Method for predicting fatigue life of welding seam of adsorber under hydrogen-rich alternating load based on digital twinning

Abstract

The invention belongs to the field of welding, and particularly discloses a method for predicting the fatigue life of an adsorber weld joint under a hydrogen-rich alternating load based on digital twinning, and the method comprises the steps: obtaining the hardness, defect and residual stress distribution of a welding joint through nondestructive testing; performing a high-cycle fatigue performance test in a pure hydrogen atmosphere, and establishing a performance database; a deep generative adversarial network (GAN) is used for enhancing data, a machine learning model is established in combination with support vector regression (SVR), and the fatigue life of the welding seam is predicted by considering material strength degradation, residual stress and defect characteristics; the performance of the weld fatigue life model is evaluated by adopting multiple indexes, and correlation analysis is carried out to improve the prediction precision. The method comprises the corresponding steps of adsorber welding seam nondestructive testing, welding seam fatigue performance testing, defective welding joint high-cycle fatigue performance testing and the like, the digital twinning technology and machine learning are combined, the precision and reliability of welding seam fatigue life prediction are improved, and the method has great significance in optimizing equipment maintenance and improving operation efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of welding, and specifically discloses a method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins. Background Art

[0002] As the core equipment in key fields such as coal chemical industry and petroleum, the stability of the performance and the health of the pressure swing adsorber are crucial to ensure the continuity and safety of the production process. Pressure swing adsorption technology realizes the effective separation of single gas in the mixed gas through the principle of high-pressure adsorption and low-pressure analysis. However, in the actual operation process, because the equipment needs to withstand complex working conditions such as high temperature, high pressure and alternating loads, the weld area often becomes a weak link in the safety of the equipment. Especially in a hydrogen-rich environment, the weld may suffer from serious failure problems such as cracking and bulging due to the combined effects of multiple factors such as alternating stress, mechanical vibration, temperature changes and hydrogen corrosion.

[0003] At present, the main means of detecting the safety status of pressure swing adsorber welds is regular sampling. This method not only has a long inspection cycle and high cost, but also has a low degree of intelligence, making it difficult to achieve real-time monitoring and accurate prediction of the equipment status. Therefore, there is an urgent need for a scientific, accurate and efficient weld fatigue life prediction method to improve the operating efficiency of pressure swing adsorption devices, ensure production safety, and reduce downtime and production costs caused by equipment failures. Summary of the invention

[0004] In order to solve the above problems, the present invention discloses a method and device for predicting the fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins. The method combines multidisciplinary technical means such as nondestructive testing, high-cycle fatigue performance testing, defect simulation and testing, database construction, deep learning adversarial network (GAN) data enhancement, support vector regression (SVR) machine learning model and digital twin technology, aiming to achieve accurate prediction and scientific management of the fatigue life of pressure swing adsorber welds. Through the present invention, the accuracy and reliability of weld fatigue life prediction can be significantly improved, providing a scientific basis for equipment maintenance plans and improvement measures, thereby improving the overall operating efficiency and safety of pressure swing adsorption devices.

[0005] The present invention includes the following technical solutions:

[0006] A method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins, characterized in that it comprises the following steps:

[0007] (a) Perform non-destructive testing on the pressure swing adsorber, including ultrasonic testing, magnetic particle testing and X-ray testing, to obtain the defects and spatial distribution of residual stress in the heat affected zone and weld of the adsorber weld joint; the defects include geometric features such as pores, microcracks, undercuts and excess height, and record the hardness of the heat affected zone and weld;

[0008] (b) In a pure hydrogen atmosphere, high cycle fatigue performance tests are performed on welded joints of Q345R steel or other steel adsorber scaled parts to obtain SN curves of the heat affected zone and welds. The maximum stress range of the test is 200-400 MPa, and the stress ratio is -1 to 0.8;

[0009] (c) Prepare defective Q345R steel or other steel adsorber welded scaled parts, count the number and size of defects, and obtain the SN curve of defective welded joints in a pure hydrogen atmosphere;

[0010] (d) establishing a high cycle fatigue performance database of the weld and heat affected zone of the adsorber weld joint in a hydrogen atmosphere based on the SN curves and defect feature distribution data obtained in steps (a) to (c);

[0011] (e) Data enhancement is performed based on the adversarial network GAN, using the generator network Generator, G and the discriminator network Discriminator, D to generate data consistent with the real data distribution to obtain a sufficient number of labeled samples;

