A method for predicting bearing performance of vanadium-added steel cylinder segment considering uneven creep deterioration

Abstract

The application discloses a kind of vanadium-added steel cylinder segment bearing performance prediction method considering uneven creep deterioration, it is related to data processing technical field, including the following implementation steps: the creep performance dataset of the material of different regions of vanadium-added steel cylinder segment is constructed;Creep performance dataset is implemented data enhancement using generative adversarial neural network;Using time fraction method, construct creep damage evaluation index;Residual strength dataset of the material after creep deterioration of different regions of vanadium-added steel cylinder segment is constructed;Using data-driven method, establish residual strength prediction model;Establish the finite element model of vanadium-added steel cylinder segment;Using time fraction method calculates its creep damage distribution;The residual strength distribution of the material after creep deterioration of vanadium-added steel cylinder segment is calculated;Realize the bearing performance prediction of vanadium-added steel cylinder segment considering uneven creep deterioration.The application has higher prediction accuracy, stronger reliability and lower implementation cost, and can provide scientific guidance for the suitability evaluation of over-service hydrogenation reactor.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a method for predicting the bearing performance of a vanadium-added steel cylinder segment considering uneven creep degradation. BACKGROUND

[0002] As the key equipment for upgrading in the petroleum and coal chemical industry, hydrogenation reactors are widely used in clean energy projects such as oil improvement, heavy oil cracking, coal-to-synthetic natural gas, and coal direct liquefaction. The vanadium-added steel cylinder segment is the core bearing part of the forged and welded hydrogenation reactor, which can withstand thermal load for a long time in actual service conditions, and the creep damage is the main failure mode. Moreover, the material properties of the vanadium-added steel cylinder segment inevitably deteriorate with the extension of service time, which adversely affects its structural bearing capacity. With the rapid development of science and technology, the suitability evaluation technology is an important way to extend the service life of the hydrogenation reactor, and accurately predicting the residual bearing performance of the vanadium-added steel cylinder segment after creep degradation is the core of the suitability evaluation technology of the hydrogenation reactor.

[0003] Currently, the existing method for predicting the bearing performance of the vanadium-added steel cylinder segment has the following two limitations:

[0004] 1. In the current engineering practice, vanadium-added steel cylinder segments are often placed with parent material and weld hanging blocks inside the hydrogenation reactor to evaluate the degradation of materials in different regions of the cylinder segment under harsh environments. However, the internal hanging blocks do not bear the working stress, which cannot reflect the damage of creep to the vanadium-added steel, affecting the prediction effect of the bearing performance of the vanadium-added steel cylinder segment.

[0005] 2. The wall thickness of the forged and welded vanadium-added steel cylinder segment is generally more than 150 mm, and the working pressure is generally more than 20 MPa. Under internal pressure, the stress distribution along the wall thickness direction is uneven, leading to different creep behaviors of materials at different wall thickness positions. At the same time, the forged and welded vanadium-added steel cylinder segment has parent material zone, weld zone and heat affected zone, and the creep properties of materials in different regions are also greatly different, resulting in low accuracy of the existing prediction results of the bearing performance of the vanadium-added steel cylinder segment, which cannot be used for suitability evaluation of the hydrogenation reactor serving beyond the period, affecting the prediction accuracy of the bearing performance of the vanadium-added steel cylinder segment.

[0006] Therefore, a new method for predicting the bearing performance of the vanadium-added steel cylinder segment considering uneven creep degradation is proposed to solve the above problems. SUMMARY

[0007] The main purpose of the present application is to provide a method for predicting the bearing performance of a vanadium-added steel cylinder segment considering uneven creep degradation, to solve the problem that the existing method cannot be used for suitability evaluation of the hydrogenation reactor serving beyond the period because it does not consider the uneven creep behavior of the vanadium-added steel cylinder segment, resulting in inaccurate prediction results.

[0008] In order to achieve the above object, the technical scheme adopted by the present application is as follows: a vanadium-added steel cylinder segment bearing performance prediction method considering uneven creep degradation, the method comprising the following implementation steps:

[0009] Step 1: Constructing a creep performance data set of materials in different regions of the vanadium-added steel cylinder segment;

[0010] Step 2: According to the creep performance data set, a creep performance prediction model is established;

[0011] Step 3: Using the time fraction method, a creep damage evaluation index is constructed;

[0012] Step 4: According to the creep damage evaluation index, a residual strength data set is constructed;

[0013] Step 5: According to the residual strength data set, a residual strength prediction model is established;

[0014] Step 6: A finite element model of the vanadium-added steel cylinder segment is established, and the stress distribution of the vanadium-added steel cylinder segment under service conditions is calculated;

[0015] Step 7: According to the creep performance prediction model, the creep damage distribution is obtained;

[0016] Step 8: The creep damage distribution and the stress distribution are input into the residual strength prediction model to obtain the residual strength distribution of the material of the vanadium-added steel cylinder segment after creep degradation;

[0017] Step 9: The material residual strength distribution is included in the plastic limit analysis to realize the bearing performance prediction of the vanadium-added steel cylinder segment considering uneven creep degradation.

