Training method, generating method and product of fatigue life curve prediction model

Abstract

The application discloses a training method and a generating method of a fatigue life curve prediction model and a product. The method comprises the following steps: processing initial consumption energy of a material and fatigue life of the material by a fatigue life curve prediction model to be trained to obtain a fatigue life prediction curve of the material; adjusting parameters of the fatigue life curve prediction model to be trained according to a difference between a fatigue life curve label of the material and the fatigue life prediction curve of the material until the adjusted model meets a training stop condition, and obtaining the fatigue life curve prediction model after the training is completed. It can be seen that the fatigue life prediction curve of the material is generated according to the initial consumption energy of the material and the fatigue life of the material in the application, so that the fatigue life curve of the material is predicted according to the initial consumption energy of the material and the fatigue life of the material, the problem that the fatigue limit of the material cannot be predicted in the related art is solved, and the prediction accuracy of the fatigue life of the material is improved.

Description

Technical Field

[0001] This application relates to the field of material fatigue life prediction technology, and in particular to training methods, generation methods and products for predictive models of fatigue life curves. Background Technology

[0002] Currently, fatigue life prediction of materials has become a significant concern in engineering projects. Researchers have proposed using predictive models to forecast the fatigue life curves of materials. However, the Manson-Coffin equation used in these models results in discrepancies between the predicted fatigue life curves and the actual fatigue life curves of the materials, leading to relatively low prediction accuracy. Therefore, improving the accuracy of fatigue life prediction is a key issue of concern for those skilled in the art. Summary of the Invention

[0003] To address the aforementioned problems, this application provides a training method, a generation method, and a product for a fatigue life curve prediction model, thereby improving the prediction accuracy of material fatigue life. The embodiments of this application disclose the following technical solutions:

[0004] Firstly, this application discloses a training method for a prediction model of fatigue life curves, comprising:

[0005] Obtain the initial energy consumption of the material, the fatigue life of the material, and the fatigue life curve label of the material;

[0006] The initial energy consumption and fatigue life of the material are input into the prediction model of the fatigue life curve to be trained. The initial energy consumption and fatigue life of the material are processed by the prediction model of the fatigue life curve to be trained to obtain the fatigue life prediction curve of the material.

[0007] Based on the difference between the fatigue life curve label of the material and the fatigue life prediction curve of the material, the parameters of the prediction model of the fatigue life curve to be trained are adjusted until the adjusted model meets the training cutoff condition, and the training ends to obtain the prediction model of the fatigue life curve.

[0008] Optionally, the step of processing the initial energy consumption of the material and the fatigue life of the material using the prediction model of the fatigue life curve to be trained, to obtain the fatigue life prediction curve of the material, includes:

[0009] The initial energy consumption of the material is predicted by the prediction model of the fatigue life curve to be trained, and the fatigue limit of the material is obtained.

[0010] The fatigue limit and fatigue life of the material are calculated to obtain the actual energy consumed by the material.

[0011] A fatigue life prediction curve for the material is generated based on the material's fatigue life and the material's actual energy consumption.

[0012] Optionally, adjusting the parameters of the prediction model for the fatigue life curve to be trained includes:

[0013] The prediction parameters of the prediction model for the fatigue life curve to be trained are adjusted to predict the initial energy consumption of the material.

[0014] Optionally, after predicting the initial energy consumption of the material using the prediction model of the fatigue life curve to be trained, and obtaining the fatigue limit of the material, the method further includes:

[0015] The first curve generation parameters and the second curve generation parameters of the material are obtained based on the fatigue limit of the material.

[0016] The calculation of the fatigue limit and fatigue life of the material to obtain the actual energy consumed by the material includes:

[0017] The fatigue limit, fatigue life, first curve generation parameters, and second curve generation parameters of the material are calculated to obtain the actual energy consumed by the material.

[0018] Optionally, before the initial energy consumption for obtaining the material, the method further includes:

[0019] Obtain the hysteresis loop of the material;

[0020] Data extraction is performed on the hysteresis loop to obtain the stress amplitude and strain amplitude of the material;

[0021] The initial energy consumption of the material and the fatigue life of the material include:

[0022] The initial energy consumption of the material is obtained by calculating the stress amplitude and the strain amplitude.

[0023] The initial energy consumption of the material is calculated to obtain the fatigue life of the material.

