Pipeline steel fatigue crack propagation rate prediction model construction method and system

Abstract

The invention provides a pipeline steel fatigue crack growth rate prediction model construction method and system, and the method comprises the steps: constructing an initial crack growth rate prediction model considering the influence of a hydrogen pressure alternating load according to a Walker formula and a joint factor model; hydrogen pressure change is introduced, and the initial crack propagation rate prediction model is optimized into a hydrogen pressure adaptive crack propagation rate prediction model; hydrogen pressure is given, constant terms in the hydrogen pressure adaptive crack growth rate prediction model are solved, and a final fatigue crack growth rate prediction model is obtained. The cyclic load is designed according to the actual pressure fluctuation of the pipeline, the fatigue crack growth rate model of the pipeline steel under the combined action of the hydrogen pressure and the fatigue load is established, and guiding significance is provided for safe operation and service life prediction of the hydrogen-doped pipeline.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline life prediction, and in particular to a pipeline steel fatigue crack growth rate prediction model construction method and system. Background Art

[0002] Hydrogen has been identified as the most promising energy carrier. Hydrogen transportation is an important link in the process of hydrogen energy utilization. Using the existing natural gas pipeline network to transport a mixture of natural gas and hydrogen is currently the most economical and efficient way to transport hydrogen.

[0003] However, hydrogen can decompose into hydrogen atoms and enter the pipeline. Hydrogen atoms can diffuse in the tetrahedral gaps of the body-centered cubic (BCC) structure of the pipeline and cause hydrogen embrittlement (HE). In addition, as the most commonly used steel in natural gas pipelines, X80 steel has a high sensitivity to hydrogen embrittlement, which may cause micro cracks in the pipeline during operation, ultimately leading to system and equipment failure. Due to the start and stop of the compressor, the flow rate adjustment caused by market demand, and changes in the external environment, the hydrogen pipeline is constantly subject to the influence of alternating loads. The interaction between high-pressure hydrogen and alternating loads will accelerate the fatigue crack propagation of pipeline steel, greatly reducing the service life of the hydrogen pipeline.

[0004] At present, many scholars have studied the effect of hydrogen accumulation on fatigue crack propagation of pipeline steel. However, most of the studies use the experimental method of electrochemical hydrogen charging, which is very different from the source, concentration and adsorption and absorption process of hydrogen atoms in actual hydrogen-doped pipelines. In addition, the alternating load in the pipeline makes the diffusion and accumulation of hydrogen more complicated. In the presence of hydrogen, the hydrogen pressure, the stress ratio and frequency of the cyclic load borne by the pipeline will affect the fatigue crack propagation. In addition, the life prediction of pipeline steel requires the establishment of a quantitative model of fatigue crack growth rate, but the current quantitative model in hydrogen environment cannot comprehensively consider the influence of stress ratio and frequency of cyclic load, and does not take hydrogen pressure into consideration as an influencing factor. Therefore, its prediction results cannot accurately reflect the actual fatigue crack growth behavior of materials in hydrogen environment. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and system for constructing a fatigue crack growth rate prediction model for pipeline steel. By integrating the Walker formula and the joint factor model, considering the hydrogen pressure alternating load, and considering the hydrogen pressure change, a pipeline steel fatigue crack growth rate prediction model that is closer to reality is constructed, which improves the adaptability and accuracy of fatigue crack growth prediction of pipeline steel in a hydrogen-containing environment.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for constructing a pipeline steel fatigue crack growth rate prediction model, comprising:

[0008] According to the Walker formula and the joint factor model, a prediction model for the initial crack growth rate considering the influence of hydrogen pressure alternating load is constructed;

[0009] By introducing hydrogen pressure variation, the initial crack growth rate prediction model is optimized into a hydrogen pressure adaptive crack growth rate prediction model.

[0010] Given the hydrogen pressure, the constant term in the hydrogen pressure adaptive crack growth rate prediction model is solved to obtain the final fatigue crack growth rate prediction model.

[0011] Preferably, the initial crack growth rate prediction model considering the influence of hydrogen pressure alternating load is constructed according to the Walker formula and the joint factor model, specifically:

[0012]

[0013] in, is the crack growth rate, ΔK is the stress intensity factor amplitude, K max is the maximum stress intensity factor, A', b', r are constants, f is the frequency, and R is the stress ratio.