[0012] (f) using the data set in step (d) and the data generated in step (e), establishing an adaptive machine learning model based on support vector regression (SVR), wherein the input variables include stress and defect characteristics, and the output variable is the corresponding fatigue life; the model uses the fatigue crack growth rate formula da / dN f =C(ΔK) m To evaluate the fatigue crack growth life, C and m are material constants; ΔK is the stress intensity factor, and ΔK is given by the formula Calculated; A is the projected defect area on the plane perpendicular to the maximum principal stress; Y is the position constant, 0.5 for internal defects and 0.65 for surface and subsurface defects; Δσ is the applied stress range;

[0013] (g) Using the coefficient of determination R 2, mean absolute percentage error MAPE and root mean square error RMSE are used to evaluate the performance of the established machine learning model to ensure prediction accuracy; wherein, the adaptive machine learning model in step (f) also includes correlation analysis between input variables, and the Pearson correlation coefficient is used to evaluate the multicollinearity between input variables to improve the prediction accuracy of the model; the predicted fatigue strength σw is calculated using the formula σw=Y1×(HV / σb)×Δσ; Y1 is the position constant, internal defects are 1.56, and surface and sub-surface defects are 1.43; HV is the Vickers hardness, and σb is the tensile strength.

[0014] In the above step (a), first, non-destructive testing is performed on the pressure swing adsorber, including ultrasonic testing, magnetic particle testing and X-ray testing, to obtain the defects (such as pores, microcracks, undercuts and excess height) and the spatial distribution of residual stress in the heat-affected zone and weld of the welded joint, and record the hardness information to provide basic data for subsequent analysis; (b) Then, the high-cycle fatigue performance test is performed on the Q345R steel or other steel adsorber scale welded joint in a pure hydrogen atmosphere to obtain the SN curve of the heat-affected zone and weld, which reflects the fatigue performance of the material within a specific stress range. (c) At the same time, a Q345R steel or other steel adsorber welded scale with defects is prepared, and its SN curve is tested in a pure hydrogen atmosphere to consider the effect of defects on fatigue performance. (d) Based on the data obtained in steps (a) and (c), a high-cycle fatigue performance database of adsorber welded joints in a hydrogen atmosphere is established to provide rich training data for the machine learning model. (e) Then, deep generative adversarial network (GAN) is used for data enhancement to generate data consistent with the real data distribution, so as to expand the sample size and improve the generalization ability of the model. (f) Subsequently, an adaptive machine learning model based on support vector regression (SVR) is established, with input variables covering stress and defect characteristics, and the output variable being the corresponding fatigue life. The model uses the fatigue crack growth rate formula to evaluate the fatigue crack growth life, and considers the correlation analysis between the input variables. The Pearson correlation coefficient is used to evaluate the multicollinearity between the input variables to improve the prediction accuracy of the model. (g) Finally, the determination coefficient R is used to evaluate the multicollinearity between the input variables. 2 , mean absolute percentage error (MAPE) and root mean square error (RMSE) are used to evaluate the performance of the established machine learning model to ensure the accuracy and reliability of the prediction results.

[0015] Furthermore, in the above-mentioned digital twin-based method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads, the step (a) also includes residual stress distribution detection along the parent material-heat-affected zone-weld direction distribution curve, and recording the axial and circumferential residual stress values ​​of the weld.

[0016] Furthermore, in the above-mentioned digital twin-based method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads, the defect type and size distribution of the defective Q345R steel or other steel adsorber welded scale parts in step (c) match the defects actually detected in step (a).

[0017] Furthermore, in the above-mentioned digital twin-based method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads, the GAN data enhancement process in step (e) includes: the generator G collects random variables z from a Gaussian distribution, obtains generated data G(z) after nonlinear transformation, and inputs the real data x and the generated data G(z) into the discriminator D at the same time. The discriminator D judges the authenticity of the data by calculating the probability that the input data comes from the real data x, thereby training the GAN model until the generator G can generate samples that are sufficiently close to the real data.

[0018] Furthermore, the above-mentioned method for predicting the fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins also includes the application of the prediction results, that is, formulating maintenance plans and improvement measures for the pressure swing adsorber based on the predicted weld fatigue life to improve the operating efficiency and safety of the equipment.

[0019] Furthermore, the above-mentioned digital twin-based method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads uses digital twin technology to digitally map, monitor, diagnose, predict, simulate and optimize the pressure swing adsorber, thereby achieving data management and equipment performance optimization throughout the entire life cycle.

[0020] Furthermore, in the above-mentioned method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins, the machine learning model in step (f) also adopts a data set of fatigue damage SN curves and defect characteristics, and combines a deep generative adversarial network GAN for data enhancement to obtain labeled samples for training the machine learning model to improve the accuracy and reliability of fatigue life prediction.

[0021] Furthermore, in the above-mentioned prediction method of fatigue life of adsorber welds under hydrogen-rich alternating load based on digital twin, when training the machine learning model, the Pearson correlation coefficient is used to perform correlation analysis on the input variables to remove multicollinearity and improve the prediction performance of the model.

