An intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation

Abstract

The present invention belongs to the technical field of hot deformation, and relates to an intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation. Data related to titanium alloy is collected; a dynamic recrystallization fraction prediction model is established to calculate the predicted value of the dynamic recrystallization fraction; the size of the predicted value of the dynamic recrystallization fraction is compared with the dynamic recrystallization threshold, triggering a metallographic supplementary test and updating the prediction model; a mechanical property prediction model is constructed to calculate the values of the tensile strength and elongation; the size of the tensile strength is compared with the qualified threshold of the tensile strength, and the size of the elongation is compared with the qualified threshold of the elongation to determine whether the hot deformation performance of the titanium alloy is qualified; a multi-objective optimization algorithm is applied to find the combination of temperature and strain rate that maximizes the tensile strength; the model parameters are dynamically corrected. The present invention can solve the problems that the existing prediction methods lack intelligent prediction and optimization algorithms and cannot automatically detect unqualified performance and trigger process parameter optimization.

Description

Technical Field

[0001] The present invention relates to an intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation, belonging to the technical field of hot deformation. Background Art

[0002] Traditional experimental methods require a large amount of time and resources, with high costs. Due to the limitations of experimental conditions, it is often difficult to comprehensively and accurately simulate the hot deformation behavior of titanium alloy during actual processing. Secondly, the hot deformation properties of titanium alloy are affected by various factors, such as chemical composition, grain size, deformation temperature, strain rate, etc. These factors interact with each other, making the hot deformation properties of titanium alloy complex and variable. Traditional experimental methods often fail to comprehensively consider these factors, resulting in low accuracy of prediction results.

[0003] With the rapid development of materials science and finite element simulation technology, people have begun to explore the use of advanced computational methods and simulation technologies to predict the hot deformation properties of titanium alloy. As a powerful numerical simulation tool, finite element simulation technology can simulate the stress, strain, and temperature field distributions of titanium alloy under complex deformation conditions, providing a new approach for predicting the hot deformation properties of titanium alloy. However, existing prediction methods based on finite element simulation still have many deficiencies.

[0004] Based on the above problems, existing prediction methods lack intelligent prediction and optimization algorithms, and cannot automatically detect unqualified performance and trigger process parameter optimization. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation, which can solve the problem that existing prediction methods lack intelligent prediction and optimization algorithms and cannot automatically detect unqualified performance and trigger process parameter optimization.

[0006] The technical solution adopted by the present invention is as follows:

[0007] An intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation, comprising the following steps:

[0008] S1. Collect data related to the chemical composition, grain size, deformation temperature, strain rate, and stress value of the titanium alloy;

[0009] S2. Calculate the peak strain and critical strain based on the collected data, and establish a dynamic recrystallization fraction prediction model to calculate the predicted value of the dynamic recrystallization fraction;

[0010] S3. Set a dynamic recrystallization threshold, compare the predicted value of the dynamic recrystallization fraction with the dynamic recrystallization threshold, trigger a metallographic supplementary test, and update the prediction model;

[0011] S4. Construct a mechanical property prediction model and calculate the values of tensile strength and elongation;

[0012] S5. Set the qualified thresholds for tensile strength and elongation, compare the tensile strength with the qualified threshold for tensile strength, compare the elongation with the qualified threshold for elongation, determine whether the hot deformation performance of the titanium alloy is qualified, and if not, optimize the process parameters;

[0013] S6. On the premise that the elongation value is qualified, apply a multi-objective optimization algorithm to find the combination of temperature and strain rate that maximizes the tensile strength;

[0014] S7. Verify the optimized process parameters through finite element simulation, and perform closed-loop feedback based on the simulation results and actual production data to dynamically correct the model parameters.