[0024] Optionally, after processing the initial energy consumption and fatigue life of the material using the prediction model of the fatigue life curve to be trained, and obtaining the fatigue life prediction curve of the material, the method further includes:

[0025] Obtain the confidence level and probability of the material;

[0026] Based on the fatigue life prediction curve of the material, the confidence level of the material, and the probability of the material, a probabilistic fatigue life prediction curve of the material is generated.

[0027] Secondly, this application discloses a method for generating fatigue life curves, including:

[0028] Obtain the initial energy consumption of the target material and the fatigue life of the target material;

[0029] The initial energy consumption and fatigue life of the target material are input into the fatigue life curve prediction model. The fatigue life and initial energy consumption of the target material are processed by the fatigue life curve prediction model to generate the fatigue life curve of the target material. The fatigue life curve prediction model is a model trained according to the training method of the fatigue life curve prediction model described in the first aspect.

[0030] Thirdly, this application discloses a training device for a prediction model of fatigue life curves, comprising:

[0031] The material data acquisition unit is used to acquire the initial energy consumption of the material, the fatigue life of the material, and the fatigue life curve label of the material.

[0032] The prediction curve acquisition unit is used to input the initial energy consumption of the material and the fatigue life of the material into the prediction model of the fatigue life curve to be trained, and to process the initial energy consumption of the material and the fatigue life of the material through the prediction model of the fatigue life curve to be trained to obtain the fatigue life prediction curve of the material.

[0033] The prediction model acquisition unit is used to adjust the parameters of the prediction model of the fatigue life curve to be trained based on the difference between the fatigue life curve label of the material and the fatigue life prediction curve of the material, until the adjusted model meets the training cutoff condition, and the training ends to obtain the prediction model of the fatigue life curve.

[0034] Optionally, the predicted curve obtaining unit includes:

[0035] The fatigue limit acquisition unit is used to predict the initial energy consumption of the material through the prediction model of the fatigue life curve to be trained, and to obtain the fatigue limit of the material.

[0036] The energy consumption acquisition unit is used to calculate the fatigue limit and fatigue life of the material to obtain the actual energy consumption of the material.

[0037] The fatigue life prediction curve generation unit is used to generate a fatigue life prediction curve for the material based on the fatigue life of the material and the actual energy consumed by the material.

[0038] Optionally, the prediction model obtaining unit is specifically used for:

[0039] The prediction parameters of the prediction model for the fatigue life curve to be trained are adjusted to predict the initial energy consumption of the material.

[0040] Optionally, the device further includes:

[0041] A parameter generation unit is used to obtain the first curve generation parameters and the second curve generation parameters of the material based on the fatigue limit of the material.

[0042] The energy-consuming acquisition unit is specifically used for:

[0043] The fatigue limit, fatigue life, first curve generation parameters, and second curve generation parameters of the material are calculated to obtain the actual energy consumed by the material.

[0044] Optionally, the device further includes:

[0045] Hysteresis loop acquisition unit, used to acquire the hysteresis loop of the material;

[0046] The data extraction unit is used to extract data from the hysteresis loop to obtain the stress amplitude and strain amplitude of the material;

[0047] The material data acquisition unit is specifically used for:

[0048] The initial energy consumption of the material is obtained by calculating the stress amplitude and the strain amplitude.

[0049] The initial energy consumption of the material is calculated to obtain the fatigue life of the material.

[0050] Optionally, the device further includes:

[0051] A confidence level acquisition unit is used to acquire the confidence level of the material and the probability of the material.

[0052] The probabilistic fatigue life prediction curve generation unit is used to generate the probabilistic fatigue life prediction curve of the material based on the fatigue life prediction curve of the material, the confidence level of the material, and the probability of the material.

[0053] Fourthly, this application discloses an apparatus for generating fatigue life curves, comprising:

[0054] A target material data acquisition unit is used to acquire the initial energy consumption of the target material and the fatigue life of the target material.

[0055] The target material curve generation unit is used to input the initial energy consumption and fatigue life of the target material into the fatigue life curve prediction model, and process the fatigue life and initial energy consumption of the target material through the fatigue life curve prediction model to generate the fatigue life curve of the target material.

[0056] Fifthly, embodiments of this application provide an electronic device, including:

[0057] Memory, used to store computer programs;

[0058] The processor is configured to execute the computer program to implement either the step of training a method for predicting a fatigue life curve in the first aspect, or the step of generating a fatigue life curve in the second aspect.

