Hydrogen conveying pipeline fatigue acceleration experiment method and system based on intelligent feedback regulation and control

Abstract

The invention relates to the technical field of hydrogen transmission pipeline fatigue testing, in particular to an intelligent feedback regulation and control hydrogen transmission pipeline fatigue acceleration experiment method and system. According to the scheme, functional modules such as a data acquisition module, an online data real-time analysis module, a crack propagation evaluation module and an intelligent experiment parameter adjustment module are integrated; by operating functional modules such as a test condition generation unit, a data acquisition unit, an intelligent analysis unit and a feedback regulation unit, human intervention can be reduced through processes such as acquisition, calculation, identification, analysis, judgment and feedback regulation, intelligent monitoring, judgment and regulation of an experiment process are realized, and the test efficiency is improved. Further, the intelligent and accelerated test effect of the pipeline material fatigue crack propagation experiment is achieved, the material fatigue crack steady-state propagation rate of the hydrogen transmission pipeline material under different service conditions is obtained through the data storage unit, and efficient and accurate prediction of the pipeline service life is guided.

Description

Technical Field

[0001] This invention relates to the technical field of fatigue testing for hydrogen pipelines, and more specifically, to an intelligent feedback-controlled accelerated fatigue testing method and system for hydrogen pipelines. Background Technology

[0002] Hydrogen pipelines, during service, are susceptible to fatigue and corrosion damage under multi-field coupling due to stress amplitude, stress ratio, loading frequency, hydrogen pressure, temperature, and other loads and environmental factors. Sudden fracture of pipeline components induced by these factors is a typical failure mode in engineering, causing not only severe economic losses but also potential casualties. To avoid fracture failures during service, it is necessary to conduct material fatigue damage and fatigue performance analysis on hydrogen pipelines before they enter service. This analysis serves as a crucial basis for reliable pipeline design and service life assessment.

[0003] In analyzing the fatigue damage and performance of materials for hydrogen pipelines, obtaining the steady-state crack propagation rate is crucial for assessing fatigue damage and predicting the associated service life of engineering materials. Currently, the primary method is to obtain fatigue crack propagation curves through fatigue crack propagation experiments, thereby deriving the steady-state crack propagation rate. Existing fatigue crack propagation experiments obtain a complete fatigue crack propagation curve under a single service condition through a single experiment; that is, only one fatigue test curve can be obtained for the same experimental sample, and the steady-state crack propagation rate under that single service condition is then determined through analysis. However, for hydrogen pipelines operating under complex service scenarios, using existing fatigue crack propagation experiments to study and analyze the effects of multiple factors on material fatigue damage requires multiple experiments. This results in low experimental efficiency and high labor costs, failing to meet the needs of efficient development of fatigue-resistant materials and accurate assessment of pipeline service life in hydrogen transportation engineering applications. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing fatigue crack propagation experiments, which suffer from low experimental efficiency and high labor costs when studying and analyzing the fatigue damage of hydrogen pipelines under complex service scenarios. These shortcomings fail to meet the needs of efficient development of anti-fatigue materials and accurate assessment of pipeline service life in hydrogen transportation engineering applications. This invention provides an intelligent feedback-controlled accelerated fatigue testing method and system for hydrogen pipelines. This solution enables rapid research and analysis of fatigue damage caused by multiple factors in hydrogen pipeline material samples through intelligent feedback control, achieving the goal of accelerating fatigue testing. While shortening the fatigue testing cycle and reducing fatigue testing costs, it can promote the efficient development of anti-fatigue materials and provide efficient solutions for fatigue damage investigation and service life evaluation.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for accelerating fatigue testing of hydrogen pipelines with intelligent feedback control is provided, comprising the following steps: Step 1: Construct the experimental conditions for fatigue testing based on the service scenarios of hydrogen pipeline materials and form an experimental condition set; set the fatigue test termination condition k value; and select the unimplemented experimental conditions in the experimental condition set to conduct fatigue tests on the hydrogen pipeline material samples. Step 2: Periodically collect experimental data during the fatigue testing of hydrogen pipeline material samples; Step 3: Process the experimental data from Step 2 to obtain the data on the fatigue crack of the hydrogen pipeline material sample when it reaches a steady state under the experimental conditions, and determine whether the stress field intensity factor of the hydrogen pipeline material sample when the fatigue crack reaches a steady state is greater than the fatigue test termination condition threshold. If yes, proceed to Step 4; otherwise, proceed to Step 1. Step 4: After replacing the hydrogen pipeline material sample, proceed with Step 1 until all experimental conditions in the experimental condition set of Step 1 are met, then end the experiment.

