Titanium alloy radial forging reduction rate collaborative optimization method based on material testing

Abstract

The invention relates to the technical field of metal plastic forming, and discloses a titanium alloy radial forging reduction rate collaborative optimization method based on material testing, which comprises the following steps of: acquiring dynamic characteristic data in a forging process in real time by acquiring multi-dimensional material performance parameters, and constructing a multi-target collaborative optimization model; and intelligent collaborative configuration of the reduction rate parameters is realized by adopting a self-adaptive weight distribution strategy. And a thermal coupling factor normalization equation and a phase field free energy functional normalization model are established, and the technical problems that in a traditional forging process, due to empirical configuration of reduction rate parameters, the structure is uneven, and residual stress exceeds the standard are solved. A lightweight model is deployed through edge computing nodes, millisecond-level dynamic correction of an optimization scheme is realized in combination with a 5G industrial private network, and the grain size qualification rate and the size precision of the titanium alloy forgings are improved. The method improves the yield of the grain size of the forge piece, ensures that the residual stress of the forge piece is reduced, stably controls the size precision, and improves the batch stability of high-end titanium alloy parts.

Description

Technical Field

[0001] This invention relates to the field of metal plastic forming technology, specifically to a method for co-optimizing radial forging reduction rate of titanium alloys based on material testing. Background Technology

[0002] Metal plastic forming is a processing method that utilizes the property of metal materials to undergo irreversible plastic deformation under external force to form and shape materials. By making the material stress exceed the elastic limit and retaining permanent deformation, the shape and size of the object are changed and the microstructure and properties are optimized. The process includes forging, rolling, extrusion, drawing, stamping, etc. According to temperature, it is divided into three categories: cold forming, warm forming and hot forming. Creep effect and changes in material properties must be considered.

[0003] The current mainstream process adopts a static reduction rate setting method based on empirical formulas. This method has the following bottlenecks: the dynamic recrystallization behavior of the material during forging has a strong coupling effect with the thermodynamic parameters. Traditional methods cannot perceive the evolution of the material's microstructure in real time, resulting in a mismatch between the reduction rate parameters and the actual deformation requirements of the material, causing grain coarsening and abnormal growth. The parameter drift and equipment disturbance lack online compensation capabilities. When the actual deformation deviates from the theoretical value, the reduction rate configuration scheme cannot be dynamically corrected, causing performance fluctuations in batches of parts.

[0004] Therefore, a collaborative optimization method for radial forging reduction rate of titanium alloys based on material testing is proposed to solve the above problems. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a collaborative optimization method for radial forging reduction rate of titanium alloys based on material testing. This method solves the problems of grain coarsening and abnormal growth, as well as batch performance fluctuations, mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a collaborative optimization method for radial forging reduction rate of titanium alloys based on material testing, the method comprising the following steps: S1. Collect multi-dimensional material performance parameters of titanium alloy bars during radial forging process and generate dynamic feature dataset of forging materials; S2. Construct a multi-objective collaborative optimization model for radial forging reduction rate based on the dataset, including a forging process parameter constraint module, a material microstructure prediction module, and a comprehensive performance evaluation module; S3. Based on the dynamic feature dataset of the forging material, perform material performance parameter preprocessing to generate a standardized material feature vector; S4. Input the standardized material feature vector into the radial forging reduction rate multi-objective collaborative optimization model to perform forging process simulation calculation and generate an initial reduction rate optimization scheme set. S5. Adaptive weight allocation strategy is used to perform multi-objective collaborative optimization on the initial pressure reduction rate optimization scheme set to generate the optimal pressure reduction rate collaborative configuration scheme. S6. The optimal reduction rate collaborative configuration scheme is executed through the forging equipment control terminal to realize the collaborative optimization control of the reduction rate in the radial forging process of titanium alloy.

[0007] Preferably, the process of collecting the dynamic feature dataset of forging materials in S1 includes: S11. Dynamic recrystallization temperature gradient data of titanium alloy at different axial positions during forging is collected synchronously through high-temperature strain testing. S12. The microstructure evolution characteristics of the titanium alloy in the forging deformation zone were obtained using an in-situ micro-area composition analysis device, among which the dynamic recrystallization volume fraction satisfies the normalization equation: ; in, For dynamic recrystallization volume fraction, 0 1, To accumulate response for the present, Normalization The critical strain threshold is 0.15 for TC4 titanium alloy. For peak strain, the experimentally determined range is [0.25, 0.35]. This is the dynamic recrystallization rate coefficient, typically 1.8. This is the dynamic recrystallization index, with a typical value of 2.0; S13. Multi-channel data fusion technology is used to integrate thermo-mechanical coupling parameters, including temperature and strain rate, microstructure parameters, including dynamic recrystallization volume fraction and dislocation density, and macroscopic dimensional parameters, including diameter and length changes, to construct a three-dimensional material performance characteristic matrix.