[0022] Furthermore, the above-mentioned method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins also includes comparing the prediction results of the machine learning model with the actual situation, and optimizing the model parameters through continuous iteration to improve the accuracy and reliability of fatigue life prediction.

[0023] The present invention also discloses a fatigue life prediction system for adsorber welds under hydrogen-rich alternating loads based on digital twins, which is characterized by comprising:

[0024] 1) Nondestructive testing module: used to perform nondestructive testing on the pressure swing adsorber, including ultrasonic testing, magnetic particle testing and X-ray testing, to obtain the defects and residual stress spatial distribution of the heat-affected zone and weld in the adsorber weld joint; the defects include geometric features such as pores, microcracks, undercuts and excess height;

[0025] 2) Fatigue performance test module: used to perform high-cycle fatigue performance tests on welded joints of Q345R steel or other steel adsorber scale parts in a pure hydrogen atmosphere to obtain SN curves of the heat-affected zone and welds;

[0026] 3) Defect simulation and testing module: used to prepare defective Q345R steel or other steel adsorber welded scaled parts, count the number and size of defects, and obtain the SN curve of defective welded joints in a pure hydrogen atmosphere;

[0027] 4) Database construction module: used to establish a high cycle fatigue performance database of adsorber welded joints in hydrogen atmosphere based on the SN curves and defect feature distribution data obtained by the nondestructive testing module and the defect simulation and testing module;

[0028] 5) Data processing and model training module: Based on the deep generative adversarial network GAN, data enhancement is performed, and the generator network and the discriminator network are used to generate data consistent with the real data distribution. The data set in the database construction module and the data generated by GAN are used to establish an adaptive machine learning model based on support vector regression SVR for predicting weld fatigue life; the model also uses the fatigue crack growth rate formula and fatigue damage SN curve for evaluation;

[0029] 6) Model evaluation and optimization module: used to adopt the determination coefficient R 2 , mean absolute percentage error (MAPE) and root mean square error (RMSE) are used to evaluate the performance of the machine learning model, and the prediction accuracy is improved by iteratively optimizing the model parameters; the module also uses the Pearson correlation coefficient to perform correlation analysis on the input variables to remove multicollinearity;

[0030] 7) Prediction result application module: used to formulate maintenance plans and improvement measures for the pressure swing adsorber based on the prediction results of the machine learning model to improve the operating efficiency and safety of the equipment;

[0031] 8) Digital twin module: used for digital mapping, monitoring, diagnosis, prediction, simulation and optimization of pressure swing adsorbers to achieve full life cycle data management and equipment performance optimization.

[0032] Compared with the prior art, the present invention has the following outstanding beneficial effects:

[0033] 1. Improve prediction accuracy: By combining nondestructive testing, high-cycle fatigue performance testing, defect simulation and testing and other multidisciplinary technical means, the present invention can comprehensively and accurately obtain the defects and residual stress spatial distribution of adsorber welded joints, as well as their fatigue performance data in a hydrogen atmosphere. These data provide a solid foundation for establishing an accurate machine learning model, thereby significantly improving the accuracy and reliability of weld fatigue life prediction.

[0034] 2. Realize intelligent management: This invention uses deep generative adversarial network GAN for data enhancement, expands the sample size, and improves the generalization ability of the model. At the same time, an adaptive machine learning model is established through support vector regression SVR to realize intelligent prediction of weld fatigue life. This helps to achieve scientific management of pressure swing adsorbers, reduce manual intervention, and improve management efficiency.

[0035] 3. Optimize maintenance plan: Based on the predicted fatigue life of welds, the present invention can formulate targeted maintenance plans and improvement measures. This helps to discover potential safety hazards in advance and take timely measures for repair or replacement, thereby avoiding downtime and production cost losses caused by equipment failure.

[0036] 4. Improve equipment performance: Through digital twin technology, the present invention digitally maps, monitors, diagnoses, predicts, simulates and optimizes the pressure swing adsorber. This helps to fully understand the operating status and performance of the equipment, discover and solve problems in a timely manner, and thus improve the overall operating efficiency and safety of the equipment.

