Method for predicting heaving and buckling of submarine flexible pipeline and optimally designing earthing parameters

Abstract

The invention relates to a method for heaving and buckling prediction and earthing parameter optimization design of a submarine flexible pipeline. The method comprises the following steps: S1, parametric modeling; s2, results are post-processed in batches; and S3, constructing a deep learning neural network model. According to the method, rapid parametric modeling can be carried out on the upheaval buckling problem of the non-adhesive flexible pipe, and accurate simulation of the upheaval behavior of the non-adhesive flexible pipe is achieved by endowing the pipeline with the Genal Beam Section beam section attribute and calculating the equivalent expansion coefficient. In addition, the neural network model obtained through a large number of finite element example training can achieve flexible pipe upheaval buckling prediction and soil covering parameter optimization design, and therefore the safety and economical efficiency of engineering are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of pipelines, and in particular relates to a method for predicting uplift and buckling of submarine flexible pipelines and optimizing the design of soil covering parameters. Background Art

[0002] In the offshore oil and gas industry, submarine pipelines undertake the important task of transporting high-temperature oil and gas. When the axial displacement of the pipeline is constrained and the operating temperature and operating pressure are higher than a certain level, the soil can no longer constrain the pipeline, and the pipeline will buckle vertically or horizontally. Vertical uplift buckling is the main form of damage to buried pipelines.

[0003] Non-bonded flexible pipes play an important role in the field of offshore oil and gas transportation. They are generally composed of a polymer barrier layer and various metal spiral armor layers, non-metallic wear-resistant layers and other structural layers. The material properties of each layer vary greatly, and the stress relationship between layers is complex, which makes the uplift buckling analysis different from that of traditional single-layer rigid pipes.

[0004] There are currently the following difficulties in solving the uplift and buckling problems of buried flexible pipelines: 1) Conventional overall buckling analysis methods cannot accurately describe the mechanical behavior of flexible pipes, and existing methods for establishing the material properties of rigid pipelines cannot accurately characterize the mechanical behavior of flexible pipelines; 2) The temperature-pressure coupling of flexible pipelines requires equivalent calculations; 3) There is currently a lack of methods for rapid modeling and efficient post-processing of submarine flexible pipeline models; 4) There is currently a lack of rapid and accurate verification of the uplift and buckling of in-service submarine flexible pipelines, as well as calculation methods for optimal design of cover.

[0005] Therefore, considering the particularity of unbonded flexible pipes, it is of great application value to develop a reliable, accurate, fast and simple method to predict the uplift buckling of buried unbonded flexible pipes and optimize the cover design. Summary of the invention

[0006] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method for predicting the uplift and buckling of submarine flexible pipelines and optimizing the design of covering parameters, aiming to accurately predict the uplift displacement generated by non-bonded flexible pipes during operation, while being able to quickly feedback the risk of buckling of pipeline installation routes and perform reasonable covering design.

[0007] The present invention solves the technical problem by the following technical solutions:

[0008] A method for predicting uplift and buckling of submarine flexible pipelines and optimizing the design of cover parameters, the method comprising the following steps:

[0009] S1. Parametric modeling:

[0010] Use Python language to perform parameterized modeling on the calculation model, batch extract soil data of drilling points in the installation route survey, and quickly establish the flexible pipeline and soil model on the overall installation route;

[0011] S2. Batch post-processing:

[0012] Use PYTHON language to batch process the finite element calculation files generated by S1 to extract the historical time history of key variables including pipeline uplift displacement and critical temperature;

[0013] S3. Construction of deep learning neural network model:

[0014] The artificial neural network machine learning model of flexible pipeline uplift and buckling is trained and verified using PYTHON language to achieve the prediction of submarine flexible pipeline uplift and buckling and optimal design of soil cover.

