Cooperative deformation failure prediction method, device and equipment of buried PE pressure pipeline under geological collapse disaster and medium

Abstract

The application discloses a buried PE pressure pipeline collaborative deformation failure state prediction method, device, equipment and medium under geological collapse disaster, and comprises the following steps: acquiring target pipeline parameters and geological collapse characteristic parameters, wherein the target pipeline parameters comprise a pipe diameter, a wall thickness, a buried depth and internal pressure, and the geological collapse characteristic parameters comprise a collapse displacement; inputting the target pipeline parameters and the geological collapse characteristic parameters into a PE pipeline collapse failure prediction model, and outputting a stress prediction value of the target pipeline and a failure state judgment result. Therefore, the application can realize rapid prediction of pipeline stress response and accurate judgment of the failure state under different working condition parameters.

Description

Technical Field

[0001] This invention relates to the field of underground pipeline safety assessment and intelligent prediction technology, specifically to a method, device, equipment and medium for predicting the collaborative deformation failure state of buried PE (polyethylene) pressure pipelines under geological collapse disasters based on machine learning. Background Technology

[0002] With the rapid advancement of urbanization, urban underground pipe networks are becoming increasingly sophisticated. Buried PE pressure pipelines, as crucial transport media for gas and water, are widely laid in urban underground spaces. However, due to factors such as subsidence in underground mining areas, disturbance from underground construction, and changes in geological conditions, ground subsidence disasters occur frequently, posing a severe safety threat to underground pipeline systems. Under the influence of ground subsidence, pipelines will bear uneven soil loads and settlement deformation, leading to localized stress concentration. In severe cases, this can cause pipeline rupture, leakage, and other failures, resulting in secondary geological disasters and casualties.

[0003] Currently, research on buried pipelines under collapse disasters mainly focuses on theoretical analysis methods and finite element numerical simulation methods. Theoretical analysis methods are typically based on the Winkler foundation beam model, assuming elastic soil support, and cannot fully consider the nonlinear interaction between the pipe and the soil. While finite element numerical simulation methods can accurately simulate complex working conditions, their long computation cycles make them difficult to meet the engineering requirements for real-time monitoring and rapid assessment of pipelines. Furthermore, existing research has not yet perfected the constitutive model of PE pipeline materials, lacks systematic analysis of the coupled effects of multiple parameters such as collapse displacement, pipeline diameter, wall thickness, burial depth, and internal pressure, and lacks effective rapid failure prediction methods.

[0004] Therefore, there is an urgent need for a method to predict the failure of buried PE pipelines by combining finite element numerical simulation with machine learning, so as to achieve rapid and accurate prediction of pipeline failure status under collapse disasters and provide technical support for pipeline safety operation and maintenance management. Summary of the Invention

[0005] This invention aims to at least solve one of the technical problems existing in the prior art. Therefore, in response to the above-mentioned problem, the purpose of this invention is to provide a method, device, equipment, and medium for predicting the failure of buried PE pressure pipelines under geological collapse disasters based on machine learning. By establishing a collaborative analysis framework of a PE pipe-soil coupled finite element model and an SSA-optimized BP neural network, it is possible to achieve rapid prediction of pipeline stress response and accurate judgment of failure state under different operating parameters.

[0006] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows: In a first aspect, the present invention provides a method for predicting the collaborative deformation failure state of buried PE pressure pipelines under geological collapse disasters, including: Obtain target pipeline parameters and geological collapse characteristic parameters. The target pipeline parameters include pipe diameter, wall thickness, burial depth and internal pressure, and the geological collapse characteristic parameters include collapse displacement. Input the target pipeline parameters and geological collapse characteristic parameters into the PE pipeline collapse failure prediction model, and output the target pipeline stress prediction value and failure state judgment result.

[0007] In some possible implementations, the construction and training process of the PE pipeline collapse failure prediction model is as follows: Establish constitutive models of PE pipes and three-dimensional finite element models of PE pipe-soil coupling; By changing the pipe diameter, wall thickness, burial depth, internal pressure and collapse displacement parameters, a large number of numerical simulations were performed on the mechanical response of the PE pipe constitutive model under collapse using a PE pipe-soil coupled three-dimensional finite element model. The maximum Von Mises stress value of the pipe under each working condition was obtained, and a training sample database was constructed. Determine the failure criteria for the pipeline and generate failure state labels for the training samples; An SSA-BP model was established to predict the maximum stress and failure state of buried PE pipelines under collapse conditions. The model was trained using a training sample library and corresponding failure state labels to obtain a PE pipeline collapse failure prediction model.