[0015] In a further aspect of the present invention, step S1 includes the following steps:

[0016] Collect the composition data of the titanium alloy using a direct-reading spectrometer, including the element contents related to Ti, Al, V, and O;

[0017] Use a Gleeble thermal simulation test machine, combined with the preset temperature T and strain rate, to obtain the true stress-strain curve, and the data acquisition frequency ≥ 100 Hz;

[0018] Use a scanning electron microscope to perform metallographic analysis on the quenched specimen, measure the dynamic recrystallization fraction DRX and the grain size, and the number of sampling areas ≥ 5 fields of view;

[0019] Synchronously collect the local strain rate and temperature field distribution data during the deformation process through a laser velocimeter and an infrared thermometer.

[0020] In a further aspect of the present invention, step S2 includes the following steps:

[0021] Calculate the peak strain and the critical strain according to the true stress-strain curve obtained in step S1;

[0022] Among them, the critical strain is the minimum strain that triggers the dynamic recrystallization fraction DRX, and the peak strain is the strain corresponding to the point with the maximum stress;

[0023] Determine the parameters K and n through laboratory measurements according to the dynamic recrystallization fraction DRX obtained in step S1.

[0024] In a further aspect of the present invention, step S2 further includes the following steps:

[0025] Establish a dynamic recrystallization fraction prediction model, which satisfies the following formula,

[0026]

[0027] Among them, represents the dynamic recrystallization fraction, represents the kinetic coefficient, and n represents the characteristic parameter reflecting the phase transformation mechanism. represents the peak strain, represents the critical strain, represents the actual strain.

[0028] A further solution of the present invention, step S3, includes the following steps:

[0029] Preset the dynamic recrystallization threshold , compare the predicted with the dynamic recrystallization threshold , and correct the critical strain based on the real-time strain feedback;

[0030] If , keep the current critical strain , and continue to the next step;

[0031] If , trigger the metallographic supplementary test, analyze the supplementary test sample by electron backscatter diffraction, recalibrate , update the in the dynamic recrystallization fraction prediction model and recalculate the predicted value.

[0032] A further solution of the present invention, step S4, includes the following steps:

[0033] Tensile strength is related to the dynamic recrystallization fraction and the grain size, and satisfies the following formula,

[0034]

[0035] Among them, represents the lattice friction stress, which represents the inherent deformation resistance of the material without the influence of grain boundaries and is related to the material purity; represents the Hall-Petch coefficient, which needs to be calibrated experimentally; the average size of the grains after recrystallization; represents the original grain size, the average grain size before deformation.

[0036] A further solution of the present invention, step S4, also includes the following steps:

[0037] Elongation , satisfies the following formula,

[0038]

[0039] Among them, represents the maximum theoretical elongation of the material, which depends on the intrinsic plasticity of the material; represents the influence coefficient of dynamic recrystallization on plasticity, which needs to be determined by data fitting.

[0040] A further solution of the present invention, step S5, includes the following steps:

[0041] Combined with the data of historical records and expert estimates, set the qualified threshold of tensile strength and the qualified threshold of elongation , compare the tensile strength with the qualified threshold of tensile strength , compare the elongation with the qualified threshold of elongation to judge;

[0042] If the predicted and , it is judged that the performance of the hot deformation of the high-strength titanium alloy is qualified;

[0043] If the predicted or , trigger the optimization of process parameters.

[0044] A further solution of the present invention, step S6, includes the following steps:

[0045] Apply a multi-objective optimization algorithm to find the temperature and strain rate that make the tensile strength the highest;

[0046] The elongation must ;

[0047] Parameter range: , strain rate ;

[0048] Within the parameter range, select 4-6 groups of key parameter combinations to cover high, medium, and low change temperatures and fast, medium, and slow strain rates, and select the optimal solution candidate.

[0049] A further solution of the present invention, step S7, includes the following steps:

[0050] Sensors are deployed inside the hot working equipment to collect temperature, strain rate, and pressure data in real time;

[0051] The real-time data is input into the finite element model within a specified time period to update the simulated stress-strain curve and dynamic recrystallization prediction;

[0052] When the measured temperature measured by the thermal simulation testing machine exceeds the range allowed by the process window, a parameter correction instruction is triggered, which satisfies the following formula:

[0053]

[0054] wherein, is the target temperature, is the actually measured temperature, is the original strain value before correction, is the strain value after correction. At least 3 batches of titanium alloys are produced using the optimized parameters, and the titanium alloys are randomly sampled to detect the tensile strength and elongation rate to determine whether the hot deformation performance of the titanium alloys is qualified. If the qualified rate is , lock the parameters as the process standard; if the qualified rate is , go back to step S2 to recalibrate the dynamic recrystallization fraction prediction model.