[0015] Moreover, the S1 is specifically:

[0016] 1) Automatically generate node numbers and spatial coordinate information according to the geometric design parameters of the flexible pipeline, and construct nodes of the finite element model, wherein the geometric design parameters include pipeline length, defect form, defect amplitude and soil thickness;

[0017] 2) Based on the node space information in 1), the pipe-soil action unit and the pipe unit are further constructed. The flexible pipe is a non-bonded flexible pipe composed of multiple layers of materials. The cross section of the flexible pipe is set to the General Beam Section beam cross section property, and the outer diameter of the flexible pipe, the inner diameter of the pipe, the axial stiffness in the compression direction and the tensile direction, the bending stiffness, the torsional stiffness, the pressure expansion coefficient, and the thermal expansion coefficient are input. The equivalent expansion coefficient method is used to simultaneously consider the pressure change and the temperature load. The equivalent expansion coefficient α eq The calculation formula is as follows:

[0018]

[0019] Where: α T is the thermal expansion coefficient, α P is the pressure expansion coefficient, T1 is the design temperature, T0 is the initial temperature, P i is the design internal pressure of the pipeline, P e Design external pressure for the pipeline;

[0020] 3) Based on the soil data of the survey drilling points, establish the pipe-soil axial, vertical and horizontal interaction model, and adjust the soil calculation according to the specific engineering design conditions;

[0021] 4) Set the initial temperature of the flexible pipe, and set the boundary conditions and loads of the model;

[0022] 5) Generate finite element calculation files in batches based on the soil data of the surveyed drilling points of the flexible pipeline installation route and submit the calculations in batches using scripts.

[0023] Moreover, the S3 is specifically:

[0024] 1) Divide the data set of S2 into a training set and a test set for the neural network model;

[0025] 2) constructing an artificial neural network model and importing the training set to train the neural network;

[0026] 3) Use the test set described in 1) to test the trained neural network model and calculate the prediction accuracy of the deep learning model. If the accuracy is lower than the expected value, modify the neural network model parameters in 2) and retrain; if the accuracy is higher than the expected value, obtain a rapid calculation model for the soil covering parameters of the buried flexible pipe.

[0027] 4) Use the prediction model constructed in 3) to predict key characterization parameters and optimize soil cover for the uplift and buckling of submarine flexible pipelines.

[0028] The advantages and beneficial effects of the present invention are:

[0029] 1. The present invention establishes a finite element analysis method for uplift and buckling of submarine flexible pipelines, and can perform rapid parameterized modeling on the uplift and buckling problem of buried flexible pipelines.

[0030] 2. Different from the beam section of a rigid pipe, the present invention models the flexible pipe as a General Beam Section beam section property by specifying a series of parameters such as axial stiffness, bending stiffness, torsional stiffness, pressure expansion coefficient, thermal expansion coefficient, etc. in the compression and tension directions of the flexible pipe in the finite element analysis, which can more accurately characterize the overall buckling behavior of the flexible pipe.

[0031] 3. The present invention aims at the temperature-pressure coupling problem of the flexible pipe, converts the pressure load into the equivalent load by calculating the equivalent expansion coefficient, and realizes a more accurate calculation of the pipe bulge behavior.

[0032] 4. The present invention is very necessary for designers in the engineering field. For in-service pipelines, the present invention can obtain the displacement amplitude of the uplift of buried flexible pipelines; for pipelines planned to be constructed, the present invention can iteratively optimize the covering parameters through a trained neural network model, play a guiding role in actual engineering construction, and improve the economy of pipeline laying and the safety of pipeline operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the process of the present invention;

[0034] Figure 2It is a schematic cross-sectional view of the pipeline and the soil surrounding the pipeline of the present invention;

[0035] Figure 3 It is a schematic diagram of the initial defect introduced at the mid-span of the pipeline according to the present invention;

[0036] Figure 4 It is a local diagram of the mid-span position of the pipe-soil interaction model of the present invention;

[0037] Figure 5 Schematic diagram of unit types of the model of the present invention;