[0006] This invention presents an intelligent feedback-controlled accelerated fatigue testing method for hydrogen pipelines. Based on the accelerated fatigue testing needs of pipeline materials under different hydrogen transportation scenarios, it can intelligently feedback and control the data of hydrogen pipeline material samples during fatigue testing, determining whether to continue the experiment or replace the sample. This accelerates the fatigue testing speed of hydrogen pipeline materials and reduces the number of samples required, while minimizing human intervention and further improving the intelligence level of the experiment. This solution enables intelligent accelerated testing of material fatigue crack propagation experiments, reducing human intervention and intelligently monitoring, judging, and adjusting the experimental process. It achieves intelligent and accelerated testing of pipeline material fatigue crack propagation, solving the long-standing problems of low efficiency, high cost, and mechanization in traditional fatigue testing. Finally, the data storage unit obtains the steady-state fatigue crack propagation rate of hydrogen pipeline materials under different service conditions, thereby enabling efficient and accurate prediction of pipeline service life.

[0007] Preferably, in step one, the experimental conditions include load parameters and environmental parameters, wherein the load parameters include the maximum stress amplitude F. max The stress ratio R and the loading frequency f are included; the environmental parameters include: temperature T, pipeline pressure P, and hydrogen doping ratio M.

[0008] Preferably, in step two, the experimental data includes material parameter information, specimen size information, load parameter information, environmental parameter information, and crack propagation information. The material parameter information includes: fracture toughness K. IC Fatigue crack propagation threshold value ΔK th ; The sample size information includes: sample width W, sample thickness B, and pre-crack length a. p ; The load parameter information includes: maximum stress amplitude F max Stress ratio R, loading frequency f; The environmental parameters include: temperature T, pipeline pressure P, and hydrogen doping ratio M. The crack propagation information includes: the fatigue crack length 'a' acquired at the current moment. The acquisition cycle for the material parameter information is the replacement cycle for the hydrogen pipeline material samples; the acquisition cycles for the sample size information, load parameter information, and environmental parameter information are the replacement cycle for the experimental conditions; the crack propagation information is acquired at a fixed frequency f. n Data is collected to obtain the fatigue crack length 'a' at the current moment, which is the fatigue crack length 'a' corresponding to the current cycle number, at a fixed frequency f. n =Loading frequency f.

[0009] Preferably, the experimental data processing in step two includes the following steps: S31: Calculate the fatigue test termination condition threshold and stress intensity factor, specifically: The fatigue test termination threshold K is calculated using the following formula. T : K T =k*K IC Where k is the value of the fatigue test termination condition; K IC For fracture toughness; The maximum stress intensity factor K is calculated using the following formula. max :

[0010]

[0011]

[0012] Where a is the fatigue crack length acquired at the current moment; F max is the maximum stress amplitude; W is the specimen width; B is the specimen thickness; S32: Obtain the fatigue crack propagation rate and stress intensity factor range at the current moment, specifically: The range of stress intensity factor at the current moment can be calculated using the following formula:

[0013]

[0014] Where i is the data point at the current time, F min This represents the minimum stress amplitude. It is the minimum stress intensity factor; S33: Obtain the fatigue crack propagation rate through the following steps: Let the maximum cycle number corresponding to the current data collection frequency be N. t The following Y data sample points are divided into equal intervals X, where 0 < X ​​< 1 / f n The data collection points are divided into N equal intervals X, thereby expanding the Y collection points to N. t / X items, and so on N t Taking the number of cycles N corresponding to X sample points as input, a neural network model is used to obtain the corresponding N. t Let a be the crack length of / X sample points, and define the fatigue crack length corresponding to sample point i as a. i Then, through formula (a) i+1 -a i The fatigue crack propagation rate (da / dN) corresponding to any sample point i can be calculated using ) / X. i This determines the fatigue crack propagation rate. Specifically, dividing the Y data sample points corresponding to the current data acquisition frequency and the maximum cycle number Nt into equal intervals X results in: each of the Y data sample points corresponds to one cycle, where the last acquired sample point corresponds to the maximum cycle number N. t ; S34: Crack propagation status assessment: Determine the maximum number of cycles N t Corresponding points Is it greater than the fatigue crack propagation threshold value ΔK? th And the maximum number of cycles N t The corresponding crack length a t0 ≥3*a p If not, execute S31; if yes, output the fatigue crack propagation rate (da / dN) under the current experimental conditions. i .