[0018] The vanadium-added steel refers to vanadium improved chromium-molybdenum steel, including 1Cr-1Mo-V steel, 2.25Cr-1Mo-0.25V steel and 3Cr-1Mo-0.25V steel;

[0019] The specific method for constructing the creep performance data set of materials in different regions of the vanadium-added steel cylinder segment is as follows:

[0020] According to the forging and welding process of the vanadium-added steel cylinder segment, corresponding forged and welded simulation test blocks are made, and materials M1, M2 and M3 are respectively cut from the weld zone, the heat affected zone and the base material zone;

[0021] The working temperature T of the vanadium-added steel cylinder segment s is used as the test temperature, and n test stresses s1, s2, …, s n , wherein n≥5;

[0022] Under the same test temperature and different test stresses, creep rupture tests are respectively conducted on materials M1, M2 and M3 to obtain the creep performance data sets D1, D2 and D3 of materials M1, M2 and M3 under different creep conditions;

[0023] The specific method of step 2 is as follows:

[0024] The creep performance data sets D1, D2 and D3 measured in step 1 are respectively subjected to data enhancement by using a generative adversarial neural network, and creep performance enhanced data sets of materials M1, M2 and M3 are obtained 、 and ;

[0025] Based on the obtained enhanced data sets, the creep performance prediction models of materials M1, M2 and M3 are respectively established by using empirical equations;

[0026] The step 3 uses the time fraction method to construct a creep damage evaluation index.

[0027] The step 4 is to respectively implement different degrees of creep degradation treatment on materials M1, M2 and M3 under test temperatures and test stresses s1, s2, …, s n , and to perform tensile tests on all degraded materials under test temperatures , to obtain the corresponding residual strength data of materials M1, M2 and M3 under different creep conditions and different degrees of degradation, and to record the data sets as 、 and ;

[0028] The step 5 is to use a data-driven method to establish residual strength prediction models of materials M1, M2 and M3 after different degrees of degradation under different creep conditions, based on the measured residual strength data sets 、 and .

[0029] The step 6 is to establish a finite element model of the vanadium-containing steel cylinder segment containing the weld zone, the heat-affected zone and the base material zone according to the geometric parameters, the manufacturing process and the service conditions of the vanadium-containing steel cylinder segment, to input the working pressure as the boundary condition into the finite element model, and to input the mechanical response data of materials M1, M2 and M3 at the working temperature as material parameters into the corresponding regions of the finite element model, and then to calculate the stress distribution of the vanadium-containing steel cylinder segment under service conditions.

[0030] The step 7 inputs the stress distribution of the vanadium-containing steel cylinder segment under service conditions obtained in step 6 into the creep performance prediction model established in step 2, calculates the creep fracture life distribution of the vanadium-containing steel cylinder segment under service conditions, and calculates the creep damage distribution of the vanadium-containing steel cylinder segment after long-term service by using the constructed creep damage evaluation index.

[0031] The step 8 is to input the creep damage distribution obtained in step 7 and the stress distribution obtained in step 6 into the residual strength prediction model established in step 5, to calculate the material residual strength distribution of the vanadium-added steel cylinder segment after long-term service.

[0032] The step 9 is to input the material residual strength distribution of the vanadium-added steel cylinder segment obtained in step 8 and into the improved double-surface model based on the Melan theorem, to obtain the ultimate load of the vanadium-added steel cylinder segment.

[0033] In the step 5, based on the residual strength data set , the data-driven method is used to predict the residual strength of the material Mk after creep degradation, so as to realize the bearing capacity prediction of the vanadium-added steel cylinder segment considering the uneven creep degradation.

[0034] The present application has the following beneficial effects:

[0035] 1. The present application adopts the solution idea of combining data-driven, numerical simulation and plastic limit analysis, avoids complex factors such as physical mechanism and load history, provides a reliable method for accurate prediction of the in-service bearing capacity of the vanadium-added steel cylinder segment serving in the creep condition for a long time, forms a set of applicability evaluation technology considering the creep degradation for the over-service hydrogen reactor, and makes the bearing capacity prediction of the vanadium-added steel cylinder segment more accurate.

[0036] 2. The present application takes into account the complex uneven creep degradation caused by material welding and structure bearing in the bearing capacity prediction of the vanadium-added steel cylinder segment, and can provide technical support for the applicability evaluation of the over-service hydrogen reactor.

[0037] 3. The present application uses the generative adversarial neural network model to supplement the sample of the measured creep data set, not only reduces the demand of the creep empirical model for the creep test sample, but also is beneficial to the improvement of the creep performance prediction accuracy, so that the present application has certain cost advantage. DETAILED DESCRIPTION

[0038] Figure 1 It is the overall flowchart of the present application, a bearing capacity prediction method of a vanadium-added steel cylinder segment considering uneven creep degradation.