[0008] In some possible implementations, the constitutive model of PE pipes uses the Suleiman hyperbolic model to describe the stress-strain relationship of the PE material: , In the formula, For actual stress, To respond realistically, and These are the fitting parameters related to material grade and strain rate.

[0009] In some possible implementations, the process of establishing the PE pipe-soil coupled three-dimensional finite element model is as follows: Establish a PE pipe geometry that is consistent with the soil model in the length direction, and reserve a pipe channel in the soil that matches the outer diameter of the pipe; The pipes and soil are discretized using three-dimensional solid elements suitable for contact and large deformation problems; The pipe-soil contact interface is defined as a surface-to-surface contact, where the principal contact surface is the outer surface of the pipe and the secondary contact surface is the inner surface of the soil. The normal contact adopts a hard contact and allows the contact surfaces to separate. The tangential contact adopts the penalty function Coulomb friction model. Loads and boundary conditions are applied according to the geological collapse process, including: Load-related aspects: applying gravitational acceleration and applying internal pressure to the inner wall of the pipe; Regarding boundary conditions: First, normal displacement constraints are applied to the sides and bottom of the soil, and axial displacement is restricted at both ends of the pipeline. Second, the pipeline length is divided into a central collapse zone, transition zones on both sides, and non-collapse zones. Downward vertical displacement is applied to the corresponding soil area in the collapse zone to simulate ground collapse. Vertical settlement is restricted in the non-collapse zone. The transition zone is used to smoothly connect the collapse zone and the non-collapse zone.

[0010] In some possible implementations, the pipeline failure criterion is as follows: based on the Von Mises yield criterion, the yield strength of the PE pipeline material is used as the critical criterion. When the maximum Von Mises equivalent stress obtained from the finite element simulation reaches or exceeds the yield strength of the pipeline material, the pipeline is determined to have failed.

[0011] In some possible implementations, an SSA-BP model is established to predict the maximum stress and failure state of buried PE pipelines under collapse conditions, specifically: A BP neural network consists of an input layer, hidden layers, and an output layer. The number of neurons in the hidden layer is initially determined by an empirical formula and then searched using the SSA algorithm. The input vector of the BP neural network is the pipeline operating parameters:

[0012] in, For pipe diameter, For wall thickness, For burial depth, For internal pressure, This is a collapse displacement; The output of a BP neural network is defined as:

[0013] in, For the maximum Von Mises equivalent stress, This is an invalidation status label.

[0014] In some possible implementations, training the SSA-BP model to obtain a PE pipeline collapse failure prediction model includes parameter encoding, BP forward propagation, error backpropagation, fitness calculation, SSA location update, and optimal model output, wherein: The SSA algorithm is used to search for better initial weights, thresholds and network structure parameters before or during BP training, and does not directly participate in the forward calculation and backpropagation of the BP network itself. During the SSA iteration process, the discoverer guides the population to perform a global search in the parameter space, the follower gathers towards the better individual, and the vigilant jumps out of the unfavorable area according to the early warning mechanism. After each round of iteration, the individual position is re-decoded, the temporary BP network is trained and the fitness is updated until the maximum number of iterations is reached or the fitness converges. After the SSA search is complete, select the parameter with the lowest fitness. The final BP neural network is initialized and trained using the Levenberg-Marquardt algorithm, Bayesian regularization algorithm, or gradient descent algorithm. After training, the model structure, standardized parameters, weights, thresholds, and failure criterion thresholds are saved to obtain the PE pipeline collapse failure prediction model.

[0015] Secondly, the present invention also provides a device for predicting the collaborative deformation and failure state of buried PE pressure pipelines under geological collapse disasters, comprising: The parameter acquisition unit is configured to acquire target pipeline parameters and geological collapse characteristic parameters. The target pipeline parameters include pipe diameter, wall thickness, burial depth and internal pressure, and the geological collapse characteristic parameters include collapse displacement. The failure prediction unit is configured to input the target pipeline parameters and geological collapse characteristic parameters into the PE pipeline collapse failure prediction model, and output the stress prediction value and failure status judgment result of the target pipeline.

