A method for building a fatigue performance prediction model for alloy functional materials

Abstract

The present invention discloses a method for building a fatigue performance prediction model for alloy functional materials, which relates to the field of materials science and technology. The method collects performance impact data of the alloy by installing a sensor group on the alloy surface and using an instrument, and transmits the data to a data processor through a wireless network for preprocessing, data storage and analysis. The load performance prediction model is constructed to calculate the thermal-mechanical coupling fatigue damage coefficient and the multi-axial load fatigue damage coefficient, and then the composite fatigue damage coefficient is obtained by summarizing and calculating, and a preliminary evaluation is performed with the safety fatigue damage threshold. The environmental corrosion impact coefficient is calculated in combination with the corrosion impact data group and the precipitate volume fraction, and the corrosion prediction risk assessment is performed with the safety fatigue damage threshold, and finally a comprehensive fatigue damage coefficient is obtained, a comprehensive corrosion assessment and fatigue damage prediction are performed, and real-time warning and optimization suggestions are provided to ensure the safe use of alloy materials and extend their service life.

Description

Technical Field

[0001] The present invention relates to the field of material science and technology, and in particular to a method for building a fatigue performance prediction model for alloy functional materials. Background Art

[0002] With the continuous acceleration of the global industrialization and modernization process, various high-performance alloy materials have been widely used in aerospace, automobile, energy and construction and other fields. These alloy materials are often at risk of fatigue damage when subjected to complex loads, extreme temperatures and corrosive environments, which seriously affects their service life and safety. Therefore, how to efficiently and accurately evaluate the fatigue performance of alloy materials has become an important topic in materials science and engineering technology. With the advancement of manufacturing technology, especially the continuous development of smart sensors, wireless communications and big data processing technology, the demand for real-time monitoring and prediction of fatigue performance of alloy materials is increasing. The attention of all sectors of society to improving material safety, extending service life and reducing maintenance costs has also promoted the continuous innovation and development of fatigue damage prediction technology. Especially in the field of structural safety and high risk, the fatigue performance prediction of alloy materials has become an important means to ensure personnel safety, improve production efficiency and reduce resource waste.

[0003] At present, the effects of fatigue damage and corrosion on the fatigue properties of alloys have not been fully considered. Existing fatigue prediction models mostly rely on the influence of a single factor, ignoring the influence of external environmental factors such as the corrosive environment and the volume fraction of precipitates, which leads to large errors in the prediction results. In addition, traditional fatigue damage assessment methods often lack dynamic real-time performance and cannot respond quickly to changes in material state, resulting in potential risks of fatigue damage that are not easy to warn in a timely manner. In a complex environment, a single load and stress analysis cannot fully reveal the comprehensive fatigue damage coefficient of the material, nor does it consider the potential impact of environmental corrosion. Therefore, how to accurately combine various data sources to make more accurate comprehensive predictions is the main challenge facing current technology. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method for building a fatigue performance prediction model for alloy functional materials, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for building a fatigue performance prediction model for alloy functional materials, comprising the following steps:

[0006] S1. Collecting performance-influencing data of the alloy by using a sensor group and an instrument on the alloy surface, and constructing a data processor, establishing a communication connection with the sensor group and the instrument through a wireless network, and then transmitting the fatigue data set to the data processor;

[0007] S2, a data processor receives the performance impact data and performs preprocessing to obtain a fatigue data set, and then constructs a data repository to store the fatigue data set;

[0008] S3. A load performance prediction model is constructed through a data processor, and the thermal-mechanical coupling fatigue damage coefficient rop(t) and the multiaxial load fatigue damage coefficient dhz(t) are calculated based on the stress fatigue data group. The composite fatigue damage coefficient fpl(t) is obtained by summarizing the calculations, and a preliminary fatigue damage assessment is performed with the preset safety fatigue damage threshold A.

[0009] S4. When the material state is normal as assessed by the initial fatigue damage, the precipitate volume fraction V is obtained by summarizing and calculating the obtained precipitate data set in combination with the temperature wd(t). p (t), and then summarize and calculate the environmental corrosion influence coefficient hwx(t) with the obtained corrosion influence data group;

[0010] S5. Based on the obtained composite fatigue damage coefficient fpl(t) and environmental corrosion influence coefficient hwx(t), a summary calculation is performed to obtain the comprehensive fatigue damage coefficient zhp(t), and the corrosion degree prediction risk assessment is performed with the preset safety fatigue damage threshold A.

[0011] Preferably, said S1 includes S11 and S12;

[0012] S11, installing a sensor group on the surface of the alloy and using a collection instrument to collect performance impact data of the alloy, and marking the collection timestamp;

[0013] The sensor group includes stress sensors, temperature sensors, X-ray fluorescence sensors, electrochemical sensors, and ultrasonic sensors;

[0014] The acquisition instrument includes a portable laser scanning microscope;

[0015] S12. Build a data processor and establish a communication connection with the sensor group and the acquisition instrument through a wireless network, and then transmit the performance impact data to the data processor.