[0008] Preferably, the construction process of the forging process parameter constraint module in S2 includes: S21. Establish a boundary constraint rule library for radial forging process parameters; S22. Training a dynamic threshold prediction network for process parameters based on historical forging data; S23. An integrated temperature compensation algorithm corrects the drift error of thermodynamic parameters during the forging process.

[0009] Preferably, the method for constructing the material microstructure prediction module in S2 includes: S24. Develop a crystal plastic constitutive model based on dislocation density evolution; S25. Predicting dynamic recrystallization volume fraction using integrated phase-field simulation method; S26. Construct a method for predicting grain orientation distribution function; The method for constructing the comprehensive performance evaluation module in S2 includes: S27. Set quantitative evaluation functions for grain size control targets, residual stress control targets, dimensional accuracy targets, and energy consumption control targets; S28. Use fuzzy membership functions to unify the evaluation dimensions of various performance indicators; S29. Establish a dynamic allocation rule base for performance index weight coefficients.

[0010] Preferably, the process of generating the initial reduction rate optimization scheme set in S4 specifically includes: S41. Deploy a material response surface computation engine in the multi-objective collaborative optimization model of radial forging reduction rate; S42. The Latin hypercube sampling method is used to generate a spatial sample point set of forging process parameters. S43. Construct the mapping relationship between reduction rate and material properties using a Kriging proxy model; S44. Filter the initial optimization scheme set based on non-dominated sorting.

[0011] Preferably, the implementation process of the adaptive weight allocation strategy in S5 includes: S51. Construct a four-dimensional optimization objective function space, including the grain size control objective. Residual stress control target Dimensional accuracy target and energy consumption control targets ; S52. The real-time weight coefficients of each optimization objective are dynamically calculated using the entropy weight method. S53. Establishing a multi-objective collaborative optimization utility function based on fuzzy decision-making theory: ; in: ; in, This represents the overall utility value, with a range of [0,1]. For the i-th objective, dynamic weight, , For fuzzy membership functions, sigmoid functions, To normalize the target value, Let the i-th target be the historical minimum value, with the same dimensions. , The historical maximum value of the i-th target, with the same dimensions. ; S54. Determine the optimal solution set using the Pareto front search algorithm.

[0012] Preferably, the method further includes: S7. Monitor changes in material performance parameters in real time during the forging process and generate dynamic feedback data stream; S8. Update the parameters of the multi-objective collaborative optimization model for radial forging reduction rate based on online data-driven technology; S9. When the performance deviation exceeds the threshold, a real-time correction mechanism is triggered.

[0013] Preferably, the triggering process of the real-time correction mechanism includes: S91. Establish a rapid response channel for sudden parameters in the forging process; S92. Employ a sliding time window algorithm to identify abnormal fluctuation patterns in material properties; S93. Generate a downtime compensation scheme through reinforcement learning strategies; S94. Deploy the new solution and verify the effect of the correction within 0.5 seconds.

[0014] Preferably, the method further includes: S10. Deploy a lightweight model execution engine on the edge computing node of the forging equipment; S11. The optimization module is decomposed using model segmentation technology; S12. Real-time synchronous updates of the optimization model are achieved through the 5G industrial private network.

[0015] Preferably, the method further includes: S13. Establish a human-machine collaborative optimization decision-making mechanism, including: S131. Display the 3D simulation results of the optimization scheme through a visual interface; S132, Receive manual correction instructions from process experts; S133. Employ federated learning technology to integrate human decision-making data to update and optimize the model; S134. Generate the final pressure rate execution plan with artificial intelligence identification.