[0059] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of the training method for the prediction model of the fatigue life curve in the first aspect, or the steps of the generation method for the fatigue life curve in the second aspect.

[0060] Compared with the prior art, this application has the following beneficial effects:

[0061] This application first obtains the initial energy consumption, fatigue life, and fatigue life curve labels of the material. Then, the initial energy consumption and fatigue life are input into a fatigue life curve prediction model to be trained. During the model training phase, the initial energy consumption and fatigue life are processed by the fatigue life curve prediction model to obtain the predicted fatigue life curve. Finally, based on the difference between the fatigue life curve labels and the predicted fatigue life curve, the parameters of the predicted fatigue life curve prediction model are adjusted until the adjusted model meets the training cutoff condition. Training is then completed, and the predicted fatigue life curve is obtained. Therefore, this application generates the fatigue life prediction curve based on the initial energy consumption and fatigue life of the material. This method of predicting the fatigue life curve based on the initial energy consumption and fatigue life solves the problem of related technologies failing to predict the fatigue limit of materials, thereby improving the prediction accuracy of material fatigue life. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 A flowchart illustrating a training method for a fatigue life curve prediction model provided in this application embodiment;

[0064] Figure 2 A schematic diagram of a training method for a fatigue life curve prediction model provided in an embodiment of this application;

[0065] Figure 3 A schematic diagram of a training method for a prediction model of fatigue life curves provided in an embodiment of this application;

[0066] Figure 4 A flowchart illustrating a method for generating a fatigue life curve as provided in an embodiment of this application;

[0067] Figure 5 A schematic diagram of the structure of a training device for a fatigue life curve prediction model provided in an embodiment of this application;

[0068] Figure 6 A schematic diagram of a fatigue life curve generation device provided in an embodiment of this application;

[0069] Figure 7 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0070] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0071] As described earlier, fatigue life prediction of materials has become a significant concern in engineering projects. Researchers have proposed using predictive models to forecast the fatigue life curves of materials. These models often employ the Manson-Coffin equation. However, because the Manson-Coffin equation fails to predict the material's fatigue limit, the predicted fatigue life curve differs from the actual fatigue life curve, resulting in low prediction accuracy. Therefore, improving the accuracy of fatigue life prediction is a key focus for those skilled in the art.

[0072] Therefore, the inventors propose the following technical solution: First, obtain the initial energy consumption, fatigue life, and fatigue life curve label of the material. Then, input the initial energy consumption and fatigue life into the fatigue life curve prediction model to be trained. During the model training phase, process the initial energy consumption and fatigue life of the material using the fatigue life curve prediction model to obtain the fatigue life prediction curve. Finally, adjust the parameters of the fatigue life curve prediction model based on the difference between the fatigue life curve label and the fatigue life prediction curve until the adjusted model meets the training cutoff condition. The training ends, and the fatigue life curve prediction model is obtained. It is evident that this application generates the fatigue life prediction curve based on the initial energy consumption and fatigue life of the material. This method of predicting the fatigue life curve based on the initial energy consumption and fatigue life of the material solves the problem of related technologies failing to predict the fatigue limit of materials, thereby improving the prediction accuracy of material fatigue life.

[0073] The method provided in this application can be executed by software on a terminal device. The terminal device may be, for example, a mobile phone, tablet computer, or computer. The software may be, for example, system software.

[0074] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0075] The following embodiment illustrates the training method for a fatigue life curve prediction model provided in this application. See also... Figure 1 The figure is a flowchart of a training method for a fatigue life curve prediction model provided in an embodiment of this application. Figure 1 As shown, the method includes:

[0076] S101: Obtain the initial energy consumption of the material, the fatigue life of the material, and the fatigue life curve label of the material.

[0077] It should be noted that the initial energy dissipation and fatigue life of the material serve as training samples for the prediction model of the fatigue life curve to be trained. The fatigue life curve labels are fatigue life curves generated during actual use and can be used as labels for training samples of the prediction model of the fatigue life curve to be trained. Before obtaining the initial energy dissipation of the material, this step can also obtain the hysteresis loop of the material, and then extract data from the hysteresis loop to obtain the stress amplitude and strain amplitude of the material. The hysteresis loop is formed during the experiment, thus reducing the influence of the elastic modulus on the accuracy of the material fatigue life prediction. Further, the stress amplitude and strain amplitude are calculated to obtain the initial energy dissipation of the material, and then the fatigue life of the material is calculated based on the initial energy dissipation.