[0039] Figure 2 It is the actual vanadium-added steel cylinder segment provided by Lanzhou Lanshi Heavy Equipment Co., Ltd. involved in the embodiment of the present application.

[0040] Figure 3 It is the creep performance enhancement data set of the material M1.

[0041] ​Figure 4 a creep performance enhanced dataset for material M2;

[0042] Figure 5 a creep performance enhanced dataset for material M3;

[0043] Figure 6 a predicted result of residual yield strength after creep degradation for material M1;

[0044] Figure 7 a predicted result of residual tensile strength after creep degradation for material M1;

[0045] Figure 8 a predicted result of residual yield strength after creep degradation for material M2;

[0046] Figure 9 a predicted result of residual tensile strength after creep degradation for material M2;

[0047] Figure 10 a predicted result of residual yield strength after creep degradation for material M3;

[0048] Figure 11 a predicted result of residual tensile strength after creep degradation for material M3;

[0049] Figure 12 a finite element model of a cylinder segment comprising a weld zone, a heat-affected zone and a base material zone constructed by an embodiment of the present application;

[0050] Figure 13 an equivalent stress distribution of a vanadium-added steel cylinder segment under a working pressure of 35 MPa and a working temperature of 550 ℃, which is related to an embodiment of the present application;

[0051] Figure 14 a load-carrying performance evolution law of a vanadium-added steel cylinder segment in a service process under a working pressure of 35 MPa and a working temperature of 550 ℃, which is related to an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the technical means, creative features, purposes and effects realized by the present application easy to understand, the present application is further described below in combination with specific embodiments.

[0053] Please refer to Figures 1 to 11 : a vanadium-added steel cylinder segment load-carrying performance prediction method considering uneven creep degradation, comprising the following implementation steps:

[0054] Step 1: Construct a creep performance dataset of materials in different regions of the vanadium-added steel cylinder segment, wherein the creep performance in step 1 includes a creep time-creep strain curve, a creep rupture life, a creep post-rupture elongation and a creep cross-sectional shrinkage rate.

[0055] Step 2: Data augmentation is performed on the creep property dataset using a generative adversarial neural network, and a creep property prediction model for the materials in different regions of the vanadium-added steel cylinder segment is established based on the augmented dataset;

[0056] Step 3: A creep damage evaluation index is constructed using the time fraction method;

[0057] Step 4: A residual strength dataset for the materials in different regions of the vanadium-added steel cylinder segment after creep degradation is constructed using creep degradation and tensile tests;

[0058] Step 5: A residual strength prediction model for the materials in different regions of the vanadium-added steel cylinder segment after creep degradation is established using data-driven methods;

[0059] Step 6: A finite element model of the vanadium-added steel cylinder segment including the weld zone, heat-affected zone, and base material zone is established, and the stress distribution under service conditions is calculated;

[0060] Step 7: Based on the stress distribution of the vanadium-added steel cylinder segment and the creep property prediction model for the materials in different regions, the creep fracture life distribution of the vanadium-added steel cylinder segment is obtained, and the creep damage distribution is calculated using the time fraction method;

[0061] Step 8: The creep damage distribution and stress distribution of the vanadium-added steel cylinder segment are input into the residual strength prediction model for the corresponding region materials of the vanadium-added steel cylinder segment, and the residual strength distribution of the materials after creep degradation of the vanadium-added steel cylinder segment is calculated;

[0062] Step 9: The residual strength distribution of the materials after creep degradation of the vanadium-added steel cylinder segment is included in the plastic limit analysis, realizing the bearing capacity prediction of the vanadium-added steel cylinder segment considering non-uniform creep degradation.

[0063] Vanadium-added steel refers to vanadium-modified chromium-molybdenum steel, including 1Cr-1Mo-V steel, 2.25Cr-1Mo-0.25V steel, and 3Cr-1Mo-0.25V steel. In this embodiment, 2.25Cr-1Mo-0.25V steel is selected as the model material, and the original material for making the forged welding simulation test block in step 1 should be taken from the real vanadium-added steel cylinder segment forge;

[0064] The welding parameters for making the forged welding simulation test block in step 1 should be consistent with the welding process of the real vanadium-added steel cylinder segment, including the type and size parameters of the bevel, preheating temperature, welding material, welding speed, welding current, and post-weld heat treatment parameters;

[0065] The specific method for constructing the creep property dataset for the materials in different regions of the vanadium-added steel cylinder segment is as follows:

[0066] According to the actual vanadium-added steel cylinder segment (this embodiment takes the actual vanadium-added steel cylinder segment provided by Lanzhou Lanshi Heavy Industry Co., Ltd. as an example, which has a wall thickness of 152 mm, an inner diameter of 2400 mm, and a length of 1700 mm, and the specific parameters are shown in Figure 2 The corresponding forging welding simulation test block is made (the welding parameters for making the forging welding simulation test block should be consistent with the welding process of the actual vanadium-added steel cylinder segment, including the type and size parameters of the bevel, the preheating temperature, the welding material, the welding speed, the welding current, the welding voltage, and the post-weld heat treatment parameters, and the main parameters of the welding process used in this embodiment are provided by Lanzhou Lanshi Heavy Industry Co., Ltd., and the specific parameters are shown in Table 1), and materials M1, M2, and M3 are cut from the weld zone, the heat-affected zone, and the base material zone, respectively;

[0067] Table 1 - Main parameters of the welding process used in this embodiment

[0068]

[0069] The working temperature T s of the vanadium-added steel cylinder segment is taken as the test temperature (in this embodiment, T s = 550℃), and five test stresses s1, s2, …, s5 are selected within a reasonable range (i.e. above the working stress of the vanadium-added steel cylinder segment and below 90% of the minimum yield strength of materials M1, M2, and M3), and the reasonable range of the test stress in step 1 is the stress range between the actual service stress level of the vanadium-added steel cylinder segment and the yield strength of the vanadium-added steel, and the specific parameters are shown in Table 2.

[0070] Table 2 - Test stress levels selected in this embodiment

[0071]

[0072] Under the same test temperature and different test stresses, creep rupture tests are performed on materials M1, M2, and M3, respectively, to obtain creep property data sets D1, D2, and D3 of materials M1, M2, and M3 under different creep conditions, and the specific parameters are shown in Table 3.

[0073] Table 3 - Creep property data sets obtained in this embodiment (only creep rupture life data is shown here)

[0074]

[0075] In step 2, the empirical equation includes the Larson-Miller parameter method, the Manson-Haferd parameter method, the theta projection method, and the Omega method, and the specific method of step 2 is as follows:

[0076] The generative adversarial neural network is used to generate the creep property data set k of material M Data augmentation is implemented, including the following sub-steps:

[0077] Step 21: Randomly extract 80% of the data from the creep property data sets D1, D2 and D3 as a training set for fitting the generative adversarial neural network, and the remaining 20% of the data as a test set for evaluating the fitting results. The data division results in this embodiment are shown in Table 4.

[0078] Table 4 - Training set and test set division results of the creep rupture life data in this embodiment

[0079]

[0080] Step 22: According to the sample size of the creep property data set , construct a full connection neural network with appropriate capacity as the generator and discriminator of the generative adversarial neural network, and initialize the model parameters;

[0081] Step 23: Sample from a random distribution, input the generator, and obtain a batch of virtual data of material M k creep properties;

[0082] Step 24: Based on the training set obtained in step 21 and the virtual data obtained in step 23, use the Wasserstein distance and gradient descent algorithm to optimize the model parameters of the discriminator, and improve its ability to distinguish between true and false data;

[0083] Step 25: Use the discriminator obtained in step 24 to optimize the model parameters of the generator, so that the output data distribution gradually approaches the data distribution of the training set in step 21;

[0084] Step 26: Repeat steps 23 to 25 until the fitting ability of the generator to the data distribution of the training set in step 21 is maximized;

[0085] Step 27: Evaluate the fitting accuracy of the generator obtained in step 26 using the training set obtained in step 21, and evaluate the generalization performance of the generator obtained in step 26 using the test set obtained in step 21. If both the fitting accuracy and the generalization performance are acceptable, a usable data augmentation model is obtained. Otherwise, adjust the hyperparameters of the full connection neural network in step 22 and repeat steps 22 to 27;

[0086] Step 28: Analyze the distribution characteristics of the creep property data in the creep stress coordinate axis, and determine the creep stress interval for which data samples are lacking (in this embodiment, the creep property data sets D1, D2 and D3 lack creep property data of vanadium-added steel in the normal working stress interval of the cylinder segment, specifically in the range of 100 to 200 MPa);

[0087] Step 29: Sample supplement is performed on the creep stress interval determined in step 28 by using the data enhancement model obtained in step 27 to obtain a creep performance enhanced data set ), the creep performance data sets D1, D2 and D3 measured in step 1 are respectively subjected to data enhancement to obtain creep performance enhanced data sets of materials M1, M2 and M3 、 and , as shown in Figure 3 、 Figure 4 and Figure 5 ;

[0088] Based on the obtained enhanced data set, a creep performance prediction model of material M1, M2 and M3 is respectively established by using the Larson-Miller empirical equation, as follows:

[0089]

[0090]

[0091] ;

[0092] In the formula, represents the creep stress, represents the Larson-Miller parameter of material M k at temperature and stress , which is calculated by , wherein, M k represents any one of materials M1, M2 and M3 (i.e. its subscript k is 1, 2 or 3), C LM is a material constant (set to 20 in this embodiment), represents the creep rupture life of material M k ;

[0093] Step 3: A creep damage evaluation index is constructed by using the time fraction method, as follows:

[0094] ;

[0095] In the formula, represents a damage factor describing the degree of creep deterioration of the material, represents the creep service time of the material, represents the creep rupture life of the material.