[0016] Preferably, S2 includes S21 and S22;

[0017] S21, after receiving the performance impact data, the data processor pre-processes the performance impact data to obtain a fatigue data set;

[0018] The preprocessing includes denoising, outlier detection, missing value processing, dimensionless processing, image processing, element composition analysis and corrosion rate analysis;

[0019] The fatigue data set includes a stress fatigue data set, a precipitate data set and a corrosion effect data set;

[0020] The stress fatigue data set includes stress and temperature wd(t);

[0021] The precipitate data set includes the total area ap of the observation area z , precipitate area ap(t) and precipitate element concentration nd(t);

[0022] The corrosion impact data set includes the corrosion rate fs(t) and the oxide layer thickness yh(t);

[0023] The image processing uses image processing software to process the images collected by the portable laser scanning microscope, automatically identify the edges of the precipitate particles, and count the total area of ​​the observation area. z , the number of precipitate particles np and the surface area of ​​the particles mj;

[0024] Then the number of precipitate particles np and the surface area of ​​the particles mj are combined to calculate the precipitate area ap. The specific calculation formula is: ,in, Represents pi, with two decimal places;

[0025] The elemental composition analysis is performed on the alloy by using an X-ray fluorescence sensor to measure the fluorescence intensity yg of the target element and the total fluorescence intensity sy of all elements in the alloy, and then the precipitate element concentration nd is calculated. The specific calculation formula is: ;

[0026] The corrosion rate analysis is performed by combining the corrosion current density fd obtained by the electrochemical sensor with the density md of the alloy material and the total area ap of the observation area. z Perform summary calculations to obtain the alloy corrosion rate fs. The specific calculation formula is: , where K represents the empirical coefficient used to convert the corrosion current density fd to the corrosion rate fs, depending on the material type, and the density md of the alloy material is initially input through the material standard;

[0027] S22. The data processor constructs a data repository and transfers the fatigue data set to the data repository for storage.

[0028] Preferably, said S3 includes S31 and S32;

[0029] S31. The data processor establishes the constitutive relationship of the material through the acquired stress fatigue data group, simulates the dynamic load and thermal coupling environment faced by the material, analyzes the influencing factors of the alloy material under different working environments, uses finite element analysis tools to simulate the stress and strain distribution of the material under multi-axial load, establishes a load performance prediction model including the x-axis, y-axis and z-axis directions, and outputs the thermal coupling fatigue damage coefficient rop(t) and the multi-axial load fatigue damage coefficient dhz(t) at time t through the load model;

[0030] The specific formula is as follows;

[0031] ;

[0032] ;

[0033] In the formula, ={ , , } represents the stress in the x, y and z directions at time t, ={ , , } represents the stress limit in the x, y and z directions, which is input by the user based on the material standard, ni={nx, xy, xz} represents the stress correction constant in the x, y and z directions, rop(t) represents the thermal-mechanical coupling fatigue damage at time t, represents the stress at time t, represents the fatigue limit of the material, wd(t) represents the temperature at time t, and wd ref represents the reference temperature, dt represents the integration in the time interval, and dhz(t) represents the multi-axial load fatigue damage coefficient at time t.

[0034] Preferably, the S32 includes S321 and S322;

[0035] S321, comprehensively analyzing the fatigue damage of the alloy at time t based on the obtained thermal-mechanical coupling fatigue damage coefficient rop(t) and the multiaxial load fatigue damage coefficient dhz(t), summarizing and calculating to obtain the composite fatigue damage coefficient fpl(t), and quantifying the influence of the common influencing factors on the fatigue damage of the alloy;

[0036] The composite fatigue damage coefficient fpl(t) is calculated by the following formula:

[0037] ;

[0038] Where fpl(t) represents the composite fatigue damage coefficient at time t, a1 and a2 represent the influence coefficients of the thermal-mechanical coupling fatigue damage coefficient and the multiaxial load fatigue damage coefficient on the composite fatigue damage coefficient, respectively, and a1+a2=1. The specific value is set by the user.

[0039] Preferably, S322, based on the historical fatigue data set in the data repository, the composite fatigue damage coefficient fpl(t) of the material under different working conditions is calculated using the cumulative damage theory, the mean is calculated to preset the safety fatigue damage threshold A, and a preliminary fatigue damage assessment is performed with the obtained composite fatigue damage coefficient fpl(t), and the specific assessment scheme is as follows;

[0040] When the composite fatigue damage coefficient fpl ≥ the safe fatigue damage threshold A, the fatigue damage of the material has a risk of failure, and fatigue warning information is generated and transmitted to the user end through a wireless network;

[0041] When the composite fatigue damage coefficient fpl is less than the safety fatigue damage threshold A, the material state is normal, monitoring is maintained and deep prediction is triggered.

[0042] Preferably, said S4 includes S41 and S42;

[0043] S41. When the initial fatigue damage assessment shows that the material state is normal, the precipitate particles of the corrosion elements on the alloy surface are analyzed. Based on the obtained precipitate data group and the influence of temperature wd(t) on the precipitate volume change, a summary calculation is performed to obtain the precipitate volume fraction V. p (t);

[0044] The precipitate volume fraction V p (t) is calculated by the following formula:

[0045] ;

[0046] Where V p (t) represents the volume fraction of the precipitate at time t, wd0 represents the reference temperature, w represents the correction constant, and nd z Indicates the concentration of total alloy elements.