[0078] In one feasible implementation, the initial energy consumed by the material can be calculated using formula (1):

[0079] ΔW1=Δε in ·Δσ (1)

[0080] Where ΔW1 is the initial energy consumed by the material, and Δε in Let Δσ be the strain amplitude of the material, and Δε be the stress amplitude of the material. in The strain range can be understood as the inelastic strain range of the material, and the stress amplitude Δσ can be understood as the stress range of the material. Further, the strain range can be understood as the deformation the material undergoes during the test, and the stress range is the stress data generated by the deformation of the material during the test. It should also be noted that if the material does not have creep strain data, then Δε... in =Δε p , where Δε p This refers to the range of plastic strain, which is not specifically limited here.

[0081] In another feasible implementation, formula (1) can be transformed into formula (2) (the initial energy consumption of the material can be calculated based on formula (2)):

[0082] ΔW1=Δε in (σ max -σ min (2)

[0083] Where, σ max σ is the maximum stress in the stress amplitude. min This represents the minimum stress within the stress amplitude.

[0084] S102: Input the initial energy consumption of the material and the fatigue life of the material into the prediction model of the fatigue life curve to be trained, and process the initial energy consumption of the material and the fatigue life of the material through the prediction model of the fatigue life curve to be trained to obtain the fatigue life prediction curve of the material.

[0085] In this step, after inputting the initial energy consumption and fatigue life of the material into the prediction model of the fatigue life curve to be trained, the initial energy consumption of the material is first predicted using the prediction model to obtain the fatigue limit of the material. Then, the fatigue limit and fatigue life of the material are calculated to obtain the actual energy consumption of the material. Finally, based on the fatigue life and actual energy consumption of the material, a fatigue life prediction curve is generated. A bisection method can be inserted into the prediction model of the fatigue life curve to predict the fatigue limit of the material. Thus, in this application, the fatigue life curve of the material is generated by predicting the existence of the material's fatigue limit, thereby improving the prediction accuracy of the material's fatigue life.

[0086] Furthermore, after predicting the initial energy consumption of the material using a prediction model of the fatigue life curve to be trained, and obtaining the fatigue limit of the material, this application can also obtain the first curve generation parameters and the second curve generation parameters of the material based on the fatigue limit. Then, the fatigue limit, fatigue life, first curve generation parameters, and second curve generation parameters of the material are calculated to obtain the actual energy consumption of the material. In this process, the least squares method can be inserted into the prediction model of the fatigue life curve to be trained, so as to calculate the fatigue limit of the material and obtain the first and second curve generation parameters.

[0087] In one feasible implementation, the actual energy consumed by the material can be calculated according to formula (3):

[0088]

[0089] Where ΔW2 is the actual energy consumed by the material, m is the parameter for generating the first curve of the material, c is the parameter for generating the second curve of the material, and N f ΔW0 represents the fatigue life of the material, and ΔW0 represents the fatigue limit of the material.

[0090] It should be further noted that this application can plot the expression (3) on a coordinate system, where the horizontal axis represents the fatigue life of the material and the vertical axis represents the actual energy consumed by the material, to generate a fatigue life prediction curve for the material in this coordinate system. This fatigue life prediction curve is the actual energy consumed by the material versus the fatigue life curve. Thus, the fatigue life trend of the material can be obtained by observing the distribution of the actual energy consumed by the fatigue life curve.

[0091] S103: Based on the difference between the fatigue life curve label of the material and the fatigue life prediction curve of the material, adjust the parameters of the prediction model of the fatigue life curve to be trained until the adjusted model meets the training cutoff condition, and the training ends to obtain the prediction model of the fatigue life curve.

[0092] Understandably, this step involves adjusting the parameters of the prediction model for the fatigue life curve to be trained, specifically adjusting the prediction parameters of the model to predict the initial energy consumption of the material. By continuously adjusting the model's prediction parameters, the model can achieve a better fit, thereby improving the accuracy of obtaining the material's fatigue limit based on its initial energy consumption, and ultimately improving the prediction accuracy of the material's fatigue life, resulting in a fatigue life prediction curve that closely approximates the fatigue life curve label.