[0096] Step 4 is as follows:

[0097] At the test temperature and the test stresses s1, s2, …, s nUnder the following conditions, materials M1, M2, and M3 were subjected to different degrees of creep degradation treatment, and the test temperature was [not specified]. Tensile tests were performed on all deteriorated materials, and the tensile tests were performed on material M. k The creep degradation and tensile tests are performed, specifically including the following sub-steps:

[0098] Step 41: Based on the creep performance dataset measured in Step 1 Determine material M k creep fracture life and the end of the steady-state creep stage (See Table 5 for details);

[0099] Table 5 - End times of steady-state creep stage for each material obtained in this embodiment under different creep conditions

[0100]

[0101] Step 42: Based on the creep damage evaluation index constructed in Step 3, calculate the material M. k Damage factor at the end of the steady-state creep stage See Table 6 for details;

[0102] Table 6 - Damage factors of each material at the steady-state termination time under different creep conditions obtained in this embodiment.

[0103]

[0104] Step 43: In [0, m damage factors were selected at equal intervals within the range. , … ,in ≥5, no. Each damage factor is denoted as In this embodiment, the damage factors corresponding to the end of the steady-state creep stage of materials M1, M2, and M3 under different creep conditions are all between 0.60 and 0.70, which are relatively close to each other. Therefore, the same 5 damage factors are selected for materials M1, M2, and M3 (see Table 7 for details). It must be pointed out that when the damage factors corresponding to the end of the steady-state creep stage of materials M1, M2, and M3 under different creep conditions are significantly different, m damage factors can be selected for different materials and different creep conditions.

[0105] Table 7 - Five damage factors selected in this embodiment

[0106]

[0107] Step 44: From material M k Sampling and processing creep sample is denoted as ; ;

[0108] Step 45: Creep interruption tests are performed on the creep samples processed in Step 44 at the test temperature and test stress s1 for different lengths of time, wherein the length of time for the creep of the sample is determined by the product of and ; ; ;

[0109] Step 46: All of the creep deteriorated samples obtained in Step 45 are further processed into high temperature tensile samples, and tensile tests are performed on all of the samples at the test temperature to measure the yield strength and tensile strength thereof;

[0110] Step 47: The test stress in Step 45 is adjusted to s2, s3, …, s n , respectively, and Steps 44 to 46 are repeated to obtain the residual strength data set corresponding to the different degrees of deterioration of the material M k under different creep conditions , the residual strength data corresponding to the different degrees of deterioration of the materials M1, M2 and M3 under different creep conditions are obtained, and the data sets thereof are denoted as , and , and are specifically shown in Tables 8, 9 and 10;

[0111] Table 8 - Residual strength data set of material M1 obtained in this example:

[0112] Table 9 - Residual strength data set of material M2 obtained in this example:

[0113]

[0114] Table 10 - Residual strength data set of material M3 obtained in this example:

[0115]

[0116]

[0117] Step 5 is based on the measured residual strength data sets , and ​​​Using a data-driven approach (a single-hidden-layer fully connected neural network model in this embodiment), a residual strength prediction model is established for materials M1, M2, and M3 after different degrees of degradation under different creep conditions, as detailed below:

[0118] ;

[0119] In the formula, Indicates the temperature of material Mk. The remaining yield strength below Material M k At temperature The remaining tensile strength below This indicates the use of data-driven methods to analyze material M. k The fitted function is based on the residual intensity dataset. Using data-driven methods, predict material M k Residual strength after creep degradation (the predicted results of materials M1, M2, and M3 obtained in this embodiment are as follows) Figure 6 , Figure 7 and Figure 8 , Figure 9 , Figure 10 and Figure 11 As shown), its implementation specifically includes the following sub-steps:

[0120] Step 51: From the residual intensity dataset 80% of the data is randomly selected and used as the training set for data-driven model fitting, while the remaining 20% ​​of the data is used as the test set for evaluating the fitting results.

[0121] Step 52: Based on the training set obtained in Step 51, optimize the model hyperparameters using grid search and cross-validation, and then retrain the model to maximize its adaptability to material M. k Predictive ability of residual strength after creep degradation;

[0122] Step 53: Evaluate the fitting accuracy of the data-driven model trained in Step 53 using the training set obtained in Step 51, and evaluate the generalization performance of the data-driven model trained in Step 53 using the test set obtained in Step 51. If both the fitting accuracy and generalization performance are acceptable, then usable material M is obtained. k The remaining strength prediction model after creep degradation (the performance of the remaining strength prediction models for materials M1, M2 and M3 after creep degradation constructed in this embodiment is shown in Table 11. Their root mean square error on the training set and test set is low, the R2 coefficient of determination is greater than 0.95, and the two are relatively close. Therefore, their fitting accuracy and generalization performance are considered acceptable); otherwise, the data-driven model is replaced and steps 51 to 53 are repeated.