[0047] Preferably, S42, based on the obtained corrosion impact data set and the precipitate volume fraction V p (t) Summarize and calculate the environmental corrosion influence coefficient hwx(t) and analyze the influence of the environment on the corrosion degree of the alloy;

[0048] The environmental corrosion influence coefficient hwx(t) is calculated by the following formula;

[0049] ;

[0050] Where hwx(t) represents the environmental corrosion influence coefficient at time t, fs(t) represents the corrosion rate at time t, yh(t) represents the oxide layer thickness at time t, yh0 represents the initial oxide layer thickness, V p，ref represents the standard precipitate volume fraction of the alloy material, and p represents the precipitate influence index.

[0051] Preferably, said S5 includes S51 and S52;

[0052] S51. Based on the obtained composite fatigue damage coefficient fpl(t) and environmental corrosion influence coefficient hwx(t), a summary calculation is performed to obtain the comprehensive fatigue damage coefficient zhp(t), analyze the change trend of the fatigue degree of the alloy under the combined effect of stress and corrosion damage, and quantify the fatigue of the alloy under the combined influence;

[0053] The comprehensive fatigue damage coefficient zhp(t) is calculated by the following formula:

[0054] ;

[0055] Where zhp(t) represents the comprehensive fatigue damage coefficient at time t, and b represents the correction factor.

[0056] Preferably, S52, performing corrosion prediction risk assessment based on the obtained comprehensive fatigue damage coefficient zhp and the preset safety fatigue damage threshold A, the specific assessment scheme is as follows;

[0057] When the comprehensive fatigue damage coefficient zhp ≥ the safety fatigue damage threshold A, the alloy material is at risk of corrosion. At this time, corrosion warning information is generated and transmitted to the user end through a wireless network.

[0058] When the comprehensive fatigue damage coefficient zhp is less than the safety fatigue damage threshold A, there is no risk of corrosion of the alloy material, the material state is normal, and normal monitoring is maintained.

[0059] The present invention provides a method for building a fatigue performance prediction model for alloy functional materials, which has the following beneficial effects:

[0060] (1) This method uses stress sensors, temperature sensors, X-ray fluorescence sensors, electrochemical sensors, ultrasonic sensors and portable laser scanning microscopes on the alloy surface to collect data on the performance of the alloy. A data processor is built to establish a communication connection with the sensor group and the instrument through a wireless network, and then the fatigue data set is transmitted to the data processor for preprocessing, completing the processing steps such as denoising, outlier detection, and missing value processing, and finally forming a fatigue data set, including a stress fatigue data set, a precipitate data set and a corrosion impact data set. After storage, a complete fatigue performance prediction model is constructed, which provides accurate data support for subsequent fatigue damage assessment and prediction.

[0061] (2) The data processor of this method analyzes the acquired stress fatigue data group and constructs a load performance prediction model including the x-axis, y-axis and z-axis directions, and then calculates the thermal-mechanical coupling fatigue damage coefficient rop(t) and the multi-axial load fatigue damage coefficient dhz(t). Through comprehensive analysis, the composite fatigue damage coefficient fpl(t) is obtained, and a preliminary fatigue damage assessment is performed with the preset safety fatigue damage threshold A. When the composite fatigue damage coefficient fpl(t) is greater than the preset safety fatigue damage threshold A, a fatigue warning message is generated to remind relevant personnel to check the material, reduce the load, and avoid further accumulation of fatigue damage. If the composite fatigue damage coefficient fpl(t) is less than the preset safety fatigue damage threshold A, it means that the material state is normal and monitoring continues.

[0062] (3) Based on the precipitate data set and the corrosion influence data set, this method constructs the environmental corrosion influence coefficient hwx(t), and combines the corrosion rate fs(t) and the oxide layer thickness yh(t) to analyze the fatigue of the alloy under environmental corrosion. When the comprehensive fatigue damage coefficient zhp(t) of the alloy material is greater than the preset safety fatigue damage threshold A, a corrosion warning message is generated, indicating that the material is at risk of corrosion and needs to be stopped and repaired and replaced. When the comprehensive fatigue damage coefficient zhp(t) of the alloy material is less than the preset safety fatigue damage threshold A, the state of the material is considered to be normal and the material will continue to be monitored. Through this series of analysis and calculation, the present invention successfully realizes the intelligent monitoring and accurate prediction of the fatigue performance of alloy functional materials under actual working conditions, which not only improves the safety of material use, but also enhances the reliability and efficiency of material maintenance management, providing important technical guarantees for the long-term stable use of alloy materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of the steps of a method for building a fatigue performance prediction model for alloy functional materials according to the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0065] Example 1, please refer to Figure 1 The present invention provides a method for building a fatigue performance prediction model for alloy functional materials. To achieve the above purpose, the present invention is implemented through the following technical scheme: comprising the following steps:

[0066] S1. Collecting performance-influencing data of the alloy by using a sensor group and an instrument on the alloy surface, and constructing a data processor, establishing a communication connection with the sensor group and the instrument through a wireless network, and then transmitting the fatigue data set to the data processor;

[0067] S2, a data processor receives the performance impact data and performs preprocessing to obtain a fatigue data set, and then constructs a data repository to store the fatigue data set;

[0068] S3. A load performance prediction model is constructed through a data processor, and the thermal-mechanical coupling fatigue damage coefficient rop(t) and the multiaxial load fatigue damage coefficient dhz(t) are calculated based on the stress fatigue data group. The composite fatigue damage coefficient fpl(t) is obtained by summarizing the calculations, and a preliminary fatigue damage assessment is performed with the preset safety fatigue damage threshold A.