[0015] Preferably, in S33, the corresponding N is obtained using a neural network model. t Before determining the crack length of / X sample points, the neural network model is trained using the following steps: Using the collected N~a data, with the cycle number N as input and the fatigue crack length a as output, train the neural network model until the neural network model parameters achieve a fitting accuracy of over 99%, thus completing the training of the neural network model.

[0016] Preferably, after step four, the method further includes: The data from the fatigue cracking of the hydrogen pipeline material samples in step three under all experimental conditions, reaching steady state, are compiled into a dataset and output. Based on the data in this dataset, the actual service life of the pipeline can be modeled and predicted.

[0017] The present invention also provides an intelligent feedback control hydrogen pipeline fatigue acceleration test system for the above-mentioned intelligent feedback control hydrogen pipeline fatigue acceleration test method, including: a data acquisition module, a control and data processing module, and a fatigue test module; The fatigue testing module is used to perform fatigue tests on hydrogen pipeline material samples; The data acquisition module is used to collect experimental data when fatigue testing hydrogen pipeline material samples are performed. The control and data processing module is connected to the fatigue test module and the data acquisition module to control the operation of the fatigue test module and the data acquisition module and to process the data from the data acquisition module.

[0018] This invention discloses an intelligent feedback-controlled accelerated fatigue testing system for hydrogen pipelines, integrating functional modules such as data acquisition, fatigue testing, and data processing. Through processes including acquisition, calculation, identification, analysis, and judgment, it achieves intelligent accelerated testing of material fatigue crack propagation, solving the long-standing problems of low efficiency, high cost, and mechanization in traditional fatigue testing. Finally, it runs a data storage unit to obtain the steady-state fatigue crack propagation rate of hydrogen pipeline materials under different service conditions, guiding efficient and accurate prediction of pipeline service life.

[0019] Preferably, the control and data processing module includes a test condition generation unit, an intelligent analysis unit, a feedback adjustment unit, and a data storage unit. The test condition generation unit is used to establish the experimental conditions for fatigue testing of hydrogen pipeline materials based on the service scenarios. The intelligent analysis unit is used to determine the crack propagation state of the hydrogen pipeline materials based on the data from the data acquisition module. The feedback adjustment unit is used to adjust the fatigue test module based on the crack propagation state results, thereby controlling the fatigue test module to switch experimental conditions. The data storage unit is used to store the data of the fatigue cracks of the hydrogen pipeline material samples reaching a steady state under all experimental conditions and to predict the service life of the pipeline based on the data.

[0020] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines.

[0021] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines.

[0022] Compared with the prior art, the beneficial effects of the present invention are: This invention provides an intelligent feedback-controlled accelerated fatigue testing method and system for hydrogen pipelines. Based on the accelerated fatigue testing needs of pipeline materials under different hydrogen transportation scenarios, it reduces human intervention and achieves intelligent monitoring, judgment, and adjustment of the experimental process. This enables intelligent and accelerated testing of fatigue crack propagation in pipeline materials, solving the long-standing problems of low efficiency, high cost, and mechanization in traditional fatigue testing. Finally, the system utilizes a data storage unit to obtain the steady-state fatigue crack propagation rate of hydrogen pipeline materials under different service conditions, thereby enabling efficient and accurate prediction of pipeline service life. Attached Figure Description

[0023] Figure 1 A flowchart of an intelligent feedback-controlled experimental method for accelerating fatigue in hydrogen pipelines; Figure 2 A block diagram of an intelligent feedback-controlled accelerated fatigue testing method for hydrogen pipelines; Figure 3 This is a graph showing the relationship between fatigue crack length and number of cycles before reaching steady state in Example 3; Figure 4 This is a graph showing the relationship between the fatigue crack propagation rate and the number of cycles obtained from model training in Example 3. Figure 5 This is a graph showing the relationship between fatigue crack length and number of cycles after reaching steady state in Example 3. Figure 6 This is a graph showing the relationship between the fatigue crack propagation rate and the number of cycles obtained from the modeling analysis in Example 3. Detailed Implementation

