A turbine disk swaging process reasoning method and system

Abstract

The application discloses a turbine disc die forging process reasoning method and system, and the method comprises the following steps: (1) selecting key points of a turbine disc which need to be controlled in organization; (2) extracting deformation information of the key points through finite element simulation of the whole forging process of the turbine disc; (3) establishing a target optimization function, and respectively setting requirements for the average grain size and the recrystallization fraction of the key points, and setting corresponding weight values for the final organization targets of the key points; (4) setting boundary values and a penalty function of process parameters according to the actual situation of forging, and when the inferred process exceeds the boundary, the penalty function starts to execute; (5) embedding the target optimization function and the penalty function into a multi-objective optimization algorithm, and simultaneously inferring multiple forging process parameters. The method can achieve the effect of optimizing the grain organization of multiple regions of a forging, and effectively protects a die, thereby providing a theoretical basis and technical support for realizing high-quality forging.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of forging, and relates to a turbine disc die forging process reasoning method and system. BACKGROUND

[0002] The regional multi-performance of a modern aero-engine turbine disc means that different regions of the part correspond to different microstructure distributions, which puts forward higher requirements for the forming process. Therefore, in combination with the model proposed in the above research and the mature research results of scholars, an effective method is established to optimize the turbine disc die forging forming process parameters by using existing multi-objective optimization means, so that the microstructure evolution of multiple key regions is effectively controlled, the final forged piece obtains multiple performances, the reliability and service life of the part are improved, and the urgent quality and yield requirements of the engineering field can be met.

[0003] In view of the above difficulties, the application proposes a process reasoning method based on the target microstructure of the key region for the die forging process of the turbine disc, and builds a system for executing the method. The method establishes a target optimization function and a penalty function for describing the target of the microstructure according to the target organization requirement of the key region, and reasons the process parameters of the turbine disc die forging process based on a multi-objective optimization algorithm. Finally, the process parameters that can be adjusted according to the target microstructure of the key region are reasoned out. The invention and application of the method have important technical guiding significance for reasonably formulating the die forging process.

[0004] The patent specification with publication number CN118735067A discloses a turbine disc die forging quality prediction method based on feature fusion and integrated learning. This method can only predict the forging data of the turbine disc die forging quality performance parameters, and cannot reason out more suitable forging process parameters.

[0005] The patent specification with publication number CN118734701A discloses a turbine disc die forging process parameter optimization method based on multi-objective optimization problem modeling. This method lacks the whole process simulation and optimization penalty mechanism of forging, and cannot fully consider the problems that may occur in the forging process.

[0006] The patent specification with publication number CN108515132B discloses a hot die forging process of a nickel-based wrought superalloy double-performance turbine disc. This method only involves nickel-based wrought superalloy materials, and cannot meet the universality of the process. SUMMARY

[0007] The application aims to provide a die forging process trajectory planning method and system. The method can reasonably plan the process trajectory in the die forging forming process, achieve the effect of refining the grain structure of the forged piece, effectively improve the quality of the forged piece, solve the problem that the existing die forging forming process cannot meet the requirements of modern industrial production, and build a system for executing the method, facilitating the implementation of the method.

[0008] To achieve the above-mentioned purpose, the technical solution adopted by the application is:

[0009] 1. A die forging process reasoning method for a turbine disc, characterized in that the method comprises the following steps:

[0010] Step 1: analyzing and selecting key points of the turbine disc that need to be controlled in terms of structure;

[0011] Step 2: extracting deformation information of the key points through finite element simulation of the whole forging process of the turbine disc;

[0012] Step 3: establishing a target optimization function, setting requirements for the average grain size and recrystallization fraction of the key points respectively, and setting corresponding weights for the final structure targets of the key points;

[0013] The target optimization function established in step 3 can be adapted to the grain structure target requirements of each key point by changing the weights, so there are mainly two optimization targets for each key point: recrystallization fraction and average grain size target, and the target optimization function is represented by formula (1),

[0014] (1)

[0015] Wherein, f i is used to represent the degree of recrystallization of the i-th key area, s i is used to represent the average grain size of the i-th key area, f i and s i are the normalized standard values of the recrystallization fraction item and the average grain size item, without unit, m j is the penalty weight, c j is the function item to be punished;

[0016] Step 4: setting the boundary values and penalty function of the process parameters according to the actual situation of forging, when the inferred process exceeds the boundary, the penalty function starts to execute;

[0017] The penalty function described in step 4 will start to take effect when the optimized parameters exceed the upper and lower boundaries, it will make the value of the target optimization function larger and the fitness worse, so as to limit the optimization range within or near the feasible region; the upper boundary x u and the lower boundary x lThen, the specific form of the penalty function is defined, and its optimization process is shown in equation (2).