[0037] 5. Reduce detection costs: Compared with the traditional regular sampling method, the present invention uses machine learning models for prediction, which reduces the number and cost of actual detection. At the same time, since the prediction results have high accuracy, they can more effectively guide the maintenance and repair of equipment, further reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a residual stress detection position diagram in Example 3;

[0039] Figure 2 is the residual stress distribution diagram in Example 3;

[0040] Figure 3 Schematic diagram of the GAN model in Example 3;

[0041] Figure 4 Specific formula diagram of the generator network Generator, G and the discriminator network Discriminator, D in Example 3;

[0042] Figure 5 This is a graph showing the thermal fatigue performance test data of the defective non-service unit in Example 3;

[0043] Figure 6 This is a data diagram of fatigue performance test of defective welds in service in Example 3;

[0044] Figure 7 The SVR-based adaptive machine learning model artificial neural network in Example 3;

[0045] Figure 8 This is the fatigue life prediction diagram of the heat-affected zone with defects that has not been in service in Example 3;

[0046] Fig. 9 is a fatigue life prediction diagram of the unserviced weld in Example 3;

[0047] Fig.10 The figure is a flow chart of the overall method of the present invention. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Example 1

[0050] Fatigue life prediction of adsorber welds under hydrogen-rich alternating loads based on digital twin.

[0051] Step (a) Nondestructive testing:

[0052] Non-destructive testing of Q345R steel pressure swing adsorbers, including ultrasonic testing, magnetic particle testing and X-ray testing.

[0053] The geometric characteristics of defects (such as pores, microcracks, undercuts, and excess height) are recorded, and the residual stress distribution is detected along the direction of base material-heat affected zone-weld.

[0054] Record the axial and circumferential residual stress values ​​of the weld, as well as the hardness of the heat-affected zone and the weld.

[0055] Step (b) High cycle fatigue performance test:

[0056] In pure hydrogen atmosphere, high cycle fatigue test is carried out on welded joints of adsorber scale parts made of Q345R steel or other steel grades.

[0057] Test stress range: 200-400MPa, stress ratio: -1~0.8.

[0058] Obtain SN curves of heat affected zone and weld.

[0059] Step (c) Testing of defective welded joints:

[0060] A Q345R steel adsorber welded scaled-down part with defects was prepared, and the defect types and size distributions matched the actual detection data envelope.

[0061] The SN curves of the weld and heat-affected zone of welded joints with different defect characteristics were tested in a pure hydrogen atmosphere.

[0062] Step (d) Database establishment:

[0063] The data from steps (a)-(c) are integrated to establish a high cycle fatigue performance database for adsorber welded joints in a hydrogen atmosphere.

[0064] Step (e) GAN data enhancement:

[0065] Generative Adversarial Network (GAN) is used for data enhancement.

[0066] The generator G collects random variables z from Gaussian distribution and obtains generated data G(z) through nonlinear transformation.

[0067] The discriminator D determines the authenticity of the data by calculating the probability that the input data comes from the real data.

[0068] The GAN model is trained iteratively until the generated data is close enough to the real data.

[0069] Step (f) Machine learning model construction:

[0070] An adaptive machine learning model is established based on support vector regression (SVR).

[0071] Input variables: stress, defect characteristics (such as defect size, number, location), residual stress value.

[0072] Output variable: Fatigue life.

[0073] The fatigue crack growth life is estimated using the fatigue crack growth rate formula:

[0074] Formula: da / dN f =C(ΔK) m Among them, C and m are material constants; ΔK is the stress intensity factor.

[0075] ΔK is given by the formula It is calculated that A is the projection of the defect area on the vertical plane of the maximum principal stress, Y is the position constant (0.5 for internal defects and 0.65 for surface and subsurface defects), and Δσ is the applied stress range.

[0076] Step (g) Model evaluation and application:

[0077] The coefficient of determination R 2 , mean absolute percentage error (MAPE) and root mean square error (RMSE) were used to evaluate the model performance.

[0078] Pearson's correlation coefficient was used to analyze the correlation between input variables and eliminate multicollinearity.

[0079] Develop maintenance plans based on prediction results to improve equipment operating efficiency and safety.

[0080] Example 2

[0081] Deepening application of digital twin technology in adsorber weld fatigue life prediction

[0082] Steps (a) to (f):

[0083] Nondestructive testing, performance testing, database establishment, data enhancement and machine learning model construction were performed according to steps (a) to (f) of Example 1.

[0084] Step (e) Further optimization of GAN data enhancement:

[0085] Conditional GAN ​​is introduced to control specific properties of generated data.

[0086] Conditional variables (e.g., stress level, defect type) are added to the input of the generator G and the discriminator D to guide the data generation process.

[0087] Step (f) Deepening of machine learning model:

[0088] Based on the SVR model, ensemble learning methods (such as Bagging and Boosting) are introduced to improve prediction stability and accuracy.

[0089] Cross-validation techniques were used to evaluate model performance and select optimal model parameters.

[0090] Step (g) Model verification and optimization:

[0091] Compare the prediction results of the machine learning model with the actual situation, and improve the prediction accuracy by iteratively optimizing the model parameters.

[0092] Use strategies such as grid search or random search to find the optimal hyperparameter combination.