[0024] Example 1 This embodiment is the first embodiment of an intelligent feedback-controlled accelerated fatigue testing method for hydrogen pipelines. Figure 1 and Figure 2 As shown, it includes the following steps: Step 1: Construct the experimental conditions for fatigue testing based on the service scenarios of hydrogen pipeline materials and form an experimental condition set; set the fatigue test termination condition k value; and select the unimplemented experimental conditions in the experimental condition set to conduct fatigue tests on the hydrogen pipeline material samples. Step 2: Periodically collect experimental data during the fatigue testing of hydrogen pipeline material samples; Step 3: Process the experimental data from Step 2 to obtain the data on the fatigue crack of the hydrogen pipeline material sample when it reaches a steady state under the experimental conditions, and determine whether the stress field intensity factor of the hydrogen pipeline material sample when the fatigue crack reaches a steady state is greater than the fatigue test termination condition threshold. If yes, proceed to Step 4; otherwise, proceed to Step 1. Step 4: After replacing the hydrogen pipeline material sample, proceed with Step 1 until all experimental conditions in the experimental condition set of Step 1 are met, then end the experiment.

[0025] Specifically, in step one, the experimental conditions include load parameters and environmental parameters, and the load parameters include the maximum stress amplitude F. max The stress ratio R and the loading frequency f are included; the environmental parameters include: temperature T, pipeline pressure P, and hydrogen doping ratio M.

[0026] Specifically, in step two, the experimental data includes material parameter information, specimen size information, load parameter information, environmental parameter information, and crack propagation information. The material parameter information includes: fracture toughness K. IC Fatigue crack propagation threshold value ΔK th ; The sample size information includes: sample width W, sample thickness B, and pre-crack length ap. The load parameter information includes: maximum stress amplitude F max Stress ratio R, loading frequency f; The environmental parameters include: temperature T, pipeline pressure P, and hydrogen doping ratio M. The crack propagation information includes: the fatigue crack length 'a' acquired at the current moment. The acquisition cycle for the material parameter information is the replacement cycle for the hydrogen pipeline material samples; the acquisition cycles for the sample size information, load parameter information, and environmental parameter information are the replacement cycle for the experimental conditions; the crack propagation information is acquired at a fixed frequency f. n Data is collected to obtain the fatigue crack length 'a' at the current moment, which is the fatigue crack length 'a' corresponding to the current cycle number, at a fixed frequency f. n =Loading frequency f.

[0027] Specifically, the data processing in step two includes the following steps: S31: Calculate the fatigue test termination condition threshold and stress intensity factor, specifically: The fatigue test termination threshold K is calculated using the following formula. T : K T =k*K IC Where k is the value of the fatigue test termination condition; K IC For fracture toughness; The maximum stress intensity factor K is calculated using the following formula. max :

[0028]

[0029]

[0030] Where a is the fatigue crack length acquired at the current moment; F max is the maximum stress amplitude; W is the specimen width; B is the specimen thickness; S32: Obtain the fatigue crack propagation rate and stress intensity factor range at the current moment, specifically: The range of stress intensity factor at the current moment can be calculated using the following formula:

[0031]

[0032] Where i is the data point at the current time, F min This represents the minimum stress amplitude. This represents the minimum value of the minimum stress field intensity factor. S33: Obtain the fatigue crack propagation rate through the following steps: Let the maximum cycle number corresponding to the current data collection frequency be N. t The following Y data sample points are divided into equal intervals X, where 0 < X ​​< 1 / f n The data collection points are divided into N equal intervals X, thereby expanding the Y collection points to N. t / X items, and so on N t Taking the number of cycles N corresponding to X sample points as input, a neural network model is used to obtain the corresponding N. t Let a be the crack length of / X sample points, and define the fatigue crack length corresponding to sample point i as a. i Then, through formula (a) i+1 -a i The fatigue crack propagation rate (da / dN) corresponding to any sample point i can be calculated using ) / X. i Thus, the fatigue crack propagation rate is determined; S34: Crack propagation status assessment: Determine the maximum number of cycles N t Corresponding points Is it greater than the fatigue crack propagation threshold value ΔK? th And the maximum number of cycles N t The corresponding crack length at0 ≥3*a p If not, execute S31; if yes, output the fatigue crack propagation rate (da / dN) under the current experimental conditions. i .

