Multi-index fused ring forging process parameter determination method, system and device

Abstract

This application provides a method, system, and equipment for determining process parameters of ring forgings based on multi-index fusion, applicable to the field of precision forging technology. It includes: determining multiple sets of first process parameters based on multiple die geometric parameters, multiple ring forging motion constraints, and multiple initial dimensions of the ring blank; simulating the ring forging process according to each set of first process parameters to obtain first forming indicators and first material performance indicators, then combining first and second weighting coefficients to determine a first comprehensive indicator as a first fitness; performing cross-validation and / or variation on the multiple sets of first process parameters to obtain multiple sets of second process parameters; when the rate of change between the maximum first fitness among the multiple first fitnesss and the maximum second fitness among the respective second fitnesss of the multiple sets of second process parameters is less than a preset rate of change threshold, the set of process parameters corresponding to the maximum value of the two maximum fitnesss is taken as the optimal process parameters. This method can quickly and accurately determine the optimal process parameters.

Description

Technical Field

[0001] This application relates to the field of precision forming technology for forgings, and in particular to a method, system and equipment for determining process parameters of ring forgings by integrating multiple indicators. Background Technology

[0002] High-temperature alloy ring forgings (hereinafter referred to as ring forgings) refer to ring forgings manufactured using high-temperature alloy materials through a ring rolling process. The ring rolling process is an incremental forming process with advantages such as good microstructure and high material utilization. It involves continuously and locally rolling a ring blank (hereinafter referred to as a ring blank) with rolls to reduce its wall thickness, increase its diameter, and shape its cross-sectional profile, ultimately obtaining a ring forging of the desired size and shape.

[0003] Traditional methods for determining ring forging process parameters heavily rely on operator experience and trial-and-error approaches, or numerical simulation techniques. The former suffers from poor process stability, long development cycles, high costs, and difficulty in precisely controlling microstructure, resulting in the inability to determine highly accurate ring forging process parameters. The latter, on the other hand, mostly focuses only on macroscopic forming quality, or typically performs isolated impact analyses on individual process parameters, also failing to determine highly accurate ring forging process parameters. Therefore, both of these methods, due to their inability to determine highly accurate ring forging process parameters, make it difficult to stably and efficiently produce high-end ring forgings that simultaneously meet the requirements of precise geometry and excellent microstructure properties.

[0004] Therefore, how to quickly and accurately determine the optimal process parameters for ring forgings in order to produce high-end ring forgings is a key technical problem that urgently needs to be solved in the current ring rolling process. Summary of the Invention

[0005] This application provides a method, system, and equipment for determining the process parameters of ring forgings by integrating multiple indicators. By combining simulation to obtain multi-indicator data (i.e., forming indicators and material performance quality), adopting a comprehensive evaluation system that integrates multiple indicators, and using an evolutionary algorithm for iterative optimization, it overcomes the limitations of traditional methods that rely on experience and isolated analysis. This enables the rapid and accurate determination of the optimal process parameters of ring forgings that simultaneously meet the requirements of precise geometry and excellent microstructure performance.

[0006] This application provides a method for determining process parameters of ring forgings by integrating multiple indicators, including:

[0007] S1. Based on the multiple die geometry parameters, multiple ring forging motion constraints and multiple ring blank initial dimensions corresponding to the ring forging, determine multiple sets of first process parameters. Each set of first process parameters includes a die geometry parameter, a ring forging motion constraint and a ring blank initial dimension.

[0008] S2. For each group of first process parameters, simulate the ring forging process according to the first process parameters to obtain the first forming index and the first material performance index of the ring forging; based on the first forming index, the first material performance index, and the first weight coefficient and the second weight coefficient corresponding to the first process parameters, determine the first comprehensive index of the first process parameters, and use it as the first fitness.

[0009] S3. Perform cross-validation and / or variation on the die geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank in the multiple sets of first process parameters to obtain multiple sets of second process parameters; and determine the maximum first fitness among the first fitness of each of the multiple sets of first process parameters, and the maximum second fitness among the second fitness of each of the multiple sets of second process parameters.

[0010] S4. If the rate of change between the maximum first fitness and the maximum second fitness is less than a preset rate of change threshold, the set of process parameters corresponding to the maximum value of the maximum first fitness and the maximum second fitness shall be taken as the optimal process parameters.

