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

Abstract

The present application 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 acquires dynamic characteristic data of a forging process in real time through multi-dimensional material performance parameter collection, constructs a multi-objective collaborative optimization model, and realizes intelligent collaborative configuration of the reduction rate parameter by using an adaptive weight distribution strategy. A thermal coupling factor normalization equation and a phase field free energy functional normalization model are established to solve the technical problems of uneven structure and excessive residual stress caused by the empirical configuration of the reduction rate parameter in the traditional forging process. A lightweight model is deployed through an edge computing node, and millisecond-level dynamic correction of the optimization scheme is realized in combination with a 5G industrial private network, thereby improving the grain size qualification rate and size accuracy of titanium alloy forgings. The present application improves the grain size qualification rate of forgings, ensures stable control of the size accuracy while reducing the residual stress of forgings, and improves the batch stability of high-end titanium alloy components.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of metal plastic forming, in particular to a titanium alloy radial forging reduction rate cooperative optimization method based on material testing. BACKGROUND

[0002] Metal plastic forming is a processing method for material forming and shaping by utilizing the characteristics of irreversible plastic deformation of metal materials under external force, permanent deformation is retained by making the material stress exceed the elastic limit, the shape and size of the object are changed, and the organization and performance are optimized, the process includes forging, rolling, extrusion, drawing, stamping, etc., and is divided into three types of cold forming, warm forming and hot forming according to temperature, and the creep effect and material property change need to be considered.

[0003] The current mainstream process adopts a static reduction rate setting method based on an empirical formula, and the method has the following bottlenecks: the material dynamic recrystallization behavior is strongly coupled with the thermal parameters in the forging process, the traditional method cannot realize real-time sensing of the material microstructure evolution state, the reduction rate parameter is mismatched with the actual deformation demand of the material, grain coarsening and abnormal growth are caused, the parameter drift and equipment disturbance lack online compensation ability, when the actual deformation amount deviates from the theoretical value, the reduction rate configuration scheme cannot be dynamically corrected, and batch performance fluctuation is caused.

[0004] Therefore, the titanium alloy radial forging reduction rate cooperative optimization method based on material testing is proposed to solve the above problems. SUMMARY

[0005] In view of the defects of the prior art, the titanium alloy radial forging reduction rate cooperative optimization method based on material testing is provided, and the titanium alloy radial forging reduction rate cooperative optimization method based on material testing provided by the application solves the problems of grain coarsening and abnormal growth and batch performance fluctuation in the background technology.

[0006] To achieve the above purpose, the application provides the following technical scheme: the titanium alloy radial forging reduction rate cooperative optimization method based on material testing, the method comprises the following steps:

[0007] S1, collecting multi-dimensional material performance parameters of titanium alloy bar radial forging process, and generating a forging material dynamic feature data set;

[0008] S2, constructing a radial forging reduction rate multi-objective cooperative optimization model according to the data set, including a forging process parameter constraint module, a material microstructure prediction module and a comprehensive performance evaluation module, and the construction of the model comprises the following steps:

[0009] The forging process parameter constraint module is constructed: a radial forging process parameter boundary constraint rule library is established, a process parameter dynamic threshold prediction network is trained based on historical forging data, and a temperature compensation algorithm is integrated to correct thermal parameter drift error in the forging process;

[0010] The material microstructure prediction module is constructed: a crystal plasticity constitutive model based on dislocation density evolution is developed, and a phase field simulation method is integrated to predict the dynamic recrystallization volume fraction, and a dynamic recrystallization volume fraction prediction function is constructed;

[0011] The comprehensive performance evaluation module is constructed: a quantitative evaluation function containing grain size, residual stress and damage value is set, a fuzzy membership function is used for normalization processing, and a comprehensive performance index is calculated based on a dynamic allocation rule library;

[0012] S3, based on the dynamic characteristic data set of the forged material, material performance parameter preprocessing is carried out, and a standardized material feature vector is generated;

[0013] S4, the standardized material feature vector is input into the radial forging reduction rate multi-objective collaborative optimization model for forging process simulation calculation, and an initial reduction rate optimization scheme set is generated;

[0014] S5, the initial reduction rate optimization scheme set is optimized by using an adaptive weight allocation strategy, and an optimal reduction rate collaborative configuration scheme is generated;

[0015] S6, the optimal reduction rate collaborative configuration scheme is executed through a forging equipment control terminal, and the reduction rate collaborative optimization control of the titanium alloy radial forging process is realized.