[0033] Specifically, in S33, the corresponding N is obtained using a neural network model. t Before determining the crack length of / X sample points, the neural network model is trained using the following steps: Using the collected N~a data, with the cycle number N as input and the fatigue crack length a as output, train the neural network model until the neural network model parameters achieve a fitting accuracy of over 99%, thus completing the training of the neural network model.

[0034] Specifically, after step four, the following is also included: The data of fatigue cracks in the hydrogen pipeline material samples in step three under all experimental conditions when they reach steady state are compiled into a dataset and output.

[0035] The beneficial effects of this embodiment are as follows: This embodiment of the intelligent feedback-controlled accelerated fatigue testing method for hydrogen pipelines is based on the accelerated fatigue testing requirements of pipeline materials under different hydrogen transportation scenarios. It can intelligently feedback and control the data of hydrogen pipeline material samples during fatigue testing, determining whether to continue the experiment or replace the sample. This accelerates the fatigue testing speed of hydrogen pipeline materials and reduces the number of samples required. This solution reduces human intervention and achieves intelligent monitoring, judgment, and adjustment of the experimental process, thereby realizing intelligent and accelerated testing of pipeline material fatigue crack propagation. It solves the long-standing problems of low efficiency, high cost, and mechanization in traditional fatigue testing. Finally, the data storage unit is used to obtain the steady-state fatigue crack propagation rate of hydrogen pipeline materials under different service conditions, enabling efficient and accurate prediction of pipeline service life.

[0036] Example 2 This embodiment is an example of an intelligent feedback-controlled hydrogen pipeline fatigue acceleration test system, used in the aforementioned intelligent feedback-controlled hydrogen pipeline fatigue acceleration test method, including: a data acquisition module, a control and data processing module, and a fatigue test module. The fatigue testing module is used to perform fatigue tests on hydrogen pipeline material samples; The data acquisition module is used to collect experimental data when fatigue testing hydrogen pipeline material samples are performed. The control and data processing module is connected to the fatigue test module and the data acquisition module to control the operation of the fatigue test module and the data acquisition module and to process the data from the data acquisition module.

[0037] Specifically, the control and data processing module includes a test condition generation unit, an intelligent analysis unit, a feedback adjustment unit, and a data storage unit. The test condition generation unit is used to establish the experimental conditions for fatigue testing of hydrogen pipeline materials based on the service scenarios. The intelligent analysis unit is used to determine the crack propagation state of the hydrogen pipeline materials based on the data from the data acquisition module. The feedback adjustment unit is used to adjust the fatigue test module based on the crack propagation state results, thereby controlling the fatigue test module to switch experimental conditions. The data storage unit is used to store the data of the fatigue cracks of the hydrogen pipeline material samples reaching a steady state under all experimental conditions and to predict the service life of the pipeline based on the data.

[0038] The beneficial effects of this embodiment are as follows: This embodiment of the intelligent feedback-controlled hydrogen pipeline fatigue accelerated testing system integrates functional modules such as data acquisition, fatigue testing, and data processing. Through processes such as acquisition, calculation, identification, analysis, and judgment, it realizes intelligent accelerated testing of material fatigue crack propagation experiments, solving the long-standing problems of low efficiency, high cost, and mechanization in traditional fatigue testing. Finally, it runs the data storage unit to obtain the steady-state fatigue crack propagation rate of the hydrogen pipeline material under different service conditions, guiding the efficient and accurate prediction of pipeline service life.

[0039] Example 3 This embodiment is an application example of an intelligent feedback-controlled hydrogen pipeline fatigue acceleration test method and system.

[0040] Specifically, it includes the following steps: S1: Using the test condition generation unit, fatigue test experimental conditions are constructed according to the service scenarios of hydrogen pipeline materials. Specifically, for the load parameter—stress amplitude F... max The stress ratio R, loading frequency f, and environmental parameters—temperature T, pipeline pressure P, and hydrogen doping ratio M—are set as shown in Appendix 1. A set of conditions or parameters for fatigue testing is constructed, and each condition or parameter is numbered as shown in Appendix 2.