[0018] (2)

[0019] Where A(x) is the penalty function and m is the penalty factor. When the optimized parameter is inside the boundary, the penalty function has no effect; when the optimized parameter is outside the boundary, the penalty function will increase as the degree of exceeding the upper and lower limits of the boundary increases.

[0020] Step 5: Embed the objective optimization function and penalty function into a multi-objective optimization algorithm, and infer multiple forging process parameters simultaneously.

[0021] 2. A turbine disk forging process reasoning system, characterized in that it is used to implement the turbine disk forging process reasoning method of claim 1, comprising:

[0022] The receiving module is used to receive the input turbine disk position information and pass it to the subsequent processing stage to provide basic data for the entire system.

[0023] The target optimization and boundary setting module is used to establish the target optimization function and set the boundary values ​​and penalty functions of the process parameters according to the actual situation of the forging process.

[0024] The inference module is used to analyze the relationships between various process parameters and the parameters to be inferred, and to deduce the parameters to be inferred corresponding to the input process parameters using these relationships. These parameters to be inferred will be used in subsequent processing to achieve optimization and quality control.

[0025] 3. The turbine disk forging process inference system according to claim 2, characterized in that, in the receiving module, the following target data attributes are selected as data features used by the model:

[0026] (1) Turbine disk position information, including the specific position data of the turbine disk during the forging process, so as to facilitate the analysis of its stress and deformation;

[0027] (2) Simulation information, including the extraction of key point deformation information through finite element simulation of the entire turbine disk forging process.

[0028] 4. The turbine disk forging process reasoning system according to claim 2, characterized in that, in the target optimization and boundary setting module, the boundary values ​​of process parameters and the penalty function are set according to the actual forging situation, and the penalty function is executed when the reasoned process exceeds the boundary.

[0029] 5. The turbine disk die forging process reasoning system of claim 2, wherein the target optimization function and the penalty function are embedded into a multi-objective optimization algorithm in the reasoning module, and a plurality of forging process parameters are reasoned simultaneously. BRIEF DESCRIPTION OF DRAWINGS

[0030] Fig. 1 is a flow chart of a turbine disk die forging process reasoning method according to an embodiment of the present application;

[0031] Fig. 2 is a distribution of key points of a turbine disk according to an embodiment of the present application;

[0032] Fig. 3 is a strain-displacement relationship of a P1 point according to an embodiment of the present application;

[0033] Fig. 4 is a flow chart of a multi-objective optimization algorithm of a "TLBO" algorithm according to an embodiment of the present application;

[0034] Fig. 5 is a cloud chart of a recrystallization fraction and a grain size distribution: (a) a cloud chart of a recrystallization fraction of a control group; (b) an average grain size of the control group; (c) a cloud chart of a recrystallization fraction of an optimization group; and (d) a cloud chart of an average grain size of the optimization group according to an embodiment of the present application;

[0035] Figure 6 Fig. 6 is a final state temperature and an equivalent stress of a turbine disk forging according to an embodiment of the present application: (a) a cloud chart of a temperature distribution; and (b) a cloud chart of an equivalent stress distribution. DETAILED DESCRIPTION

[0036] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0037] The present application is a die forging process reasoning method and system, and the die forging process reasoning of a high-pressure turbine disk of an aircraft engine will be taken as an example to introduce the implementation details of the die forging process reasoning method and system in detail.

[0038] The method mainly includes the following steps:

[0039] Step 1: In actual use, the stress field of the turbine disk changes with time, but only a few areas will fail. Therefore, strict microstructure control is not required for all areas on the turbine disk. Some key points can be selected, and the microstructure corresponding to the performance of the key points is taken as a control target.