[0055] In summary, the present invention includes the following beneficial technical effects:

[0056] 1. By comprehensively collecting multi-dimensional data such as the chemical composition and grain size of titanium alloys, and using advanced finite element simulation technology and dynamic recrystallization fraction prediction model, the hot deformation performance of high-strength titanium alloys is intelligently predicted. Compared with traditional experimental methods, this method can more comprehensively consider various factors affecting the hot deformation performance of titanium alloys, thereby significantly improving the accuracy and reliability of prediction. Accurate prediction helps to reduce material waste and production cost losses caused by non-conforming performance;

[0057] 2. Based on predicting the hot deformation performance of titanium alloys, this method can timely detect unqualified performance and automatically trigger the optimization of process parameters. By finely adjusting the process parameters, it can ensure that titanium alloy products obtain excellent mechanical properties and processing performance during hot deformation. This not only improves the overall quality of the products, but also enhances the stability of the performance, making titanium alloy products better meet the stringent requirements in practical applications;

[0058] 3. It can significantly reduce manual trial and error and the number of experiments, thereby reducing the time and cost in the product R & D and production processes. By quickly and accurately predicting the hot deformation performance of titanium alloys, enterprises can determine the appropriate process parameters faster and accelerate the time to market of new products. In addition, the intelligent prediction method helps enterprises achieve lean production, improve production efficiency and resource utilization rate, further reduce costs and enhance market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow schematic diagram of an intelligent prediction method for hot deformation of high-strength titanium alloys based on finite element simulation.

[0060] Figure 2 It is a schematic diagram of the framework of an intelligent prediction system for hot deformation of high-strength titanium alloy based on finite element simulation. Specific implementation manners

[0061] The present invention will be described in detail below with reference to the accompanying drawings.

[0062] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0063] The following will be described in detail with reference to the appended Figure 1-2 Make a preferred and detailed description of the present invention.

[0064] Refer to the appended Figure 1 The present invention provides an intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation, including the following steps:

[0065] S1. Collect data related to the chemical composition, grain size, deformation temperature, strain rate, and stress value of the titanium alloy; establish a multi-dimensional input basis to provide a complete input parameter system for the subsequent model, and ensure that the model covers all the main influencing factors.

[0066] S2. Calculate the peak strain and critical strain according to the collected data, and establish a dynamic recrystallization fraction prediction model to calculate the predicted value of the dynamic recrystallization fraction; connect the process parameters with the microstructure evolution, quantify the microstructure change, and provide an intermediate bridge for the subsequent mechanical property prediction.

[0067] S3. Set the dynamic recrystallization threshold, compare the predicted value of the dynamic recrystallization fraction with the dynamic recrystallization threshold, trigger the metallographic supplement test and update the prediction model; intelligently calibrate the reliability of the model, avoid the failure of the model caused by the long-term accumulation of simulation errors, and realize data-driven self-adaptability.

[0068] S4. Construct a mechanical property prediction model to calculate the values of the tensile strength and elongation; map from the microstructure to the macroscopic properties, directly relate the microstructure evolution to the engineering property indicators, and provide a quantifiable target for process optimization.

[0069] S5. Set the qualified thresholds for the tensile strength and elongation, compare the tensile strength with the qualified threshold for the tensile strength, compare the elongation with the qualified threshold for the elongation, judge whether the hot deformation performance of the titanium alloy is qualified, and if it is unqualified, optimize the process parameters; realize real-time quality monitoring and process self-adjustment, and replace the inefficient process that traditionally relies on manual trial and error.