[0016] Thirdly, the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, the instructions being executed by the processor to enable the processor to perform the method described thereon.

[0017] Fourthly, the present invention also provides a computer-readable storage medium for storing one or more programs, said one or more programs including computer instructions for causing a computer to perform the method.

[0018] Because the present invention adopts the above technical solution, it has the following characteristics: 1. This invention is the first to organically combine the constitutive model of PE pipeline, pipe-soil coupled finite element simulation and SSA-BP neural network prediction to form a complete method for predicting failure of buried PE pipelines under the cooperative deformation condition under collapse disaster, which solves the problems of low efficiency and inability to quickly evaluate traditional numerical simulation.

[0019] 2. This invention establishes a constitutive model of PE pipes based on tensile tests, accurately characterizing the elastoplastic mechanical properties of PE pipe materials and improving the accuracy and reliability of finite element simulation.

[0020] 3. This invention introduces a sparrow search algorithm to globally optimize the BP neural network, effectively overcoming the defect of traditional BP neural networks being prone to getting trapped in local optima. The average prediction error is within 15%, and the prediction error in high-stress regions is reduced to 3.61% and 4.62% respectively, with a determination coefficient R0. 2 All scores reached above 0.95, demonstrating significantly better prediction accuracy than the unoptimized BP neural network.

[0021] 4. This invention establishes failure prediction models for two pipeline grades, PE80 and PE100, respectively. These models can quickly provide the stress prediction values ​​and failure states of the target pipeline, meeting the rapid assessment needs of actual engineering projects and possessing significant engineering application value.

[0022] In summary, this invention can be widely applied to the stress response prediction and failure assessment of buried pressure pipelines under ground subsidence loads. Attached Figure Description

[0023] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. In the drawings: Figure 1 This is a schematic diagram of the process for predicting the collaborative deformation and failure state of buried PE pressure pipelines under geological collapse disasters, according to an embodiment of the present invention. Figure 2 This is a schematic diagram of a three-dimensional finite element model of a PE pipe-soil coupling according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the SSA-BP neural network structure and optimization process according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the electronic device structure according to an embodiment of the present invention. Detailed Implementation

[0024] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also mean including the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0025] Although terms such as first, second, third, etc., may be used in this document to describe multiple elements, components, regions, layers, and / or segments, these elements, components, regions, layers, and / or segments should not be limited by these terms. These terms may be used only to distinguish one element, component, region, layer, or segment from another. Unless the context clearly indicates otherwise, terms such as "first," "second," and other numerical terms used herein do not imply order or sequence. Therefore, the first element, component, region, layer, or segment discussed below may be referred to as the second element, component, region, layer, or segment without departing from the teachings of the exemplary embodiments.

[0026] For ease of description, spatial relative terms may be used in the text to describe the relationship of one element or feature relative to another element or feature as shown in the figure. These relative terms include, for example, "inside," "outside," "middle," "outer," "below," "above," etc. Such spatial relative terms are intended to include different orientations of the device in use or operation, other than those depicted in the figure.

[0027] Existing technologies for establishing constitutive models of PE pipe materials are still incomplete, lacking systematic analysis of the coupled effects of multiple parameters such as collapse displacement, pipe diameter, wall thickness, burial depth, and internal pressure, and lacking effective and rapid failure prediction methods. This invention provides a method, device, equipment, and medium for predicting the synergistic deformation failure state of buried PE pressure pipelines under geological collapse disasters. The method includes acquiring target pipeline parameters and geological collapse characteristic parameters, wherein the target pipeline parameters include pipe diameter, wall thickness, burial depth, and internal pressure, and the geological collapse characteristic parameters include collapse displacement; inputting the target pipeline parameters and geological collapse characteristic parameters into a PE pipeline collapse failure prediction model, and outputting the predicted stress value of the target pipeline and the failure state judgment result. Therefore, this invention can achieve rapid prediction of pipeline stress response and accurate judgment of failure state under different operating conditions.

[0028] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.