[0014] Preferably, the introduction of hydrogen pressure variation to optimize the initial crack growth rate prediction model to a hydrogen pressure adaptive crack growth rate prediction model is specifically as follows:

[0015]

[0016] in, is the crack growth prediction item in the low hydrogen pressure domain, is the prediction item of crack growth acceleration in high hydrogen pressure domain, P H and P th are hydrogen partial pressure and hydrogen pressure threshold respectively; Z represents load-related factor; b1, b2, b3 are constants.

[0017] Preferably, the given hydrogen pressure is used to solve the constant term in the hydrogen pressure adaptive crack growth rate prediction model to obtain the final fatigue crack growth rate prediction model;

[0018] Obtain the initial crack growth rate prediction model, and obtain the r value based on the given hydrogen pressure using a multivariate linear regression algorithm;

[0019] The fitting results in nitrogen environment are used as the value of the constant for crack growth prediction in low hydrogen pressure domain;

[0020] The r value and the constant value of the crack growth prediction item in the low hydrogen pressure domain are substituted into the hydrogen pressure adaptive crack growth rate prediction model. The least squares method is used for nonlinear surface fitting. The initial value changing iterative algorithm is adopted to solve the constant value of the crack growth acceleration prediction item in the high hydrogen pressure domain to obtain the final fatigue crack growth rate prediction model.

[0021] In a second aspect, the present invention provides a pipeline steel fatigue crack growth rate prediction model construction system, comprising:

[0022] The initial model building module is used to build an initial crack growth rate prediction model considering the influence of hydrogen pressure alternating load based on the Walker formula and the joint factor model;

[0023] A model optimization module is used to introduce hydrogen pressure changes and optimize the initial crack growth rate prediction model into a hydrogen pressure adaptive crack growth rate prediction model;

[0024] The final model building module is used to solve the constant term in the hydrogen pressure adaptive crack growth rate prediction model for a given hydrogen pressure, and obtain the final fatigue crack growth rate prediction model.

[0025] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for constructing a pipeline steel fatigue crack growth rate prediction model described in the first aspect.

[0026] In a fourth aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for constructing a pipeline steel fatigue crack growth rate prediction model described in the first aspect are implemented.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] First, by integrating the Walker formula and the joint factor model, the traditional crack growth theory model innovatively incorporates the hydrogen pressure alternating load factor, thereby comprehensively considering the stress ratio of the cyclic load and the influence of the frequency, and constructing a more comprehensive and accurate initial prediction model. At the same time, by introducing the concept of hydrogen pressure change, the model is deeply optimized so that it can flexibly adapt to the crack growth characteristics under different hydrogen pressure environments, forming a hydrogen pressure adaptive crack growth rate prediction model. In addition, by accurately solving the constant terms in the model under a given hydrogen pressure, a highly reliable and applicable final prediction model is obtained, which improves the adaptability and accuracy of the fatigue crack growth prediction of pipeline steel in a hydrogen-containing environment, and provides strong technical support and decision-making basis for the safety assessment, design optimization and long-term maintenance of pipeline steel.

[0029] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their description are used to explain the present invention but do not constitute a limitation of the present invention.

[0031] Figure 1 A main flow chart of a method for constructing a pipeline steel fatigue crack growth rate prediction model provided by an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of fitting data of formula (7) under a hydrogen pressure of 2 MPa provided in an embodiment of the present invention;

[0033] Figure 3 A schematic diagram for comparing the predicted values ​​and experimental results under different loading conditions and hydrogen pressures provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0035] The main purpose of studying fatigue crack growth is to obtain the theory of crack growth, establish the relationship between da / dN and ΔK and material properties, and express it with a universal formula. In the stable growth zone of fatigue crack growth, in double logarithmic coordinates, the crack growth rate da / dN and the stress intensity factor amplitude ΔK show a linear relationship. The Paris formula is simple in form and is more accurate in predicting the fatigue crack growth rate in the stable growth zone. It is widely used. The form of the formula is:

[0036]

[0037] Where C and m are characteristic constants describing fatigue crack growth, which can be obtained by fitting experimental data, and ΔK is the amplitude of the stress intensity factor.