[0070] S6. On the premise that the elongation value is qualified, apply the multi-objective optimization algorithm to find the combination of temperature and strain rate that maximizes the tensile strength; solve the common multi-objective conflict problems in engineering and ensure the global optimality of process parameters under complex constraints.

[0071] S7. Verify the optimized process parameters through finite element simulation, perform closed-loop feedback based on the simulation results and actual production data, and dynamically correct the model parameters; form a closed loop of "simulation → optimization → verification → correction" to ensure the long-term applicability of the model with changes in production conditions.

[0072] In this solution, the dynamic recrystallization model and the mechanical property model are connected in series, breaking through the limitations of traditional single-scale simulation and being closer to the actual material behavior. By comparing the dynamic recrystallization fraction with the threshold in real time, trigger the directional metallographic experiment to achieve "on-demand update" of model parameters instead of fixed-period adjustment, avoiding the lag of manual intervention. First, ensure the qualification of elongation, and then perform single-objective optimization of the tensile strength to avoid multi-objective conflicts, which is more in line with the actual engineering requirements. The finite element provides high-fidelity physical field data, and the intelligent algorithm is responsible for decision-making optimization. The two cooperate to form a prediction system. Through hybrid modeling and intelligent control, high-precision prediction of the hot deformation properties of titanium alloys and autonomous optimization of process parameters are achieved, solving the pain points of high cost, low efficiency, and insufficient accuracy of traditional methods, and providing a popularizable intelligent solution for complex material processing.

[0073] In one embodiment of the present invention, step S1 includes the following steps:

[0074] Use a direct-reading spectrometer to collect the composition data of the titanium alloy, including the element contents related to Ti, Al, V, and O; the direct-reading spectrometer can non-destructively detect solid samples within seconds, without complex chemical pretreatment, and directly output high-precision element content data, providing high-fidelity basic parameters for subsequent hot deformation property modeling and avoiding the accumulation of model errors caused by composition deviations.

[0075] Exemplarily, use a direct-reading spectrometer to collect the composition of TC4 titanium alloy. The excitation energy of the direct-reading spectrometer is 4.8 , the argon flow rate is 12 , measure the composition of TC4 titanium alloy, the content of Al is 5.75%, the content of V is 3.92%, the content of O is 0.15%, and the rest is Ti.

[0076] Using a Gleeble thermo-simulation testing machine, combined with a preset temperature T and strain rate, a true stress-strain curve is obtained, and the data acquisition frequency is ≥100 Hz; the advantage of Gleeble lies in its ability to precisely control the temperature and strain rate, ensuring high-fidelity dynamic response capture and process traceability. The ultra-high sampling frequency can completely record the stress fluctuation details corresponding to the microstructure evolution, providing high-resolution time series data for the dynamic recrystallization model and mechanical property prediction.

[0077] Exemplarily, based on the Gleeble thermo-simulation testing machine, the specimen size of TC4 titanium alloy is , and the TC4 titanium alloy is preheated to 950 , and the temperature is maintained within the range of for 180 seconds;

[0078] Combined with the preset temperature, 800 , 900 , 1000 , 1050 , and the preset strain rate, 0.001 , 0.01 , 0.1 , 1 , 10 , according to 4 groups of temperatures and 5 groups of strain rates , 20 groups of tests are conducted. The stress values collected at constant strain rate intervals are recorded to obtain the true stress-strain curves at different temperatures T and strain rates.

[0079] The metallographic analysis of the quenched specimens is carried out using a scanning electron microscope to measure the dynamic recrystallization fraction DRX and grain size, and the number of sampling regions is ≥5 fields of view; it provides statistically reliable microstructure verification data for the dynamic recrystallization model and solves the accidental error problem of traditional single-field analysis.

[0080] Exemplarily, within 1 second after the hot deformation ends, it is quenched by pouring into ice brine. A metallographic specimen is prepared using an automatic grinding machine, and the TC4 titanium alloy is etched with Kroll reagent for 15 seconds. Professional software is used to measure the dynamic recrystallization fraction DRX and the statistically average grain size.