[0011] According to an embodiment of this application, a method for determining process parameters of a ring forging based on multi-index fusion is provided. The step of determining a first comprehensive index of the first process parameter based on the first forming index, the first material performance index, and the first weighting coefficient and second weighting coefficient corresponding to the first process parameter includes: using the entropy weight method to determine the first weighting coefficient corresponding to the first process parameter based on the forming fluctuation degree corresponding to multiple first forming indices; and using the entropy weight method to determine the second weighting coefficient corresponding to the first process parameter based on the material performance fluctuation degree corresponding to multiple first material performance indices; wherein the sum of the first weighting coefficient and the second weighting coefficient is 1; and for each group of first process parameters, a weighted sum is performed on the first forming index, the first weighting coefficient, the first material performance index, and the second weighting coefficient of the first process parameter to obtain the first comprehensive index of the first process parameter.

[0012] According to an embodiment of this application, a method for determining process parameters of ring forging based on multi-index fusion is provided. Each first forming index includes at least a first cross-sectional filling rate, a first equivalent strain distribution variance, a first maximum rolling force, and a first temperature distribution variance. The method employs entropy weighting to determine the first weighting coefficients corresponding to the first process parameters based on the forming fluctuation levels corresponding to the multiple first forming indices. This includes: standardizing the multiple first cross-sectional filling rates, multiple first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first temperature distribution variances to obtain multiple second cross-sectional filling rates, multiple second equivalent strain distribution variances, multiple second maximum rolling forces, and multiple second temperature distribution variances; and determining the first sum of the multiple second cross-sectional filling rates, the second sum of the multiple second equivalent strain distribution variances, the third sum of the multiple second maximum rolling forces, and the multiple second temperature distribution variances. The fourth sum of variances; the ratio of each second section filling rate among the plurality of second section filling rates to the first sum is taken as the first fluctuation degree of each second section filling rate; the ratio of each second equivalent variation distribution variance among the plurality of second equivalent variation distribution variances to the second sum is taken as the second fluctuation degree of each second equivalent variation distribution variance; the ratio of each second maximum rolling force among the plurality of second maximum rolling forces to the third sum is taken as the third fluctuation degree of each second maximum rolling force; and the ratio of each second temperature distribution variance among the plurality of second temperature distribution variances to the fourth sum is taken as the fourth fluctuation degree of each second temperature distribution variance; all first fluctuation degrees, all second fluctuation degrees, all third fluctuation degrees, and all fourth fluctuation degrees are taken as the forming fluctuation degree, and the first weighting coefficient is determined according to the forming fluctuation degree.

[0013] According to an embodiment of this application, a method for determining process parameters of ring forging based on multi-index fusion is provided. The step of taking all first fluctuation degrees, all second fluctuation degrees, all third fluctuation degrees, and all fourth fluctuation degrees as the forming fluctuation degree, and determining the first weighting coefficient based on the forming fluctuation degree, includes: determining a first information entropy based on all first fluctuation degrees; determining a second information entropy based on all second fluctuation degrees; determining a third information entropy based on all third fluctuation degrees; and determining a fourth information entropy based on all fourth fluctuation degrees; determining a first redundancy sum value of the first process parameter based on the first information redundancy corresponding to the first information entropy, the second information redundancy corresponding to the second information entropy, the third information redundancy corresponding to the third information entropy, and the fourth information redundancy corresponding to the fourth information entropy; and determining the first weighting coefficient based on the first information redundancy, the second information redundancy, the third information redundancy, the fourth information redundancy, and the first redundancy sum value.

[0014] According to an embodiment of this application, a method for determining process parameters of a ring forging based on multi-index fusion is provided. Each first material performance index includes at least a first target region proportion and a first grain size distribution variance. The first target region proportion is the proportion of regions where the dynamic recrystallization volume fraction exceeds a preset threshold. The method of using the entropy weight method to determine the second weight coefficients corresponding to the first process parameters based on the degree of material performance fluctuation corresponding to multiple first material performance indices includes: standardizing multiple first target region proportions and multiple first grain size distribution variances to obtain multiple second target region proportions and multiple second grain size distribution variances. The process involves determining a fifth sum of the proportions of the plurality of second target regions and a sixth sum of the variances of the plurality of second grain size distributions; using the ratio of each proportion of the plurality of second target regions to the fifth sum as the fifth degree of fluctuation of each proportion of the second target regions; using the ratio of each variance of the plurality of second grain size distributions to the sixth sum as the sixth degree of fluctuation of each variance of the second grain size distribution; using all fifth and sixth degree of fluctuation as the degree of fluctuation of the material properties; and determining the second weighting coefficient based on the degree of fluctuation of the material properties.