[0016] Compared with existing technologies, this invention provides a method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing, which has the following beneficial effects: 1. In this invention, by constructing a multi-dimensional material performance parameter real-time acquisition system, dynamic recrystallization temperature gradient and microstructure evolution characteristics are simultaneously acquired during the radial forging process of titanium alloy. Combined with a thermo-coupling factor normalization early warning mechanism, millisecond-level perception of material deformation state is achieved. This technology solves the problem that traditional methods cannot respond to changes in material microstructure in real time, suppresses grain coarsening and abnormal growth, and improves the grain size qualification rate of forgings.

[0017] 2. In this invention, by establishing a multi-objective collaborative optimization model for the reduction rate, the entropy weight method is used to dynamically allocate the weight coefficients for grain size control, residual stress reduction, dimensional accuracy improvement, and energy consumption optimization. Based on Pareto front search, the optimal solution set is generated. This innovative scheme solves the parameter oscillation defect caused by multi-objective conflict, and while ensuring the reduction of residual stress in the forging, the dimensional accuracy is stably controlled within the tolerance range.

[0018] 3. In this invention, a lightweight model is executed by deploying edge computing nodes and combined with a 5G industrial private network to achieve real-time synchronization and dynamic correction of the optimization scheme. When the material performance deviation is detected to exceed the threshold, a millisecond-level reduction rate compensation mechanism is triggered based on the normalized comprehensive deviation. This technology breaks through the limitations of offline adjustment in traditional forging processes, reduces energy consumption and material loss, and improves the batch stability of high-end titanium alloy parts. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of the method for co-optimizing radial forging reduction rate of titanium alloys based on material testing, as described in this invention. Detailed Implementation