[0029] Example 1: As Figure 1 As shown in this embodiment, the method for predicting the collaborative deformation and failure state of buried PE pressure pipelines under geological collapse disasters based on machine learning includes: S1. Obtain the mechanical parameters of the material.

[0030] In this embodiment, PE80 and PE100 tensile specimens were prepared according to the requirements for testing the tensile properties of thermoplastic pipes, and tensile tests were performed at room temperature with a tensile strength of 0.00167 s⁻¹. -1 0.0067s -1 and 0.0167s -1 The strain rate was subjected to uniaxial tension, and the tensile force, axial displacement, axial strain and radial strain were recorded to obtain the engineering stress-strain curve.

[0031] Furthermore, during data processing, based on the initial gauge length of the sample... Real-time gauge length Tensile force Initial cross-sectional area and real-time cross-sectional area The engineering stress-strain curve is transformed into true stress-true strain. Engineering strain, engineering stress, true strain, and true stress are respectively calculated according to... , , and Determined. Real-time cross-sectional area when recording radial strain during the experiment. The calculation is based on the cross-sectional dimensions after radial deformation; when radial strain is not recorded, Poisson's ratio correction or the assumption of approximately constant volume can be used for estimation. Among these, the identification of material mechanical parameters based on the true stress-true strain curve includes: Material elastic modulus Obtained by fitting the slope of the initial near-linear segment; Poisson's ratio Determined by the ratio of radial strain to axial strain in the elastic stage; Yield strength The critical stress is determined by the point at which the curve first reaches its peak or enters a distinct plastic flow stage; density The values ​​are determined by the pipe material property test values ​​or the values ​​given in the pipe material instruction manual.

[0032] Specifically, the elastic modulus of PE80 in this embodiment is... 780MPa, Poisson's ratio 0.4, density 950kg / m 3 Yield strength The elastic modulus of PE100 is 16.8 MPa. 900MPa, Poisson's ratio 0.4, density 950kg / m 3 Yield strength The value is 19.8 MPa, and this is just one example; it is not limited to this.

[0033] S2 and PE pipe constitutive models were established.

[0034] In this embodiment, PE pipe constitutive models are established for PE80 and PE100 pipes respectively. The PE pipe constitutive model is used to characterize the correspondence between the test identification parameters and the material stress-strain response, and to provide a callable material model for finite element calculation.

[0035] Specifically, the constitutive model of PE pipes is established using the Suleiman hyperbolic model to describe the stress-strain relationship of PE material, and its expression is as follows: The equivalent form is ; In the formula, For actual stress, To respond realistically, and These are the fitting parameters related to material grade and strain rate. Least squares regression is performed on the true stress-true strain curve for each material grade and strain rate to obtain the corresponding... , Parameters, for different strain rates , The parameters are fitted as a function of strain rate and filled into the hyperbolic model formula. Combined with the material mechanics parameters in S1, a rate-dependent constitutive model for PE80 and PE100 materials is constructed.

[0036] Furthermore, in the finite element method, the hyperbolic constitutive relation described above can be discretized into multiple sets of real stress-strain data, which are then input into the finite element material model along with the elastic modulus, Poisson's ratio, and density. Alternatively, the user material subroutine can be used to call parameters a and b according to the current strain rate and update the stress.

[0037] S3. Establish a three-dimensional finite element model of PE pipe-soil coupling.

[0038] In this embodiment, as Figure 2 As shown, a three-dimensional nonlinear simulation model of the coupling between the pipeline and the soil was established using ABAQUS finite element software. The model is divided into three regions: a collapse zone, a transition zone, and a non-collapse zone. The specific process is as follows: S31. Establish a PE pipe geometry that is consistent with the soil model in the length direction, and reserve a pipe channel in the soil that matches the outer diameter of the pipe.

[0039] In this embodiment, the soil model is 30m long, 4m wide, and 5m high; the pipe is arranged along the length of the soil, and the pipe diameter is... The pipe diameter is taken from 110mm to 400mm. The pipe material is assigned values ​​according to the mechanical parameters of PE80 or PE100 in S1 and the rate-dependent stress-strain relationship obtained in S2. The soil is modeled using the Drucker-Prager elastoplastic model; soil parameters are taken as an elastic modulus of 20MPa and a density of 1600kg / m³. 3 Set Poisson's ratio to 0.4, friction angle to 29°, and dilatation angle to 0°, and input the corresponding DP model hardening parameters, as shown in Table 1.