[0015] According to an embodiment of this application, a method for determining process parameters of ring forgings based on multi-index fusion is provided. The step of taking all fifth and sixth fluctuation degrees as the material property fluctuation degrees and determining the second weighting coefficient based on the material property fluctuation degrees includes: determining a fifth information entropy based on all fifth fluctuation degrees; determining a sixth information entropy based on all sixth fluctuation degrees; determining a second redundancy sum value of the first process parameter based on the fifth information redundancy corresponding to the fifth information entropy and the sixth information redundancy corresponding to the sixth information entropy; and determining the second weighting coefficient based on the fifth information redundancy, the sixth information redundancy, and the second redundancy sum value.

[0016] According to an embodiment of this application, a method for determining process parameters of ring forging based on multi-index fusion is provided. The method further includes: when the rate of change is greater than or equal to the preset rate of change threshold, taking a portion of the second process parameters from the plurality of second process parameters as the new plurality of first process parameters, and repeating the above steps S2-S3 until the rate of change between the last determined maximum fitness and the previously determined maximum fitness is less than the preset rate of change threshold, and taking a set of process parameters corresponding to the maximum value in each historical iteration as the optimal process parameters; wherein, the second fitness of each of the portion of the second process parameters is greater than the preset fitness threshold.

[0017] According to an embodiment of this application, a method for determining process parameters of a ring forging based on multi-index fusion is provided. The method further includes: simulating the ring forging process according to the second process parameters for each group of second process parameters to obtain a second forming index and a second material performance index of the ring forging; determining a second comprehensive index of the second process parameters based on the second forming index, the second material performance index, and the third and fourth weighting coefficients corresponding to the second process parameters, and using it as a second fitness.

[0018] This application also provides a multi-index fusion system for determining process parameters of ring forgings, including:

[0019] The process parameter determination module is used to determine multiple sets of first process parameters based on multiple die geometry parameters corresponding to the ring forging, multiple ring forging forming motion constraints, and multiple ring blank initial dimensions. Each set of first process parameters includes a die geometry parameter, a ring forging forming motion constraint, and a ring blank initial dimension.

[0020] The fitness determination module is used to simulate the ring forging process according to the first process parameters for each group of first process parameters to obtain the first forming index and the first material performance index of the ring forging; and to determine the first comprehensive index of the first process parameters based on the first forming index, the first material performance index, and the first weight coefficient and the second weight coefficient corresponding to the first process parameters, and use it as the first fitness.

[0021] The process parameter determination module is further configured to perform cross- and / or variation on the mold geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank in the plurality of first process parameters to obtain a plurality of second process parameters; and determine the maximum first fitness among the first fitness of each of the plurality of first process parameters, and the maximum second fitness among the second fitness of each of the plurality of second process parameters; if the rate of change between the maximum first fitness and the maximum second fitness is less than a preset rate of change threshold, the set of process parameters corresponding to the maximum value of the maximum first fitness and the maximum second fitness is taken as the optimal process parameters.

[0022] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for determining the process parameters of ring forging by multi-index fusion as described above.

[0023] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method for determining process parameters of ring forgings by multi-index fusion as described above.

[0024] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method for determining process parameters of ring forgings by multi-index fusion as described above.

[0025] The method, system, and equipment for determining process parameters of ring forgings by integrating multiple indicators provided in this application determine multiple sets of first process parameters based on multiple die geometric parameters, multiple ring forging forming motion constraints, and multiple initial dimensions of the ring blank. Each set of first process parameters includes one die geometric parameter, one ring forging forming motion constraint, and one initial dimension of the ring blank. For each set of first process parameters, the ring forging forming process is simulated according to the first process parameters to obtain the first forming index and the first material performance index of the ring forging. Based on the first forming index, the first material performance index, and the first weighting coefficient and the second weighting coefficient corresponding to the first process parameters, the method further determines multiple sets of first process parameters. The method uses a multiplication coefficient to determine the first comprehensive index of the first process parameter, which serves as the first fitness. It then performs cross-validation and / or variation on the die geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank among the multiple sets of first process parameters to obtain multiple sets of second process parameters. Finally, it determines the maximum first fitness among the first fitness of each set of first process parameters, and the maximum second fitness among the second fitness of each set of second process parameters. If the rate of change between the maximum first fitness and the maximum second fitness is less than a preset rate of change threshold, the set of process parameters corresponding to the maximum value of the maximum first fitness and the maximum second fitness is taken as the optimal process parameters. This method overcomes the limitations of traditional methods that rely on experience and isolated analysis by combining simulation to obtain multi-index data (i.e., forming index and material performance quality), employing a comprehensive evaluation system that integrates multiple indices, and using an evolutionary algorithm for iterative optimization. This enables the rapid and accurate determination of the optimal process parameters for ring forgings that simultaneously meet the requirements of precise geometry and excellent microstructure properties. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart illustrating the method for determining process parameters of ring forgings by integrating multiple indicators, as provided in the embodiments of this application.