[0081] Exemplarily, a laser Kepler velocimeter can be used, with a sampling rate of 10 , and a measurement point density of 1 point , collect real-time temperature data; use an infrared thermal imager and a Gleeble thermal simulation testing machine to trigger synchronously to collect local strain rate data. Through a laser velocimeter and an infrared thermometer, synchronously collect local strain rate and temperature field distribution data during the deformation process; the synchronous monitoring of the laser velocimeter + infrared thermometer realizes the real-time matching of the local strain rate and the temperature field gradient during the deformation process, provides boundary condition calibration data for finite element simulation, significantly improves the accuracy of the coupling of the stress-strain curve and the real thermal field, and avoids model distortion caused by the assumption of uniformity.

[0082] In one embodiment of the present invention, step S2 includes the following steps:

[0083] According to the true stress-strain curve obtained in step S1, calculate the peak strain and the critical strain;

[0084] Among them, the critical strain is the minimum strain that triggers the dynamic recrystallization fraction DRX, and the peak strain is the strain corresponding to the point with the maximum stress;

[0085] Directly extract the peak strain from the high-frequency stress-strain curve of the Gleeble test, determine the critical strain, provide the core input parameters for the dynamic recrystallization model, and solve the problem of subjective error in traditional visual interpretation.

[0086] Exemplarily, the calculated peak strain and the critical strain .

[0087] According to the dynamic recrystallization fraction DRX obtained in step S1, determine the parameters K and n through laboratory measurements;

[0088] Establish a dynamic recrystallization fraction prediction model that satisfies the following formula,

[0089]

[0090] Among them, represents the dynamic recrystallization fraction, represents the kinetic coefficient, n represents the characteristic parameter reflecting the phase transformation mechanism, represents the peak strain, represents the critical strain, represents the actual strain;

[0091] Make the prediction model have the support of physical mechanism and avoid the overfitting risk of pure data-driven.

[0092] Exemplarily, for TC4 titanium alloy as a specimen, use DEFORM software for finite element simulation to obtain and ; the experimental fitting parameters of TC4 titanium alloy obtain and ; actual strain , and substitute it into the dynamic recrystallization fraction prediction model;

[0093] It is known that .

[0094] In one embodiment of the present invention, step S3 includes the following steps:

[0095] Combined with the data of historical records and expert estimates, set the dynamic recrystallization threshold , and compare the predicted with the dynamic recrystallization threshold , and correct the critical strain based on the real-time strain feedback;

[0096] If , keep the current critical strain , and continue to the next step;

[0097] If , trigger the metallographic supplementary test, analyze the supplementary test sample by the electron backscatter diffraction method, recalibrate , update the in the dynamic recrystallization fraction prediction model and recalculate the predicted value. Automatically identify abnormal working conditions through the threshold criterion, and only trigger supplementary tests for unqualified samples, reducing more than 80% of invalid experiments.

[0098] Exemplarily, set the dynamic recrystallization threshold ;

[0099] If , keep the current critical strain ; if , trigger the metallographic supplementary test, analyze the supplementary test sample by electron backscatter diffraction, recalibrate , where .

[0100] In one embodiment of the present invention, step S4 includes the following steps:

[0101] Tensile strength is related to the dynamic recrystallization fraction and the grain size, and satisfies the following formula

[0102]

[0103] where represents the lattice friction stress, which represents the inherent deformation resistance of the material without the influence of grain boundaries and is related to the material purity; represents the Hall-Petch coefficient, which needs to be calibrated by experiments; The average grain size after recrystallization; represents the original grain size, i.e., the average grain size of the undeformed material;

[0104] Elongation , satisfying the following formula,

[0105]

[0106] wherein, represents the maximum theoretical elongation of the material, which depends on the intrinsic plasticity of the material; represents the influence coefficient of dynamic recrystallization on plasticity, which needs to be determined by data fitting;