[0040] The rim and hub may undergo minor plastic deformation during each start-up and shutdown process. The key to fatigue failure lies in the accumulation of plastic deformation and crack propagation; therefore, key points P1 and P6 should be set for the rim and hub. The spokes of the turbine disk are the main body of the turbine disk. The area near the rim has a higher temperature, and due to the interaction of thermal stress and centrifugal force, fracture failure or yielding may occur. Therefore, key point P5 is set; in fact, point P5 also belongs to the rim area. Furthermore, stress concentration may occur at the connection between the spokes and the hub; therefore, key points P2 and P3 should also be set at the connection between the spokes and the upper and lower hubs. Key point P4 represents the general position of the spokes to ensure the overall uniformity of the forging. The distribution of key points is as follows: Figure 1 As shown.

[0041] Step 2: Process reasoning. First, it is necessary to establish a finite element model of the turbine disk forging and extract the deformation information of key points. Figure 2 The diagram shows the structure of a high-pressure turbine disk for a certain type of aero-engine. The base material of the turbine disk is GH4169 alloy. The initial parameter settings of the finite element model are shown in Table 1.

[0042] Table 1 Initial parameter settings for the finite element model

[0043]

[0044] During the forging process of turbine disk components, the strain rate at various points inside the forging is not constant under ideal conditions, but changes continuously with the specific shape changes of each region and the flow law of the metal. The time-varying strain rate makes the commonly used constant strain rate recrystallization kinetic model unsuitable for actual working conditions. The GH4169 kinetic model proposed by Chen can be used, which is applicable to this working condition, as shown in equation (1).

[0045] (1)

[0046] in, The recrystallization fraction, This is the fractional term for recrystallization. This is the critical strain for dynamic recrystallization. The strain is the strain when the recrystallization fraction reaches 50%. For deformation temperature ( ), Let be the strain rate. Based on the above formula, after obtaining the deformation history of the key points, the recrystallization fraction of each key point can be calculated.

[0047] For the recrystallization grain size model, the dynamic recrystallization grain size model proposed by Lin can be selected, which can well describe the change of grain size of the alloy during deformation, and its formula is as follows:

[0048] (2)

[0049] Where R is the ideal gas constant (8.31 J / mol·K), and Z is the Zener-Hollomon parameter. The above kinetics and average grain size model are also embedded in the DEFORM-2D finite element software by means of secondary development as the basic model of finite element simulation calculation.

[0050] Before process reasoning, a reference finite element simulation is carried out to simulate the isothermal die forging process of GH4169 alloy, and point tracking is carried out on six key point regions, and the strain rate-displacement and strain-displacement process relationship of each key point P1 to P6 is extracted, as shown in the strain-displacement relationship of P1 point. Figure 3 The reference condition set is that the die and blank deformation temperature is 980℃, and the pressing speed is 1mm / s. The final distribution of the simulated forgings will also be used as a comparison observation group for subsequent process optimization group.

[0051] Step 3: Establish the target optimization function, respectively for the average grain size and recrystallization fraction of the key points, and set the corresponding weight value for the final microstructure target of each key point;

[0052] In the current optimization problem of near isothermal die forging of turbine disc, the target is to meet the microstructure requirements corresponding to the service performance of each key point without damaging the die. Therefore, there are two optimization targets for each key point: recrystallization fraction and average grain size target.

[0053] Therefore, the 12 parallel optimization targets corresponding to the 6 key points can be represented by formula (3).

[0054] (3)

[0055] Where f i is used to represent the degree of recrystallization of the i-th key area, s i is used to represent the average grain size of the i-th key area, f i and s i are the normalized standard values of the recrystallization fraction and the average grain size, without unit, m j is the penalty weight, c j is the function item to be punished.

[0056] As mentioned above, the regions of the wheel core and the wheel hub must have good low cycle fatigue resistance. It has been found that fine grain size can improve the high temperature low cycle fatigue deformation behavior. Therefore, the microstructure of points P1, P5 and P6 must be strictly uniform and completely refined. Thus, the value of the weight coefficient should be relatively large. The main failure mode of points P2 and P3 is fracture caused by stress concentration. For most alloys, when the structure is not uniform, cracks are prone to occur. Therefore, the microstructure of points P2 and P3 must be uniform, whether it is coarse grain or fine grain. That is, the recrystallization volume fraction of P2 and P3 is the key criterion, and the grain size is not an absolute requirement. Therefore, according to the deformation conditions of P2 and P3, the value of w2 should be set to be large, and the sign of w3 is opposite to that of w2, to ensure that P2 and P3 achieve complete recrystallization or do not recrystallize. The values of r2 and r3 can be set to zero. As a general point, P4 is given general recrystallization fraction and grain size requirements, so w4 and r4 are not very large. The weights of the key points are shown in Table 2.