[0040] Table 1. Hardening parameters of the soil DP model .

[0041] S32. Pipes and soil are discretized using three-dimensional solid elements suitable for contact and large deformation problems.

[0042] In this embodiment, the pipeline and surrounding soil are represented by eight-node linear hexahedral reduced integral elements C3D8R; the pipeline wall thickness direction is divided into three layers of elements; local mesh refinement is applied to a 1m×1m area around the pipeline and the central collapse zone. A suitable mesh density is determined through mesh independence analysis. When the number of meshes is approximately 149,760, the stress results tend to stabilize. This is used as an example, but is not limited to this.

[0043] S33. Define the pipe-soil contact interface as surface-to-surface contact.

[0044] In this embodiment, since the pipe stiffness is higher than that of the surrounding soil, the main contact surface is set as the outer surface of the pipe, and the secondary surface is set as the inner surface of the soil. The normal contact adopts hard contact and allows the contact surfaces to separate. The tangential contact adopts the penalty function Coulomb friction model, and the friction coefficient can be selected according to the soil type. In this embodiment, it is set to 0.4, which can simultaneously describe the support, relative slippage and local separation between the pipe and the soil.

[0045] S34. Apply boundary conditions and loads according to the geological collapse process.

[0046] In this embodiment, boundary conditions and loads are applied according to the geological collapse process, specifically as follows: Regarding the load, the applied gravitational acceleration is 9.8 m / s². 2 and apply internal pressure to the inner wall of the pipe. The internal pressure range is 0 to 0.4 MPa.

[0047] Regarding boundary conditions, firstly, normal displacement constraints are applied to the sides and bottom of the soil, and axial displacement is restricted at both ends of the pipeline. Secondly, the pipeline length is divided into a central collapse zone, transition zones on both sides, and non-collapse zones. Downward vertical displacement is applied to the soil regions corresponding to the collapse zones. To simulate ground subsidence, vertical settlement is restricted in the non-subsidence zone, and a transition zone is used to smoothly connect the subsidence zone and the non-subsidence zone. The vertical displacement can be applied in stages according to the displacement control method, so that the model can output the pipeline stress, strain and deformation response at each loading stage.

[0048] S4. Multi-parameter numerical simulation and sample database construction.

[0049] In this embodiment, by changing multiple influencing parameters such as pipe diameter, wall thickness, burial depth, internal pressure, and collapse displacement, a large number of numerical simulation calculations are performed on the mechanical response of PE80 and PE100 pipes under collapse, the maximum Von Mises stress value of the pipe under each working condition is obtained, and a training sample database is constructed.

[0050] Furthermore, the parameter values ​​cover common actual working conditions in engineering: the nominal pipe diameter ranges from 110mm to 400mm, the wall thickness series standard data is determined according to the SDR (Standard Dimension Ratio) series, the burial depth ranges from 1m to 3m, the internal pressure ranges from 0 to the maximum allowable working pressure, and the collapse displacement ranges from 0 to 1000mm; the parameter combinations are generated using Latin hypercube sampling or full factorial design methods to ensure the uniform distribution of the samples.

[0051] S5. Determine the failure criteria for the pipeline and generate failure status labels for the samples.

[0052] In this embodiment, based on the Von Mises yield criterion, the yield strength of the PE pipe material is used as the critical criterion. When the maximum Von Mises equivalent stress obtained from the finite element simulation reaches or exceeds the yield strength of the pipe material, the pipe is determined to have failed, and a failure status label is formed for each sample.

[0053] Training and optimization of S6 and SSA-BP prediction models.

[0054] In this embodiment, an SSA-BP model is established to predict the maximum stress and failure state of buried PE pipelines under collapse conditions, including the following: A BP neural network includes an input layer, hidden layers, and an output layer. The number of neurons in the hidden layer can be initially determined by an empirical formula and then searched by the SSA algorithm. In this embodiment, the preferred number of hidden layer neurons obtained by the SSA search for the PE80 and PE100 models is 5. This is just one example and is not limited to this.