[0041]

[0042] Table 1 - Requirements for Fatigue Test Load Parameters and Environmental Parameters

[0043] Table 2 - Fatigue Testing Conditions Set Set the fatigue test termination condition k value to 70%. Select the test condition or parameter setting corresponding to number 3, i.e., stress amplitude F. max3With a load of 5kN, a stress ratio R3 of 0.3, a loading frequency f3 of 0.01Hz, and environmental parameters—temperature T3 of 50℃, pipeline pressure P3 of 2MPa, and hydrogen doping ratio M3 of 3%—the fatigue test module was run to begin the experiment.

[0044] S2: Using the data acquisition module, data is collected from the fatigue test module at a frequency of f3 to obtain the fracture toughness K of the current test material. IC It is 93.6 MPa•m 0.5 Fatigue crack propagation threshold value ΔK th 2.5 MPa•m 0.5 The fatigue specimen has a width W of 30 mm, a thickness B of 6 mm, and a pre-existing crack length a. p The crack thickness was 6.15 mm; the load and environmental parameters were as described in S1. An experimental batch was then created, numbered the same as the test condition number in S1, and designated as #1. Real-time crack propagation information is attached. Figure 2 As shown.

[0045] S3: Report the data collected in S2 to the intelligent analysis unit. The intelligent analysis unit performs calculations to determine the fatigue experiment termination condition threshold: K T =k*K IC =70%*93.6MPa•m 0.5 =65.52MPa•m 0.5 Subsequently, based on the currently acquired fatigue crack length of 8.86 mm, according to the formula... The stress intensity factor K was calculated. max 35.7 MPa•m 0.5 , The intelligent analysis unit identifies and determines K. max ≤K T , The intelligent analysis unit then utilizes the currently collected N~a data, i.e., the attached... Figure 2 Using N~a data points as input and a as output, a neural network model is trained, and the model parameters are optimized until the fitting accuracy reaches 99.5%. Then, the maximum number of cycles N corresponding to the 12 data sample points at the current data acquisition frequency is... t =15300, divided into equal intervals of 50, thus expanding the 12 sampling points to 15300 / 50 = 306. Using the cycle number N corresponding to these 306 sample points as input, the previously trained high-precision neural network model predicts the crack length corresponding to these 306 sample points. The fatigue crack length corresponding to sample point i is defined as a. i Then, through formula (a) i+1 -a iThe fatigue crack propagation rate (da / dN) corresponding to sample point i is calculated by dividing the result by 50. i Thus, the fatigue crack propagation rate is determined, as shown in the attached figure. Figure 3 As shown. Simultaneously, according to the formula... The range ΔK of the stress field intensity factor corresponding to any sample point i is calculated.

[0046] Current cycle number N t Corresponding ΔK 21MPa•m 0.5 ≥ΔK th 2.5 MPa•m 0.5 Crack length a Nt =8.86mm<3*a p =3*6.15mm=18.45mm. According to the judgment criteria, the intelligent analysis unit determines that the fatigue crack propagation in the current test has not reached a steady state, so the data acquisition module continues to collect data.

[0047] The updated crack propagation data is attached. Figure 4 As shown, the intelligent analysis unit recalculates based on the updated crack propagation data. Based on the currently acquired fatigue crack length of 18.56 mm, according to the formula... The stress intensity factor K was calculated. max 48.2 MPa•m 0.5 , The intelligent analysis unit identifies and determines K. max ≤K T , The intelligent analysis unit then utilizes the currently collected N~a data, i.e., the attached... Figure 4 Using the N~a data points as input and a as output, the neural network model was retrained, and the model parameters were optimized to achieve a fitting accuracy of 99.7%. Then, the maximum number of cycles N corresponding to the 54 data sample points at the current data acquisition frequency was determined. t =28300, divided into equal intervals of 50, thus expanding the 54 sampling points to 28300 / 50 = 566. Using the cycle number N corresponding to these 566 sample points as input, the previously trained high-precision neural network model predicts the crack length corresponding to these 566 sample points. The fatigue crack length corresponding to sample point i is defined as a. i Then, through formula (a) i+1 -a i The fatigue crack propagation rate (da / dN) for any sample point i is calculated by dividing the result by 50. i Thus, the fatigue crack propagation rate is determined, as shown in the attached figure. Figure 5 As shown. Simultaneously, according to the formula... The range ΔK of the stress field intensity factor corresponding to sample point i is calculated.