[0069] S4. When the material state is normal as assessed by the initial fatigue damage, the precipitate volume fraction V is obtained by summarizing and calculating the obtained precipitate data set in combination with the temperature wd(t). p (t), and then summarize and calculate the environmental corrosion influence coefficient hwx(t) with the obtained corrosion influence data group;

[0070] S5. Based on the obtained composite fatigue damage coefficient fpl(t) and environmental corrosion influence coefficient hwx(t), a summary calculation is performed to obtain the comprehensive fatigue damage coefficient zhp(t), and the corrosion degree prediction risk assessment is performed with the preset safety fatigue damage threshold A.

[0071] In this embodiment, the performance impact data of the alloy is obtained in real time by using a sensor group and an acquisition instrument, and the data is preprocessed and stored by a data processor. With the support of a wireless network, the data processor can receive data from the sensor group in a timely manner and form a fatigue data set, providing an accurate data basis for subsequent analysis. Through this modular design, the present invention achieves a significant improvement in the efficiency of data acquisition and processing, overcomes the problems of cumbersome manual acquisition and calculation in traditional fatigue performance monitoring, and thus improves the real-time and accuracy of data processing. In terms of fatigue damage prediction, the present invention calculates the thermal coupling fatigue damage coefficient rop(t) and the multi-axial load fatigue damage coefficient dhz(t) by constructing a load performance prediction model, combining the stress fatigue data group, and further calculating the composite fatigue damage coefficient fpl(t), thereby realizing an accurate assessment of the fatigue state of the alloy material. By comparing with the preset safety fatigue damage threshold A, the fatigue damage risk of the material can be discovered in time, and an early warning signal can be issued in advance. Compared with the traditional fatigue damage assessment method, this prediction model adds multi-dimensional environmental factors, such as the combined influence of thermal coupling and multi-axial load, provides a more accurate and comprehensive prediction result, and avoids the errors and deficiencies caused by the limitations of the traditional method. In further corrosion risk assessment, the present invention combines precipitate data and temperature changes, calculates the precipitate volume fraction Vp(t) and the environmental corrosion influence coefficient hwx(t), and completes the real-time assessment of the corrosion degree of the alloy material. By summarizing the composite fatigue damage coefficient fpl(t) and the environmental corrosion influence coefficient hwx(t), the comprehensive fatigue damage coefficient zhp(t) is obtained, and compared with the preset safety fatigue damage threshold A, a scientific assessment of the corrosion risk of the material is provided. This innovative method not only improves the monitoring accuracy of corrosion effects, but also enhances the ability to predict the safety of material use in complex environments, and significantly improves the service life and reliability of the material. In general, compared with the prior art, the present invention brings higher accuracy and better real-time performance in the comprehensive application of data acquisition, processing, fatigue damage prediction and corrosion risk assessment, and provides a more efficient and accurate technical solution for the intelligent monitoring and management of alloy functional materials.

[0072] Example 2: This example is an explanation of Example 1. Figure 1 , specifically: the S1 includes S11 and S12;

[0073] S11, installing a sensor group on the surface of the alloy and using a collection instrument to collect performance impact data of the alloy, and marking the collection timestamp;

[0074] The sensor group includes stress sensors, temperature sensors, X-ray fluorescence sensors, electrochemical sensors, and ultrasonic sensors;

[0075] The acquisition instrument includes a portable laser scanning microscope;

[0076] Stress sensors are used to collect information about the stress on the alloy. , the temperature sensor is used to collect the alloy surface temperature wd;

[0077] X-ray fluorescence sensor is used to measure the fluorescence intensity yg of the target element and the total fluorescence intensity sy of all elements in the alloy;

[0078] Electrochemical sensors are used to obtain alloy corrosion current density fd;

[0079] Ultrasonic sensors are used to collect the thickness of the oxide layer on the alloy surface yh;

[0080] A portable laser scanning microscope was used to scan and acquire images of the alloy surface;

[0081] S12. Build a data processor and establish a communication connection with the sensor group and the acquisition instrument through a wireless network, and then transmit the performance impact data to the data processor.

[0082] In this embodiment, by installing a variety of sensor groups and acquisition instruments on the alloy surface, combined with wireless network data transmission, the present invention achieves a high degree of intelligence and automation in the acquisition and transmission of performance data. The application of various sensors covers real-time monitoring of multiple dimensions such as stress, temperature, corrosion, electrochemical properties, and oxide layer thickness, ensuring the comprehensive evaluation of alloy materials under various working conditions. This diversified data acquisition scheme greatly improves the accuracy and comprehensiveness of monitoring, and provides rich input for subsequent data analysis and fatigue performance prediction. In particular, the introduction of a portable laser scanning microscope can not only scan the alloy surface image with high precision, but also obtain information on surface precipitates in real time, further improving the reliability of the data. By transmitting the data of these sensors and acquisition instruments to the data processor in real time through a wireless network, the hysteresis and errors existing in traditional manual acquisition and data transmission are avoided, making the entire monitoring process more efficient, real-time and accurate, thereby providing a solid technical foundation for the continuous monitoring and prediction of material properties.