[0055] The input vector of the BP neural network is the pipeline operating parameters: ; in, For pipe diameter, For wall thickness, For burial depth, For internal pressure, This is a collapse displacement.

[0056] The output of a BP neural network is defined as: ; in, For the maximum Von Mises equivalent stress, This is an invalidation status label.

[0057] Before training, the input features and stress output are standardized or normalized to eliminate dimensional differences and improve the convergence efficiency of the neural network. The finite element samples are divided into training set, validation set and test set in an 8:1:1 ratio.

[0058] like Figure 3 As shown, the SSA-BP training process includes parameter encoding, BP forward propagation, error backpropagation, fitness calculation, SSA position update, and optimal model output, specifically: BP forward propagation can be represented as: ; in, and The weight matrix, and For threshold or bias, and This is the activation function.

[0059] Based on the predicted output With finite element sample output Construct a loss function based on the error between them. ; Backpropagation (BP) updates the weights and thresholds based on the gradient direction. , ,in, This is the learning rate.

[0060] The SSA algorithm is used to search for optimal initial weights, thresholds, and network structure parameters before or during BP training. It does not directly participate in the forward computation and backpropagation of the BP network itself. Let the sparrow population size be... Search dimensions are Then the population position matrix is , Indicates the first i The sparrow in the first j The current position in each dimension. The position vector of each sparrow, after decoding, corresponds to a set of candidate BP parameters. This includes initial weights, initial thresholds, the number of hidden layer neurons, and optional training parameters. For each set of candidate parameters... Construct a temporary BP network and train it on the training set. Calculate the fitness on the validation set. The fitness function can be written as: , in, The root mean square error of stress prediction, For failure state classification error, This is a complexity penalty term. , and , where is the weighting coefficient. When the failure state is determined solely by the stress prediction value via the S5 threshold, the fitness function can also be primarily composed of the validation set MSE or RMSE.

[0061] The root mean square error of stress prediction is: .

[0062] During the SSA iteration process, discoverers guide the population to perform a global search in the parameter space, followers gather towards better individuals, and vigilants jump out of unfavorable regions based on the early warning mechanism. After each iteration, the individual positions are re-decoded, a temporary BP network is trained, and the fitness is updated until the maximum number of iterations is reached or the fitness converges. The SSA population size can be set to 30 to 50, the maximum number of iterations can be set to 100 to 200, the discoverer ratio can be set to 0.2, and the early warning ratio can be set to 0.1.

[0063] After the SSA search is complete, select the parameter with the lowest fitness. Initialize the final backpropagation neural network and complete the final training using the Levenberg-Marquardt algorithm, Bayesian regularization algorithm, or gradient descent algorithm. After training, save the model structure, standardized parameters, weights, thresholds, and failure criterion thresholds to form a callable PE pipeline collapse failure prediction model.

[0064] S6. Pipeline Failure Condition Prediction and Assessment.

[0065] In this embodiment, the pipeline parameters and geological collapse characteristic parameters in the actual project are input into the trained PE pipeline collapse failure prediction model, which quickly outputs the stress prediction value and failure status judgment result of the target pipeline, providing a decision-making basis for pipeline safe operation and maintenance.

[0066] Example 2: Following the method for predicting the collaborative deformation and failure of buried PE pressure pipelines under geological subsidence disasters provided in Example 1, this example provides a device for predicting the collaborative deformation and failure of buried PE pressure pipelines under geological subsidence disasters. The device provided in this example can implement the method for predicting the collaborative deformation and failure of buried PE pressure pipelines under geological subsidence disasters as described in Example 1. This device can be implemented through software, hardware, or a combination of both. For ease of description, this example is described by dividing the functionality into various units. Of course, in implementation, the functions of each unit can be implemented in one or more software and / or hardware components. For example, the device may include integrated or separate functional modules or units to execute the corresponding steps in the methods of Example 1. Since the device in this example is basically similar to the method example, the description process of this example is relatively simple. For relevant details, please refer to the description in Example 1. The example of the device for predicting the collaborative deformation and failure of buried PE pressure pipelines under geological subsidence disasters provided by this invention is merely illustrative.