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] Please see Figure 1 The specific implementation of the collaborative optimization method for radial forging reduction rate of titanium alloys based on material testing is as follows, and the method includes the following steps: S1. Collect multi-dimensional material performance parameters of titanium alloy bars during radial forging process and generate dynamic feature dataset of forging materials; S2. Construct a multi-objective collaborative optimization model for radial forging reduction rate based on the dataset, including a forging process parameter constraint module, a material microstructure prediction module, and a comprehensive performance evaluation module; S3. Based on the dynamic feature dataset of forging materials, preprocess the material performance parameters to generate standardized material feature vectors; S4. Input the standardized material feature vector into the radial forging reduction rate multi-objective collaborative optimization model to perform forging process simulation calculation and generate an initial reduction rate optimization scheme set; S5. Adaptive weight allocation strategy is used to perform multi-objective collaborative optimization on the initial pressure reduction rate optimization scheme set to generate the optimal pressure reduction rate collaborative configuration scheme. S6. By executing the optimal reduction rate collaborative configuration scheme through the forging equipment control terminal, the reduction rate collaborative optimization control of the radial forging process of titanium alloy is realized; S11. Dynamic recrystallization temperature gradient data of titanium alloy at different axial positions during forging is collected synchronously through high-temperature strain testing. S12. The microstructure evolution characteristics of the titanium alloy in the forging deformation zone were obtained using an in-situ micro-area composition analysis device, among which the dynamic recrystallization volume fraction satisfies the normalization equation: ; in, For dynamic recrystallization volume fraction, 0 1, To accumulate response for the present, Normalization The critical strain threshold is 0.15 for TC4 titanium alloy. For peak strain, the experimentally determined range is [0.25, 0.35]. This is the dynamic recrystallization rate coefficient, typically 1.8. This is the dynamic recrystallization index, with a typical value of 2.0; S13. Multi-channel data fusion technology is used to integrate thermo-mechanical coupling parameters including temperature and strain rate, microstructure parameters including dynamic recrystallization volume fraction and dislocation density, and macroscopic size parameters including diameter and length changes to construct a three-dimensional material performance characteristic matrix. S21. Establish a boundary constraint rule library for radial forging process parameters; S22. A dynamic threshold prediction network for process parameters is trained based on historical forging data, wherein the thermo-coupling factor adopts a normalized equation: ; in, Thermodynamic coupling factor; a value greater than 0.6 triggers an early warning. This refers to the real-time strain rate, in units of... , For the maximum allowable strain rate, Normalization The melting point of the material is expressed in Kelvin (K). This is the current forging temperature, in Kelvin (K). ; S23. Integrated temperature compensation algorithm corrects the drift error of thermodynamic parameters during the forging process; S24. Develop a crystal plastic constitutive model based on dislocation density evolution; S25. Integrated phase-field simulation method for predicting dynamic recrystallization volume fraction, with its normalized free energy functional: ; in, For normalized free energy, The phase field sequence parameter is 0~1. For normalized energy density, This is the gradient energy coefficient, in units of J / m. for J / m, Reference free energy, in J / m³; S26. Construct a method for predicting grain orientation distribution function; S27. Set quantitative evaluation functions for grain size control targets, residual stress control targets, dimensional accuracy targets, and energy consumption control targets; S28. The evaluation dimensions of each performance index are unified using fuzzy membership functions, and its normalized calculation formula is: ; in, A warning is issued if the membership degree of the k-th performance indicator is less than 0.6. These are the measured values ​​of the performance indicators. The target value for the performance index, with the same dimensions. , This is a tolerance parameter, with the same dimensions. ; S29. Establish a dynamic allocation rule base for performance indicator weight coefficients; S41. Deploy a material response surface computation engine in the multi-objective collaborative optimization model of radial forging reduction rate; S42. The Latin hypercube sampling method is used to generate a spatial sample point set of process parameters. The sampling process is as follows: First, each process parameter dimension is divided into N equally probable sub-intervals. A sample point is randomly selected in each sub-interval. Finally, the uniform distribution and uncorrelatedness of the sample points in each dimension are achieved by random arrangement. S43. The mapping relationship between reduction rate and material properties is constructed using a Kriging proxy model, and its normalized covariance function is: ; in, Normalization parameters and Covariance between Let k be the dimensionless normalized value of the k-th dimension process parameter. This represents the process variance; a value less than 0.1 indicates high precision. Let be the correlation coefficient of the k-th dimension parameter, when >5 strong correlation, This is the smoothness parameter for the k-th dimension, with a default value of 1.8. The maximum value of the k-th dimension parameter, with the same dimensions. ; S44. The initial set of optimization schemes is selected based on non-dominated sorting. The selection rule is as follows: calculate the objective function value of each scheme, classify the schemes that are not dominated by any other schemes into the first non-dominated layer according to the Pareto dominance relationship, remove the schemes in the first layer and continue to select the second non-dominated layer. Iterate until all layers are completed, and finally select the schemes in the first non-dominated layer as the optimization set. S51. Construct a four-dimensional optimization objective function space, including the grain size control objective. Residual stress control target Dimensional accuracy target and energy consumption control targets ; S52. The real-time weight coefficients of each optimization objective are dynamically calculated using the entropy weight method. S53. Establishing a multi-objective collaborative optimization utility function based on fuzzy decision-making theory: ; in: ; in, This represents the overall utility value, with a range of [0,1]. For the i-th objective, dynamic weight, , For fuzzy membership functions, sigmoid functions, To normalize the target value, Let the i-th target be the historical minimum value, with the same dimensions. , The historical maximum value of the i-th target, with the same dimensions. ; S54. The optimal solution set is determined by the Pareto front search algorithm. The execution process is as follows: First, identify the non-dominated solutions in the current solution set that are not dominated by any other solution to form the Pareto front. If the number of front solutions exceeds a set threshold, the crowding distance sorting algorithm is used to filter the elite solution set with the most uniform distribution. S7. Monitor changes in material performance parameters in real time during the forging process and generate dynamic feedback data stream; S8. Update the parameters of the multi-objective collaborative optimization model for radial forging reduction rate based on online data-driven technology; S9. When the performance deviation exceeds the threshold, a real-time correction mechanism is triggered, where the normalized deviation is: ; in, The normalized overall bias is greater than 1.5, triggering a correction. Let k be the measured value of the performance item. Let k be the predicted performance value. This is the tolerance coefficient, with the same dimensions. , The number of monitoring parameters; S91. Establish a rapid response channel for sudden parameters in the forging process; S92. Employ a sliding time window algorithm to identify abnormal fluctuation patterns in material properties; S93. Generate a downtime compensation scheme through reinforcement learning strategies; S94. Deploy the new solution and verify the effect of the correction within 0.5 seconds; S10. Deploy a lightweight model execution engine on the edge computing node of the forging equipment; S11. The module is decomposed and optimized using model fragmentation technology, and its normalized transmission efficiency is: ; in, To normalize transmission efficiency, For the maximum theoretical efficiency of 1.0, This refers to the bandwidth of the 5G private network, measured in Mbps. Mbps, For synchronization time windows, the unit is seconds. s threshold, Network reliability coefficient; S12. Real-time synchronous updates of the optimization model are achieved through the 5G industrial private network; S13. Establish a human-machine collaborative optimization decision-making mechanism, including: S131. Display the 3D simulation results of the optimization scheme through a visual interface; S132, Receive manual correction instructions from process experts; S133. Employ federated learning technology to integrate human decision-making data to update and optimize the model; S134. Generate the final pressure rate execution plan with artificial intelligence identification.