[0038] However, the Paris formula has limitations, namely, it does not take into account the crack initiation and instability stages, and cannot describe the influence of factors such as stress ratio on the crack growth rate.

[0039] In order to characterize the influence of stress ratio R on da / dN-ΔK curve, Walker proposed the Walker prediction model based on Paris formula, and its formula is as follows:

[0040]

[0041] It can be seen that the m value is the characteristic constant, r is a constant, R is the stress ratio, ΔK is the amplitude of the stress intensity factor, but the C value is a function of R, that is:

[0042]

[0043] The Walker formula takes into account the influence of stress ratio, but still does not consider the influence of loading frequency.

[0044] In the joint factor model, both ΔK and K are used. max Quantify the change in stress intensity and take into account the effect of loading frequency. The equation is in the form of:

[0045]

[0046] Where A and b are characteristic constants, f is the frequency, ΔK is the amplitude of the stress intensity factor, and K max is the maximum stress intensity factor.

[0047] The joint factor model is suitable for scenarios with a fixed stress ratio. When the stress ratio R is determined, the prediction of the crack growth rate under different frequency conditions is relatively accurate. However, when the stress ratio is different under certain frequency conditions, especially because the alternating load changes with time, the minimum stress and maximum stress inside the material change with time. This change directly causes the stress ratio (i.e., the ratio of the minimum stress to the maximum stress) to change with time and is no longer a constant value. Therefore, the fitting of the parameters in the formula will be quite different, and the formula is not very universal under different R values.

[0048] In addition to the above fatigue crack growth rate model, there are a large number of other forms of evolution models, but most of them are only suitable for certain materials or models, and it is difficult to obtain parameters. At present, the Paris formula is still the most widely used fatigue crack prediction model, but its flexibility and versatility are poor and it cannot be used on a large scale. Therefore, it is necessary to design cyclic loads according to the actual pressure fluctuations of the pipeline and establish a fatigue crack growth rate model for pipeline steel under the combined action of hydrogen pressure and fatigue load, which is of great significance for the safe operation and life prediction of hydrogen-doped pipelines in the future.

[0049] Embodiment 1

[0050] like Figure 1 As shown, this embodiment discloses a method for constructing a pipeline steel fatigue crack growth rate prediction model, comprising the following steps:

[0051] S1: Based on the Walker formula and the joint factor model, a prediction model for the initial crack growth rate considering the influence of hydrogen pressure alternating load is constructed;

[0052] S2: Introducing hydrogen pressure changes, the initial crack growth rate prediction model is optimized to a hydrogen pressure adaptive crack growth rate prediction model;

[0053] S3: Given the hydrogen pressure, solve the constant term in the hydrogen pressure adaptive crack growth rate prediction model to obtain the final fatigue crack growth rate prediction model.

[0054] Next, combine Figure 1 , a method for constructing a pipeline steel fatigue crack growth rate prediction model disclosed in this embodiment is described in detail.

[0055] Based on the Walker formula and combined with the joint factor model, the initial crack growth rate prediction model is obtained, which is expressed as:

[0056]

[0057] Where b', A' and r are constants, R is the stress ratio, f is the frequency, ΔK is the stress intensity factor amplitude, K max is the maximum stress intensity factor.

[0058] That is, the Walker formula The ΔK in is replaced by the joint factor model In By considering the influence of stress ratio and frequency at the same time, the versatility and applicability of the model are enhanced, and a prediction model for the initial crack growth rate is obtained.

[0059] As a specific implementation method, in order to solve the constant value in the model, the model can be simplified and converted into the following form:

[0060]

[0061] At a specific hydrogen pressure (2 MPa), according to the experimental data, a multiple linear regression method was used to determine the fitting constants from the two independent variables and one dependent variable in formula (6), and a multiple linear regression model was established. The least squares method was used for parameter estimation, and the obtained values ​​of b', r, and A' were 0.88, 7.02, and 5.44×10 -6 Substituting the constant value into the initial crack growth rate prediction model, the fatigue crack growth rate model of pipeline steel under a specific hydrogen pressure (2MPa) is obtained as follows:

[0062]

[0063] It should be understood that those skilled in the art can select a suitable multivariate linear regression model for fitting in the origin software based on the existing experimental data set to obtain corresponding parameter values.

