Method and device for evaluating integrity of pressure vessel and storage medium

By obtaining load displacement curves and driving forces in the pressure vessel, combining linear elastic fracture mechanics and machine learning, optimizing load rate and fracture toughness rate, and establishing a failure evaluation curve model, solving the low accuracy of pressure vessel integrity evaluation in the existing technology The problem of the evaluation improves the accuracy and reliability of the evaluation.

CN118937058APending Publication Date: 2024-11-12PIPECHINA SOUTH CHINA CO +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410933868.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, the accuracy of the evaluation of the completeness of the pressure vessel is low, and the allocation of multi-parameter contribution is inaccurate, which affects the accuracy of the evaluation.

Method used

By obtaining the area surrounded by the load displacement curve when the crack sample is in the stable crack expansion stage, the elastic-plastic driving force and elastic driving force are determined, and based on linear elastic fracture mechanics and machine learning algorithms, the load rate and fracture toughness rate are optimized, and the load rate and fracture toughness rate are established. Failure evaluation curve model.

Benefits of technology

It improves the accuracy of pressure vessel evaluation, reduces the problem of inaccurate allocation of multi-parameter contribution, and enhances the reliability of pressure vessel integrity evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118937058A_ABST
    Figure CN118937058A_ABST
Patent Text Reader

Abstract

The invention discloses a method for evaluating the integrity of a pressure vessel. The method comprises the following steps: acquiring a first area enclosed by a first load displacement curve and a second area enclosed by a second load displacement curve generated by the crack sample through a flexibility unloading method for two adjacent times under the condition that the crack sample is in a crack stable expansion stage; determining a difference area between the first area and the second area; determining the elastic-plastic driving force of the crack sample according to the difference area; determining a shape factor of the crack sample based on linear elastic fracture mechanics; determining a stress intensity factor of the crack sample at the tip of the crack according to the shape factor; determining an elastic driving force of the crack sample based on the stress intensity factor and an elastic model; determining the fracture toughness of the crack sample according to the elastic-plastic driving force and the elastic driving force; and training and optimizing the load rate and the fracture toughness rate based on a machine learning algorithm to determine an evaluation model. According to the invention, the accuracy of pressure vessel integrity evaluation can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of pipeline engineering, and in particular to a method, a device and a storage medium for evaluating the integrity of a pressure vessel. Background Art

[0002] In the early research on fatigue fracture of welded structures, it was customary to attribute the fatigue failure of welded structures to welding quality problems, and then to find the cause of the problem from the perspective of manufacturing quality, such as fatigue failure of welded structures caused by factors such as poor welding quality and welding defects. In response to this, the British Welding Institute proposed the Engineering Critical Assessment (ECA) method, and formed a Failure Assessment Diagram (FAD) with the Failure Assessment Curve (FAC). There are many factors that affect the Failure Assessment Curve FAC, and the traditional calculation method is prone to inaccurate distribution of multi-parameter contributions, which ultimately affects the accuracy of the pressure vessel integrity assessment. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, device and storage medium for evaluating the integrity of a pressure vessel, so as to solve the problem of low accuracy in evaluating the integrity of a pressure vessel in the prior art.

[0004] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for evaluating the integrity of a pressure vessel, the method comprising:

[0005] When the crack specimen is in a stable crack extension stage, obtaining a first area enclosed by a first load-displacement curve generated by the crack specimen passing through the compliance unloading method for the first time and a second area enclosed by a second load-displacement curve generated by the crack specimen passing through the compliance unloading method for the second time;

[0006] determining a difference area between the first area and the second area;

[0007] Determine the elastic-plastic driving force of the cracked specimen based on the difference area;

[0008] Determine the shape factor of the cracked specimen based on linear elastic fracture mechanics;

[0009] Determine the stress intensity factor of the cracked specimen at the crack tip based on the shape factor;

[0010] Determine the elastic driving force of the cracked specimen based on the stress intensity factor and elastic model;

[0011] Determine the fracture toughness rate of the cracked specimen based on the elastoplastic driving force and the elastic driving force;

[0012] The load rate and fracture toughness rate are trained and optimized based on the machine learning algorithm to determine the failure assessment curve model of the pressure vessel.

[0013] In the embodiment of the present application, determining the difference area between the first area and the second area includes determining the difference area according to formula (1):

[0014]

[0015] Among them, A pl(i) is the second area, A pl(i-1) is the first area, P i is the load at the crack tip when the crack specimen passes the compliance unloading method for the second time, P i-1 is the load at the crack tip when the crack specimen passes the compliance unloading method for the first time, V pl(i) is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the second time, V pl(i-1) It is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the first time.

[0016] In the embodiment of the present application, determining the elastic-plastic driving force of the pressure vessel according to the difference area includes determining the elastic-plastic driving force according to formula (2):

[0017]

[0018] Among them, η pl(i-1) is the plasticity factor of the cracked specimen when it passes the compliance unloading method for the first time, γ pl(i-1) is the shape factor of the cracked specimen when it first passes the compliance unloading method, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the second time, a (i-1) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, b (i-1) is the offset number when the cracked specimen passes the compliance unloading method for the first time, B N is the effective width of the crack specimen, J pl(i-1) is the elastic-plastic driving force of the cracked specimen when it passes the compliance unloading method for the first time, J pl(i) is the elastic-plastic driving force.

[0019] In the embodiment of the present application, based on linear elastic fracture mechanics, determining the shape factor of the cracked specimen includes determining the shape factor according to formula (3):

[0020]

[0021] in, is the shape factor, a (i)is the crack length of the crack specimen when it passes the compliance unloading method for the first time, and W is the thickness of the crack specimen.