[0093] Deepening application of digital twin technology:

[0094] A digital twin model of the pressure swing adsorber is established to monitor the equipment operating status and weld fatigue in real time. When the weld fatigue life is predicted to be close to the critical value, the early warning mechanism is triggered and maintenance recommendations are automatically generated. The digital twin model is used to simulate and optimize equipment performance and guide equipment design and improvement.

[0095] Example 3

[0096] This embodiment provides a practical application of a method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins. Figure 1-10 Embodiments of the present invention are described in detail.

[0097] The overall method flow of the present invention is as follows Fig.10 shown.

[0098] Step (a): Nondestructive testing

[0099] First, non-destructive testing is performed on the pressure swing adsorber, including ultrasonic testing, magnetic particle testing and X-ray testing. Figure 1 Residual stress detection is performed at the position shown, and the defects and residual stress spatial distribution of the heat-affected zone and weld in the weld joint are obtained. The defects mainly include geometric features such as pores, microcracks, undercuts and excess height, and the hardness of the heat-affected zone and weld is recorded. In addition, the residual stress distribution detection along the parent material-heat-affected zone-weld direction distribution curve is also performed, and the residual stress values ​​of the weld axial and circumferential directions are recorded, such as Figure 2 shown.

[0100] Step (b): High cycle fatigue performance test

[0101] In pure hydrogen atmosphere, high cycle fatigue performance test was carried out on the welded joint of Q345R steel adsorber scale parts. The maximum stress range of the test was 200-400MPa, and the stress ratio was -1 to 0.8. Through the test, the SN curve of the heat affected zone and the weld was obtained, which reflects the fatigue performance of the material within a specific stress range.

[0102] Step (c): Defect simulation and testing

[0103] A Q345R steel adsorber welded scaled-down part with defects was prepared, and the defect type and size distribution matched the defects actually detected in step (a). The number and size of defects were counted, and the SN curve of the defective welded joint was obtained under a pure hydrogen atmosphere. Figure 5 and Figure 6 The heat impact diagram of the unserviced defective weld and the defective weld diagram of the serviced weld are shown respectively, and the formula Among them, Y is the position constant, which is 0.5 for internal defects and 0.65 for surface and subsurface defects; A is the projected defect area on the plane perpendicular to the maximum principal stress; Δσ is the applied stress range, and the specific value is set according to the test conditions.

[0104] Step (d): Database construction

[0105] Based on the SN curves and defect feature distribution data obtained in steps (a)-(c), a high-cycle fatigue performance database of adsorber welded joints in a hydrogen atmosphere was established. This database provides rich data support for the training of subsequent machine learning models.

[0106] Step (e): Data augmentation

[0107] Data enhancement based on deep generative adversarial network GAN. Figure 3 As shown in the figure, the GAN model includes a generator network Generator, G and a discriminator network Discriminator, D. The generator G collects random variables z from the Gaussian distribution and obtains the generated data G(z) after nonlinear transformation. The real data x and the generated data G(z) are input into the discriminator D at the same time. The discriminator D determines the authenticity of the data by calculating the probability that the input data comes from the real data x. The GAN model is trained in this way until the generator G can generate samples that are close enough to the real data. Figure 4 The specific formula diagrams of the generator network Generator, G and the discriminator network Discriminator, D are shown.

[0108] Step (f): Machine learning model building

[0109] Using the data set in step (d) and the data generated in step (e), an adaptive machine learning model based on support vector regression (SVR) is established. The input variables include stress and defect characteristics, and the output variable is the corresponding fatigue life. The model uses the fatigue crack growth rate formula da / dN f =C(ΔK) m To evaluate the fatigue crack growth life, C and m are material constants determined according to experimental data. ΔK is the stress intensity factor, which is given by the formula The model also considers the correlation analysis between input variables and uses the Pearson correlation coefficient to evaluate the multicollinearity between input variables to improve the prediction accuracy of the model. Figure 7 A schematic diagram of establishing an artificial neural network for an adaptive machine learning model based on SVR is shown.

[0110] Step (g): Model evaluation and optimization

[0111] The coefficient of determination R 2The performance of the established machine learning model is evaluated by the mean absolute percentage error (MAPE) and the root mean square error (RMSE) to ensure the prediction accuracy. At the same time, the prediction results of the machine learning model are compared with the actual situation, and the model parameters are optimized through continuous iteration to improve the accuracy and reliability of fatigue life prediction.

[0112] Application of prediction results

[0113] According to the predicted fatigue life of welds, maintenance plans and improvement measures for pressure swing adsorbers are formulated to improve the operating efficiency and safety of the equipment. Specifically, the prediction results can be used to manage welds in a graded manner, and welds with shorter predicted lifespans can be repaired or replaced first.