[0022] The operational steps of the collaborative optimization method for radial forging reduction rate of titanium alloys based on material testing are as follows: Step 1: Acquisition of dynamic material characteristics Temperature distribution data of titanium alloy bars at different axial positions during forging was captured in real time by high-temperature strain testing. At the same time, the microstructure evolution characteristics of the deformation zone were obtained by in-situ micro-area analysis device. Multi-channel data fusion technology was used to integrate thermodynamic parameters, microstructure parameters and macroscopic dimensional parameters into a three-dimensional material performance characteristic matrix.

[0023] Step 2: Construction of Multi-Objective Optimization Model A collaborative optimization model is established, which includes process boundary constraints, microstructure prediction, and comprehensive performance evaluation. The process constraint module trains a dynamic threshold prediction network based on historical data, the microstructure module integrates dislocation density evolution and phase field simulation mechanisms, and the performance evaluation module sets four-dimensional optimization objectives: grain size, residual stress, dimensional accuracy, and energy consumption.

[0024] Step 3: Standardization of Material Characteristics The collected dynamic feature data is normalized to reduce dimensional differences, and standardized input parameters are generated through feature vector reconstruction technology to provide feature data of a uniform magnitude for process simulation.

[0025] Step 4: Simulation generation of reduction rate scheme Standardized features are input into the optimization model, and a sample point set is generated in the process parameter domain using a spatial sampling method. The mapping relationship between the reduction rate and material properties is constructed using a process response prediction model, and an initial set of optimization schemes is selected based on a non-dominated sorting algorithm.

[0026] Step 5: Multi-objective collaborative optimization A dynamic weight allocation algorithm is used to calculate the real-time weight coefficients of each optimization objective. A multi-objective utility function is established for comprehensive evaluation of the scheme. The optimal synergistic scheme of grain refinement, stress reduction, accuracy improvement and energy consumption control is determined through a balanced solution set search mechanism.

[0027] Step Six: Real-time Control of the Forging Process The optimal reduction ratio configuration scheme is executed by the control terminal of the forging equipment. The material performance parameters are continuously monitored during the forging process. When the deviation exceeds the set threshold, the dynamic reduction ratio compensation mechanism is immediately triggered to complete the parameter correction within milliseconds.

[0028] Step 7: Online Model Update A lightweight execution engine is deployed based on edge computing nodes. The optimization model is synchronized in real time through a high-speed industrial network. Combined with feedback from process experts' human decision-making, incremental learning technology is used to continuously update the model parameters, forming a closed-loop optimization system.

[0029] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0030] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing, characterized in that: The method includes the following steps: S1. Collect multi-dimensional material performance parameters of titanium alloy bars during radial forging process and generate dynamic feature dataset of forging materials; S2. Construct a multi-objective collaborative optimization model for radial forging reduction rate based on the dataset, including a forging process parameter constraint module, a material microstructure prediction module, and a comprehensive performance evaluation module; S3. Based on the dynamic feature dataset of the forging material, perform material performance parameter preprocessing to generate a standardized material feature vector; S4. Input the standardized material feature vector into the radial forging reduction rate multi-objective collaborative optimization model to perform forging process simulation calculation and generate an initial reduction rate optimization scheme set. S5. Adaptive weight allocation strategy is used to perform multi-objective collaborative optimization on the initial pressure reduction rate optimization scheme set to generate the optimal pressure reduction rate collaborative configuration scheme. S6. The optimal reduction rate collaborative configuration scheme is executed through the forging equipment control terminal to realize the collaborative optimization control of the reduction rate in the radial forging process of titanium alloy.

2. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The process of collecting the dynamic feature dataset of forging materials in S1 includes: S11. Dynamic recrystallization temperature gradient data of titanium alloy at different axial positions during forging is collected synchronously through high-temperature strain testing. S12. The microstructure evolution characteristics of the titanium alloy in the forging deformation zone were obtained using an in-situ micro-area composition analysis device, among which the dynamic recrystallization volume fraction satisfies the normalization equation: ； in, For dynamic recrystallization volume fraction, 0 1, To accumulate response for the present, Normalization The critical strain threshold is 0.15 for TC4 titanium alloy. For peak strain, the experimentally determined range is [0.25, 0.35]. This is the dynamic recrystallization rate coefficient, typically 1.

8. This is the dynamic recrystallization index, with a typical value of 2.0; S13. Multi-channel data fusion technology is used to integrate thermo-mechanical coupling parameters, including temperature and strain rate, microstructure parameters, including dynamic recrystallization volume fraction and dislocation density, and macroscopic dimensional parameters, including diameter and length changes, to construct a three-dimensional material performance characteristic matrix.

3. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The construction process of the forging process parameter constraint module in S2 includes: S21. Establish a boundary constraint rule library for radial forging process parameters; S22. Training a dynamic threshold prediction network for process parameters based on historical forging data; S23. An integrated temperature compensation algorithm corrects the drift error of thermodynamic parameters during the forging process.

4. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The method for constructing the material microstructure prediction module in S2 includes: S24. Develop a crystal plastic constitutive model based on dislocation density evolution; S25. Predicting dynamic recrystallization volume fraction using integrated phase-field simulation method; S26. Construct a method for predicting grain orientation distribution function; The method for constructing the comprehensive performance evaluation module in S2 includes: S27. Set quantitative evaluation functions for grain size control targets, residual stress control targets, dimensional accuracy targets, and energy consumption control targets; S28. Use fuzzy membership functions to unify the evaluation dimensions of various performance indicators; S29. Establish a dynamic allocation rule base for performance index weight coefficients.

5. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The process of generating the initial reduction rate optimization scheme set in S4 specifically includes: S41. Deploy a material response surface computation engine in the multi-objective collaborative optimization model of radial forging reduction rate; S42. The Latin hypercube sampling method is used to generate a spatial sample point set of forging process parameters. S43. Construct the mapping relationship between reduction rate and material properties using a Kriging proxy model; S44. Filter the initial optimization scheme set based on non-dominated sorting.

6. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The implementation process of the adaptive weight allocation strategy in S5 includes: S51. Construct a four-dimensional optimization objective function space, including the grain size control objective. Residual stress control target Dimensional accuracy target and energy consumption control targets ; S52. The real-time weight coefficients of each optimization objective are dynamically calculated using the entropy weight method. S53. Establishing a multi-objective collaborative optimization utility function based on fuzzy decision-making theory: ； in: ； in, This represents the overall utility value, with a range of [0,1]. For the i-th objective, dynamic weight, , For fuzzy membership functions, sigmoid functions, To normalize the target value, Let the i-th target be the historical minimum value, with the same dimensions. , The historical maximum value of the i-th target, with the same dimensions. ; S54. Determine the optimal solution set using the Pareto front search algorithm.

7. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The method further includes: S7. Monitor changes in material performance parameters in real time during the forging process and generate dynamic feedback data stream; S8. Update the parameters of the multi-objective collaborative optimization model for radial forging reduction rate based on online data-driven technology; S9. When the performance deviation exceeds the threshold, a real-time correction mechanism is triggered.

8. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 7, characterized in that: The triggering process of the real-time correction mechanism includes: S91. Establish a rapid response channel for sudden parameters in the forging process; S92. Employ a sliding time window algorithm to identify abnormal fluctuation patterns in material properties; S93. Generate a downtime compensation scheme through reinforcement learning strategies; S94. Deploy the new solution and verify the effect of the correction within 0.5 seconds.

9. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The method further includes: S10. Deploy a lightweight model execution engine on the edge computing node of the forging equipment; S11. The optimization module is decomposed using model segmentation technology; S12. Real-time synchronous updates of the optimization model are achieved through the 5G industrial private network.

10. The method for synergistic optimization of radial forging reduction rate of titanium alloys based on material testing according to claim 1, characterized in that: The method further includes: S13. Establish a human-machine collaborative optimization decision-making mechanism, including: S131. Display the 3D simulation results of the optimization scheme through a visual interface; S132, Receive manual correction instructions from process experts; S133. Employ federated learning technology to integrate human decision-making data to update and optimize the model; S134. Generate the final pressure rate execution plan with artificial intelligence identification.

Images