[0107] Exemplarily, for TC4 titanium alloy as a specimen, assuming belongs to a classical empirical value, , , , when , substituting the tensile strength into the formula:

[0108]

[0109] For TC4 titanium alloy as a specimen, assuming , , substituting the elongation into the formula:

[0110]

[0111] In one embodiment of the present invention, step S5 includes the following steps:

[0112] Combining the data of historical records and expert estimates, set the qualified threshold of tensile strength and the qualified threshold of elongation , compare the tensile strength with the qualified threshold of tensile strength , compare the elongation with the qualified threshold of elongation , for judgment,

[0113] If the predicted and , it is determined that the performance of the high-strength titanium alloy hot deformation is qualified;

[0114] If the predicted or , trigger the optimization of process parameters.

[0115] Tensile strength and elongation, as orthogonal evaluation dimensions, cover the core requirements of material strength and toughness, and are more in line with engineering practice than single indicators. By setting a hard threshold and making flexible process adjustments, the flexibility of the process window is maximized while ensuring the bottom line of quality.

[0116] Exemplarily, assume that the qualified threshold of tensile strength is , and the qualified threshold of elongation is ;

[0117] If the predicted and , it is determined that the performance of the hot deformation of the high-strength titanium alloy is qualified;

[0118] If the predicted or , the optimization of process parameters is triggered.

[0119] In one embodiment of the present invention, step S6 includes the following steps:

[0120] Apply a multi-objective optimization algorithm to find the temperature and strain rate that maximize the tensile strength;

[0121] The elongation must be ;

[0122] Parameter range: , strain rate ;

[0123] Within the parameter range, select 4-6 groups of key parameter combinations to cover high, medium, and low temperature changes and fast, medium, and slow strain rates, and select candidate optimal solutions.

[0124] Taking elongation as a hard constraint to avoid the risk of brittle fracture caused by simply pursuing strength. By replacing the traditional grid search with an intelligent algorithm, the calculation efficiency is greatly improved. The parameter combination avoids local optima and ensures global search ability.

[0125] Exemplarily, the elongation must be ,

[0126] The first group ( ) corresponds to , 10.5%;

[0127] The second group ( ) corresponds to , 14.5%;

[0128] The third group ( ) corresponds to , 13%;

[0129] The fourth group ( ) corresponding to , 11.8%;

[0130] So the optimal solution candidate: the second group ( ) corresponding to , 14.5%.

[0131] In one embodiment of the present invention, step S7 includes the following steps:

[0132] Sensors are deployed inside the hot processing equipment to collect temperature, strain rate, and pressure data in real time;

[0133] The real-time data is input into the finite element model within a specified time period to update the simulated stress-strain curve and dynamic recrystallization prediction;

[0134] When the measured temperature measured by the hot simulation testing machine exceeds the range allowed by the process window, a parameter correction instruction is triggered, satisfying the following formula,

[0135]

[0136] where is the target temperature, is the actually measured temperature, is the original strain value before correction, is the corrected strain value. The process parameters are dynamically corrected through sensor data to avoid batch scrapping caused by traditional "post-detection". The strain rate correction formula is based on physical relationships to ensure that the adjusted process still conforms to the material hot deformation law.

[0137] Exemplarily, a certain batch of hot simulation testing machine fails, and the actual temperature drops from to (lower than the lower limit of the process window ); the predicted value of in the dynamic recrystallization fraction prediction model drops from 75% to 68%, the value of

[0138] drops to 852 MPa;

[0139]

[0140] Produce at least 3 batches of titanium alloy using the optimized parameters, randomly sample the titanium alloy to detect the tensile strength and elongation, and determine whether the hot deformation performance of the titanium alloy is qualified. If the qualified rate is , lock the parameters as the process standard; if the qualified rate is , go back to step S2 to recalibrate the dynamic recrystallization fraction prediction model. The strict standard of 95% qualification rate for 3 batches ensures the process robustness.