[0064] Will As the x-axis, refit the fatigue crack growth curve, such as Figure 2 As shown in the figure, the model is in good agreement with the experimental data at different R ratios and loading frequencies.

[0065] Since the influence of various load conditions may be different under different hydrogen pressures, or more specifically under different hydrogen concentrations, when describing the crack growth rate under hydrogen pressures other than 2 MPa, formula (5) can be used to determine the parameters through fatigue crack growth tests.

[0066] If the influence of hydrogen pressure is further considered in the model, the fatigue crack growth model of X80 pipeline steel in hydrogen can be established using a linear summation model. This model assumes that the total increment of fatigue cracks is the sum of each independent increment, and the general form is:

[0067]

[0068] As a specific implementation method, when considering the influence of hydrogen pressure, there is a pressure threshold for the influence of hydrogen pressure on fatigue crack growth. It is believed that below this value, hydrogen will not have an effect on fatigue crack growth or can be ignored. Based on this, the model is established as follows:

[0069]

[0070] That is, we can convert the formula (8) into Decomposed into formula (9) In formula (9), The term represents the fatigue crack growth rate under the hydrogen pressure threshold, which is 0.02MPa; The term represents the accelerating effect of changing the hydrogen pressure on crack growth when the hydrogen pressure exceeds the threshold. When the hydrogen pressure is below the threshold, only the first term is calculated. When the hydrogen pressure is higher than the threshold, the The first item uses the data of 0.02MPa. Based on the initial crack growth rate prediction model, the hydrogen pressure adaptive crack growth rate prediction model can be obtained as follows:

[0071]

[0072] In the formula, the parameters related to the load conditions are expressed by a total factor Z; is the crack growth prediction item in the low hydrogen pressure domain, is the prediction term for crack growth acceleration in the high hydrogen pressure domain; the exponential constant of the stress ratio R term has been calculated in equation (7); P H and P thare hydrogen partial pressure and hydrogen pressure threshold, in MPa, respectively. b1, b2, and b3 are constants. It should be understood that the hydrogen pressure threshold of 0.02 MPa can be determined by those skilled in the art according to actual conditions.

[0073] Due to the lack of experimental data at 0.02 MPa, and this value is the critical point, the fitting result of the experimental data in nitrogen environment is used to replace this term. Then, the A1 of the crack growth prediction term in the low hydrogen pressure domain in equation (10) is 6.28×10 -7 , b1 is 1.14. It should be understood that those skilled in the art know that in a mixture of hydrogen and nitrogen, if the partial pressure of hydrogen is lower than 0.02MPa, then hydrogen has no obvious accelerating effect on the fatigue crack growth rate and can be ignored; similarly, nitrogen, as an inert gas, has very little effect on the fatigue crack growth of the material. Therefore, in this case, in order to simplify the experiment and save costs, the experimental data in a pure nitrogen environment can be used instead of analyzing the material behavior in a mixed gas environment.

[0074] In order to solve the other constant values ​​in the model, the least squares method was used for nonlinear surface fitting, and the experimental results of X80 pipeline steel under different hydrogen pressures were programmed and solved. Since the solution of equation (11) is highly dependent on the initial value, the origin software was used to change the initial value and iteratively to obtain the converged constant value, that is, A2 in the high hydrogen pressure domain crack growth acceleration prediction item is 4.27×10 -6 , b2 is 0.21, b3 is 4.61, then the model after fitting the parameters is:

[0075]

[0076] It should be understood that, in addition to the least square method and the calculation method of changing the initial value iteration, those skilled in the art may select other calculation methods according to actual conditions.