[0083] Example 3: This example is an explanation of Example 2. Figure 1 , specifically: S2 includes S21 and S22;

[0084] S21, after receiving the performance impact data, the data processor pre-processes the performance impact data to obtain a fatigue data set;

[0085] The preprocessing includes denoising, outlier detection, missing value processing, dimensionless processing, image processing, element composition analysis and corrosion rate analysis;

[0086] The fatigue data set includes a stress fatigue data set, a precipitate data set and a corrosion effect data set;

[0087] The stress fatigue data set includes stress and temperature wd(t);

[0088] The precipitate data set includes the total area ap of the observation area z , precipitate area ap(t) and precipitate element concentration nd(t);

[0089] The corrosion impact data set includes the corrosion rate fs(t) and the oxide layer thickness yh(t);

[0090] The image processing uses image processing software to process the images collected by the portable laser scanning microscope, automatically identify the edges of the precipitate particles, and count the total area of ​​the observation area. z , the number of precipitate particles np and the surface area of ​​the particles mj;

[0091] Then the number of precipitate particles np and the surface area of ​​the particles mj are combined to calculate the precipitate area ap. The specific calculation formula is: ,in, Represents pi, with two decimal places;

[0092] The elemental composition analysis is performed on the alloy by using an X-ray fluorescence sensor to measure the fluorescence intensity yg of the target element and the total fluorescence intensity sy of all elements in the alloy, and then the precipitate element concentration nd is calculated. The specific calculation formula is: ;

[0093] The corrosion rate analysis is performed by combining the corrosion current density fd obtained by the electrochemical sensor with the density md of the alloy material and the total area ap of the observation area. z Perform summary calculations to obtain the alloy corrosion rate fs. The specific calculation formula is: , where K represents the empirical coefficient used to convert the corrosion current density fd to the corrosion rate fs, depending on the material type, and the density md of the alloy material is initially input through the material standard;

[0094] S22. The data processor constructs a data repository and transfers the fatigue data set to the data repository for storage.

[0095] In this embodiment, by comprehensive preprocessing and analysis of performance-influencing data, the present invention significantly improves the effect of alloy fatigue performance prediction in terms of data processing accuracy and reliability. Specifically, by means of denoising, outlier detection, missing value processing, etc., the quality of the data is effectively ensured, and errors caused by data noise and outliers are avoided. In addition, image processing technology automatically identifies precipitate particles in images collected by a portable laser scanning microscope, further enhancing the ability to quantitatively analyze the characteristics of precipitates on the surface of the material, and providing more accurate parameters for the prediction of fatigue damage. The elemental composition analysis and corrosion rate analysis, using the synergistic effect of X-ray fluorescence sensors and electrochemical sensors, provide fine composition and corrosion rate data of alloy materials, so that the fatigue performance of materials under different environmental conditions can be deeply analyzed. These multidimensional data are converted into time series data and stored in a data repository, further enhancing the systematicness and operability of data management. Overall, the above processing greatly improves the comprehensiveness and accuracy of data processing, provides a more detailed and reliable basis for fatigue performance prediction, and effectively supports the long-term performance evaluation and risk warning of alloy materials under complex working conditions.

[0096] Example 4: This example is an explanation of Example 3. Figure 1 , specifically: S3 includes S31 and S32;

[0097] S31. The data processor establishes the constitutive relationship of the material through the acquired stress fatigue data group, simulates the dynamic load and thermal coupling environment faced by the material, analyzes the influencing factors of the alloy material under different working environments, uses finite element analysis tools to simulate the stress and strain distribution of the material under multi-axial load, establishes a load performance prediction model including the x-axis, y-axis and z-axis directions, and outputs the thermal coupling fatigue damage coefficient rop(t) and the multi-axial load fatigue damage coefficient dhz(t) at time t through the load model;

[0098] The specific formula is as follows;

[0099] ;

[0100] ;

[0101] In the formula, ={ , , } represents the stress in the x, y and z directions at time t, ={ , , } represents the stress limit in the x, y and z directions, which is input by the user based on the material standard, ni={nx, xy, xz} represents the stress correction constant in the x, y and z directions, rop(t) represents the thermal-mechanical coupling fatigue damage at time t, represents the stress at time t, represents the fatigue limit of the material, wd(t) represents the temperature at time t, and wd ref represents the reference temperature, dt represents the integration in the time interval, and dhz(t) represents the multi-axial load fatigue damage coefficient at time t.

[0102] The S32 includes S321 and S322;

[0103] S321, comprehensively analyzing the fatigue damage of the alloy at time t based on the obtained thermal-mechanical coupling fatigue damage coefficient rop(t) and the multiaxial load fatigue damage coefficient dhz(t), summarizing and calculating to obtain the composite fatigue damage coefficient fpl(t), and quantifying the influence of the common influencing factors on the fatigue damage of the alloy;

[0104] The composite fatigue damage coefficient fpl(t) is calculated by the following formula:

[0105] ;

[0106] Where fpl(t) represents the composite fatigue damage coefficient at time t, a1 and a2 represent the influence coefficients of the thermal-mechanical coupling fatigue damage coefficient and the multiaxial load fatigue damage coefficient on the composite fatigue damage coefficient, respectively, and a1+a2=1. The specific value is set by the user.