[0016] Preferably, the process of collecting the dynamic characteristic data set of the forged material in S1 comprises:

[0017] S11, titanium alloy dynamic recrystallization temperature gradient data at different axial positions in the forging process are synchronously collected through high-temperature strain testing;

[0018] S12, titanium alloy microstructure evolution characteristic parameters of the forging deformation zone are obtained by using an in-situ micro-area composition analysis device, wherein the dynamic recrystallization volume fraction satisfies a normalization equation:

[0019] ;

[0020] Wherein, is the dynamic recrystallization volume fraction, 0 1, is the current cumulative strain, which is normalized, is the critical strain threshold value, TC4 titanium alloy takes 0.15, is the peak strain, the experimentally determined value range is [0.25, 0.35], is the dynamic recrystallization rate coefficient, a typical value is 1.8, is the dynamic recrystallization index, a typical value is 2.0;

[0021] S13, adopt multi-channel data fusion technology to integrate thermal 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 change amount, and construct a three-dimensional material performance characteristic matrix.

[0022] Preferably, the construction process of the forging process parameter constraint module in S2 includes:

[0023] S21, establish a radial forging process parameter boundary constraint rule base;

[0024] S22, train a process parameter dynamic threshold prediction network based on historical forging data;

[0025] S23, integrate a temperature compensation algorithm to correct thermal parameter drift error in the forging process.

[0026] Preferably, the construction method of the material microstructure prediction module in S2 includes:

[0027] S24, develop a crystal plasticity constitutive model based on dislocation density evolution;

[0028] S25, integrate a phase field simulation method to predict the dynamic recrystallization volume fraction;

[0029] S26, construct a grain orientation distribution function prediction method;

[0030] The construction method of the comprehensive performance evaluation module in S2 includes:

[0031] S27, set a quantitative evaluation function of the grain size control target, the residual stress control target, the size precision target, and the energy consumption control target;

[0032] S28, adopt a fuzzy membership function to unify the evaluation dimensions of various performance indicators;

[0033] S29, establish a performance index weight coefficient dynamic distribution rule base.

[0034] Preferably, the process of generating an initial reduction rate optimization scheme set in S4 specifically includes:

[0035] S41, deploy a material response surface calculation engine in the radial forging reduction rate multi-objective collaborative optimization model;

[0036] S42, adopt a Latin hypercube sampling method to generate a set of forging process parameter space sample points;

[0037] S43, constructing a mapping relationship between the reduction rate and the material performance through the Kriging surrogate model;

[0038] S44, screening the initial optimization scheme set based on the non-dominated sorting.

[0039] Preferably, the implementation process of the adaptive weight allocation strategy in S5 comprises:

[0040] S51, constructing a four-dimensional optimization objective function space, including a grain size control objective , a residual stress control objective , a dimensional accuracy objective , and an energy consumption control objective ;

[0041] S52, dynamically calculating real-time weight coefficients of each optimization objective by using the entropy weight method;

[0042] S53, establishing a multi-objective collaborative optimization utility function based on the fuzzy decision theory:

[0043] ;

[0044] Wherein:

[0045] ;

[0046] wherein, is the comprehensive utility value, the value range [0, 1], is the dynamic weight of the i-th objective, , is the fuzzy membership function, S-shaped function, is the normalized target value, is the historical minimum value of the i-th objective, with the same dimension as , is the historical maximum value of the i-th objective, with the same dimension as ;

[0047] S54, determining the optimal solution set by using the Pareto front search algorithm.