[0123] Table 11 - Performance of the creep degradation residual strength prediction model constructed in this example for materials M1, M2 and M3

[0124]

[0125] Step 6 is specified as follows:

[0126] According to the geometric parameters of the vanadium-added steel cylinder segment (in this example, the geometric parameters of the vanadium-added steel cylinder segment are a wall thickness of 152 mm, an inner diameter of 2400 mm, and a length of 1700 mm), the manufacturing process (in this example, the vanadium-added steel cylinder segment is a forged and welded vanadium-added steel cylinder segment, and the welding uses a V-shaped groove full penetration), and the service condition (in this example, the service condition of the vanadium-added steel cylinder segment is a working pressure of 40 MPa and a working temperature of 550 ℃), a finite element model of the vanadium-added steel cylinder segment containing the weld zone, the heat-affected zone, and the base material zone is established (see Figure 12 ), the working pressure = 40 MPa is input as a boundary condition into the finite element model, and the mechanical response data of materials M1, M2, and M3 at the working temperature = 550 ℃ are input as material parameters into the corresponding regions of the finite element model, respectively, and then the stress distribution of the vanadium-added steel cylinder segment under the service condition is calculated (as shown in Figure 13 , it must be pointed out that the distribution cloud map can only show part of the calculation results on the surface of the vanadium-added steel cylinder segment, and it is difficult to clearly illustrate the data mapping and transmission relationship in the subsequent calculation steps, so in this example, the subsequent calculation process is described in mathematical expressions), which is specified as follows:

[0127] ;

[0128] In the formula, represents the stress distribution of the vanadium-added steel cylinder segment at the working temperature and the working pressure , represents the spatial position of any point in the vanadium-added steel cylinder segment in the cylindrical coordinate system, represents the finite element model considering the non-uniform mechanical behavior of the weld zone, the heat-affected zone, and the base material zone.

[0129] Step 7 inputs the stress distribution of the vanadium-added steel cylinder segment under the service condition obtained in Step 6 into the creep performance prediction model established in Step 2, calculates the creep fracture life distribution of the vanadium-added steel cylinder segment under the service condition, which is specified as follows:

[0130] ;

[0131] In the formula, represents the creep fracture life distribution of the vanadium-added steel cylinder segment at the working temperature and the working pressure .

[0132] And using the constructed creep damage evaluation index, the creep damage distribution of the vanadium-added steel cylinder section after long-term service is calculated, specifically:

[0133] ;

[0134] In the formula, represents the creep service time of the vanadium-added steel cylinder section, represents the creep damage distribution of the vanadium-added steel cylinder section after serving at the working temperature and the working pressure for a long time.

[0135] Step 8 is to input the creep damage distribution obtained in step 7 and the stress distribution obtained in step 6 into the corresponding regional material residual strength prediction model established in step 5 to calculate the material residual strength distribution of the vanadium-added steel cylinder section after serving for a long time, specifically as follows:

[0136] ;

[0137] In the formula, represents the material residual yield strength distribution of the vanadium-added steel cylinder section after serving at the working temperature and the working pressure for a long time, represents the material residual tensile strength distribution of the vanadium-added steel cylinder section after serving at the working temperature and the working pressure for a long time.

[0138] The specific steps of step 9 are as follows:

[0139] Input the material residual strength distribution of the vanadium-added steel cylinder section obtained in step 8 and into the improved double-surface model based on the Melan theorem, specifically as follows:

[0140] ;

[0141] In the formula, α represents the load multiplier, represents the yield function, represents the Gaussian point number of the finite element discrete model of the vanadium-added steel cylinder section, represents the total number of Gaussian points, represents the corner point number of the load space involved in the vanadium-added steel cylinder section, represents the total number of load corner points, represents the load corner point​​​​ elastic stress field generated at the first Gauss point, represents the self-balanced residual stress at the first Gauss point of the finite element discrete model of the vanadized steel cylinder segment, represents the back stress describing the dynamic recovery effect at the first Gauss point of the finite element discrete model of the vanadized steel cylinder segment, represents the cylindrical coordinate position at the first Gauss point of the finite element discrete model of the vanadized steel cylinder segment, represents the residual yield strength of the material at the first Gauss point of the finite element discrete model of the vanadized steel cylinder segment after service for a long time at the working temperature and the working pressure represents the residual tensile strength of the material at the first Gauss point of the finite element discrete model of the vanadized steel cylinder segment after service for a long time at the working temperature and the working pressure represents the stress-node load conversion coefficient related to meshing and boundary conditions at the first Gauss point of the finite element discrete model of the vanadized steel cylinder segment.