[0107] S322. Based on the historical fatigue data set in the data repository, the composite fatigue damage coefficient fpl(t) of the material under different working conditions is calculated using the cumulative damage theory, the mean is calculated to preset the safety fatigue damage threshold A, and a preliminary fatigue damage assessment is performed with the obtained composite fatigue damage coefficient fpl(t). The specific assessment scheme is as follows;

[0108] When the composite fatigue damage coefficient fpl ≥ the safe fatigue damage threshold A, the fatigue damage of the material has the risk of failure, and fatigue warning information is generated and transmitted to the user end through the wireless network to remind relevant personnel to check the material and reduce the use load;

[0109] When the composite fatigue damage coefficient fpl is less than the safety fatigue damage threshold A, the material state is normal, monitoring is maintained and deep prediction is triggered.

[0110] In this embodiment, the present invention can accurately evaluate the fatigue damage of alloy materials under various complex working environments by comprehensively analyzing the thermal-mechanical coupling fatigue damage coefficient rop(t) and the multi-axial load fatigue damage coefficient dhz(t). By establishing a fatigue performance prediction model including loads in the x-axis, y-axis and z-axis directions, combining the finite element analysis tool to simulate the stress and strain distribution of the material, the composite fatigue damage coefficient fpl(t) is further accurately calculated, and the thermal-mechanical coupling effect and the multi-axial load influence are comprehensively considered, which significantly improves the accuracy and reliability of fatigue damage prediction. This model effectively evaluates the fatigue damage of materials under different working conditions by introducing the cumulative damage theory, and provides early warning information based on actual working conditions in combination with historical fatigue data. When the composite fatigue damage coefficient fpl(t) exceeds the safe fatigue damage threshold A, an early warning is generated in time and transmitted to the user end, reminding the necessary inspection and load reduction measures to effectively avoid premature failure of the material due to fatigue damage. This intelligent fatigue damage prediction method improves the safety and reliability of alloy materials, and is particularly suitable for material monitoring and management in long-term, heavy-loaded or complex environments, and has strong practical application value and potential.

[0111] Example 5: This example is an explanation of Example 4. Please refer to Figure 1 , specifically: the S4 includes S41 and S42;

[0112] S41. When the initial fatigue damage assessment shows that the material state is normal, the precipitate particles of the corrosion elements on the alloy surface are analyzed. Based on the obtained precipitate data group and the influence of temperature wd(t) on the precipitate volume change, a summary calculation is performed to obtain the precipitate volume fraction V. p (t);

[0113] The precipitate volume fraction V p (t) is calculated by the following formula:

[0114] ;

[0115] Where V p (t) represents the volume fraction of the precipitate at time t, wd0 represents the reference temperature, w represents the correction constant, and nd z Indicates the concentration of total alloy elements.

[0116] S42, based on the obtained corrosion impact data set and precipitate volume fraction V p (t) Summarize and calculate the environmental corrosion influence coefficient hwx(t) and analyze the influence of the environment on the corrosion degree of the alloy;

[0117] The environmental corrosion influence coefficient hwx(t) is calculated by the following formula;

[0118] ;

[0119] Where hwx(t) represents the environmental corrosion influence coefficient at time t, fs(t) represents the corrosion rate at time t, yh(t) represents the oxide layer thickness at time t, yh0 represents the initial oxide layer thickness, V p，ref represents the standard precipitate volume fraction of the alloy material, and p represents the precipitate influence index.

[0120] In this embodiment, by analyzing the precipitate particles of corrosion elements on the alloy surface, combined with the effect of temperature change on the precipitate volume fraction Vp(t), it is possible to dynamically track the changes of precipitates under different temperature conditions, and further quantify the changes in the microstructure of the material. This detailed analysis helps reveal the profound influence of temperature and precipitates on the fatigue properties of the alloy, and provides a more accurate basis for fatigue damage assessment. Then, combined with the corrosion rate fs and the oxide layer thickness yh, the precipitate volume fraction Vp(t) is used to summarize and calculate the environmental corrosion influence coefficient hwx(t), so as to analyze the contribution of corrosion to material fatigue damage under different environmental conditions. Through this process, the invention can comprehensively evaluate the fatigue performance of alloy materials in complex environments, especially the behavior under dynamic temperature and corrosion conditions. Compared with traditional methods, the present invention has significant advantages in the accuracy, comprehensiveness and real-time performance of corrosion assessment, significantly improves the reliability and accuracy of material fatigue performance prediction, and further extends the service life of alloy materials.

[0121] Example 6: This example is an explanation of Example 5. Please refer to Figure 1 , specifically: the S5 includes S51 and S52;

[0122] S51. Based on the obtained composite fatigue damage coefficient fpl(t) and environmental corrosion influence coefficient hwx(t), a summary calculation is performed to obtain the comprehensive fatigue damage coefficient zhp(t), analyze the change trend of the fatigue degree of the alloy under the combined effect of stress and corrosion damage, and quantify the fatigue of the alloy under the combined influence;

[0123] The comprehensive fatigue damage coefficient zhp(t) is calculated by the following formula:

[0124] ;

[0125] Where zhp(t) represents the comprehensive fatigue damage coefficient at time t, and b represents the correction factor.