[0048] Preferably, the method further comprises:

[0049] S7, monitoring the change of the material performance parameter in real time during the forging process to generate a dynamic feedback data stream;

[0050] S8, updating the radial forging reduction rate multi-objective collaborative optimization model parameters based on online data-driven technology;

[0051] S9, triggering a real-time correction mechanism when the performance deviation exceeds a threshold value.

[0052] Preferably, the triggering process of the real-time correction mechanism comprises:

[0053] S91, a rapid response channel of forging process mutation parameters is established;

[0054] S92, a sliding time window algorithm is used to identify abnormal fluctuation patterns of material performance;

[0055] S93, a reduction compensation scheme is generated through reinforcement learning strategy;

[0056] S94, new scheme deployment is completed within 0.5 seconds and the correction effect is verified.

[0057] Preferably, the method further comprises:

[0058] S10, a lightweight model execution engine is deployed on the edge computing node of the forging equipment;

[0059] S11, the optimization module is decomposed by using model slicing technology;

[0060] S12, real-time synchronous updating of the optimization model is realized through 5G industrial private network.

[0061] Preferably, the method further comprises:

[0062] S13, a man-machine collaborative optimization decision mechanism is established, comprising:

[0063] S131, a three-dimensional simulation result of the optimization scheme is displayed through a visual interface;

[0064] S132, an artificial correction instruction of the process expert is received;

[0065] S133, the optimization model is updated by using federated learning technology to fuse artificial decision data;

[0066] S134, a final reduction execution scheme with artificial intelligence mark is generated.

[0067] Compared with the prior art, the present application provides a titanium alloy radial forging reduction collaborative optimization method based on material testing, which has the following beneficial effects:

[0068] 1. In the present application, by constructing a multi-dimensional material performance parameter real-time acquisition, the dynamic recrystallization temperature gradient and microstructure evolution characteristics are synchronously obtained in the titanium alloy radial forging process, and the thermal force coupling factor is normalized to realize the millisecond-level perception of the material deformation state. This technical means solves the problem that the traditional method cannot respond to the change of the material microstate in real time, inhibits the grain coarsening and abnormal growth phenomenon, and improves the pass rate of the grain size of the forgings.

[0069] 2. In the application, by establishing the reduction rate multi-objective collaborative optimization model, the weight coefficients of grain size control, residual stress reduction, size precision improvement and energy optimization are dynamically allocated by using the entropy weight method, and the optimal solution set is generated based on the Pareto frontier search, which solves the parameter oscillation defects caused by multi-objective conflict, and stabilizes the size precision within the tolerance range while reducing the residual stress of the forged piece.

[0070] 3. In the application, by deploying edge computing nodes to execute lightweight models, the real-time synchronization and dynamic correction of the optimization scheme are realized in combination with 5G industrial private networks. When the material performance deviation exceeds the threshold value, the millisecond-level reduction rate compensation mechanism is triggered based on the normalized comprehensive deviation, which breaks through the offline adjustment limitations of traditional forging processes, reduces energy consumption and material loss, and improves the batch stability of high-end titanium alloy parts. BRIEF DESCRIPTION OF DRAWINGS

[0071] Figure 1 The step flowchart of the titanium alloy radial forging reduction rate collaborative optimization method based on material testing of the application. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0073] Please refer to Figure 1 The specific implementation of the titanium alloy radial forging reduction rate collaborative optimization method based on material testing is as follows. The method comprises the following steps:

[0074] S1, collecting multi-dimensional material performance parameters of titanium alloy bar radial forging process, generating forging material dynamic characteristic data set;

[0075] S2, constructing a radial forging reduction rate multi-objective collaborative optimization model according to the data set, including a forging process parameter constraint module, a material microstructure prediction module and a comprehensive performance evaluation module. The construction of the model comprises the following steps:

[0076] Constructing the forging process parameter constraint module: establishing a radial forging process parameter boundary constraint rule library, training a process parameter dynamic threshold prediction network based on historical forging data, and integrating a temperature compensation algorithm to correct the thermal parameter drift error in the forging process;

[0077] Microstructure prediction module: a crystal plasticity constitutive model based on dislocation density evolution is developed, and a phase field simulation method is integrated to predict the dynamic recrystallization volume fraction, and a dynamic recrystallization volume fraction prediction function is constructed;