[0048] For the newly acquired crack propagation data, the current cycle number N t The corresponding ΔK 27.8 MPa•m 0.5 ≥ΔK th 2.5 MPa•m 0.5 Crack length a Nt =18.56mm>3*a p =3 * 6.15 mm = 18.45 mm. Based on the judgment criteria, the intelligent analysis unit determines that the fatigue crack propagation in the current test has reached a steady state. The steady-state crack propagation rate is the number of cycles N. t The corresponding crack propagation rate.

[0049] S4: Based on the judgment result of the intelligent analysis unit in S3, the feedback adjustment unit sends an instruction to the control terminal of the fatigue test module. Specifically, it randomly selects the untested test condition number 11 from the fatigue test condition set in S1, adjusts the test parameters according to its corresponding load parameters and environmental parameters, restarts the experiment, and continues to S2.

[0050] Simultaneously, the current experimental batch 1# and its corresponding test condition 1, steady-state crack propagation rate (i.e., Figure 5 Medium cycle N t The corresponding crack propagation rate (4.11E-03 mm / cycle) is transmitted to the data storage unit.

[0051] S5: Continue executing S2—S3—S4—S2 until the fatigue test condition set in S1. The conditions (i.e., load parameters and environmental parameters) under all the corresponding user requirement numbers have been tested. The data storage unit stores the results as shown in Table 3.

[0052]

[0053] Table 3 - Fatigue Steady-State Crack Propagation Rates under Different Test Conditions The beneficial effects of this embodiment are as follows: Using the aforementioned intelligent feedback control method and system for parameters, the fatigue steady-state crack propagation rate, which traditionally required 24 samples and experimentally determined data, can now be obtained with only 7 samples. This solution requires only one-third of the original experimental samples to complete the fatigue experiment, achieving an acceleration effect of more than three times. At the same time, fewer samples are used, reducing experimental costs and increasing the level of intelligence in the experiment, effectively reducing the number of human interventions in fatigue test tests under different scenarios.

[0054] Example 4 This embodiment is an example of a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines described in Embodiment 1 above.

[0055] Example 5 This embodiment is an embodiment of a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines described in Embodiment 1 above.

[0056] In the specific implementation of the above embodiments, the technical features can be combined in any non-contradictory way. For the sake of brevity, not all possible combinations of the above technical features are described. However, as long as the combination of these technical features is not contradictory, it should be considered to be within the scope of this specification.

[0057] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for accelerating fatigue testing of hydrogen pipelines with intelligent feedback control, characterized in that, Includes the following steps: Step 1: Construct the experimental conditions for fatigue testing based on the service scenarios of hydrogen pipeline materials and form an experimental condition set; set the fatigue test termination condition k value; and select the unimplemented experimental conditions in the experimental condition set to conduct fatigue tests on the hydrogen pipeline material samples. Step 2: Periodically collect experimental data during the fatigue testing of hydrogen pipeline material samples; Step 3: Process the experimental data from Step 2 to obtain the data on the fatigue crack of the hydrogen pipeline material sample when it reaches a steady state under the experimental conditions, and determine whether the stress field intensity factor of the hydrogen pipeline material sample when the fatigue crack reaches a steady state is greater than the fatigue test termination condition threshold. If yes, proceed to Step 4; otherwise, proceed to Step 1. Step 4: After replacing the hydrogen pipeline material sample, proceed with Step 1 until all experimental conditions in the experimental condition set of Step 1 are met, then end the experiment.

2. The intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines according to claim 1, characterized in that, In step one, the experimental conditions include load parameters and environmental parameters, and the load parameters include the maximum stress amplitude F. max Stress ratio R, loading frequency f; The environmental parameters include: temperature T, pipeline pressure P, and hydrogen doping ratio M.

3. The intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines according to claim 2, characterized in that, In step two, the experimental data includes material parameter information, specimen size information, load parameter information, environmental parameter information, and crack propagation information. The material parameter information includes: fracture toughness K. IC Fatigue crack propagation threshold value ΔK th ; The sample size information includes: sample width W, sample thickness B, and pre-crack length a. p ; The load parameter information includes: maximum stress amplitude F max Stress ratio R, loading frequency f; The environmental parameters include: temperature T, pipeline pressure P, and hydrogen doping ratio M. The crack propagation information includes: the fatigue crack length 'a' acquired at the current moment. The acquisition cycle for the material parameter information is the replacement cycle for the hydrogen pipeline material samples; the acquisition cycles for the sample size information, load parameter information, and environmental parameter information are the replacement cycle for the experimental conditions; the crack propagation information is acquired at a fixed frequency f. n Data is collected to obtain the fatigue crack length 'a' at the current moment, which is the fatigue crack length 'a' corresponding to the current cycle number, at a fixed frequency f. n =Loading frequency f.