[0093] It should be noted that the hysteresis loop of the material in this application is obtained using the nominal strain control group method. Due to the inherent dispersion of fatigue in the material—that is, different data will exist at the same strain level—the initial energy consumption calculated based on this hysteresis loop will also differ. Therefore, in this application, the scatter plot method can be used to process the data to ultimately generate the fatigue life prediction curve of the material.

[0094] like Figure 2 As shown, Figure 2 This is a schematic diagram of a training method for a fatigue life curve prediction model provided in an embodiment of this application. Figure 2 The paper shows the fatigue life prediction curves of material GH909 generated under different temperature environments (400℃, 500℃, 600℃ and 650℃). There are multiple data points under the same temperature environment and the same strain condition. Therefore, this application uses the scatter method to statistically process the multiple data points to generate the actual energy consumption-fatigue life curve of the material (the horizontal axis is the fatigue life of the material and the vertical axis is the actual energy consumption of the material). In this way, the prediction accuracy of the material fatigue life curve is improved.

[0095] It should be further noted that, after processing the initial energy consumption and fatigue life of the material using the prediction model of the fatigue life curve to be trained, this application can also obtain the material's confidence level and probability. Then, the fatigue life prediction curve, the material's confidence level, and the material's probability are calculated to generate a probabilistic fatigue life prediction curve. Here, the material's probability represents its survival rate. The material's survival rate and confidence level are preset; the confidence level can be 95%, and the survival rate can be 99.87%, without specific limitations. In practical applications, these can be preset as needed.

[0096] Understandably, when this application uses the scatter plot method to statistically process multiple data points under the same strain condition, the equal standard deviation method can be adopted. This allows for the generation of the material's fatigue life curve based on the mean data, which can better improve the model's fitting ability. Furthermore, based on the generated material fatigue life curve—that is, assuming the material's fatigue life follows a log-normal distribution and has equal standard deviations at all stress levels—preset confidence levels and probabilities for the material are obtained. Based on the material's fatigue life prediction curve, confidence level, and probability, a probability-actual energy consumption-fatigue life curve is generated.

[0097] In one feasible implementation, the probabilistic fatigue life prediction curve of the material can be generated according to formulas (4) and (5):

[0098]

[0099]

[0100] Among them, X γ,P K represents the logarithmic fatigue life of a material under certain confidence and probability conditions. γ,P β is the one-sided tolerance factor, S is the standard deviation correction factor, γ is the standard deviation (i.e., the average standard deviation of all data of the material under the same strain condition), P is the confidence level of the material, and u is the probability of the material. p u is a standard normal skewness related to probability. γ The standard normal skewness is related to the confidence level. The value is the median of the fitted curve, and n is the number of samples. The value of n is a positive integer, such as n can be 1 or n can be 2, without any specific limitation. Furthermore, in this application, the data points obtained according to formulas (4) and (5) can be fitted using the three-parameter power function energy method to obtain the probability-actual energy consumption-fatigue life prediction curve of the material.

[0101] like Figure 3 As shown, Figure 3A schematic diagram of a training method for a prediction model of fatigue life curves provided in an embodiment of this application. Figure 3 The diagram shows the probability-actual energy consumption-fatigue life prediction curves (the horizontal axis represents the material's fatigue life, and the vertical axis represents the material's actual energy consumption) generated based on the material's fatigue life prediction curves, confidence levels, and probabilities under different temperature environments (400℃, 500℃, 600℃, and 650℃). The material's confidence level is 95%, the probability is 99.87%, and the fitting parameter for the probability-actual energy consumption-fatigue life prediction curve can be -1. It should be noted that this application can predict both low-cycle and high-cycle fatigue life performance of the material, thus ensuring fatigue life prediction across the entire range.

[0102] The following embodiment illustrates a method for generating a fatigue life curve provided in this application. See also... Figure 4 The figure is a flowchart of a method for generating a fatigue life curve according to an embodiment of this application. Figure 4 As shown, the method includes:

[0103] S401: Obtain the initial energy consumption of the target material and the fatigue life of the target material.

[0104] In this step, the initial energy consumption of the target material is obtained based on the hysteresis loop of the target material, and then the fatigue life of the target material is calculated based on the initial energy consumption. The calculation process in this step is similar to that in step S101, and the specific calculation process has been described in detail in step S101, so it will not be repeated here.