[0078] Performance evaluation module: a quantitative evaluation function containing grain size, residual stress and damage value is set, a fuzzy membership function is used for normalization processing, and a comprehensive performance index is calculated based on a dynamic allocation rule base;

[0079] S3, material performance parameter preprocessing based on dynamic characteristic data set of forging material, generating standardized material feature vector;

[0080] 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;

[0081] S5, using adaptive weight allocation strategy to perform multi-objective collaborative optimization on the initial reduction rate optimization scheme set, and generate an optimal reduction rate collaborative configuration scheme;

[0082] S6, execute the optimal reduction rate collaborative configuration scheme through the forging equipment control terminal, realize the reduction rate collaborative optimization control of the titanium alloy radial forging process;

[0083] S11, synchronously collect titanium alloy dynamic recrystallization temperature gradient data at different axial positions in the forging process through high temperature strain test;

[0084] S12, use in-situ micro-area composition analysis device to obtain titanium alloy microstructure evolution characteristic parameters in the deformation zone, wherein the dynamic recrystallization volume fraction satisfies the normalization equation:

[0085] ;

[0086] Wherein, is the dynamic recrystallization volume fraction, 0 1, is the current cumulative strain, normalized, is the critical strain threshold, TC4 titanium alloy takes 0.15, is the peak strain, the experimental value range is [0.25, 0.35], is the dynamic recrystallization rate coefficient, the typical value is 1.8, is the dynamic recrystallization index, the typical value is 2.0;

[0087] ​S13, adopt multi-channel data fusion technology to integrate thermal 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 change amount, and construct a three-dimensional material performance characteristic matrix;

[0088] S21, establish a radial forging process parameter boundary constraint rule library;

[0089] S22, train a process parameter dynamic threshold prediction network based on historical forging data, wherein the thermal coupling factor adopts a normalization equation:

[0090] ;

[0091] wherein, the thermal coupling factor is greater than 0.6 to trigger a warning, the real-time strain rate is in , the maximum allowable strain rate is normalized, the material melting point is in K, the current forging temperature is in K, ;

[0092] S23, integrate a temperature compensation algorithm to correct thermal parameter drift error in the forging process;

[0093] S24, develop a crystal plasticity constitutive model based on dislocation density evolution;

[0094] S25, integrate a phase field simulation method to predict the dynamic recrystallization volume fraction, and the normalized free energy functional thereof:

[0095] ;

[0096] wherein, the normalized free energy is the phase field order parameter is 0~1, the normalized energy density is the gradient energy coefficient is in J / m, the is in J / m, the reference free energy is in J / m³;

[0097] S26, construct a grain orientation distribution function prediction method;

[0098] S27, set a quantitative evaluation function of grain size control target, residual stress control target, size precision target and energy consumption control target;

[0099] S28, the evaluation dimension of each performance index is unified by using a fuzzy membership function, and the normalization calculation formula is:

[0100] ;

[0101] wherein, is the membership degree of the kth performance index, and less than 0.6 is a pre-warning, is the measured value of the performance index, is the target value of the performance index, and the dimension is the same as , is a tolerance parameter, and the dimension is the same as ;

[0102] S29, a performance index weight coefficient dynamic distribution rule library is established;

[0103] S41, a material response surface calculation engine is deployed in the radial forging reduction rate multi-objective collaborative optimization model;

[0104] S42, a Latin hypercube sampling method is used to generate a process parameter space sample point set, and the sampling process is as follows: first, each process parameter dimension is equally divided into N equal probability subintervals, and a sample point is randomly selected in each subinterval; and finally, uniform distribution and irrelevance of sample points in each dimension are achieved by random arrangement;

[0105] S43, a Kriging surrogate model is used to construct the mapping relationship between the reduction rate and the material performance, and the normalized covariance function is:

[0106] ;