[0067] Specifically, the present invention also provides a device for predicting the collaborative deformation and failure state of buried PE pressure pipelines under geological collapse disasters, comprising: The parameter acquisition unit is configured to acquire target pipeline parameters and geological collapse characteristic parameters. The target pipeline parameters include pipe diameter, wall thickness, burial depth and internal pressure, and the geological collapse characteristic parameters include collapse displacement. The failure prediction unit is configured to input the target pipeline parameters and geological collapse characteristic parameters into the PE pipeline collapse failure prediction model, and output the stress prediction value and failure status judgment result of the target pipeline.

[0068] Example 3: This example provides an electronic device corresponding to the method for predicting the collaborative deformation failure of buried PE pressure pipelines under geological collapse disasters provided in Example 1. The electronic device can be an electronic device for the client, such as a mobile phone, laptop, tablet computer, desktop computer, etc., to execute the method of Example 1.

[0069] like Figure 4 As shown, the electronic device includes a processor, a memory, a communication interface, and a bus. The processor, memory, and communication interface are connected via the bus to enable communication between them. The memory stores a computer program that can run on the processor. When the processor runs the computer program, it executes the method of Embodiment 1. The implementation principle and technical effects are similar to those of Embodiment 1, and will not be repeated here. Those skilled in the art will understand that... Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computing device on which the present application is applied. The specific computing device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0070] In a preferred embodiment, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), and optical discs.

[0071] In a preferred embodiment, the processor can be any type of general-purpose processor such as a central processing unit (CPU) or a digital signal processor (DSP), and is not limited thereto.

[0072] Example 4: This example provides a computer-readable storage medium for storing one or more programs, the one or more programs including computer instructions, which, when executed by a computer, cause the computer to perform the method provided in Example 1 above.

[0073] In a preferred embodiment, the computer-readable storage medium may be a tangible device for holding and storing instructions executable, such as, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. The computer-readable storage medium stores computer program instructions that cause a computer to perform the method provided in Embodiment 1 above.

[0074] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0075] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0076] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0077] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In the description of this specification, the terms "a preferred embodiment," "furthermore," "specifically," "in this embodiment," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0078] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the collaborative deformation and failure state of buried PE pressure pipelines under geological subsidence disasters, characterized in that, include: Obtain target pipeline parameters and geological collapse characteristic parameters. The target pipeline parameters include pipe diameter, wall thickness, burial depth and internal pressure, and the geological collapse characteristic parameters include collapse displacement. Input the target pipeline parameters and geological collapse characteristic parameters into the PE pipeline collapse failure prediction model, and output the target pipeline stress prediction value and failure state judgment result.

2. The method for predicting the synergistic deformation and failure state of buried PE pressure pipelines under geological subsidence disasters according to claim 1, characterized in that, The construction and training process of the PE pipeline collapse failure prediction model is as follows: Establish constitutive models of PE pipes and three-dimensional finite element models of PE pipe-soil coupling; By changing the pipe diameter, wall thickness, burial depth, internal pressure and collapse displacement parameters, a large number of numerical simulations were performed on the mechanical response of the PE pipe constitutive model under collapse using a PE pipe-soil coupled three-dimensional finite element model. The maximum Von Mises stress value of the pipe under each working condition was obtained, and a training sample database was constructed. Determine the failure criteria for the pipeline and generate failure state labels for the training samples; An SSA-BP model was established to predict the maximum stress and failure state of buried PE pipelines under collapse conditions. The model was trained using a training sample library and corresponding failure state labels to obtain a PE pipeline collapse failure prediction model.

3. The method for predicting the synergistic deformation and failure state of buried PE pressure pipelines under geological collapse disasters according to claim 2, characterized in that, The constitutive model for PE pipes uses the Suleiman hyperbolic model to describe the stress-strain relationship of the PE material: ， In the formula, For actual stress, To respond realistically, and These are the fitting parameters related to material grade and strain rate.