[0038] Figure 6 This is a diagram of the uplift simulation calculation results of the pipeline model of the present invention;

[0039] Figure 7 The present invention is a curve diagram of the uplift displacement changing with temperature;

[0040] Figure 8 The displacement versus temperature curve calculated under different soil parameters according to the present invention;

[0041] Fig. 9 It is a critical temperature diagram of pipeline uplift under different soil parameters determined according to the first type of uplift standard of the present invention;

[0042] Fig.10 Schematic diagram of the neural network of the present invention. DETAILED DESCRIPTION

[0043] The present invention is further described in detail below through specific examples. The following examples are only illustrative and not restrictive, and the protection scope of the present invention cannot be limited thereto.

[0044] like Figure 1 As shown, a method for predicting the uplift and buckling of submarine flexible pipelines and optimizing the design of cover parameters is innovative in that the steps of the method are:

[0045] 1. Parametric modeling: Use PYTHON language to perform parametric modeling on the finite element calculation file, combine the soil data of the survey drilling points of the pipeline installation route, realize the rapid establishment of the flexible pipeline and soil model on the overall installation route, and use the script to submit the calculation in batches. The specific steps include:

[0046] 1) Calculate the node number and coordinates based on the geometric parameters of the pipeline and generate the nodes in the model space. The cross-sectional diagram of the pipeline is as follows: Figure 2 As shown in Figure 2, the geometry of the defect segment is as follows: Figure 3 shown.

[0047] 2) Generate pipe-soil interaction units and pipe units based on the nodes in step 1). The overall model is as follows Figure 4 As shown, the unit type is Figure 5 Then, the cross-sectional properties of the flexible pipe are established according to the relevant parameters.

[0048] 3) Establish pipe-soil interaction according to soil parameters of the survey drilling points, including axial, vertical and horizontal directions.

[0049] 4) Set the initial temperature of the pipeline and set the boundary conditions and loads of the model.

[0050] 5) Extract soil data at different drilling points of the pipeline installation route, repeat steps 1) to 4), batch generate finite element calculation files and use scripts to batch submit calculations.

[0051] 2. Batch post-processing results: Use PYTHON language to batch extract key variables such as uplift displacement and temperature from the calculation result file. In this embodiment, the uplift displacement results of finite element calculation are as follows: Figure 6 As shown in the figure, it can be seen that the bulge is most serious at the top of the pipe, and the bulge is basically zero at the farther end of the pipe. The extracted temperature-bulge displacement curve is shown in Figure 7 As shown in the figure, the two dotted lines correspond to two different uplift standards. It can be seen from the figure that as the temperature increases, the uplift at the top of the pipe increases. At the final temperature, the uplift height has exceeded the allowable value of the first type of uplift standard, but is still within the allowable value of the second type of uplift standard. The temperature-uplift displacement curves at different drilling points of the batch-drawn pipeline installation route are shown in Figure 8 By extracting the temperature corresponding to when the pipeline uplift reaches the first type of uplift standard, the critical temperature under different soil parameters is obtained as follows: Fig. 9 shown.

[0052] 3. Construct an artificial neural network model for optimizing soil cover design:

[0053] 1) Divide the input parameters and output parameters into the training set and test set of the neural network model. The input parameters include: pipeline inner diameter, pipeline outer diameter, defect height, pipeline length, pipeline axial stiffness, pipeline bending stiffness, pipeline torsional stiffness, pipeline design external pressure, design internal pressure, design temperature, pipeline buoyancy, pipeline thermal expansion coefficient, pressure expansion coefficient, undrained shear strength of soil, empirical adhesion coefficient, bearing capacity coefficient, uplift coefficient, axial limit displacement, vertical (including upward and downward parts) limit displacement. The output parameters include: uplift displacement. 85% of the samples are selected as training set data, and 15% of the samples are selected as test set data.

[0054] 2) constructing an artificial neural network, and importing the training set described in step 1) to train the neural network. 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.