[0077] The comparison between the model prediction results and the experimental results is shown in Figure 3As shown, the fitted model coincides well with the experimental results in hydrogen at pressures below 2MPa. At present, the hydrogen ratio in actual hydrogen-doped transmission pipelines is less than 20%. Since the transmission pressure of natural gas pipelines is generally lower than 10MPa, the partial pressure of hydrogen is lower than 2MPa. Therefore, the fatigue crack growth rate model obtained in the hydrogen environment can be used to estimate the fatigue life of X80 pipeline steel for hydrogen-doped transmission. When the hydrogen pressure reaches 3MPa, the fatigue crack growth rate is nearly an order of magnitude higher than that in a hydrogen-free environment, and cracks will rapidly expand unstably. Therefore, the fatigue crack growth rate equation for hydrogen pressures below 2MPa in this embodiment can still be used to estimate the fatigue life of X80 pipeline steel for hydrogen-doped transmission. The law of crack growth in X80 pipeline steel under higher hydrogen pressures needs to be further explored, and the application of models under hydrogen conditions below 2MPa is more concerned in actual field practice.

[0078] By fitting the experimental parameters, the adaptability of the established model, namely, formula (10), has been proven. When more experimental data under hydrogen pressure and load conditions are obtained, the formula can be used for further fitting to improve accuracy. In practical applications, by recording the gas pressure fluctuation data in the pipeline and filtering the data to obtain the characteristic pressure waveform, the parameters related to the load conditions can be obtained by combining the pipeline and crack geometric parameters, and formula (12) can be used to describe and predict the crack propagation of X80 pipeline steel in different actual hydrogen partial pressure environments.

[0079] This embodiment innovatively incorporates the hydrogen pressure alternating load factor into the traditional crack propagation theoretical model by integrating the Walker formula and the joint factor model, thereby comprehensively considering the stress ratio of the cyclic load and the influence of the frequency, and constructing a more comprehensive and accurate initial prediction model. At the same time, by introducing the concept of hydrogen pressure change, the model is deeply optimized so that it can flexibly adapt to the crack propagation characteristics under different hydrogen pressure environments, forming a hydrogen pressure adaptive crack propagation rate prediction model. In addition, by accurately solving the constant terms in the model under a given hydrogen pressure, a highly reliable and highly applicable final prediction model is obtained, which improves the adaptability and accuracy of the fatigue crack propagation prediction of pipeline steel in hydrogen-containing environments, and provides strong technical support and decision-making basis for the safety assessment, design optimization and long-term maintenance of pipeline steel.

[0080] Embodiment 2

[0081] This embodiment provides a pipeline steel fatigue crack growth rate prediction model construction system, including:

[0082] The initial model building module is used to build an initial crack growth rate prediction model considering the influence of hydrogen pressure alternating load based on the Walker formula and the joint factor model;

[0083] A model optimization module is used to introduce hydrogen pressure changes and optimize the initial crack growth rate prediction model into a hydrogen pressure adaptive crack growth rate prediction model;

[0084] The final model building module is used to solve the constant term in the hydrogen pressure adaptive crack growth rate prediction model for a given hydrogen pressure, and obtain the final fatigue crack growth rate prediction model.

[0085] Embodiment 3

[0086] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method for constructing a pipeline steel fatigue crack growth rate prediction model as described in the first embodiment above are implemented.

[0087] Embodiment 4

[0088] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for constructing a pipeline steel fatigue crack growth rate prediction model as described in the first embodiment above are implemented.

[0089] The steps or modules involved in the above embodiments 2 to 4 correspond to those in embodiment 1. For the specific implementation, please refer to the relevant description of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing a pipeline steel fatigue crack growth rate prediction model, characterized in that: include: According to the Walker formula and the joint factor model, a prediction model for the initial crack growth rate considering the influence of hydrogen pressure alternating load is constructed; By introducing hydrogen pressure variation, the initial crack growth rate prediction model is optimized into a hydrogen pressure adaptive crack growth rate prediction model. Given the hydrogen pressure, the constant term in the hydrogen pressure adaptive crack growth rate prediction model is solved to obtain the final fatigue crack growth rate prediction model.

2. The method for constructing a pipeline steel fatigue crack growth rate prediction model according to claim 1, characterized in that: According to the Walker formula and the joint factor model, an initial crack growth rate prediction model considering the influence of hydrogen pressure alternating load is constructed, specifically: in, is the crack growth rate, ΔK is the stress intensity factor amplitude, K max is the maximum stress intensity factor, A', b', r are constants, f is the frequency, and R is the stress ratio.