[0142] Based on the dimension reduction iteration framework, the effective set algorithm is used to solve the improved double-surface model, so as to obtain the limit load of the vanadized steel cylinder segment after service for a long time at the working temperature and the working pressure , and realize the bearing capacity prediction of the vanadized steel cylinder segment with uneven creep deterioration; the calculation result of the embodiment is shown in , and it should be noted that only the vanadized steel cylinder segment with complete structure is considered in the embodiment, and when local damage occurs, it is considered to lose bearing capacity. Figure 14

[0143] The geometric parameters and manufacturing process of the vanadized steel cylinder segment involved in the embodiment are consistent with engineering practice, but it should be pointed out that, in order to accelerate the deterioration of the vanadized steel cylinder segment and reduce the cost of creep test, the working temperature 550 ℃ and the working pressure 35 MPa used in the embodiment are higher than those in engineering practice, that is, the service conditions used in the embodiment are only illustrative.

[0144] ​​​​​It should be pointed out that the formulas in steps 6, 7 and 8 can clearly show how the working stress distribution, creep life distribution, creep damage distribution and residual strength distribution of the vanadium-added steel cylinder segment in the embodiment are mapped and calculated, and the formula in step 9 can clearly express how the residual strength calculation result is incorporated into the calculation framework of plastic limit analysis, and these formulas can assist technicians in the field to understand and apply the present application and facilitate them to program and realize the technical content of the present application.

[0145] In the present application, a vanadium-added steel cylinder segment bearing performance prediction method considering uneven creep degradation is provided. First, a creep performance dataset of materials in different regions of the vanadium-added steel cylinder segment is constructed. A generative adversarial neural network is used to implement data enhancement on the creep performance dataset, and based on the enhanced dataset, a creep performance prediction model of materials in different regions of the vanadium-added steel cylinder segment is established. By adopting a solution approach combining data-driven, numerical simulation and plastic limit analysis, complex factors such as physical mechanisms and load history are avoided, providing a reliable method for accurate prediction of the in-service bearing performance of vanadium-added steel cylinder segments serving in creep conditions for a long time. A set of applicability evaluation techniques considering creep degradation is formed for over-service hydrogen reactors, making the bearing performance prediction of vanadium-added steel cylinder segments more accurate. A creep damage evaluation index is constructed using the time fraction method. A residual strength dataset of materials in different regions of the vanadium-added steel cylinder segment after creep degradation is constructed using creep degradation and tensile tests. A residual strength prediction model of materials in different regions of the vanadium-added steel cylinder segment after creep degradation is established using a data-driven method. A finite element model of the vanadium-added steel cylinder segment including the weld zone, heat-affected zone and base material zone is established, and the stress distribution under service conditions is calculated. Based on the stress distribution of the vanadium-added steel cylinder segment and the creep performance prediction model of materials in different regions, the creep fracture life distribution of the vanadium-added steel cylinder segment is obtained, and the creep damage distribution is calculated using the time fraction method. The creep damage distribution and stress distribution of the vanadium-added steel cylinder segment are input into the residual strength prediction model of the corresponding region materials of the vanadium-added steel cylinder segment, and the residual strength distribution of the materials of the vanadium-added steel cylinder segment after creep degradation is calculated. By incorporating the complex uneven creep degradation caused by material welding and structural bearing into the bearing performance prediction of the vanadium-added steel cylinder segment, technical support is provided for the applicability evaluation of over-service hydrogen reactors. The residual strength distribution of the materials of the vanadium-added steel cylinder segment after creep degradation is incorporated into plastic limit analysis to realize the bearing performance prediction of the vanadium-added steel cylinder segment considering uneven creep degradation. By using the generative adversarial neural network model to supplement the measured creep dataset, not only the demand for creep test samples of the creep empirical model is reduced, but also the creep performance prediction accuracy is improved, thus the present application has certain cost advantages.