[0022] In an embodiment of the present application, determining the stress intensity factor of the crack specimen at the crack tip according to the shape factor includes determining the stress intensity factor according to formula (4):

[0023]

[0024] Where B is the specimen width of the crack specimen, B N is the effective width of the crack specimen, W is the thickness of the crack specimen, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the second time, P is the load of the cracked specimen at the crack tip, K (i) is the stress intensity factor.

[0025] In the embodiment of the present application, determining the elastic driving force of the crack specimen based on the stress intensity factor and the elastic model includes determining the elastic driving force according to formula (5):

[0026]

[0027] Among them, K (i) is the stress intensity factor, ν is the Poisson's ratio of the cracked specimen, E is the elastic model of the cracked specimen, J el(i) The driving force for elasticity.

[0028] In the embodiment of the present application, determining the fracture toughness rate of the cracked specimen according to the elastoplastic driving force and the elastic driving force includes determining the fracture toughness rate according to formula (6):

[0029]

[0030] Among them, J el is the elastic driving force, J pl is the elastoplastic driving force, K r is the fracture toughness rate.

[0031] In the embodiment of the present application, the method further includes determining the load rate according to formula (7):

[0032]

[0033] Among them, σ load is the stress at the crack tip of the crack specimen, σ yield is the yield stress at the crack tip of the crack specimen, L r is the load rate.

[0034] A second aspect of the present application provides a device for evaluating the integrity of a pressure vessel, the device comprising:

[0035] a memory configured to store instructions; and

[0036] The processor is configured to call instructions from the memory and implement the above method for evaluating the integrity of a pressure vessel when executing the instructions.

[0037] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned method for assessing the integrity of a pressure vessel.

[0038] Through the above technical scheme, when the crack specimen is in the stable crack extension stage, the first area enclosed by the first load displacement curve and the second area enclosed by the second load displacement curve generated by the compliance unloading method of the crack specimen twice adjacently are obtained; the elastoplastic driving force of the crack specimen is determined according to the difference between the first area and the second area; the shape factor of the crack specimen is determined based on linear elastic fracture mechanics; the stress intensity factor of the crack specimen at the crack tip is determined according to the shape factor; the elastic driving force of the crack specimen is determined based on the stress intensity factor and the elastic model; the fracture toughness rate of the crack specimen is determined according to the elastoplastic driving force and the elastic driving force; the load rate and fracture toughness rate are trained and optimized based on the machine learning algorithm to determine the failure assessment curve model of the pressure vessel. This application combines the engineering critical assessment method with machine learning, and optimizes the load rate and fracture toughness rate training through machine learning, thereby reducing the problem of inaccurate distribution of multi-parameter contributions to improve the accuracy of pressure vessel assessment.

[0039] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0041] Figure 1 A flow chart of a method for evaluating the integrity of a pressure vessel according to an embodiment of the present application is schematically shown;

[0042] Figure 2 The schematic diagram of the engineering criticality assessment according to the embodiment of the present application is shown;

[0043] Figure 3 The schematic diagram shows the principle diagram of calculating the plastic component of the crack tip using the load displacement curve (LDD) according to an embodiment of the present application;

[0044] Figure 4The load displacement curve (LDD) obtained based on the SENT cyclic compliance unloading method according to an embodiment of the present application is schematically shown;

[0045] Figure 5 A FAC curve diagram obtained based on the SENT cycle compliance unloading method according to an embodiment of the present application is schematically shown;

[0046] Figure 6 The calculation flow chart of the machine learning method of physical constraints according to the embodiment of the present application is schematically shown;

[0047] Figure 7 A schematic diagram of reducing the neural network error according to an embodiment of the present application is schematically shown;

[0048] Figure 8 The uncertainty analysis diagram of the neural network prediction model based on physical constraints according to an embodiment of the present application is schematically shown;

[0049] Fig. 9 A diagram schematically shows a FAC probability model diagram based on physical constraints according to an embodiment of the present application;

[0050] Fig.10 The structure of a device for evaluating the integrity of a pressure vessel according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0052] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0053] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0054] Figure 1 A flow chart of a method for evaluating the integrity of a pressure vessel according to an embodiment of the present application is schematically shown. Figure 1 As shown, an embodiment of the present application provides a method for evaluating the integrity of a pressure vessel, which may include the following steps.

[0055] Step 101: When the crack specimen is in a stable crack extension stage, a first area enclosed by a first load-displacement curve generated when the crack specimen passes through the compliance unloading method for the first time and a second area enclosed by a second load-displacement curve generated when the crack specimen passes through the compliance unloading method for the second time are obtained;

[0056] In the embodiments of the present application, after the cracks show unstable expansion, the engineering critical assessment (ECA) assessment based on the "Fitness for service" (FFS) principle is no longer applicable, but the pressure vessel should be evaluated based on the "leak-before-break" (LBB) criterion. The flexibility unloading method is a technology used to improve the durability and service life of structural materials. It fundamentally changes the organizational structure and mechanical properties of the material by repeatedly loading and unloading the structural material with small amplitudes. The evolution of the load-displacement curve reflects the mechanism of action of the flexibility unloading method in material organizational adjustment.