[0141] See the appendix Figure 2 , the present invention also proposes an intelligent prediction system for hot deformation of high-strength titanium alloy based on finite element simulation, including: titanium alloy data acquisition module, dynamic recrystallization fraction prediction model establishment module, dynamic recrystallization threshold setting module, mechanical property prediction model construction module, qualified threshold setting module for tensile strength and elongation, optimization process module, optimization verification module;

[0142] The titanium alloy data acquisition module is used to collect data related to the chemical composition, grain size, deformation temperature, strain rate, and stress value of the titanium alloy;

[0143] The dynamic recrystallization fraction prediction model establishment module is used to calculate the peak strain and critical strain according to the collected data, establish a dynamic recrystallization fraction prediction model, and calculate the dynamic recrystallization fraction prediction value;

[0144] The dynamic recrystallization threshold setting module is used to set the dynamic recrystallization threshold, compare the dynamic recrystallization fraction prediction value with the dynamic recrystallization threshold, trigger the metallographic supplementary test and update the prediction model;

[0145] The mechanical property prediction model construction module is used to construct a mechanical property prediction model and calculate the values of tensile strength and elongation;

[0146] The qualified threshold setting module for tensile strength and elongation is used to set the qualified threshold for tensile strength and the qualified threshold for elongation, compare the tensile strength with the qualified threshold for tensile strength, compare the elongation with the qualified threshold for elongation, judge whether the hot deformation performance of the titanium alloy is qualified, and optimize the process parameters if unqualified;

[0147] The optimization process module, on the premise that the elongation value is qualified, finds the combination of temperature and strain rate that makes the tensile strength the highest;

[0148] The optimization verification module verifies the optimized process parameters through finite element simulation, and performs closed-loop feedback according to the simulation results and actual production data to dynamically correct the model parameters.

[0149] Each of the above-mentioned modules can be implemented in whole or in part by software, hardware and their combination, supports being embedded in the processor of the computer device in the form of hardware or being independent of it, and also supports being stored in the memory of the computer device in the form of software so that the processor can call and execute the operations corresponding to each of the above-mentioned modules.

[0150] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. The present invention extends to any new feature or any new combination disclosed in this specification, and any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the detailed technical features not disclosed in this embodiment, such as specific structures, are all prior art, and those skilled in the art can obtain them from the prior art.

Claims

1. An intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation, characterized in that It includes the following steps: S1. Collect data related to the chemical composition, grain size, deformation temperature, strain rate, and stress value of titanium alloy; S2. Calculate the peak strain and critical strain based on the collected data, and establish a dynamic recrystallization fraction prediction model to calculate the predicted value of the dynamic recrystallization fraction; S3. Set the dynamic recrystallization threshold, compare the predicted value of the dynamic recrystallization fraction with the dynamic recrystallization threshold, trigger the metallographic supplementary test and update the prediction model; S4. Construct a mechanical property prediction model to calculate the values of tensile strength and elongation; Tensile strength is related to the dynamic recrystallization fraction and grain size and satisfies the following formula Among them, represents the lattice friction stress, which represents the inherent deformation resistance of the material without the influence of grain boundaries and is related to the material purity; represents the Hall-Petch coefficient, which needs to be experimentally calibrated; represents the average grain size after recrystallization; represents the original grain size, the average grain size of the undeformed; Elongation rate , satisfying the following formula, Among them, represents the maximum theoretical elongation of the material, which depends on the intrinsic plasticity of the material; represents the influence coefficient of dynamic recrystallization on plasticity, which needs to be determined by data fitting; S5. Set the qualified thresholds for tensile strength and elongation, compare the tensile strength with the qualified threshold for tensile strength, compare the elongation with the qualified threshold for elongation, and judge whether the hot deformation performance of the titanium alloy is qualified. If not, optimize the process parameters; S6. On the premise that the elongation value is qualified, apply the multi-objective optimization algorithm to find the combination of temperature and strain rate that maximizes the tensile strength; S7. Verify the optimized process parameters through finite element simulation, and perform closed-loop feedback based on the simulation results and actual production data to dynamically correct the model parameters.