[0107] wherein, is the normalized parameter , is the covariance between and is the dimensionless normalized value of the kth process parameter, is the process variance, and less than 0.1 is high precision, is the correlation coefficient of the kth parameter, and when >5 is strongly correlated, is the smoothness parameter of the kth parameter, and the default is 1.8, is the maximum value of the kth parameter, and the dimension is the same as ;

[0108] S44, the initial optimization scheme set is screened based on non-dominated sorting, and the screening rule is: the objective function values of each scheme are calculated, the schemes that are not dominated by any other scheme are classified into the first non-dominated layer according to the Pareto dominance relationship, the first layer scheme is removed, and the second non-dominated layer is continuously screened, and the iteration is continued until all layers are completed, and finally the first non-dominated layer scheme is selected as the optimization set;

[0109] S51, construct a four-dimensional optimization objective function space, including grain size control objectives , residual stress control objectives , dimensional accuracy objectives and energy consumption control objectives ;

[0110] S52, dynamically calculate the real-time weight coefficients of each optimization objective using the entropy weight method;

[0111] S53, establish a multi-objective collaborative optimization utility function based on fuzzy decision theory:

[0112] ;

[0113] Wherein:

[0114] ;

[0115] Wherein, is the comprehensive utility value, the value range is [0, 1], is the dynamic weight of the i-th objective, , is the fuzzy membership function, S-shaped function, is the normalized target value, is the historical minimum value of the i-th objective, with the same dimension as , is the historical maximum value of the i-th objective, with the same dimension as ;

[0116] S54, determine the optimal solution set by the Pareto front search algorithm, the execution process is: first identify the non-dominated solutions in the current scheme set which are not dominated by any other scheme to form the Pareto front, if the number of front schemes exceeds the set threshold, then use the crowding distance sorting algorithm to filter the most evenly distributed elite solution set;

[0117] S7, real-time monitoring of material performance parameter changes during forging, generating dynamic feedback data flow;

[0118] S8, update the radial forging reduction rate multi-objective collaborative optimization model parameters based on online data-driven technology;

[0119] S9, trigger the real-time correction mechanism when the performance deviation exceeds the threshold, wherein the normalized deviation amount is:

[0120] ;

[0121] Wherein, is the normalized comprehensive deviation, greater than 1.5 to trigger correction, is the k-th performance measured value, is the k-th performance predicted value, is a tolerance coefficient, dimensionless , is the number of monitoring parameters;

[0122] S91, establish a rapid response channel for forging process mutation parameters;

[0123] S92, identify material performance abnormal fluctuation patterns using sliding time window algorithm;

[0124] S93, generate a reduction compensation scheme through reinforcement learning strategy;

[0125] S94, complete new scheme deployment and verify the correction effect within 0.5 seconds;

[0126] S10, deploy a lightweight model execution engine on the edge computing node of the forging equipment;

[0127] S11, decompose the optimization module using model slicing technology, with normalized transmission efficiency:

[0128] ;

[0129] wherein, is the normalized transmission efficiency, is the maximum theoretical efficiency 1.0, is the 5G private network bandwidth, in Mbps, Mbps, is the synchronization time window, in s, s threshold, is the network reliability coefficient;

[0130] S12, realize real-time synchronization update of the optimization model through the 5G industrial private network;

[0131] S13, establish a human-machine collaborative optimization decision mechanism, including:

[0132] S131, display the three-dimensional simulation results of the optimization scheme through a visual interface;

[0133] S132, receive artificial correction instructions from process experts;

[0134] S133, update the optimization model by fusing artificial decision data using federated learning technology;

[0135] S134, generate the final reduction execution scheme with artificial intelligence identification.

[0136] The operation steps of the titanium alloy radial forging reduction collaborative optimization method based on material testing are as follows:

[0137] Step 1: Material dynamic characteristic acquisition

[0138] The temperature distribution data of titanium alloy bar at different axial positions during forging process is captured in real time by high temperature strain test, and the microstructure evolution characteristics of deformation zone are obtained by in-situ micro-area analysis device. Multi-channel data fusion technology is used to integrate thermal and mechanical parameters, organizational parameters and macro size parameters into three-dimensional material performance characteristic matrix.