[0105] S402: Input the initial energy consumption of the target material and the fatigue life of the target material into the fatigue life curve prediction model, and process the fatigue life of the target material and the initial energy consumption of the target material through the fatigue life curve prediction model to generate the fatigue life curve of the target material.

[0106] In this step, the fatigue life curve prediction model is a model trained using the method described above. It is understood that through training the prediction model and adjusting its parameters, a better model for generating material fatigue life curves can be obtained. Therefore, in this step, the initial energy consumption of the target material can be predicted using the fatigue life curve prediction model to obtain the fatigue limit. Then, the fatigue limit and fatigue life of the target material are calculated to obtain the actual energy consumption. Finally, based on the actual energy consumption and fatigue life of the target material, the fatigue life curve is generated, thus improving the prediction accuracy of material fatigue life.

[0107] In summary, this embodiment predicts the fatigue limit of a material based on its initial energy consumption and fatigue life, and generates a fatigue life curve based on the material's fatigue limit. This solves the problem of failing to predict the fatigue limit of materials in related technologies, thereby improving the accuracy of material fatigue life prediction.

[0108] The following describes a training device for a fatigue life curve prediction model provided in an embodiment of this application. The training device for a fatigue life curve prediction model described below and the training method for a fatigue life curve prediction model described above can be referred to in correspondence.

[0109] See Figure 5 The figure is a schematic diagram of the structure of a training device for a fatigue life curve prediction model provided in an embodiment of this application. Figure 5 As shown, the training device for the prediction model of the fatigue life curve includes:

[0110] The material data acquisition unit 501 is used to acquire the initial energy consumption of the material, the fatigue life of the material, and the fatigue life curve label of the material.

[0111] The prediction curve acquisition unit 502 is used to input the initial energy consumption of the material and the fatigue life of the material into the prediction model of the fatigue life curve to be trained, and to process the initial energy consumption of the material and the fatigue life of the material through the prediction model of the fatigue life curve to be trained to obtain the fatigue life prediction curve of the material.

[0112] The prediction model acquisition unit 503 is used to adjust the parameters of the prediction model of the fatigue life curve to be trained based on the difference between the fatigue life curve label of the material and the fatigue life prediction curve of the material, until the adjusted model meets the training cutoff condition, and the training ends to obtain the prediction model of the fatigue life curve.

[0113] Optionally, the predicted curve obtaining unit 502 includes:

[0114] The fatigue limit acquisition unit is used to predict the initial energy consumption of the material through the prediction model of the fatigue life curve to be trained, and to obtain the fatigue limit of the material.

[0115] The energy consumption acquisition unit is used to calculate the fatigue limit and fatigue life of the material to obtain the actual energy consumption of the material.

[0116] The fatigue life prediction curve generation unit is used to generate a fatigue life prediction curve for the material based on the fatigue life of the material and the actual energy consumed by the material.

[0117] Optionally, the prediction model obtaining unit 503 is specifically used for:

[0118] The prediction parameters of the prediction model for the fatigue life curve to be trained are adjusted to predict the initial energy consumption of the material.

[0119] Optionally, the device further includes:

[0120] A parameter generation unit is used to obtain the first curve generation parameters and the second curve generation parameters of the material based on the fatigue limit of the material.

[0121] The energy-consuming acquisition unit is specifically used for:

[0122] The fatigue limit, fatigue life, first curve generation parameters, and second curve generation parameters of the material are calculated to obtain the actual energy consumed by the material.

[0123] Optionally, the device further includes:

[0124] Hysteresis loop acquisition unit, used to acquire the hysteresis loop of the material;

[0125] The data extraction unit is used to extract data from the hysteresis loop to obtain the stress amplitude and strain amplitude of the material;

[0126] The material data acquisition unit 501 is specifically used for:

[0127] The initial energy consumption of the material is obtained by calculating the stress amplitude and the strain amplitude.

[0128] The initial energy consumption of the material is calculated to obtain the fatigue life of the material.

[0129] Optionally, the device further includes:

[0130] A confidence level acquisition unit is used to acquire the confidence level of the material and the probability of the material.

[0131] The probabilistic fatigue life prediction curve generation unit is used to generate the probabilistic fatigue life prediction curve of the material based on the fatigue life prediction curve of the material, the confidence level of the material, and the probability of the material.