[0057] Step 102: Determine the difference area between the first area and the second area;

[0058] Step 103: determining the elastic-plastic driving force of the cracked specimen according to the difference area;

[0059] In the embodiments of the present application, the elastic-plastic driving force is a model used in the field of crack mechanics to describe and calculate the driving force of crack extension. Considering that the sample material exhibits elastic-plastic behavior when subjected to force at the crack tip, the elastic-plastic material theory is used to describe its stress-strain state, thereby calculating the driving force of the crack.

[0060] Step 104: determining a shape factor of the cracked specimen based on linear elastic fracture mechanics;

[0061] Step 105: determining the stress intensity factor of the crack specimen at the crack tip according to the shape factor;

[0062] In the embodiments of the present application, linear elastic fracture mechanics is used to describe and study the crack behavior of materials under linear elastic state. The shape factor is used to quantitatively describe the stress state at the tip of the crack specimen. Through the theory and calculation method of linear elastic fracture mechanics, based on the shape factor Y provided by the specific crack specimen structure, the stress intensity factor K value at the crack tip can be calculated by a simple formula.

[0063] Step 106: determining the elastic driving force of the cracked specimen based on the stress intensity factor and the elastic model;

[0064] In the embodiments of the present application, the elastic driving force reflects the degree of mechanical driving force to which crack extension is subjected under the linear elastic assumption.

[0065] Step 107: determining the fracture toughness rate of the cracked specimen according to the elastoplastic driving force and the elastic driving force;

[0066] In the embodiments of the present application, the fracture toughness rate refers to the rate of change of the stress intensity factor required at the tip of the crack specimen under unit extension length.

[0067] Step 108: Based on the machine learning algorithm, the load rate and fracture toughness rate of the cracked specimen are trained and optimized to determine the failure assessment curve model of the pressure vessel.

[0068] In an embodiment of the present application, machine learning is used to train a FAC prediction model with extrapolation capability using the load rate and fracture toughness rate of the cracked specimen calculated by the above technical solution.

[0069] Through the above technical scheme, when the crack specimen is in the stable crack extension stage, the first area enclosed by the first load displacement curve and the second area enclosed by the second load displacement curve generated by the compliance unloading method of the crack specimen twice adjacently are obtained; the elastoplastic driving force of the crack specimen is determined according to the difference between the first area and the second area; the shape factor of the crack specimen is determined based on linear elastic fracture mechanics; the stress intensity factor of the crack specimen at the crack tip is determined according to the shape factor; the elastic driving force of the crack specimen is determined based on the stress intensity factor and the elastic model; the fracture toughness rate of the crack specimen is determined according to the elastoplastic driving force and the elastic driving force; the load rate and fracture toughness rate are trained and optimized based on the machine learning algorithm to determine the failure assessment curve model of the pressure vessel. This application combines the engineering critical assessment method with machine learning, and optimizes the load rate and fracture toughness rate training through machine learning, thereby reducing the problem of inaccurate distribution of multi-parameter contributions to improve the accuracy of pressure vessel assessment.

[0070] In the embodiment of the present application, determining the difference area between the first area and the second area may include determining the difference area according to formula (1):

[0071]

[0072] Among them, A pl(i) is the second area, A pl(i-1) is the first area, P i is the load at the crack tip when the crack specimen passes the compliance unloading method for the second time, P i-1 is the load at the crack tip when the crack specimen passes the compliance unloading method for the first time, V pl(i) is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the second time, V pl(i-1) It is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the first time.

[0073] In the embodiments of the present application, i refers to the number of unloading times, and the difference area is the area difference of the load displacement curves formed by the crack specimen passing through the SENT compliance unloading method twice. SENT refers to the "cyclic-SENT technology" used, which is a general term for many small-amplitude cyclic operations.

[0074] In the embodiment of the present application, determining the elastic-plastic driving force of the pressure vessel according to the difference area may include determining the elastic-plastic driving force according to formula (2):

[0075]

[0076] Among them, η pl(i-1) is the plasticity factor of the cracked specimen when it passes the compliance unloading method for the first time, γ pl(i-1)is the shape factor of the cracked specimen when it first passes the compliance unloading method, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the second time, a (i-1) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, b (i-1) is the offset number when the cracked specimen passes the compliance unloading method for the first time, B N is the effective width of the crack specimen, J pl(i-1) is the elastic-plastic driving force of the cracked specimen when it passes the compliance unloading method for the first time, J pl(i) is the elastic-plastic driving force.

[0077] In the embodiment of the present application, when the material is subjected to the compliance unloading method, the change of the plasticity factor can be evaluated by observing its load-displacement curve. The plasticity factor refers to a factor used to express the degree of hardening effect of the material during plastic deformation under the elastic-plastic theory model. Observing the evolution of the load-displacement curve of the specimen can be used to evaluate whether the compliance unloading method can effectively improve the plasticity factor H of the material, thereby improving its strain hardening ability.

[0078] In an embodiment of the present application, based on linear elastic fracture mechanics, determining the shape factor of the crack specimen may include determining the shape factor according to formula (3):

[0079]

[0080] in, is the shape factor, a (i) is the crack length of the crack specimen when it passes the compliance unloading method for the second time, and W is the thickness of the crack specimen.

[0081] In an embodiment of the present application, determining the stress intensity factor of the crack specimen at the crack tip according to the shape factor may include determining the stress intensity factor according to formula (4):

[0082]

[0083] Where B is the specimen width of the crack specimen, B N is the effective width of the crack specimen, W is the thickness of the crack specimen, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, P is the load of the cracked specimen at the crack tip, K (i) is the stress intensity factor.