[0146] The above shows and describes the basic principles and main features of the present application and the advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for predicting the load-carrying capacity of a vanadium-added steel cylinder segment considering uneven creep degradation, characterized by, The method comprises the following implementation steps: Step 1: Constructing a creep property data set of the materials in different regions of the vanadium-added steel cylinder segment; Step 2: Establishing a creep property prediction model according to the creep property data set; Step 3: Constructing a creep damage evaluation index by using the time fraction method; Step 4: Constructing a residual strength data set according to the creep damage evaluation index; Step 5: Establishing a residual strength prediction model according to the residual strength data set; Step 6: Establishing a finite element model of the vanadium-added steel cylinder segment, and calculating the stress distribution of the vanadium-added steel cylinder segment under service conditions; Step 7: Obtaining the creep damage distribution according to the creep property prediction model; Step 8: Inputting the creep damage distribution and the stress distribution into the residual strength prediction model to obtain the residual strength distribution of the material of the vanadium-added steel cylinder segment after creep degradation; Step 9: Including the residual strength distribution of the material into plastic limit analysis to realize the bearing capacity prediction of the vanadium-added steel cylinder segment considering uneven creep degradation; The residual strength data set in step 4 is constructed as follows: at working temperature and test stresses s1, s2,..., s n Next, different degrees of creep degradation treatment are performed on materials M1, M2 and M3 respectively, and tensile tests are performed on all degraded materials at working temperature to obtain the residual strength data sets of materials M1, M2 and M3 corresponding to different degrees of degradation under different creep conditions , and ; The step 5 is based on the measured residual strength data set , and , using a data-driven method, a residual strength prediction model of materials M1, M2 and M3 after different degrees of deterioration under different creep conditions is established. In step 4, the material M k The creep degradation and tensile test is implemented, comprising the following steps: Step 41 : determining the creep rupture lifetime and the end of steady state creep time of the material M k based on the creep property data set ; Step 42: Based on the creep damage evaluation index, calculate the material M k Damage factor corresponding to the end time of the steady-state creep stage ; Step 43: In [0, m damage factors were selected at equal intervals within the range. , … ,in ≥5, no. Each damage factor is denoted as ; Step 44: Sampling from material M k Processing the same creep specimen, where the first creep specimen is denoted ; Step 45: At the working temperature and the test stress s1, the creep specimens processed in step 44 are respectively subjected to creep interruption tests with different lengths of time, wherein the length of time of the creep of the specimen is determined by the product of the creep rate of the specimen in step 44 and the test stress s1. Step 46: The creep rate of the specimen in step 45 is determined. Step 47: The creep rate of the specimen in step 45 is determined. Step 48: The creep rate of the specimen in step 45 is determined. Step 49: The creep rate of the specimen in step 45 is determined. Step 46: All the creep deteriorated samples obtained in step 45 are further processed into high temperature tensile samples, and the tensile test is carried out at the working temperature The tensile test is carried out on all the samples respectively, and the yield strength and tensile strength are measured. Step 47: adjust the test stress in step 45 to s2, s3, …, s n , respectively, and repeat steps 44 to 46 to obtain the residual strength data set of the material M k under different creep conditions corresponding to different degrees of deterioration ; In step 5, based on the measured residual strength dataset , using a data-driven approach, predict the material M k residual strength after creep degradation, comprising the following steps: Step 51 : Randomly extract 80% data from the remaining intensity dataset as training set for data-driven model fitting, and the remaining 20% data as test set for fitted result evaluation; Step 52: Based on the training set obtained in step 51, the model hyperparameters are optimized using grid search and cross-validation, and the model is retrained to maximize its prediction of the residual strength of the material M k the ability to predict the residual strength after creep deterioration; Step 53: Evaluate the fitting accuracy of the data-driven model trained in step 52 using the training set obtained in step 51, and evaluate the generalization performance of the data-driven model trained in step 52 using the test set obtained in step 51, and if both the fitting accuracy and the generalization performance are acceptable, a usable material M is obtained k creep deterioration residual strength prediction model; otherwise, replace the data-driven model and re-perform steps 51 to 53.

2. The method of claim 1, wherein: The specific method for constructing the creep property data set of the materials in different regions of the vanadium-added steel cylinder segment is as follows: According to the forging and welding process of the vanadium-added steel cylinder segment, corresponding forged and welded simulation test blocks are made, and materials M1, M2 and M3 are cut from the weld zone, heat affected zone and base material zone, respectively; The working temperature T of the vanadium-added steel cylinder joint s Use as test temperature, and select n test stresses s1, s2, …, s n Wherein n≥5; Under the same test temperature and different test stresses, the creep rupture test is performed on the materials M1, M2 and M3, respectively, to obtain the creep property data sets D1, D2 and D3 of the materials M1, M2 and M3 under different creep conditions.

3. The method of claim 1, wherein: The step 6 is as follows: According to the geometric parameters, manufacturing process and service conditions of the vanadium-containing steel cylinder segment, a finite element model of the vanadium-containing steel cylinder segment containing the weld zone, the heat-affected zone and the base material zone is established, the working pressure is input into the finite element model as a boundary condition, and the mechanical response data of the materials M1, M2 and M3 at the working temperature are input into the corresponding regions of the finite element model as material parameters, and then the stress distribution of the vanadium-containing steel cylinder segment at the working temperature and the working pressure is calculated , wherein represents the spatial position in the vanadium-containing steel cylinder segment in the column coordinate system.

4. The method of claim 3, wherein: The specific step of the step 7 is to obtain the stress distribution of the vanadium-added steel cylinder segment in the service condition The creep damage distribution of the vanadium-added steel cylinder segment after long-term service is calculated by using the established creep damage evaluation index.

5. The method of claim 3, wherein: The step 8 calculates the creep damage distribution and the stress distribution obtained in step 6 , input the residual strength prediction model established in step 5, to calculate the material residual strength distribution of the vanadium-added steel cylinder segment after serving for a long time.

6. The method of claim 5, wherein: The specific steps of step 9 are as follows: The material obtained in step 8 is subjected to a remaining strength distribution and An improved double-sided model based on the Melan theorem is inputted to obtain the ultimate load of the vanadium-added steel cylinder segment.

Images