[0114] Digital Twin Technology

[0115] The present invention also uses digital twin technology to digitally map, monitor, diagnose, predict, simulate and optimize the pressure swing adsorber, realizing data management and equipment performance optimization throughout the entire life cycle. Digital twin technology can reflect the operating status and performance of the equipment in real time, providing strong support for equipment maintenance and management.

[0116] Specific examples:

[0117] Taking a certain type of pressure swing adsorber as an example, the fatigue life of welds is predicted according to the above steps. The spatial distribution data of defects and residual stress in the heat affected zone and welds of welded joints are obtained through non-destructive testing; high-cycle fatigue performance tests and defect simulation and testing are carried out to establish a high-cycle fatigue performance database; an SVR machine learning model is established after data enhancement based on GAN; and the prediction results are obtained after performance evaluation and optimization of the model. Figure 8 and Fig. 9 The predicted fatigue life diagrams of the unserviced defective heat affected zone and weld are shown separately.

[0118] Verification and comparison with measured data: The applicant has compared the predicted results with the fatigue life data of the PSA welds in actual service. Through long-term monitoring and recording, we found that the error rate between the predicted life and the actual life was extremely low, verifying the high accuracy of the prediction model. In the process of establishing the SVR machine learning model, we performed multiple iterations, continuously adjusted the model parameters, and used cross-validation to reduce the risk of overfitting. The final model showed good prediction performance on both the training set and the validation set, ensuring the stability and reliability of the prediction results.

[0119] For comparison: We also used other commonly used fatigue life prediction methods, such as the prediction method based on fracture mechanics and the empirical formula method, to predict the same set of weld data. Through comparative analysis, our method showed higher prediction accuracy and applicability, especially when dealing with complex defects and residual stress distribution.

[0120] In summary, as described in Example 3, the present invention achieves accurate prediction and scientific management of the fatigue life of the pressure swing adsorber weld by combining multidisciplinary technical means such as non-destructive testing, high-cycle fatigue performance testing, defect simulation and testing, database construction, deep generative adversarial network GAN data enhancement, support vector regression SVR machine learning model and digital twin technology.

[0121] Example 4

[0122] Fatigue life prediction system of adsorber weld under hydrogen-rich alternating load based on digital twin

[0123] 1. System Overview

[0124] This system aims to build a comprehensive, digital twin-based adsorber weld fatigue life prediction system under hydrogen-rich alternating loads. The system integrates nondestructive testing, fatigue performance testing, defect simulation and testing, database construction, data processing and model training, model evaluation and optimization, prediction result application, and digital twin modules, and combines necessary hardware equipment and technical support to achieve accurate prediction of pressure swing adsorber weld fatigue life and full life cycle management.

[0125] 2. System composition

[0126] Hardware device layer

[0127] Servers and storage devices: provide high-performance computing and large-capacity storage to support data processing, model training, and the operation of digital twin models.

[0128] Sensors and data acquisition equipment: Real-time monitoring of the operating status of the pressure swing adsorber, including temperature, pressure, vibration and other parameters, to provide data support for digital twins and digital operation and maintenance.

[0129] Network communication equipment: ensures smooth data communication between modules within the system and supports remote access and collaboration.

[0130] Professional testing equipment: including ultrasonic flaw detectors, magnetic particle flaw detectors, X-ray testing equipment, etc., used for non-destructive testing of weld defects and residual stress distribution.

[0131] Fatigue testing machine: used to test the fatigue performance of welded joints of Q345R steel adsorber scale parts and obtain key data such as SN curves.

[0132] Software and Technology Layer

[0133] Database management system: stores and manages non-destructive testing data, fatigue performance test data, defect simulation data, digital twin models and other data to ensure data security and reliability.

[0134] Data analysis and processing software: Process and analyze the collected data, including defect identification, residual stress calculation, fatigue life prediction, etc., to provide data support for model training and prediction.

[0135] Machine learning framework and tools: A machine learning model is established based on algorithms such as support vector regression (SVR) to predict weld fatigue life, and data enhancement is performed through deep generative adversarial networks (GAN) to improve model generalization capabilities.

[0136] Digital twin platform: Build a digital model of the pressure swing adsorber to realize functions such as digital mapping, monitoring, diagnosis, prediction, simulation and optimization, and provide technical support for full life cycle management.

[0137] Security protection software: ensure the security and stability of the system, prevent data leakage and illegal access, including firewalls, anti-virus software, etc.

[0138] Functional module layer

[0139] Nondestructive testing module: Use professional testing equipment to perform nondestructive testing on welds to obtain defect and residual stress distribution data.