[0057] Table 2 Weight of fitness function of each key point

[0058]

[0059] Step 4: In the general product design or process design process, restrictions and penalty functions are often added to ensure that the results meet the practical application requirements. When the optimized parameters exceed the upper and lower limits of the boundary, the penalty function starts to take effect, which will make the value of the target optimization function larger and the fitness worse, so as to limit the optimization range within or near the feasible region. There are many forms of penalty functions, and different types of penalty functions can be set according to different problems. In this study, a fixed penalty factor penalty function form is used. First, the upper limit x u and the lower limit x l of the optimized parameter should be set, that is, ; then, the specific form of the penalty function is set, as shown in equation (4).

[0060] (4)

[0061] where A(x) is the penalty function, and m is the penalty factor. When the optimized parameter is within the boundary, the penalty function does not work; when the optimized parameter is not within the boundary range, the penalty function will increase with the increase of the degree of exceeding the upper and lower limits of the boundary.

[0062] For the isothermal forging process of the current GH4169 alloy turbine disc, the main safety problems are the safety and service life of the die. Therefore, the penalty function should be designed in terms of temperature and stress.

[0063] First, a penalty function for deformation heat generation is established. During turbine disk forging, a large amount of deformation heat is easily generated, resulting in different temperatures in different areas of the forging. This may eventually lead to a decrease in mold strength, or even overheating or mold damage. The deformation heat of GH4169 alloy is directly related to the flow stress. Therefore, the flow stress at key points at various moments during deformation is calculated first, and then the deformation heat generation under each strain is calculated. Finally, the total deformation heat is accumulated to obtain the final total deformation heat, as shown in equation (5).

[0064] (5)

[0065] When the deformation temperature of GH4169 alloy reaches above 1040℃, the recrystallized grains coarsen rapidly, and carbides may even form, causing overheating and damaging the die cavity surface. Therefore, the temperature should be limited to below 1040℃. High-temperature alloys are difficult-to-deform alloys. When the temperature is below 950℃, the dynamic recrystallization behavior of GH4169 alloy is extremely slow, and its plasticity is poor. This not only easily causes uneven deformation but also easily generates great rheological resistance, which will have an adverse effect on the normal use of the die and the normal operation of the forging equipment. Therefore, the minimum temperature should be set above 950℃. In summary, the penalty function considering the temperature rise is shown in equation (6).

[0066] (6)

[0067] Where c1 is the penalty function considering the effect of deformation heat on grain structure, m1 is the penalty factor, T' is the temperature after considering deformation heat, T is the original temperature, and ΔT is the temperature rise. The strain rate is... The value can be derived by differentiating the mapping relationship between the pressing displacement of the die forging press and the strain at various key points. The penalty factor is temporarily set to 1.

[0068] The yield strength of the mold material currently used is 700 MPa at 1050℃. Based on experience, at the same temperature, the yield strength of the mold material should be about three times that of the forging material. Therefore, the flow stress of the forged GH4169 alloy should be less than or equal to 220 MPa, and the penalty function is shown in equation (7).

[0069] (7)

[0070] Where c2 is the penalty function considering the influence of the deformation resistance of the forging material on the die performance, m2 is the penalty factor, and the rheological stress σ used is obtained through equation (5). The value of the penalty factor is set to 1.

[0071] Step 5: For the current optimization problem, the main optimization objects are the forging starting temperature and the forging downstroke speed, and the goal is to coordinate the control of the microstructure at each key point to obtain a multi-performance turbine disc part. The difficulty of this problem lies in the fact that the deformation process parameters or organizational goals of each control key point are not consistent. To coordinate the optimization of each key point goal, all goals need to be considered in parallel, making the constraints of the optimization process numerous and complex, increasing the difficulty of the optimization problem, and posing a great challenge to the fast and correct convergence of the optimization algorithm.

[0072] The "Teaching and Learning" multi-objective optimization algorithm (TLBO) is a relatively new optimization method with simple logic, fast convergence speed, and concise implementation code, and has been widely used in engineering and mathematical fields. For this optimization problem, the coupling relationship between the process parameters to be optimized and the target is relatively complex, and the "Teaching and Learning" algorithm can well adapt to the characteristics of this problem, quickly and accurately converging to the optimal result.