[0139] Step two: multi-objective optimization model construction

[0140] A collaborative optimization model is established, which includes process boundary constraints, microstructure prediction and comprehensive performance evaluation. The process constraint module predicts the dynamic threshold value network according to the historical data, the microstructure module integrates the dislocation density evolution and phase field simulation mechanism, and the performance evaluation module sets four-dimensional optimization objectives of grain size, residual stress, size accuracy and energy consumption.

[0141] Step three: material characteristic standardization processing

[0142] The collected dynamic characteristic data is normalized to reduce the dimensional difference, and the standardized input parameters are generated by feature vector reconstruction technology to provide uniform order of magnitude characteristic data for process simulation.

[0143] Step four: reduction rate scheme simulation generation

[0144] The standardized characteristic input is optimized, and the sample point set is generated in the process parameter domain by using space sampling method. The mapping relationship between reduction rate and material performance is constructed by using process response prediction model, and the initial optimization scheme set is selected based on non-dominated sorting algorithm.

[0145] Step five: multi-objective collaborative optimization

[0146] The real-time weight coefficient of each optimization objective is calculated by using dynamic weight distribution algorithm, the multi-objective utility function is established for scheme comprehensive evaluation, and the optimal collaborative scheme of grain refinement, stress reduction, precision improvement and energy consumption control is determined by balance solution set search mechanism.

[0147] Step six: real-time control of forging process

[0148] The optimal reduction rate configuration scheme is executed through the forging equipment control terminal, and the material performance parameters are continuously monitored during the forging process. When the deviation exceeds the set threshold, the reduction rate dynamic compensation mechanism is triggered immediately, and the parameter correction is completed within milliseconds.

[0149] Step seven: model online update

[0150] A lightweight execution engine is deployed based on edge computing node, the real-time synchronization of optimization model is realized through high-speed industrial network, the model parameters are continuously updated by using incremental learning technology combined with artificial decision feedback of process experts, and a closed-loop optimization system is formed.

[0151] It has to be noted that, in the present document, the terms "first", "second", etc. merely serve to identify a subject or action from another subject or action, without necessarily requiring or implying any actual such relationship or order between such subjects or actions. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0152] While embodiments of the application have been shown and described, it is to be understood that the application is not limited to the details of the embodiments described, since numerous further modifications and changes can be apparent to one skilled in the art without departing from the spirit and scope of the application, which is defined by the claims and their equivalents.

Claims

1. A method for synergistic optimization of titanium alloy radial forging reduction ratio based on material testing, characterized in that: The method comprises the following steps: S1, collecting multi-dimensional material performance parameters of titanium alloy bar radial forging process to generate a dynamic characteristic data set of the forged material; S2, constructing a radial forging reduction rate multi-objective collaborative optimization model according to the data set, including a forging process parameter constraint module, a material microstructure prediction module and a comprehensive performance evaluation module, the construction of the model comprising the following steps: constructing the forging process parameter constraint module: establishing a radial forging process parameter boundary constraint rule base, training a process parameter dynamic threshold prediction network based on historical forging data, and integrating a temperature compensation algorithm to correct thermal parameter drift errors in the forging process; constructing the material microstructure prediction module: developing a crystal plasticity constitutive model based on dislocation density evolution, and integrating a phase field simulation method to predict the dynamic recrystallization volume fraction, and constructing a dynamic recrystallization volume fraction prediction function; constructing the comprehensive performance evaluation module: setting a quantitative evaluation function containing grain size, residual stress and damage value, normalizing by using a fuzzy membership function, and calculating a comprehensive performance index based on a dynamic allocation rule base; S3, preprocessing material performance parameters based on the dynamic characteristic data set of the forged material to generate a standardized material feature vector; S4, inputting the standardized material feature vector into the radial forging reduction rate multi-objective collaborative optimization model to perform forging process simulation calculation, and generating an initial reduction rate optimization scheme set; S5, using an adaptive weight allocation strategy to perform multi-objective collaborative optimization on the initial reduction rate optimization scheme set to generate an optimal reduction rate collaborative configuration scheme; S6, executing the optimal reduction rate collaborative configuration scheme through a forging equipment control terminal to realize reduction rate collaborative optimization control of the titanium alloy radial forging process.

2. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The process of collecting the dynamic characteristic data set of the forged material in S1 comprises: S11, synchronously collecting titanium alloy dynamic recrystallization temperature gradient data at different axial positions in the forging process through high-temperature strain testing; S12, obtaining titanium alloy microstructure evolution characteristic parameters of the forging deformation zone using an in-situ micro-area composition analysis device, wherein the dynamic recrystallization volume fraction satisfies a 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, using a multi-channel data fusion technology to integrate thermal and 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 change, and constructing a three-dimensional material performance characteristic matrix.

3. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The construction process of the forging process parameter constraint module in S2 comprises: S21, establishing a radial forging process parameter boundary constraint rule base; S22, training a process parameter dynamic threshold prediction network based on historical forging data; S23, integrating a temperature compensation algorithm to correct thermal parameter drift errors in the forging process.

4. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The construction method of the material microstructure prediction module in S2 comprises: S24, developing a crystal plasticity constitutive model based on dislocation density evolution; S25, integrating a phase field simulation method to predict the dynamic recrystallization volume fraction; S26, constructing a grain orientation distribution function prediction method; The construction method of the comprehensive performance evaluation module in S2 comprises: S27, set the grain size control target, residual stress control target, size accuracy target and energy consumption control target quantitative evaluation function; S28, adopt fuzzy membership function to unify the evaluation dimension of each performance index; S29, establish performance index weight coefficient dynamic allocation rule library.

5. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The S4 generates an initial reduction rate optimization scheme set process specifically includes: S41, deploy material response surface calculation engine in the radial forging reduction rate multi-objective collaborative optimization model; S42, generate a set of forging process parameter space sample points by using Latin hypercube sampling method; S43, construct the mapping relationship between reduction rate and material performance through Kriging surrogate model; S44, filter the initial optimization scheme set based on non-dominated sorting.

6. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The implementation process of the adaptive weight allocation strategy in S5 includes: S51, constructing a four-dimensional optimization objective function space, including a grain size control objective , a residual stress control objective , a dimensional accuracy objective , and an energy consumption control objective ; S52, dynamically calculate the real-time weight coefficient of each optimization objective by using entropy weight method; S53, establish multi-objective collaborative optimization utility function based on fuzzy decision theory: ； Wherein: ； wherein, is the comprehensive utility value, value range [0, 1], is the ith target dynamic weight, , is the fuzzy membership function, S-shaped function, is the normalized target value, is the ith target historical minimum value, dimension same as , is the ith target historical maximum value, dimension same as ; S54, determine the optimal solution set by using Pareto front search algorithm.

7. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The method further includes: S7, real-time monitoring of material performance parameter changes in the forging process to generate dynamic feedback data stream; S8, update the radial forging reduction rate multi-objective collaborative optimization model parameters based on online data-driven technology; S9, trigger real-time correction mechanism when performance deviation exceeds threshold value.

8. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 7, wherein: The triggering process of the real-time correction mechanism includes: S91, establish a rapid response channel for mutation parameters in the forging process; S92, use sliding time window algorithm to identify abnormal fluctuation mode of material performance; S93, generate reduction rate compensation scheme through reinforcement learning strategy; S94, complete new scheme deployment and verify the correction effect within 0.5 seconds.

9. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The method further includes: S10, deploy lightweight model execution engine on the edge computing node of the forging equipment; S11, decompose optimization module by using model slicing technology; S12, realize real-time synchronization update of optimization model through 5G industrial private network.

10. The material testing based titanium alloy radial forging reduction rate co-optimization method of claim 1, wherein: The method further includes: S13, establish human-machine collaborative optimization decision mechanism, including: S131, display three-dimensional simulation results of optimization scheme through visual interface; S132, receive artificial correction instructions of process experts; S133, update optimization model by using federated learning technology to fuse artificial decision data; S134, generate final reduction rate execution scheme with artificial intelligence mark.

Images