[0132] The training device for the fatigue life curve prediction model provided in this application embodiment has the same beneficial effects as the training method for the fatigue life curve prediction model provided in the above embodiment, and therefore will not be described again.

[0133] The following describes a fatigue life curve generation apparatus provided in an embodiment of this application. The fatigue life curve generation apparatus described below and the fatigue life curve generation method described above can be referred to in correspondence.

[0134] See Figure 6 The figure is a schematic diagram of the structure of a fatigue life curve generation device provided in an embodiment of this application, as shown below. Figure 6 As shown, the device for generating the fatigue life curve includes:

[0135] A target material data acquisition unit is used to acquire the initial energy consumption of the target material and the fatigue life of the target material.

[0136] The target material curve generation unit is used to input the initial energy consumption and fatigue life of the target material into the fatigue life curve prediction model, and process the fatigue life and initial energy consumption of the target material through the fatigue life curve prediction model to generate the fatigue life curve of the target material.

[0137] The fatigue life curve generation apparatus provided in this application embodiment has the same beneficial effects as the fatigue life curve generation method provided in the above embodiments, and therefore will not be described again.

[0138] Electronic device examples

[0139] See Figure 7 This figure is a schematic diagram of an electronic device structure provided in an embodiment of this application, such as... Figure 7 As shown, it includes:

[0140] Memory 11 is used to store computer programs;

[0141] The processor 12 is configured to execute the computer program to implement the steps of training the prediction model of the fatigue life curve as described in any of the above method embodiments, or to implement the steps of generating the fatigue life curve as described in any of the above method embodiments.

[0142] In this embodiment, the device can be a PC (Personal Computer), or a terminal device such as a smartphone, tablet computer, handheld computer, or portable computer.

[0143] The device may include a memory 11, a processor 12, and a bus 13. The memory 11 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic storage, magnetic disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the device, such as the hard disk of the device. In other embodiments, the memory 11 may also be an external storage device of the device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 may include both internal and external storage units of the device. The memory 11 can be used not only to store application software and various types of data installed on the device, but also to temporarily store data that has been output or will be output.

[0144] In some embodiments, processor 12 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 11 or process data.

[0145] This bus 13 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0146] Furthermore, the device may also include a network interface 14, which may optionally include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), typically used to establish communication connections between the device and other electronic devices.

[0147] Optionally, the device may further include a user interface 15, which may include a display, an input unit such as a keyboard, and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the device and to display a visual user interface.

[0148] Figure 7 Only devices with components 11-15 are shown; those skilled in the art will understand that... Figure 7 The structure shown does not constitute a limitation on the device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0149] Readable storage medium embodiments

[0150] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the steps of the training method for the prediction model of the fatigue life curve, or the steps of the generation method for the fatigue life curve. The storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0151] It should be noted that the training and generation methods of the fatigue life curve prediction model provided by this invention can be used in the field of material fatigue life prediction technology. The above are merely examples and do not limit the application areas of the training and generation methods of the fatigue life curve prediction model provided by this invention.

[0152] It should also be noted that the "first" and "second" in the names such as "first" and "second" (if they exist) mentioned in the embodiments of this application are only used as name identifiers and do not represent the first and second in order.

[0153] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0154] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0155] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0156] The training method, generation method, and product of the fatigue life curve prediction model provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A training method for a prediction model of fatigue life curves, characterized in that, include: Obtain the initial energy consumption of the material, the fatigue life of the material, and the fatigue life curve label of the material; The initial energy consumption and fatigue life of the material are input into the prediction model of the fatigue life curve to be trained. The initial energy consumption and fatigue life of the material are processed by the prediction model of the fatigue life curve to be trained to obtain the fatigue life prediction curve of the material. Based on the difference between the fatigue life curve label of the material and the fatigue life prediction curve of the material, adjust the parameters of the prediction model of the fatigue life curve to be trained until the adjusted model meets the training cutoff condition, and the training ends to obtain the prediction model of the fatigue life curve. The step of processing the initial energy consumption and fatigue life of the material using the prediction model of the fatigue life curve to be trained, and obtaining the fatigue life prediction curve of the material, includes: The initial energy consumption of the material is predicted by the prediction model of the fatigue life curve to be trained, and the fatigue limit of the material is obtained. The fatigue limit and fatigue life of the material are calculated to obtain the actual energy consumed by the material. Based on the fatigue life of the material and the actual energy consumed by the material, a fatigue life prediction curve for the material is generated; After predicting the initial energy consumption of the material using the prediction model based on the fatigue life curve to be trained, and obtaining the fatigue limit of the material, the method further includes: The first curve generation parameters and the second curve generation parameters of the material are obtained based on the fatigue limit of the material. The calculation of the fatigue limit and fatigue life of the material to obtain the actual energy consumed by the material includes: The fatigue limit, fatigue life, first curve generation parameters, and second curve generation parameters of the material are calculated to obtain the actual energy consumed by the material.

