface parameters of the base layer and the cladding layer in the composite tube; the first processing unit 802 is used to input the geometric parameters, material parameters and contact surface parameters into a pre-trained prediction model to obtain the delamination strain of the base layer and the cladding layer.

[0098] Optionally, the first acquisition unit 801 is further used to obtain first geometric parameters, first material parameters, and first contact surface parameters of the base layer and the coating in the first composite tube; the first processing unit 802 is further used to construct a finite element model based on the first geometric parameters, the first material parameters, and the first contact surface parameters; the first processing unit 802 is further used to perform calculations based on the finite element model to obtain the delamination strain of the base layer and the coating in the first composite tube.

[0099] Optionally, the first processing unit 802 is also used to determine the node information of the finite element model based on the first geometric parameters, the node information including spatial coordinate information; based on the node information and the first material parameters, the base layer entity unit and the coating entity unit are modeled; based on the first contact surface parameter, the cohesion unit is modeled; the cohesion unit is used to simulate the contact surface between the base layer and the coating.

[0100] Optionally, the first processing unit 802 is also used to set the boundary conditions and stress loads of the finite element model to obtain multiple finite element calculation files; the stress load represents the axial tensile stress applied to the finite element model; the finite element calculation file is calculated to obtain multiple interface separation distances; and the stratification strain is determined based on the multiple interface separation distances.

[0101] Optionally, the geometric parameters include the base layer thickness and the coating thickness; the material parameters include at least one of the base layer elastic modulus, the base layer nominal yield strength, the base layer strain hardening index, the coating elastic modulus, the coating nominal yield strength and the coating strain hardening index; the contact surface parameters include at least one of the normal stiffness, normal strength, normal fracture energy, tangential stiffness, tangential strength and tangential fracture energy of the interlayer bonding interface.

[0102] like Figure 9 , which is a structural diagram of a model training device provided in an embodiment of the present application. Figure 9 The model training device shown includes: a second acquisition unit 901 and a second processing unit 902.

[0103] The second acquisition unit 901 is used to acquire training data, which includes: geometric parameters, material parameters, contact surface parameters of the base layer and the cladding layer in multiple composite tubes, and the first layer strain corresponding to the composite tubes; the second processing unit 902 is used to input the training data into the initial model to obtain the second layer strain output by the initial model; the second processing unit 902 is also used to adjust the parameters of the initial model based on the first layer strain and the second layer strain.

[0104] An embodiment of the present application further provides an electronic device comprising a processor and a memory; the memory is used to store computer-executable instructions, and the processor and the memory are connected via a bus; when the device for predicting the delamination strain at the composite pipe interface is running, the processor executes the computer-executable instructions stored in the memory, so that the electronic device executes the method for predicting the delamination strain at the composite pipe interface described in the first aspect.

[0105] An embodiment of the present application further provides a computer-readable storage medium, which includes computer-executable instructions. When the computer-executable instructions are executed on a computer, the computer executes the method for predicting the composite pipe interface delamination strain described in the first aspect.

[0106] The embodiments of the present application also provide a computer program product that can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement the method for predicting the delamination strain of the composite pipe interface provided in the above embodiments.

[0107] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for predicting delamination strain at the interface of a composite pipe, characterized in that: include: Obtaining geometric parameters, material parameters and contact surface parameters of the base layer and the cladding layer in the composite pipe; The geometric parameters, the material parameters and the contact surface parameters are input into a pre-trained prediction model to obtain the delamination strain of the base layer and the cover layer.

2. The method for predicting interfacial delamination strain of a composite pipe according to claim 1, characterized in that: The method further comprises: Obtaining first geometric parameters, first material parameters, and first contact surface parameters of the base layer and the cladding layer in the first composite tube; constructing a finite element model based on the first geometric parameter, the first material parameter, and the first contact surface parameter; Calculation is performed based on the finite element model to obtain delamination strains of the base layer and the cladding layer in the first composite pipe.

3. The method for predicting the delamination strain of the composite pipe interface according to claim 2, characterized in that: The constructing of a finite element model based on the first geometric parameter, the first material parameter, and the first contact surface parameter includes: determining node information of the finite element model based on the first geometric parameters, wherein the node information includes spatial coordinate information; Modeling a base layer entity unit and a cladding layer entity unit based on the node information and the first material parameter; Based on the first contact surface parameter, a cohesion unit is modeled; the cohesion unit is used to simulate the contact surface between the base layer and the covering layer.

4. The method for predicting interfacial delamination strain of a composite pipe according to claim 3, characterized in that: The calculating based on the finite element model to obtain the delamination strain of the base layer and the cladding layer in the first composite pipe includes: Setting boundary conditions and stress loads of the finite element model to obtain a plurality of finite element calculation files; the stress loads represent the axial tensile stress applied to the finite element model; Calculating the finite element calculation file to obtain multiple interface separation distances; The delamination strain is determined based on the plurality of interface separation distances.

5. The method for predicting interfacial delamination strain of a composite pipe according to any one of claims 1 to 4, characterized in that: The geometric parameters include the base layer thickness and the coating thickness; the material parameters include at least one of the base layer elastic modulus, the base layer nominal yield strength, the base layer strain hardening index, the coating elastic modulus, the coating nominal yield strength and the coating strain hardening index; the contact surface parameters include at least one of the interlayer bonding interface normal stiffness, normal strength, normal fracture energy, tangential stiffness, tangential strength and tangential fracture energy.

6. A model training method, characterized in that: include: Acquiring training data, the training data including: geometric parameters, material parameters, contact surface parameters of a base layer and a cladding layer in a plurality of composite tubes, and first layered strain corresponding to the composite tubes; Inputting the training data into an initial model to obtain a second layered strain output by the initial model; Parameters of the initial model are adjusted based on the first layered strain and the second layered strain.

7. A device for predicting delamination strain at the interface of a composite pipe, characterized in that: The device comprises: The first acquisition unit is used to obtain geometric parameters, material parameters and contact surface parameters of the base layer and the cladding layer in the composite pipe; The first processing unit is configured to input the geometric parameters, the material parameters, and the contact surface parameters into a pre-trained prediction model to obtain the delamination strains of the base layer and the cover layer.

8. An electronic device, characterized in that: include: A processor and a memory; wherein the memory is used to store one or more programs, and the one or more programs include computer-executable instructions. When the device is running, the processor executes the computer-executable instructions stored in the memory to enable the device to perform the method according to any one of claims 1 to 5 or 6.

9. A computer-readable storage medium, characterized in that When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the method according to any one of claims 1 to 5 or 6.

10. A computer program product, characterized in that The computer program product comprises: a computer program or instructions, and when the computer program or instructions are run on a computer, the computer is caused to perform the method according to any one of claims 1 to 5 or 6.

Images