[0073] The "Teaching and Learning" algorithm simulates the scene of classroom learning in real life. For the current process optimization problem, the "students" are regarded as a population, and the process parameters to be optimized are regarded as "subjects". Through the target optimization function and the penalty function (equation (3)), the "grades" of the "students" are calculated. The individual with the best "grade" is called the "teacher", and the others are "students". The task of the "teacher" is to improve the average score of the "students" and gradually approach the level T of the "teacher", i.e. in the ith iteration, the "teacher" tries to let the average score M j of the "students" approach the "teacher's" score T i , so as to obtain the new average score M new of the "students", and the difference between the original average score and the new average score is recorded as Difference Mean i , as shown in equation (8).

[0074] (8)

[0075] where T F is the teaching constant, which determines the size of the average value; r i is a random constant in the ith iteration, ranging from 0 to 1, and the value of T F is set in the interval [1, 2]. They are heuristic process quantities, usually determined by equal probability distribution at each step of iteration.

[0076] (9)

[0077] According to Difference Mean iThe value of the optimization variable can be updated as shown in equation (10).

[0078] (10)

[0079] In addition to the "teacher" teaching, the "student" can also improve the performance by learning from each other in the population, which is another important feature of the TLBO algorithm. The "student" improves the performance in the population by random influence, if the performance of other "students" is better than him, he will learn from other students, otherwise, other students will learn from him, as shown in equation (11).

[0080] (11)

[0081] If the value of f (X new,i ) is greater than the value of f (X old,i ), accept this learning process; otherwise, let X new,i =X old,i . The flow of the TLBO algorithm is shown in Figure 4 . As can be seen from the figure, after 50 iterations, the algorithm result has approached to convergence, and the time is about 5 minutes. The optimized process feasible region is: the initial temperature range is 982℃~988℃, the pressing rate range is 0.240 mm / s~0.390 mm / s.

[0082] In order to carry out subsequent process verification, the initial temperature of the optimization group is 985℃, and the pressing rate is 0.315 mm / s. The optimized process parameters (985 , 0.315 mm / s) are introduced into the DEFORM 2D finite element simulation software for simulation verification, and compared with the control group (980 , 1 mm / s) to verify the reliability of the results, and the simulation results are shown in Figure 5 .

[0083] As shown in Figure 5As shown, overall, the turbine disk forgings using optimized process parameters exhibit a higher recrystallization fraction, smaller average grain size, and more uniform grain size distribution. At key points, the optimized group forgings achieve complete recrystallization at the wheel core, similar to the control group, but the optimized group has a larger area of ​​complete recrystallization, better meeting the requirements. At the wheel rim, the optimized group shows sufficient recrystallization across almost the entire rim, with sufficiently refined grains, while the control group only shows complete recrystallization in about half of the area, and the microstructure is in a mixed-grain state. At the two hub key points, the optimized group shows sufficient recrystallization in the lower hub area and partial recrystallization in the upper hub, but to a low degree, retaining relatively coarse grains. For general points, the optimized group's turbine disk also shows recrystallization from the outside in, refining the grains overall.

[0084] Table 3. Tissue distribution of key points in the optimized group and the control group.

[0085]

[0086] As shown in Table 3, the recrystallization volume fractions at points P1, P2, and P6 in the optimized group were 0.992, 0.975, and 0.982, respectively, all higher than those in the control group. Furthermore, the average grain size of points P1 and P6 in the optimized group was smaller than that in the control group, indicating that the low-cycle fatigue and machinability of these optimized forging regions were superior to those in the control group. For point P5, the recrystallization fraction in the control group was slightly higher than that in the optimized group. Recrystallization behavior at point P3 in both the optimized and control groups remained limited, but the recrystallization level in the optimized group P4 was significantly higher than that in the initial group. This means that a more thorough recrystallization process can occur in the general area of ​​the turbine disk, and the optimized machining parameters can satisfactorily meet the key requirements globally.

[0087] Figure 6 (a) shows the temperature distribution during the final forming stage of turbine disk forging. It can be seen that the temperature in most areas is below 1000°C, indicating that the optimized process parameters can effectively control the generation of deformation heat without excessive recrystallization grain growth. Figure 6 (b) shows the distribution of equivalent stress. For most forging processes, the effective stress is at a low level, with an average of 126 MPa. This indirectly reveals that the load between the die and the forging is relatively small, which is important for extending the die's service life. On the other hand, low effective stress means better forming performance under these forging conditions, which can improve filling capacity and ensure suitable material flow lines. Therefore, the inferred forging process parameters can ensure good billet plasticity and die safety during die forging.