2. The method according to claim 1, characterized in that, The adjustment of parameters of the prediction model for the fatigue life curve to be trained includes: The prediction parameters of the prediction model for the fatigue life curve to be trained are adjusted to predict the initial energy consumption of the material.

3. The method according to claim 1, characterized in that, Before the initial energy consumption for acquiring the material, the method further includes: Obtain the hysteresis loop of the material; Data extraction is performed on the hysteresis loop to obtain the stress amplitude and strain amplitude of the material; The initial energy consumption of the material and the fatigue life of the material include: The initial energy consumption of the material is obtained by calculating the stress amplitude and the strain amplitude. The initial energy consumption of the material is calculated to obtain the fatigue life of the material.

4. The method according to claim 1, characterized in that, After processing the initial energy consumption and fatigue life of the material using the prediction model of the fatigue life curve to be trained, and obtaining the fatigue life prediction curve of the material, the method further includes: Obtain the confidence level and probability of the material; Based on the fatigue life prediction curve of the material, the confidence level of the material, and the probability of the material, a probabilistic fatigue life prediction curve of the material is generated.

5. A method for generating a fatigue life curve, characterized in that, include: Obtain the initial energy consumption of the target material and the fatigue life of the target material; The initial energy consumption and fatigue life of the target material are input into the fatigue life curve prediction model. The fatigue life and initial energy consumption of the target material are processed by the fatigue life curve prediction model to generate the fatigue life curve of the target material. The fatigue life curve prediction model is a model trained by the training method of the fatigue life curve prediction model according to any one of claims 1-4.

6. A training device for a predictive model of fatigue life curves, characterized in that, include: The material data acquisition unit is used to acquire the initial energy consumption of the material, the fatigue life of the material, and the fatigue life curve label of the material. The prediction curve acquisition unit is used to input the initial energy consumption and fatigue life of the material into the prediction model of the fatigue life curve to be trained, and to process the initial energy consumption and fatigue life of the material through the prediction model of the fatigue life curve to be trained to obtain the fatigue life prediction curve of the material. The prediction model acquisition unit is used to adjust the parameters of the prediction model of the fatigue life curve to be trained based on the difference between the fatigue life curve label of the material and the fatigue life prediction curve of the material, until the adjusted model meets the training cutoff condition, and the training ends to obtain the prediction model of the fatigue life curve. The step of processing the initial energy consumption and fatigue life of the material using the prediction model of the fatigue life curve to be trained, and obtaining the fatigue life prediction curve of the material, includes: The initial energy consumption of the material is predicted by the prediction model of the fatigue life curve to be trained, and the fatigue limit of the material is obtained. The fatigue limit and fatigue life of the material are calculated to obtain the actual energy consumed by the material. Based on the fatigue life of the material and the actual energy consumed by the material, a fatigue life prediction curve for the material is generated; After predicting the initial energy consumption of the material using the prediction model based on the fatigue life curve to be trained, and obtaining the fatigue limit of the material, the method further includes: The first curve generation parameters and the second curve generation parameters of the material are obtained based on the fatigue limit of the material. The calculation of the fatigue limit and fatigue life of the material to obtain the actual energy consumed by the material includes: The fatigue limit, fatigue life, first curve generation parameters, and second curve generation parameters of the material are calculated to obtain the actual energy consumed by the material.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the steps of training a fatigue life curve prediction model as described in any one of claims 1 to 4, or to implement the steps of generating a fatigue life curve as described in claim 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of a training method for a fatigue life curve prediction model as described in any one of claims 1 to 4, or the steps of a method for generating a fatigue life curve as described in claim 5.

Images