[0084] In the embodiments of the present application, the stress intensity factor can quantitatively describe the stress state at the crack tip and is directly related to the crack propagation mechanism.

[0085] In an embodiment of the present application, determining the elastic driving force of the crack specimen based on the stress intensity factor and the elastic model may include determining the elastic driving force according to formula (5):

[0086]

[0087] Among them, K (i) is the stress intensity factor, ν is the Poisson's ratio of the cracked specimen, E is the elastic model of the cracked specimen, J el(i) The driving force for elasticity.

[0088] In the embodiments of the present application, the Poisson's ratio refers to the ratio of the longitudinal and transverse reduction degrees of a material under a compressive load.

[0089] In an embodiment of the present application, determining the fracture toughness rate of the cracked specimen according to the elastoplastic driving force and the elastic driving force may include determining the fracture toughness rate according to formula (6):

[0090]

[0091] Among them, J el is the elastic driving force, J pl is the elastoplastic driving force, K r is the fracture toughness rate.

[0092] In the embodiment of the present application, the method may further include: determining the load rate according to formula (7):

[0093]

[0094] Among them, σ load is the stress at the crack tip of the crack specimen, σ yield is the yield stress at the crack tip of the crack specimen, L r is the load rate.

[0095] In the embodiments of the present application, the load rate is used to describe the ratio of the minimum load to the maximum load during a deformation load cycle; the yield stress refers to the maximum stress at the crack tip after considering the plastic effect of the material; the stress at the crack tip of the crack specimen refers to the stress at the crack tip under the current load.

[0096] The following is a specific embodiment:

[0097] 1. Determine the formula for crack driving force based on the "fit for use" FFS principle, use finite element method to calculate the formula, use the dual parameters of fracture toughness rate and load rate to express the critical relationship of fracture, and the fracture toughness rate and load rate satisfy formula (6) and formula (7):

[0098]

[0099] Among them, J el is the elastic driving force, J pl is the elastoplastic driving force, K r is the fracture toughness ratio, σ load is the stress at the crack tip of the crack specimen, σ yield is the yield stress at the crack tip of the crack specimen, L r is the load rate.

[0100] Formula (6) clearly explains the core idea of ​​the pipeline engineering critical assessment method ECA, that is, the failure assessment curve is represented as a smooth curve, which is formed by interpolation between linear elastic fracture and plastic collapse. The curve above represents the effect of material yield flow on the increase of fracture driving force. The key to the assessment is to calculate the elastic value of the crack driving force, and then deduct the driving force caused by yield flow from the total driving force at the crack tip.

[0101] 2. Determine the crack tip driving force J el and J pl The elastic driving force and elastoplastic driving force are determined by using the SENT specimen with the same constraint conditions as the full tube to perform the compliance unloading method and obtain the area (A) enclosed by the load displacement curve (LDD). pl(i) ) to calculate the plastic part of the crack driving force, J pl(i) Satisfying formula (2), A pl(i) -A pl(i-1) Satisfies formula (1):

[0102]

[0103] Among them, η pl(i-1) is the plasticity factor of the cracked specimen when it passes the compliance unloading method for the first time, γ pl(i-1) is the shape factor of the cracked specimen when it first passes the compliance unloading method, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the second time, a (i-1) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, b (i-1) is the offset number when the cracked specimen passes the compliance unloading method for the first time, B N is the effective width of the crack specimen, J pl(i-1) is the elastic-plastic driving force of the cracked specimen when it passes the compliance unloading method for the first time, J pl(i) is the elastic-plastic driving force, A pl(i) is the second area, A pl(i-1) is the first area, P i is the load at the crack tip when the crack specimen passes the compliance unloading method for the second time, P i-1 is the load at the crack tip when the crack specimen passes the compliance unloading method for the first time, V pl(i)is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the second time, V pl(i-1) It is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the first time. The unloading point at the stable crack extension stage is used to perform the dual parameter calculation of the engineering critical assessment. The purpose of this is that after the crack shows unstable extension, the ECA assessment based on the FFS principle is no longer applicable, but based on the "leak before break" criterion (Leak-before-break, LBB).

[0104] 3. After determining the driving force at the elastoplastic crack tip based on the load-displacement curve LDD, the linear elastic fracture mechanics (LEFM) theory is used to solve the elastic component of the crack driving force, that is, to solve the elastic driving force and determine the elastic driving force J. el(i) Satisfies formula (5):

[0105]

[0106] Among them, K (i) is the stress intensity factor, ν is the Poisson's ratio of the cracked specimen, E is the elastic model of the cracked specimen, J el(i) The driving force for elasticity.

[0107] Determine K (i) The stress intensity factor satisfies formula (4):

[0108]

[0109] Where P is the load at the crack tip, B is the specimen width of the crack specimen, and B N is the effective width of the crack specimen, W is the thickness of the crack specimen, is the shape factor of the cracked specimen.

[0110] Satisfies formula (3):

[0111]

[0112] is the shape factor, a (i) is the crack length of the crack specimen when it passes the compliance unloading method for the second time, and W is the thickness of the crack specimen.

[0113] It can be deduced from the linear elastic fracture theory that in the dominant part of linear elastic fracture mechanics, the path-independent J-integral and the energy release rate G are equivalent, and J∝K 2 , so the elastic component of the crack driving force is calculated by formula (5), that is, the elastic driving force is solved.