[0088] Step 6: on the basis of all items in steps 1-5, a turbine disc die forging process reasoning system is proposed, which is used to execute the turbine disc die forging process reasoning method described above; comprising a receiving module, a target optimization and boundary setting module, and a reasoning module.

[0089] The receiving module is used to receive input turbine disc position information and pass it to subsequent processing links to provide basic data for the entire system.

[0090] The target optimization and boundary setting module is used to establish a target optimization function and set boundary values and penalty functions of process parameters according to the actual situation of the forging process.

[0091] The reasoning module is used to analyze the relationship between each process parameter and the to-be-reasoned parameter, and to deduce the to-be-reasoned parameter corresponding to the input process parameter using these relationships. These to-be-reasoned parameters will be used in subsequent processing, thereby achieving optimization and quality control.

Claims

1. A process reasoning method for turbine disk forging, characterized in that, The method includes the following steps: Step 1: Analyze and select the key points of the turbine disk that require organizational control; Step 2: Extract deformation information of key points through finite element simulation of the entire turbine disk forging process; Step 3: Establish the target optimization function, propose requirements for the average grain size and recrystallization fraction of the key points, and set corresponding weights for the final organizational target of each key point; The objective optimization function established in step 3 can be adapted to the grain structure target requirements of each key point by changing the weights. Therefore, there are two main optimization objectives for each key point: recrystallization fraction and average grain size target. The objective optimization function is expressed by equation (1). (1) Among them, f i The degree of recrystallization used to characterize the i-th critical region, s i f is used to characterize the average grain size of the i-th critical region. i With s i The normalized standard values ​​for the recrystallization fraction and average grain size terms are unitless, in meters. j For the penalty weight, c j For the penalized function term; Step 4: Set the boundary values ​​and penalty function of the process parameters according to the actual forging situation. When the inferred process exceeds the boundary, the penalty function will start to be executed. The penalty function described in step 4 will take effect when the optimization parameters exceed the upper and lower bounds. It will increase the value of the objective optimization function and decrease the fitness, thereby limiting the optimization range to or near the feasible region. The upper bound x of the optimized parameters is set. u and lower limit x l Then, the specific form of the penalty function is defined, and its optimization process is shown in equation (2). (2) Where A(x) is the penalty function and m is the penalty factor. When the optimized parameter is inside the boundary, the penalty function has no effect; when the optimized parameter is outside the boundary, the penalty function will increase as the degree of exceeding the upper and lower limits of the boundary increases. Step 5: Embed the objective optimization function and penalty function into a multi-objective optimization algorithm, and infer multiple forging process parameters simultaneously.

2. A turbine disk die forging process inference system, characterized in that, A method for reasoning about the process of a turbine disk forging as described in claim 1 includes: The receiving module is used to receive the input turbine disk position information and pass it to the subsequent processing stage to provide basic data for the entire system. The target optimization and boundary setting module is used to establish the target optimization function and set the boundary values ​​and penalty functions of the process parameters according to the actual situation of the forging process. The reasoning module is used to filter the results and analyze the relationship between each process parameter and the parameter to be reasoned. Using these relationships, the parameters to be reasoned corresponding to the input process parameters are derived. These parameters to be reasoned will be used in the subsequent processing to achieve optimization and quality control.

3. The turbine disk forging process inference system according to claim 2, characterized in that, In the receiving module, the following target data attributes are selected as data features used by the model: (1) Turbine disk position information, including the specific position data of the turbine disk during the forging process, so as to facilitate the analysis of its stress and deformation; (2) Simulation information, including the extraction of key point deformation information through finite element simulation of the entire turbine disk forging process.

4. The turbine disk forging process inference system according to claim 2, characterized in that, In the target optimization and boundary setting module, the boundary values ​​of process parameters and penalty functions are set according to the actual situation of forging. When the inferred process exceeds the boundary, the penalty function starts to be executed.

5. The turbine disk forging process inference system according to claim 2, characterized in that, The inference module embeds the objective optimization function and penalty function into a multi-objective optimization algorithm, and infers multiple forging process parameters simultaneously.

Images