4. The method for predicting the synergistic deformation and failure state of buried PE pressure pipelines under geological collapse disasters according to claim 2, characterized in that, The process of establishing the PE pipe-soil coupled three-dimensional finite element model is as follows: Establish a PE pipe geometry that is consistent with the soil model in the length direction, and reserve a pipe channel in the soil that matches the outer diameter of the pipe; The pipes and soil are discretized using three-dimensional solid elements suitable for contact and large deformation problems; The pipe-soil contact interface is defined as a surface-to-surface contact, where the principal contact surface is the outer surface of the pipe and the secondary contact surface is the inner surface of the soil. The normal contact adopts a hard contact and allows the contact surfaces to separate. The tangential contact adopts the penalty function Coulomb friction model. Loads and boundary conditions are applied according to the geological collapse process, including: Load-related aspects: applying gravitational acceleration and applying internal pressure to the inner wall of the pipe; Regarding boundary conditions: First, normal displacement constraints are applied to the sides and bottom of the soil, and axial displacement is restricted at both ends of the pipeline. Second, the pipeline length is divided into a central collapse zone, transition zones on both sides, and non-collapse zones. Downward vertical displacement is applied to the corresponding soil area in the collapse zone to simulate ground collapse. Vertical settlement is restricted in the non-collapse zone. The transition zone is used to smoothly connect the collapse zone and the non-collapse zone.

5. The method for predicting the synergistic deformation and failure state of buried PE pressure pipelines under geological collapse disasters according to claim 2, characterized in that, The pipeline failure criterion is as follows: based on the Von Mises yield criterion, the yield strength of the PE pipeline material is used as the critical criterion. When the maximum Von Mises equivalent stress obtained from the finite element simulation reaches or exceeds the yield strength of the pipeline material, the pipeline is determined to have failed.

6. The method for predicting the synergistic deformation and failure state of buried PE pressure pipelines under geological collapse disasters according to claim 2, characterized in that, An SSA-BP model is established to predict the maximum stress and failure state of buried PE pipelines under collapse conditions, specifically as follows: A BP neural network consists of an input layer, hidden layers, and an output layer. The number of neurons in the hidden layer is initially determined by an empirical formula and then searched using the SSA algorithm. The input vector of the BP neural network is the pipeline operating parameters: in, For pipe diameter, For wall thickness, For burial depth, For internal pressure, This is a collapse displacement; The output of a BP neural network is defined as: in, For the maximum Von Mises equivalent stress, This is an invalidation status label.

7. The method for predicting the synergistic deformation and failure state of buried PE pressure pipelines under geological collapse disasters according to claim 6, characterized in that, The SSA-BP model is trained to obtain a PE pipeline collapse failure prediction model, which includes parameter encoding, BP forward propagation, error backpropagation, fitness calculation, SSA position update, and optimal model output, wherein: The SSA algorithm is used to search for better initial weights, thresholds and network structure parameters before or during BP training, and does not directly participate in the forward calculation and backpropagation of the BP network itself. During the SSA iteration process, the discoverer guides the population to perform a global search in the parameter space, the follower gathers towards the better individual, and the vigilant jumps out of the unfavorable area according to the early warning mechanism. After each round of iteration, the individual position is re-decoded, the temporary BP network is trained and the fitness is updated until the maximum number of iterations is reached or the fitness converges. After the SSA search is complete, select the parameter with the lowest fitness. The final BP neural network is initialized and trained using the Levenberg-Marquardt algorithm, Bayesian regularization algorithm, or gradient descent algorithm. After training, the model structure, standardized parameters, weights, thresholds, and failure criterion thresholds are saved to obtain the PE pipeline collapse failure prediction model.

8. A device for predicting the collaborative deformation and failure state of buried PE pressure pipelines under geological subsidence disasters, characterized in that, include: The parameter acquisition unit is configured to acquire target pipeline parameters and geological collapse characteristic parameters. The target pipeline parameters include pipe diameter, wall thickness, burial depth and internal pressure, and the geological collapse characteristic parameters include collapse displacement. The failure prediction unit is configured to input the target pipeline parameters and geological collapse characteristic parameters into the PE pipeline collapse failure prediction model, and output the stress prediction value and failure status judgment result of the target pipeline.

9. An electronic device, characterized in that, include: At least one processor; And a memory communicatively connected to the processor; wherein the memory stores instructions executable by the processor, the instructions being executed by the processor to enable the processor to perform the method according to any one of claims 1-7.

10. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include computer instructions for causing a computer to perform the method according to any one of claims 1-7.

Images