[0140] Fatigue performance test module: Perform high cycle fatigue performance test on the welded joint of Q345R steel adsorber scale parts in pure hydrogen atmosphere to obtain SN curve.

[0141] Defect simulation and testing module: prepare defective welded scale parts, count the number and size of defects, and obtain the SN curve of defective welded joints.

[0142] Database construction module: Integrate data from non-destructive testing, fatigue performance testing, and defect simulation and testing to establish a high-cycle fatigue performance database.

[0143] Data processing and model training module: Data processing and model training are performed based on machine learning frameworks and tools to establish a weld fatigue life prediction model.

[0144] Model evaluation and optimization module: using the determination coefficient R 2 , MAPE, and RMSE are used to evaluate the performance of the model, and the prediction accuracy is improved through iterative optimization.

[0145] Prediction result application module: formulate maintenance plans and improvement measures based on the model prediction results to improve equipment operation efficiency and safety.

[0146] Digital twin module: realizes digital mapping, real-time monitoring, fault diagnosis, performance prediction, simulation optimization and other functions of the pressure swing adsorber, providing decision support for full life cycle management.

[0147] 3. System Implementation

[0148] Hardware deployment and configuration: Select appropriate hardware devices according to system requirements, and install, configure and debug them to ensure the stability and reliability of the system hardware environment.

[0149] Software development and integration: Develop various functional modules based on the selected software and technologies, and conduct integration testing to ensure the integrity and synergy of system functions.

[0150] Data preparation and import: Collect and organize data from non-destructive testing, fatigue performance testing, and defect simulation and testing, and import them into the database management system for storage and management.

[0151] Model training and optimization: Use data processing and model training modules to perform model training and optimization to ensure the accuracy and stability of the weld fatigue life prediction model.

[0152] System testing and acceptance: Conduct comprehensive testing on the system, including functional testing, performance testing, safety testing, etc., to ensure that the system meets the design requirements and has practical application capabilities.

[0153] Operation maintenance and optimization: Perform daily operation and maintenance of the system, regularly update data, optimize models, upgrade software, etc., to ensure the long-term stable operation and continuous optimization of the system.

[0154] From the above embodiments, it can be seen that the specific advantage of the present invention is that by integrating multidisciplinary technical means such as non-destructive testing, fatigue performance testing, defect simulation and testing, database construction, deep generative adversarial network GAN data enhancement, support vector regression SVR machine learning model and digital twin technology, it can achieve accurate prediction and scientific management of the fatigue life of the pressure swing adsorber weld, effectively improve the operating efficiency and safety of the equipment, reduce maintenance costs and risks, and provide strong support for the full life cycle management of the equipment.

[0155] The above are only a few preferred embodiments of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for predicting fatigue life of adsorber welds under hydrogen-rich alternating loads based on digital twins, characterized in that: The following steps are involved: (a) Perform non-destructive testing on the pressure swing adsorber, including ultrasonic testing, magnetic particle testing and X-ray testing, to obtain the defects and spatial distribution of residual stress in the heat affected zone and weld of the adsorber weld joint; the defects include geometric features such as pores, microcracks, undercuts and excess height, and record the hardness of the heat affected zone and weld; (b) In a pure hydrogen atmosphere, high cycle fatigue performance tests were performed on the welded joints of Q345R steel adsorber scaled parts to obtain the SN curves of the heat affected zone and weld. The maximum stress range of the test was 200-400 MPa, and the stress ratio was -1 to 0.

8. (c) Prepare defective Q345R steel adsorber welded scaled parts or defective high-cycle fatigue specimens, count the number and size of defects, and obtain the SN curves of the weld and heat-affected zone of the defective weld joint in a pure hydrogen atmosphere; (d) establishing a high cycle fatigue performance database of adsorber welded joints in a hydrogen atmosphere based on the SN curves and defect feature distribution data obtained in steps (a)-(c); (e) Data enhancement is performed based on the adversarial network GAN, using the generator network Generator, G and the discriminator network Discriminator, D to generate data consistent with the real data distribution to obtain a sufficient number of labeled samples; (f) using the data set in step (d) and the data generated in step (e), establishing an adaptive machine learning model based on support vector regression (SVR), wherein the input variables include stress and defect characteristics, and the output variable is the corresponding fatigue life; the model uses the fatigue crack growth rate formula da / dN f =C(ΔK) m To evaluate the fatigue crack growth life, C and m are material constants; ΔK is the stress intensity factor, and ΔK is given by the formula Calculated; A is the projected defect area on the plane perpendicular to the maximum principal stress; Y is the position constant, which is 0.5 for internal defects and 0.65 for surface and subsurface defects; Δσ is the applied stress range; (g) Using the coefficient of determination R 2 , mean absolute percentage error MAPE and root mean square error RMSE are used to evaluate the performance of the established machine learning model to ensure prediction accuracy; wherein, the adaptive machine learning model in step (f) also includes correlation analysis between input variables, and the Pearson correlation coefficient is used to evaluate the multicollinearity relationship between input variables to improve the prediction accuracy of the model; the fatigue strength σw is predicted using the formula σ w =Y1×(HV / σb)×Δσ; Y1 is the position constant, 1.56 for internal defects, 1.43 for surface and subsurface defects; HV is the Vickers hardness, and σb is the tensile strength.