[0114] 4. By adopting the cyclic compliance unloading method, the elastic and elastoplastic crack driving forces and the applied load values ​​are obtained. According to the above calculation formula, the double parameters of the failure assessment curve FAC of the stable crack extension part in the cyclic compliance unloading method can be obtained, as shown in Table 1. 0 is the crack length, W is the thickness of the cracked specimen, B is the specimen width of the cracked specimen, σ y is the yield stress at the crack tip of the crack specimen, σ l is the stress at the crack tip of the crack specimen, L r is the load rate, K r is the fracture toughness rate.

[0115] Table 1

[0116] No. <![CDATA[a 0 / W]]> B <![CDATA[σ y / s l ]]> <![CDATA[L r ]]> <![CDATA[K r ]]> 1 0.249 17.090 0.884 0.983 0.907 2 0.249 17.090 0.884 1.084 0.811 3 0.249 17.090 0.884 1.148 0.740 4 0.249 17.090 0.884 1.183 0.681 5 0.249 17.090 0.884 1.215 0.633 6 0.249 17.090 0.884 1.237 0.595 7 0.249 17.090 0.884 1.257 0.560 8 0.249 17.090 0.884 1.267 0.533 9 0.249 17.090 0.884 1.278 0.511 10 0.249 17.090 0.884 1.290 0.487 11 0.249 17.090 0.884 1.292 0.466 12 0.249 17.090 0.884 1.307 0.448

[0117] 5. Since the test process is complicated and is affected by uncertain factors such as equipment accuracy, measurement accuracy, material properties, and environmental variables, the data often fluctuate to a certain extent, so it is difficult to obtain continuous and stable test data. Therefore, the present invention adopts a machine learning algorithm based on physical constraints (physics-informed machine learning), which utilizes the advantages of machine learning in the field of nonlinear complex model learning. The complex FAC curve can be modeled and extrapolated, and the general fitting criteria satisfy formula (8):

[0118]

[0119] Where x is the test set input data, is the predicted output data, f * (·) is the optimal approximate mapping function that satisfies the Universal Approximation Theorem, that is, the trained neural network. At the same time, the neural network also needs to satisfy formula (9), formula (10), formula (11) and formula (12):

[0120]

[0121] in, is a parameterized function family, f(x;θ) is a function of parameter θ, w and b are the weight and bias of the activation function φ(x), K is the number of nonlinear activation functions in the hidden layer, and f * (·) is the general approximation theorem function.

[0122] The difference between the feedforward neural network and the BP neural network lies in the parameter update method during the training of the neural network. The following formula (14) and formula (15) are used to explain the parameter update methods of the two networks respectively:

[0123] z (l) =w (l) a (l-1) +b (l) (14)

[0124] a (l) =φ l (z (l) ) (15)

[0125] where z (l) is the net input value of the lth layer of neurons and a (l) is the output value of the neuron in the lth layer. Since the weights and bias values ​​are randomly assigned rather than optimal values ​​when the neural network is initialized, it is necessary to update the network parameters through the gradient descent method, and then update the overall network parameters to improve the prediction accuracy. The method for training a feedforward neural network to update the network parameters is to adjust the network parameters in the opposite direction of the gradient increase, start the next round of training and satisfy formula (16) and formula (17):

[0126]

[0127] where w t and b t is the network parameter of the tth iteration, and α is the learning rate of the feedforward neural network.

[0128] When training the error back propagation network, the gradient descent method is also used, but the difference is that the error is reversely updated through the learning rate hyperparameter α through the chain rule of derivation until the first layer is updated. Then the next round of training begins and satisfies formulas (18) and (19):

[0129]

[0130] where z (l) is the net input value of each layer of the neural network, δ (l) is the partial derivative of the lth layer. After obtaining the error value of each layer, the weight value and bias value are reversely updated through the preset learning rate α to satisfy formula (20) and formula (21):

[0131] w (l) ←w (l) -αδ (l) (z (l-1) ) (20)

[0132] b (l) ←b (l) -αδ (l) (twenty one)

[0133] 6. The innovative concept of the probability model is introduced to enhance the interpretability of the existing FAC, make up for the data caused by the discontinuity of the test, and play a role in collaborative inference, that is, through the existing data and constraints, the data is reasonably extrapolated and the robustness is reduced. The probability model can filter outliers in the data. At the same time, the dual-parameter model used in the present invention is expressed in polar coordinates, because in the polar coordinate system, the relationship between the angle and the distance in the FAL can be better reflected, which is convenient for fracture failure assessment.

[0134] Formula (22) and Formula (23) illustrate the necessity of using the probability model, which can effectively reduce the conservatism of the existing ECA evaluation and improve the design economy while ensuring safety during the engineering construction process.

[0135]

[0136] Perform probability statistics on the prediction interval and the angle θ r and the distance from the origin ρ r , perform probability statistics and finally obtain the FAC curve under the probability model.