3. The method for constructing a pipeline steel fatigue crack growth rate prediction model according to claim 1, characterized in that: The introduction of hydrogen pressure change optimizes the initial crack growth rate prediction model into a hydrogen pressure adaptive crack growth rate prediction model, specifically: in, is the crack growth prediction item in the low hydrogen pressure domain, is the prediction item of crack growth acceleration in high hydrogen pressure domain, P H and P th are hydrogen partial pressure and hydrogen pressure threshold respectively; Z represents load-related factor; b1, b2, b3 are constants.

4. A pipeline steel fatigue crack growth rate prediction model construction method according to claim 3, characterized in that: Given the hydrogen pressure, solving the constant term in the hydrogen pressure adaptive crack growth rate prediction model to obtain the final fatigue crack growth rate prediction model; Obtain the initial crack growth rate prediction model, and obtain the r value based on the given hydrogen pressure using a multivariate linear regression algorithm; The fitting results in nitrogen environment are used as the value of the constant for crack growth prediction in low hydrogen pressure domain; The r value and the constant value of the crack growth prediction item in the low hydrogen pressure domain are substituted into the hydrogen pressure adaptive crack growth rate prediction model. The least squares method is used for nonlinear surface fitting. The initial value changing iterative algorithm is adopted to solve the constant value of the crack growth acceleration prediction item in the high hydrogen pressure domain to obtain the final fatigue crack growth rate prediction model.

5. A pipeline steel fatigue crack growth rate prediction model construction system, characterized in that: include: The initial model building module is used to build an initial crack growth rate prediction model considering the influence of hydrogen pressure alternating load based on the Walker formula and the joint factor model; A model optimization module is used to introduce hydrogen pressure changes and optimize the initial crack growth rate prediction model into a hydrogen pressure adaptive crack growth rate prediction model; The final model building module is used to solve the constant term in the hydrogen pressure adaptive crack growth rate prediction model for a given hydrogen pressure, and obtain the final fatigue crack growth rate prediction model.

6. A pipeline steel fatigue crack growth rate prediction model construction system according to claim 5, characterized in that: According to the Walker formula and the joint factor model, an initial crack growth rate prediction model considering the influence of hydrogen pressure alternating load is constructed, specifically: in, is the crack growth rate, ΔK is the stress intensity factor amplitude, K max is the maximum stress intensity factor, A', b', r are constants, f is the frequency, and R is the stress ratio.

7. A pipeline steel fatigue crack growth rate prediction model construction system according to claim 5, characterized in that: The introduction of hydrogen pressure change optimizes the initial crack growth rate prediction model into a hydrogen pressure adaptive crack growth rate prediction model, specifically: in, is the crack growth prediction item in the low hydrogen pressure domain, is the prediction item of crack growth acceleration in high hydrogen pressure domain, P H and P th are hydrogen partial pressure and hydrogen pressure threshold respectively; Z represents load-related factor; b1, b2, b3 are constants.

8. A pipeline steel fatigue crack growth rate prediction model construction system according to claim 7, characterized in that: Given the hydrogen pressure, solving the constant term in the hydrogen pressure adaptive crack growth rate prediction model to obtain the final fatigue crack growth rate prediction model; Obtain the initial crack growth rate prediction model, and obtain the r value based on the given hydrogen pressure using a multivariate linear regression algorithm; The fitting results in nitrogen environment are used as the value of the constant for crack growth prediction in low hydrogen pressure domain; The r value and the constant value of the crack growth prediction item in the low hydrogen pressure domain are substituted into the hydrogen pressure adaptive crack growth rate prediction model. The least squares method is used for nonlinear surface fitting. The initial value changing iterative algorithm is adopted to solve the constant value of the crack growth acceleration prediction item in the high hydrogen pressure domain to obtain the final fatigue crack growth rate prediction model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in a method for constructing a pipeline steel fatigue crack growth rate prediction model as described in any one of claims 1 to 4 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the method for constructing a pipeline steel fatigue crack growth rate prediction model as described in any one of claims 1 to 4 are implemented.

Images