4. The intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines according to claim 3, characterized in that, The data processing in step two includes the following steps: S31: Calculate the fatigue test termination condition threshold and stress intensity factor, specifically: The fatigue test termination threshold K is calculated using the following formula. T : K T =k*K IC Where k is the value of the fatigue test termination condition; K IC For fracture toughness; The maximum stress intensity factor K is calculated using the following formula. max : Where a is the fatigue crack length acquired at the current moment; F max is the maximum stress amplitude; W is the specimen width; B is the specimen thickness; S32: Obtain the fatigue crack propagation rate and stress intensity factor range at the current moment, specifically: The range of stress intensity factor at the current moment is calculated using the following formula. : Where i is the data point at the current time, F min This represents the minimum stress amplitude. It is the minimum stress intensity factor; S33: Obtain the fatigue crack propagation rate through the following steps: Let the maximum cycle number corresponding to the current data collection frequency be N. t The following Y data sample points are divided into equal intervals X, where 0 < X ​​< 1 / f n This expands the number of collection points from Y to N. t / X items, and so on N t Taking the number of cycles N corresponding to X sample points as input, a neural network model is used to obtain the corresponding N. t Let a be the crack length of / X sample points, and define the fatigue crack length corresponding to sample point i as a. i Then, through formula (a) i+1 -a i The fatigue crack propagation rate (da / dN) corresponding to any sample point i can be calculated using ) / X. i Thus, the fatigue crack propagation rate is determined; S34: Crack propagation status assessment: Determine the maximum number of cycles N t fatigue crack propagation value at corresponding point Is it greater than the fatigue crack propagation threshold value ΔK? th And the maximum number of cycles N t The corresponding crack length a t0 ≥3*a p If not, execute S31; if yes, output the fatigue crack propagation rate (da / dN) under the current experimental conditions. i .

5. The intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines according to claim 4, characterized in that, In step S33, the corresponding N is obtained using a neural network model. t Before determining the crack length of / X sample points, the neural network model is trained using the following steps: Using the collected N~a data, with the cycle number N as input and the fatigue crack length a as output, the neural network model is trained until the neural network model parameters achieve a fitting accuracy of over 99%, thus completing the training of the neural network model.

6. The intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines according to claim 1, characterized in that, Following step four, the following is also included: The data of fatigue cracks in the hydrogen pipeline material samples in step three under all experimental conditions when they reach steady state are compiled into a dataset and output.

7. A smart feedback-controlled accelerated fatigue testing system for hydrogen pipelines, characterized in that, The method for accelerating fatigue testing of a hydrogen pipeline with intelligent feedback control as described in any one of claims 1-6 includes: a data acquisition module, a control and data processing module, and a fatigue testing module. The fatigue testing module is used to perform fatigue tests on hydrogen pipeline material samples; The data acquisition module is used to collect experimental data when fatigue testing hydrogen pipeline material samples are performed. The control and data processing module is connected to the fatigue test module and the data acquisition module to control the operation of the fatigue test module and the data acquisition module and to process the data from the data acquisition module.

8. The intelligent feedback control-based accelerated fatigue testing system for hydrogen pipelines according to claim 7, characterized in that, The control and data processing module includes a test condition generation unit, an intelligent analysis unit, a feedback adjustment unit, and a data storage unit. The test condition generation unit is used to establish the experimental conditions for fatigue testing of hydrogen pipeline materials based on the service scenarios. The intelligent analysis unit is used to determine the crack propagation state of the hydrogen pipeline materials based on the data from the data acquisition module. The feedback adjustment unit is used to adjust the fatigue test module based on the crack propagation state results, thereby controlling the fatigue test module to switch experimental conditions. The data storage unit is used to store the data of the fatigue cracks of the hydrogen pipeline material samples reaching a steady state under all experimental conditions and to predict the service life of the pipeline based on the data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines as described in any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent feedback control method for accelerating fatigue testing of hydrogen pipelines as described in any one of claims 1 to 6.

Images