[0137] Figure 2 The schematic diagram of the engineering criticality assessment according to the embodiment of the present application is shown as follows: Figure 2 As shown, Figure 2The relationship between the material fracture toughness rate and the load rate in the failure assessment diagram is explained in the text. In addition, the relationship between the crack driving force obtained based on finite element calculation and the failure assessment curve is also explained to explain the basic working principle of engineering critical assessment. Flaw Dimensions of cracked specimens. Stress analysis refers to the use of finite element method to analyze the stress state of cracked components, and the crack driving force is obtained through stress analysis calculation to provide a basis for subsequent failure assessment. Stress concentration factor (SIF), the calculation of crack driving force requires the use and consideration of stress concentration factor. Material toughness, that is, material fracture toughness rate (Material Toughness), this parameter can reflect the energy absorption capacity of a material when it fractures and characterize its toughness. The material toughness ratio is equal to the ratio of the stress concentration factor to the material fracture toughness rate, which represents the maximum strain that the material can withstand after being subjected to a certain stress. Brittle fracture (Brittle Fracture). Failure Assessment Diagram Envelope, the curve forms an enveloping area, which can be called the failure assessment diagram limit range. Unacceptable failure region refers to the region outside the limit range of the failure assessment graph, which is defined as the region of structural failure from the perspective of engineering technology. Mixed Mode-Brittle Fracture And Plastic Collapse refers to the mixed failure of brittle and plastic modes in the failure process. Acceptable region is used to define the standard reference region where the structure has not yet reached the failure threshold. Assessment point is used to indicate the detection value point of the actual structural failure state. Figure 2The coordinate system represents the point, i.e., the "assessment point". Plastic collapse refers to the overall structural collapse failure mode dominated by viscoplastic deformation that occurs after the structural material exceeds the elastic limit. Load ratio refers to the ratio of the current loading level to the maximum load level of the structural design benchmark in structural analysis. Flaw dimensions refer to the size parameters of the initial defects considered in structural analysis. Reference stress solution is a set of reference stress data obtained by numerical calculation or theoretical formula, providing a benchmark result for comparative analysis of actual test data. Material yield strength refers to the strength value at which a material first undergoes permanent deformation when subjected to stress. The numerator represents the reference stress solution, i.e., the stress value obtained by theoretical calculation; the denominator represents the yield strength of the material, i.e., the critical stress at which the material begins to undergo plastic deformation. The horizontal axis represents stress and the vertical axis represents strength.

[0138] Figure 3 The schematic diagram shows the principle diagram of calculating the plastic component of the crack tip using the load displacement curve (LDD) according to the embodiment of the present application. Figure 3 As shown, Figure 3 The LDD curve is used to analyze and calculate the plastic deformation of the crack tip. The horizontal axis represents the displacement, which is the distance the material moves relative to its original position after being affected by the external load. It can reflect the degree of deformation of the material during the deformation process. The vertical axis represents the external force (Load) applied to the material. The size of the Load directly affects the degree of strain of the material during the deformation process. Figure 3 The shaded area (A pl ) represents the effective plastic energy absorbed by the material throughout the stress-strain curve and is used to quantify and compare the energy absorption capacity of different materials in the plastic deformation stage.

[0139] Figure 4 The load displacement curve (LDD) obtained based on the SENT cyclic compliance unloading method according to an embodiment of the present application is schematically shown. Figure 4 As shown, Figure 4 The definitions of the stable crack extension part and the unstable crack extension part on the LDD curve are clarified, providing a basis for subsequent analysis. Figure 4The curve in records the relationship between the material crack opening displacement and the applied load. The horizontal axis represents the opening displacement of the material crack mouth over time. The vertical axis represents the load applied to the material during the same period. Crack Mouth Opening Displacement (CMOD), the horizontal axis unit is millimeter (mm). Load size (P), the vertical axis unit is kilonewton (KN). Stable propagation refers to the stage of uniform and stable crack expansion process. Unstable propagation refers to the stage of uneven and unstable crack expansion process. Speciment No. 9. The change of crack opening displacement and applied load (PV Curve), through the PV Curve, the pressure bearing capacity of the material at different crack expansion stages can be judged. Valid data means that these data can reflect the actual situation and are representative.

[0140] Figure 5 The FAC curve diagram obtained based on the SENT cycle compliance unloading method according to an embodiment of the present application is schematically shown, as shown in FIG. Figure 5 As shown, Figure 5 The fracture probability of the material under different stresses is recorded to provide a reference for engineering critical assessment. The unsafe area (Pontentially unsafe) and the corresponding shaded area are the safe area (Safe). The vertical axis is Kr, which represents the fracture rate, and the horizontal axis is Lr, which represents the load rate. The conservative assessment region (Conservative assessment region) is Figure 5 The part between the dotted curve and the solid point curve, that is, the part between the safe area and the unsafe area, is intended to improve the safety and reliability of the assessment.

[0141] Figure 6 The calculation flow chart of the machine learning method of physical constraints according to the embodiment of the present application is schematically shown. Figure 6 As shown, Figure 6 The main steps of using physical constraints to train and optimize machine learning models are described: Input parameters, labeling input parameters, preprocessing, training dataset, artificial neural network model, testing dataset, generating model, and output.

[0142] Figure 7 A schematic diagram of reducing the neural network error according to an embodiment of the present application is shown schematically. Figure 7 As shown, Figure 7 It explains how to combine physical constraints with neural networks to train and optimize models. Mean squared error (MSE) The learning curve of the ANN model based on the MSE loss function on the test data reflects that its fitting accuracy is improving. The 50th percentile training epochs refers to the number of cycles when the number of training epochs reaches the middle value and median from the overall change curve of MSE, which can reflect an important progress indicator of the model fitting effect. The number of cycles of model training (Training epochs).

[0143] Figure 8 The uncertainty analysis diagram of the neural network prediction model based on physical constraints according to an embodiment of the present application is schematically shown. Figure 8 As shown, Figure 8 Used to analyze the uncertainty of the results obtained based on such networks. Prediction value after BPNN network training (BPNN training value). Regression target value (Regression target value). The data used for training is divided into 70% training set (training set), 15% testing set (testing set), and 15% validation set (validset). The purpose of dividing the data set is to enhance the training accuracy of the neural network. After the original data is input into the neural network, the prediction value (training value) will be obtained through training. At this time, the prediction value and the target value (target value) are linearly regressed. The purpose of this step is to evaluate the accuracy of the prediction model. The closer the Rsquared value is to 1, the higher the model accuracy. The Rsquared of this model is 0.95, which proves that the FAC curve predicted by the neural network has a high accuracy.