2. The intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation according to claim 1, wherein Step S1 includes the following steps: S11. Use a direct-reading spectrometer to collect the composition data of titanium alloy, including the element contents related to Ti, Al, V, and O; S12. Use a Gleeble thermal simulation test machine, combined with the preset temperature T and strain rate, to obtain the true stress-strain curve, and the data acquisition frequency ≥ 100 Hz; S13. Use a scanning electron microscope to perform metallographic analysis on the quenched specimen, measure the dynamic recrystallization fraction DRX and grain size, and the number of sampling areas ≥ 5 fields of view; S14. Synchronously collect the local strain rate and temperature field distribution data during the deformation process through a laser velocimeter and an infrared thermometer.

3. The intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation according to claim 2, characterized in that Step S2 includes the following steps: S21. Calculate the peak strain and critical strain based on the true stress-strain curve obtained in step S1; Among them, the critical strain is the minimum strain that triggers the dynamic recrystallization fraction DRX, and the peak strain is the strain corresponding to the point with the maximum stress; S22. Determine the kinetic coefficient K and the characteristic parameter n reflecting the phase transformation mechanism based on the dynamic recrystallization fraction DRX obtained in step S1 through laboratory measurement.

4. An intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation according to claim 3, characterized in that Step S2 also includes the following steps: S23. Establish a dynamic recrystallization fraction prediction model that satisfies the following formula Among them, represents the dynamic recrystallization fraction, represents the kinetic coefficient, and n represents the characteristic parameter reflecting the phase transformation mechanism, represents the peak strain, represents the critical strain, represents the actual strain.

5. A method for intelligent prediction of hot deformation of high-strength titanium alloy based on finite element simulation according to claim 4, characterized in that Step S3 includes the following steps: S31. Preset the dynamic recrystallization threshold , compare the predicted with the dynamic recrystallization threshold in terms of magnitude, and correct the critical strain based on the real-time strain feedback; If , maintain the current critical strain , and continue to the next step; If , trigger the metallographic supplementary test, analyze the supplementary test sample using electron backscatter diffraction, and recalibrate , update the in the dynamic recrystallization fraction prediction model and recalculate the predicted value.

6. The intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation according to claim 5, characterized in that Step S5 includes the following steps: Set the qualified threshold of tensile strength and the qualified threshold of elongation , compare the tensile strength with the qualified threshold of tensile strength , compare the elongation with the qualified threshold of elongation to judge If it is predicted and , it is determined that the properties of the hot deformation of the high-strength titanium alloy are qualified; If predicted or , trigger the optimization of process parameters.

7. A method for intelligent prediction of hot deformation of high-strength titanium alloy based on finite element simulation according to claim 6, characterized in that Step S6 includes the following steps: Apply a multi-objective optimization algorithm to find the temperature and strain rate that maximize the tensile strength. and strain rate; Elongation rate ; Parameter range: , ; Within the parameter range, select 4 - 6 groups of key parameter combinations, covering high, medium, and low changing temperatures and fast, medium, and slow strain rates, and select the candidate for the optimal solution.

8. An intelligent prediction method for hot deformation of high-strength titanium alloy based on finite element simulation according to claim 7, characterized in that, Step S7 includes the following steps: Sensors are deployed inside the hot processing equipment to collect temperature, strain rate, and pressure data in real time; The real-time data is input into the finite element model within the specified time period to update the simulated stress-strain curve and dynamic recrystallization prediction; When the measured temperature measured by the thermal simulation test machine exceeds the range allowed by the process window, trigger the parameter correction instruction, which satisfies the following formula Among them, is the target temperature, is the actually measured temperature, is the original strain value before correction, is the strain value after correction; Produce at least 3 batches of titanium alloy with optimized parameters, randomly sample the titanium alloy to detect the tensile strength and elongation, and judge whether the hot deformation performance of the titanium alloy is qualified. If the pass rate , lock the parameters as the process standard; if the pass rate , return to step S2 to recalibrate the dynamic recrystallization fraction prediction model.

Images