[0055] 3) The trained neural network model is tested using the test set described in step 1) to calculate the accuracy of the model prediction. If the accuracy is lower than the expected value, the neural network model parameters in step 2) are modified and retrained; if the accuracy is higher than the expected value, a rapid prediction model for optimizing the soil covering parameters of the buried flexible pipe is obtained.

[0056] 4) Use the prediction model constructed in step 3) to predict the uplift and buckling of the submarine flexible pipeline and optimize the cover parameters.

[0057] Although the embodiments and drawings of the present invention are disclosed for illustrative purposes, those skilled in the art will appreciate that various substitutions, changes and modifications are possible without departing from the spirit and scope of the present invention and the appended claims. Therefore, the scope of the present invention is not limited to the contents disclosed in the embodiments and drawings.

Claims

1. A method for predicting uplift and buckling of submarine flexible pipelines and optimizing the design of cover parameters, characterized by: The steps of the method are: S1. Parametric modeling: Use Python language to perform parameterized modeling on the calculation model, batch extract soil data of drilling points in the installation route survey, and quickly establish the flexible pipeline and soil model on the overall installation route; S2. Batch post-processing: Use PYTHON language to batch process the finite element calculation files generated by S1 and extract the historical time history of key variables including pipeline uplift displacement and critical temperature; S3. Construction of deep learning neural network model: The artificial neural network machine learning model of flexible pipeline uplift and buckling is trained and verified using PYTHON language to achieve the prediction of submarine flexible pipeline uplift and buckling and optimal design of soil cover.

2. The method for predicting uplift and buckling of submarine flexible pipelines and optimizing soil covering parameters according to claim 1 is characterized in that: The S1 is specifically: 1) Automatically generate node numbers and spatial coordinate information according to the geometric design parameters of the flexible pipeline, and construct nodes of the finite element model, wherein the geometric design parameters include pipeline length, defect form, defect amplitude and soil thickness; 2) Based on the node space information in 1), the pipe-soil action unit and the pipe unit are further constructed. The flexible pipe is a non-bonded flexible pipe composed of multiple layers of materials. The cross section of the flexible pipe is set to the General Beam Section beam cross section property, and the outer diameter of the flexible pipe, the inner diameter of the pipe, the axial stiffness in the compression direction and the tensile direction, the bending stiffness, the torsional stiffness, the pressure expansion coefficient, and the thermal expansion coefficient are input. The equivalent expansion coefficient method is used to simultaneously consider the pressure change and the temperature load. The equivalent expansion coefficient α eq The calculation formula is as follows: Where: α T is the thermal expansion coefficient, α P is the pressure expansion coefficient, T1 is the design temperature, T0 is the initial temperature, P i is the design internal pressure of the pipeline, P e Design external pressure for the pipeline; 3) Based on the soil data of the survey drilling points, establish the pipe-soil axial, vertical and horizontal interaction model, and adjust the soil calculation according to the specific engineering design conditions; 4) Set the initial temperature of the flexible pipe, and set the boundary conditions and loads of the model; 5) Generate finite element calculation files in batches based on the soil data of the surveyed drilling points of the flexible pipeline installation route and submit the calculations in batches using scripts.

3. The method for predicting uplift and buckling of submarine flexible pipelines and optimizing soil covering parameters according to claim 1 is characterized in that: The S3 is specifically: 1) Divide the data set of S2 into a training set and a test set for the neural network model; 2) constructing an artificial neural network model and importing the training set to train the neural network; 3) Use the test set described in 1) to test the trained neural network model and calculate the prediction accuracy of the deep learning model. If the accuracy is lower than the expected value, modify the neural network model parameters in 2) and retrain; if the accuracy is higher than the expected value, obtain a rapid calculation model for the soil covering parameters of the buried flexible pipe. 4) Use the prediction model constructed in 3) to predict key characterization parameters and optimize soil cover for the uplift and buckling of submarine flexible pipelines.

Images