[0144] Fig. 9 The following schematically shows a FAC probability model diagram based on physical constraints according to an embodiment of the present application. Fig. 9 As shown in the figure, the model combines physical constraints to derive the probability distribution of material failure under different conditions, providing a decision reference for engineering evaluation. BP neural network prediction: 90% confidence interval (BP predicts: 90% confidence region). BP neural network predicts a survival rate of 50% (BP predicts: survival rate 50%). The vertical axis is Kr, which represents the fracture rate, and the horizontal axis is Lr, which represents the load rate. There is a certain confidence area in the structure predicted by the neural network, such as Fig. 9As shown, the 90% confidence interval is selected for display, the curve of 50% inventory rate is taken as the average curve, and the dashed line is the evaluation safety zone of the existing specification. The solid line (neural network prediction) FAC curve, the dashed line (current standard) FAC curve.

[0145] Fig.10 The structure block diagram of a device for evaluating the integrity of a pressure vessel according to an embodiment of the present application is schematically shown. Fig.10 As shown, an embodiment of the present application provides a controller, which may include:

[0146] Memory 1010, configured to store instructions; and

[0147] The processor 1020 is configured to call instructions from the memory 1010 and implement the above-mentioned method for evaluating the integrity of a pressure vessel when executing the instructions.

[0148] Specifically, in the embodiment of the present application, the processor 1020 may be configured to:

[0149] When the crack specimen is in a stable crack extension stage, obtaining a first area enclosed by a first load-displacement curve generated by the crack specimen passing through the compliance unloading method for the first time and a second area enclosed by a second load-displacement curve generated by the crack specimen passing through the compliance unloading method for the second time;

[0150] determining a difference area between the first area and the second area;

[0151] Determine the elastic-plastic driving force of the cracked specimen based on the difference area;

[0152] Determine the shape factor of the cracked specimen based on linear elastic fracture mechanics;

[0153] Determine the stress intensity factor of the cracked specimen at the crack tip based on the shape factor;

[0154] Determine the elastic driving force of the cracked specimen based on the stress intensity factor and elastic model;

[0155] Determine the fracture toughness rate of the cracked specimen based on the elastoplastic driving force and the elastic driving force;

[0156] The load rate and fracture toughness rate of cracked specimens are trained and optimized based on machine learning algorithms to determine the failure assessment curve model of pressure vessels.

[0157] Furthermore, the processor 1020 may be further configured to:

[0158] Determining the difference area between the first area and the second area includes determining the difference area according to formula (1):

[0159]

[0160] Among them, A pl(i) is the second area, A pl(i-1) is the first area, P i is the load at the crack tip when the crack specimen passes the compliance unloading method for the second time, P i-1 is the load at the crack tip when the crack specimen passes the compliance unloading method for the first time, V pl(i) is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the second time, V pl(i-1) It is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the first time.

[0161] Furthermore, the processor 1020 may be further configured to:

[0162] Determining the elastic-plastic driving force of the pressure vessel according to the difference area includes determining the elastic-plastic driving force according to formula (2):

[0163]

[0164] Among them, η pl(i-1) is the plasticity factor of the cracked specimen when it passes the compliance unloading method for the first time, γ pl(i-1) is the shape factor of the cracked specimen when it first passes the compliance unloading method, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the second time, a (i-1) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, b (i-1) is the offset number when the cracked specimen passes the compliance unloading method for the first time, B N is the effective width of the crack specimen, J pl(i-1) is the elastic-plastic driving force of the cracked specimen when it passes the compliance unloading method for the first time, J pl(i) is the elastic-plastic driving force.

[0165] Furthermore, the processor 1020 may be further configured to:

[0166] Based on linear elastic fracture mechanics, determining the shape factor of a cracked specimen includes determining the shape factor according to formula (3):

[0167]

[0168] in, is the shape factor, a (i) is the crack length of the crack specimen when it passes the compliance unloading method for the second time, and W is the thickness of the crack specimen.

[0169] Furthermore, the processor 1020 may be further configured to:

[0170] Determining the stress intensity factor of the crack specimen at the crack tip based on the shape factor includes the stress intensity factor according to formula (4):

[0171]

[0172] Where B is the specimen width of the crack specimen, B N is the effective width of the crack specimen, W is the thickness of the crack specimen, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, P is the load of the cracked specimen at the crack tip, K (i) is the stress intensity factor.

[0173] Furthermore, the processor 1020 may be further configured to:

[0174] Determining the elastic driving force of a cracked specimen based on the stress intensity factor and the elastic model includes determining the elastic driving force according to formula (5):

[0175]

[0176] Among them, K (i) is the stress intensity factor, v is the Poisson's ratio of the cracked specimen, E is the elastic model of the cracked specimen, J el(i) The driving force for elasticity.

[0177] Furthermore, the processor 1020 may be further configured to:

[0178] Determining the fracture toughness rate of a cracked specimen based on the elastoplastic driving force and the elastic driving force includes determining the fracture toughness rate based on formula (6):

[0179]

[0180] Among them, J el is the elastic driving force, J pl is the elastoplastic driving force, K r is the fracture toughness rate.