2. The method according to claim 1, characterized in that Step (a) also includes detecting the residual stress distribution along the parent material-heat affected zone-weld direction distribution curve, and recording the residual stress values ​​in the axial and circumferential directions of the weld.

3. The method according to claim 1, characterized in that The defect type and size distribution of the defective Q345R steel adsorber weld joint in step (c) match the defect geometric envelope actually detected in step (a).

4. The method according to claim 1, characterized in that The GAN data enhancement process in step (e) includes: the generator G collects random variables z from the Gaussian distribution, obtains the generated data G(z) after nonlinear transformation, and inputs the real data x and the generated data G(z) into the discriminator D at the same time. The discriminator D judges the authenticity of the data by calculating the probability that the input data comes from the real data x, thereby training the GAN model until the generator G can generate samples that are close enough to the real data.

5. The method according to claim 1, characterized in that It also includes the application of prediction results, that is, formulating maintenance plans and improvement measures for pressure swing adsorbers based on the predicted weld fatigue life to improve the operating efficiency and safety of the equipment.

6. The method according to any one of claims 1 to 5, characterized in that The method uses digital twin technology to digitally map, monitor, diagnose, predict, simulate and optimize the pressure swing adsorber, thereby achieving full life cycle data management and equipment performance optimization.

7. The method according to claim 1, characterized in that The machine learning model in step (f) also uses the fatigue damage SN curve and its corresponding defect feature data set, and combines it with the deep generative adversarial network GAN for data enhancement to obtain labeled samples for training the machine learning model to improve the accuracy and reliability of fatigue life prediction.

8. The method according to claim 7, characterized in that When training the machine learning model, the Pearson correlation coefficient is used to perform correlation analysis on the input variables to remove multicollinearity and improve the predictive performance of the model.

9. The method according to claim 8, characterized in that It also includes comparing the prediction results of the machine learning model with the actual situation, and optimizing the model parameters through continuous iteration to improve the accuracy and reliability of fatigue life prediction.

10. A fatigue life prediction system for adsorber welds under hydrogen-rich alternating loads based on digital twins, characterized in that: include: 1) Nondestructive testing module: used to perform nondestructive testing on the pressure swing adsorber, including ultrasonic testing, magnetic particle testing and X-ray testing, to obtain the defects and residual stress spatial distribution of the heat-affected zone and weld in the adsorber weld joint; the defects include geometric features such as pores, microcracks, undercuts and excess height; 2) Fatigue performance test module: used to perform high-cycle fatigue performance test on the welded joints of Q345R steel adsorber scale parts in a pure hydrogen atmosphere to obtain the SN curves of the heat-affected zone and welds; 3) Defect simulation and testing module: used to prepare defective Q345R steel adsorber welded scale parts, count the number and size of defects, and obtain the SN curve of defective welded joints in a pure hydrogen atmosphere; 4) Database construction module: used to establish a high cycle fatigue performance database of adsorber welded joints in hydrogen atmosphere based on the SN curves and defect feature distribution data obtained by the nondestructive testing module and the defect simulation and testing module; 5) Data processing and model training module: Based on the deep generative adversarial network GAN, data enhancement is performed, and the generator network and the discriminator network are used to generate data consistent with the real data distribution. The data set in the database construction module and the data generated by GAN are used to establish an adaptive machine learning model based on support vector regression SVR for predicting weld fatigue life; the model also uses the fatigue crack growth rate formula and fatigue damage SN curve for evaluation; 6) Model evaluation and optimization module: used to adopt the determination coefficient R 2 , mean absolute percentage error (MAPE) and root mean square error (RMSE) are used to evaluate the performance of the machine learning model, and the prediction accuracy is improved by iteratively optimizing the model parameters; the module also uses the Pearson correlation coefficient to perform correlation analysis on the input variables to remove multicollinearity; 7) Prediction result application module: used to formulate maintenance plans and improvement measures for the pressure swing adsorber based on the prediction results of the machine learning model to improve the operating efficiency and safety of the equipment; 8) Digital twin module: used for digital mapping, monitoring, diagnosis, prediction, simulation and optimization of pressure swing adsorbers to achieve full life cycle data management and equipment performance optimization.

Images