[0126] S52. Based on the obtained comprehensive fatigue damage coefficient zhp and the preset safety fatigue damage threshold A, a corrosion degree prediction risk assessment is performed. The specific assessment scheme is as follows;

[0127] When the comprehensive fatigue damage coefficient zhp ≥ the safe fatigue damage threshold A, the alloy material is at risk of corrosion. At this time, corrosion warning information is generated and transmitted to the user end through the wireless network to remind relevant personnel to stop using this material and to carry out maintenance and replacement;

[0128] When the comprehensive fatigue damage coefficient zhp is less than the safety fatigue damage threshold A, there is no risk of corrosion of the alloy material, the material state is normal, and normal monitoring is maintained.

[0129] In this embodiment, the comprehensive fatigue damage coefficient zhp(t) is successfully obtained by comprehensive calculation of the composite fatigue damage coefficient fpl(t) and the environmental corrosion influence coefficient hwx(t), which provides a comprehensive evaluation of the fatigue performance and corrosion risk of the alloy material. Through this calculation, the fatigue change trend of the material under the dual influence of stress and corrosion can be quantified, accurately reflecting the comprehensive fatigue state of the material. Combined with the preset safety fatigue damage threshold A, the corrosion risk of the material can be predicted in real time, and early warning information can be generated to remind relevant personnel to take measures such as stopping use, overhauling and replacing materials. This process significantly improves the safety of alloy materials and reduces the risk of sudden failures caused by fatigue damage or corrosion, thereby providing a guarantee for the long-term stable operation of the material. Compared with traditional methods, the present invention not only enhances the real-time monitoring capability of material performance, but also realizes the comprehensive evaluation of fatigue damage and corrosion risks, effectively improves the management efficiency and safety of materials, and ensures the reliability and durability of materials in complex working environments.

[0130] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for building a fatigue performance prediction model for alloy functional materials, characterized by: The following steps are involved: S1. Collecting performance-influencing data of the alloy by using a sensor group and an instrument on the alloy surface, and constructing a data processor, establishing a communication connection with the sensor group and the instrument through a wireless network, and then transmitting the fatigue data set to the data processor; S2, a data processor receives the performance impact data and performs preprocessing to obtain a fatigue data set, and then constructs a data repository to store the fatigue data set; S3. A load performance prediction model is constructed through a data processor, and the thermal-mechanical coupling fatigue damage coefficient rop(t) and the multiaxial load fatigue damage coefficient dhz(t) are calculated based on the stress fatigue data group. The composite fatigue damage coefficient fpl(t) is obtained by summarizing the calculations, and a preliminary fatigue damage assessment is performed with the preset safety fatigue damage threshold A. S4. When the material state is normal as assessed by the initial fatigue damage, the precipitate volume fraction V is obtained by summarizing and calculating the obtained precipitate data set in combination with the temperature wd(t). p (t), and then summarize and calculate the environmental corrosion influence coefficient hwx(t) with the obtained corrosion influence data group; S5. Based on the obtained composite fatigue damage coefficient fpl(t) and environmental corrosion influence coefficient hwx(t), a summary calculation is performed to obtain the comprehensive fatigue damage coefficient zhp(t), and the corrosion degree prediction risk assessment is performed with the preset safety fatigue damage threshold A.

2. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 1, characterized in that: Said S1 includes S11 and S12; S11, installing a sensor group on the surface of the alloy and using a collection instrument to collect performance impact data of the alloy, and marking the collection timestamp; The sensor group includes stress sensors, temperature sensors, X-ray fluorescence sensors, electrochemical sensors, and ultrasonic sensors; The acquisition instrument includes a portable laser scanning microscope; S12. Build a data processor and establish a communication connection with the sensor group and the acquisition instrument through a wireless network, and then transmit the performance impact data to the data processor.

3. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 1, characterized in that: S2 includes S21 and S22; S21, after receiving the performance impact data, the data processor pre-processes the performance impact data to obtain a fatigue data set; The preprocessing includes denoising, outlier detection, missing value processing, dimensionless processing, image processing, element composition analysis and corrosion rate analysis; The fatigue data set includes a stress fatigue data set, a precipitate data set and a corrosion effect data set; The stress fatigue data set includes stress and temperature wd(t); The precipitate data set includes the total area ap of the observation area z , precipitate area ap(t) and precipitate element concentration nd(t); The corrosion impact data set includes the corrosion rate fs(t) and the oxide layer thickness yh(t); The image processing uses image processing software to process the images collected by the portable laser scanning microscope, automatically identify the edges of the precipitate particles, and count the total area of ​​the observation area. z , the number of precipitate particles np and the surface area of ​​the particles mj; Then the number of precipitate particles np and the surface area of ​​the particles mj are combined to calculate the precipitate area ap. The specific calculation formula is: ,in, Represents pi, with two decimal places; The elemental composition analysis is performed on the alloy by using an X-ray fluorescence sensor to measure the fluorescence intensity yg of the target element and the total fluorescence intensity sy of all elements in the alloy, and then the precipitate element concentration nd is calculated. The specific calculation formula is: ; The corrosion rate analysis is performed by combining the corrosion current density fd obtained by the electrochemical sensor with the density md of the alloy material and the total area ap of the observation area. z Perform summary calculations to obtain the alloy corrosion rate fs. The specific calculation formula is: , where K represents the empirical coefficient used to convert the corrosion current density fd to the corrosion rate fs, depending on the material type, and the density md of the alloy material is initially input through the material standard; S22. The data processor constructs a data repository and transfers the fatigue data set to the data repository for storage.

4. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 3, characterized in that: The S3 includes S31 and S32; S31. The data processor establishes the constitutive relationship of the material through the acquired stress fatigue data group, simulates the dynamic load and thermal coupling environment faced by the material, analyzes the influencing factors of the alloy material under different working environments, uses finite element analysis tools to simulate the stress and strain distribution of the material under multi-axial load, establishes a load performance prediction model including the x-axis, y-axis and z-axis directions, and outputs the thermal coupling fatigue damage coefficient rop(t) and the multi-axial load fatigue damage coefficient dhz(t) at time t through the load model; The specific formula is as follows; ； ； In the formula, ={ , , } represents the stress in the x, y and z directions at time t, ={ , , } represents the stress limit in the x, y and z directions, which is input by the user based on the material standard, ni={nx, xy, xz} represents the stress correction constant in the x, y and z directions, rop(t) represents the thermal-mechanical coupling fatigue damage at time t, represents the stress at time t, represents the fatigue limit of the material, wd(t) represents the temperature at time t, and wd ref represents the reference temperature, dt represents the integration in the time interval, and dhz(t) represents the multi-axial load fatigue damage coefficient at time t.

5. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 4, characterized in that: The S32 includes S321 and S322; S321, comprehensively analyzing the fatigue damage of the alloy at time t based on the obtained thermal-mechanical coupling fatigue damage coefficient rop(t) and the multiaxial load fatigue damage coefficient dhz(t), summarizing and calculating to obtain the composite fatigue damage coefficient fpl(t), and quantifying the influence of the common influencing factors on the fatigue damage of the alloy; The composite fatigue damage coefficient fpl(t) is calculated by the following formula: ； Where fpl(t) represents the composite fatigue damage coefficient at time t, a1 and a2 represent the influence coefficients of the thermal-mechanical coupling fatigue damage coefficient and the multiaxial load fatigue damage coefficient on the composite fatigue damage coefficient, respectively, and a1+a2=1. The specific value is set by the user.

6. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 5, characterized in that: S322. Based on the historical fatigue data set in the data repository, the composite fatigue damage coefficient fpl(t) of the material under different working conditions is calculated using the cumulative damage theory, the mean is calculated to preset the safety fatigue damage threshold A, and a preliminary fatigue damage assessment is performed with the obtained composite fatigue damage coefficient fpl(t). The specific assessment scheme is as follows; When the composite fatigue damage coefficient fpl ≥ the safe fatigue damage threshold A, the fatigue damage of the material has a risk of failure, and fatigue warning information is generated and transmitted to the user end through a wireless network; When the composite fatigue damage coefficient fpl is less than the safety fatigue damage threshold A, the material state is normal, monitoring is maintained and deep prediction is triggered.

7. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 6, characterized in that: The S4 includes S41 and S42; S41. When the initial fatigue damage assessment shows that the material state is normal, the precipitate particles of the corrosion elements on the alloy surface are analyzed. Based on the obtained precipitate data group and the influence of temperature wd(t) on the precipitate volume change, a summary calculation is performed to obtain the precipitate volume fraction V. p (t); The precipitate volume fraction V p (t) is calculated by the following formula: ； Where V p (t) represents the volume fraction of the precipitate at time t, wd0 represents the reference temperature, w represents the correction constant, and nd z Indicates the concentration of total alloy elements.

8. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 7, characterized in that: S42, based on the obtained corrosion impact data set and precipitate volume fraction V p (t) Summarize and calculate the environmental corrosion influence coefficient hwx(t) and analyze the influence of the environment on the corrosion degree of the alloy; The environmental corrosion influence coefficient hwx(t) is calculated by the following formula; ； Where hwx(t) represents the environmental corrosion influence coefficient at time t, fs(t) represents the corrosion rate at time t, yh(t) represents the oxide layer thickness at time t, yh0 represents the initial oxide layer thickness, V p，ref represents the standard precipitate volume fraction of the alloy material, and p represents the precipitate influence index.

9. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 8, characterized in that: The S5 includes S51 and S52; S51. Based on the obtained composite fatigue damage coefficient fpl(t) and environmental corrosion influence coefficient hwx(t), a summary calculation is performed to obtain the comprehensive fatigue damage coefficient zhp(t), analyze the change trend of the fatigue degree of the alloy under the combined effect of stress and corrosion damage, and quantify the fatigue of the alloy under the combined influence; The comprehensive fatigue damage coefficient zhp(t) is calculated by the following formula; ； Where zhp(t) represents the comprehensive fatigue damage coefficient at time t, and b represents the correction factor.

10. The method for constructing a fatigue performance prediction model for alloy functional materials according to claim 9, characterized in that: S52. Based on the obtained comprehensive fatigue damage coefficient zhp and the preset safety fatigue damage threshold A, a corrosion degree prediction risk assessment is performed. The specific assessment scheme is as follows; When the comprehensive fatigue damage coefficient zhp ≥ the safety fatigue damage threshold A, the alloy material is at risk of corrosion. At this time, corrosion warning information is generated and transmitted to the user end through a wireless network. When the comprehensive fatigue damage coefficient zhp is less than the safety fatigue damage threshold A, there is no risk of corrosion of the alloy material, the material state is normal, and normal monitoring is maintained.

Images