[0181] Furthermore, the processor 1020 may be further configured to:

[0182] Determine the load rate according to formula (7):

[0183]

[0184] Among them, σ load is the stress at the crack tip of the crack specimen, σ yield is the yield stress at the crack tip of the crack specimen, L r is the load rate.

[0185] Through the above technical solution, when the crack specimen is in the stable crack extension stage, the processor 1020 obtains the first area enclosed by the first load displacement curve and the second area enclosed by the second load displacement curve generated by the compliance unloading method for two adjacent times of the crack specimen; the elastoplastic driving force of the crack specimen is determined according to the difference between the first area and the second area; the shape factor of the crack specimen is determined based on linear elastic fracture mechanics; the stress intensity factor of the crack specimen at the crack tip is determined according to the shape factor; the elastic driving force of the crack specimen is determined based on the stress intensity factor and the elastic model; the fracture toughness rate of the crack specimen is determined according to the elastoplastic driving force and the elastic driving force; the processor 1020 optimizes the load rate and the fracture toughness rate training based on the machine learning algorithm to determine the failure assessment curve model of the pressure vessel. This application combines the engineering critical assessment method with machine learning, and optimizes the load rate and the fracture toughness rate training through machine learning, thereby reducing the problem of inaccurate multi-parameter contribution distribution, so as to improve the accuracy of pressure vessel assessment.

[0186] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned method for evaluating the integrity of a pressure vessel.

[0187] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0188] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0189] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0190] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0191] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0192] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0193] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0194] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0195] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for assessing the integrity of a pressure vessel, characterized in that The method comprises: When the crack specimen is in a stable crack extension stage, obtaining a first area enclosed by a first load-displacement curve generated by the crack specimen passing through the compliance unloading method for the first time and a second area enclosed by a second load-displacement curve generated by the crack specimen passing through the compliance unloading method for the second time; determining a difference area between the first area and the second area; determining the elastic-plastic driving force of the crack specimen according to the difference area; Determining a shape factor of the cracked specimen based on linear elastic fracture mechanics; determining a stress intensity factor of the crack specimen at a crack tip according to the shape factor; determining an elastic driving force of the crack specimen based on the stress intensity factor and the elastic model; determining a fracture toughness rate of the crack specimen according to the elastoplastic driving force and the elastic driving force; The load rate and the fracture toughness rate of the crack specimen are trained and optimized based on a machine learning algorithm to determine a failure assessment curve model of the pressure vessel.

2. The method according to claim 1, characterized in that Determining the difference area between the first area and the second area includes determining the difference area according to formula (1): Among them, A pl(i) is the second area, A pl(i-1) is the first area, P i is the load at the crack tip when the cracked specimen passes the compliance unloading method for the second time, P i-1 is the load at the crack tip when the crack specimen passes the compliance unloading method for the first time, V pl(i) is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the second time, V pl(i-1) It is the displacement of the crack mouth when the crack specimen passes the compliance unloading method for the first time.

3. The method according to claim 1, characterized in that Determining the elastic-plastic driving force of the pressure vessel according to the difference area includes determining the elastic-plastic driving force according to formula (2): Among them, η pl(i-1) is the plasticity factor of the cracked specimen when it passes the compliance unloading method for the first time, γ pl(i-1) is the shape factor of the cracked specimen when it passes the compliance unloading method for the first time, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the second time, a (i-1) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, b (i-1) is the offset number when the cracked specimen passes the compliance unloading method for the first time, B N is the effective width of the crack specimen, J pl(i-1) is the elastic-plastic driving force of the cracked specimen when it passes the compliance unloading method for the first time, J pl(i) is the elastic-plastic driving force.

4. The method according to claim 1, characterized in that: Determining the shape factor of the crack specimen based on linear elastic fracture mechanics includes determining the shape factor according to formula (3): in, is the shape factor, a (i) is the crack length of the crack specimen when it passes the compliance unloading method for the second time, and W is the thickness of the crack specimen.

5. The method according to claim 1, characterized in that Determining the stress intensity factor of the crack specimen at the crack tip according to the shape factor includes determining the stress intensity factor according to formula (4): Wherein, B is the specimen width of the crack specimen, B N is the effective width of the crack specimen, W is the thickness of the crack specimen, a (i) is the crack length of the cracked specimen when it passes the compliance unloading method for the first time, P is the load of the cracked specimen at the crack tip, K (i) is the stress intensity factor.

6. The method according to claim 1, characterized in that Determining the elastic driving force of the crack specimen based on the stress intensity factor and the elastic model includes determining the elastic driving force according to formula (5): Among them, K (i) is the stress intensity factor, ν is the Poisson's ratio of the cracked specimen, E is the elastic model of the cracked specimen, J el(i) is the elastic driving force.

7. The method according to claim 1, characterized in that Determining the fracture toughness rate of the crack specimen according to the elastoplastic driving force and the elastic driving force includes determining the fracture toughness rate according to formula (6): Among them, J el is the elastic driving force, J pl is the elastic-plastic driving force, K r is the fracture toughness rate.

8. The method according to claim 1, characterized in that The method further includes determining the load rate according to formula (7): Among them, σ load is the stress at the crack tip of the crack specimen, σ yield is the yield stress at the crack tip of the crack specimen, L r is the load rate.

9. A device for evaluating the integrity of a pressure vessel, characterized in that include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and implement the method for assessing the integrity of a pressure vessel according to any one of claims 1 to 8 when executing the instructions.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for causing a machine to execute the method for evaluating the integrity of a pressure vessel according to any one of claims 1 to 8.