[0028] Figure 2This is a schematic diagram of the core roller feed speed provided in an embodiment of this application;

[0029] Figure 3 This is a schematic diagram illustrating the implementation process of PID in the ABAQUS algorithm provided in the embodiments of this application.

[0030] Figure 4 This is a schematic diagram of the structure of the ring forging process parameter determination system with multi-index fusion provided in the embodiments of this application;

[0031] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] To better understand the embodiments of this application, the application scenarios of the method for determining process parameters of ring forgings by multi-index fusion provided in the embodiments of this application will be described in detail first:

[0034] The method for determining ring forging process parameters provides data support for efficient and precise ring rolling processes and is commonly used in high-end equipment manufacturing. Specifically, in the aerospace field, this method is used to determine the optimal process parameters for key load-bearing components such as engine casings and rocket shells to meet stringent requirements for high-performance materials. In the energy sector, this method is used to determine the optimal process parameters for typical ring forgings such as large wind turbine bearing rings and nuclear power pressure vessel support rings, resulting in ring forgings with excellent load-bearing and fatigue performance. Furthermore, this method is also widely used to determine the optimal process parameters for core basic components such as slewing bearings in heavy machinery, wheel hub bearings in rail transportation, and high-strength gear rings in automobiles. It should be noted that this method significantly improves material utilization, enhances the comprehensive mechanical properties of components, and enables the efficient forming of large rings, making it an indispensable advanced manufacturing method in modern industry.

[0035] It should be noted that the execution entity involved in the embodiments of this application can be a multi-index fusion ring forging process parameter determination system or an electronic device. Optionally, the electronic device may include: computer / laptop, mobile terminal, electronic assembly equipment and electrical production equipment, etc.

[0036] The following uses electronic devices as an example to illustrate in detail the method for determining process parameters of ring forgings based on the fusion of multiple indicators provided in this application:

[0037] Figure 1 This is a flowchart illustrating the method for determining process parameters of ring forgings based on the fusion of multiple indicators provided in this application. Figure 1 As shown, the method includes the following steps 101-104.

[0038] Step 101: Based on the multiple die geometry parameters corresponding to the ring forging, the multiple ring forging forming motion constraints, and the multiple ring blank initial dimensions, determine multiple sets of first process parameters. Each set of first process parameters includes a die geometry parameter, a ring forging forming motion constraint, and a ring blank initial dimension.

[0039] Among them, ring forgings refer to ring-shaped parts produced by ring rolling processes, which are obtained by plastic deformation of ring blanks and have specific / complex cross-sectional shapes (such as rectangular, L-shaped, grooved, irregular shapes, etc.) and precise dimensions. Optionally, the ring forgings may include at least bearing rings, gear rings, flange rings, aerospace engine casings, and wind turbine tower flanges. For example, the ring forgings are GH4169 high-temperature alloy ring forgings, TC4 high-temperature alloy ring forgings, etc.

[0040] Die geometry parameters refer to the design shape, size, or configuration parameters of dies (such as mandrels, drive rollers, axial rollers, etc.) that directly affect plastic deformation and material flow during the ring forging process. Optionally, each die geometry parameter may include at least the diameter and surface shape of the mandrel, the diameter and surface shape of the drive roller, etc.

[0041] The motion constraints in ring forging refer to the restrictions on the movement, speed, and displacement of the die (especially the mandrel and axial roller) relative to the ring blank during the ring forging process. These are key parameters for controlling the size and cross-sectional shape of the ring. Optionally, each ring forging motion constraint may include at least the following: mandrel feed speed (which may include at least... Figure 2 The schemes shown include uniform speed, uniform speed change, and uniform speed reduction, as well as the driving roller angular velocity and axial roller feed speed.

[0042] The initial dimensions of a ring blank refer to the geometric dimensions and state parameters of the original ring blank after blanking and pre-forging (such as upsetting and punching) before the ring forging process begins. Optionally, the initial dimensions of each ring blank may include at least: outer diameter, inner diameter, height, and ring blank preheating temperature.

[0043] Optionally, the electronic device determines multiple sets of first process parameters based on multiple die geometry parameters corresponding to the ring forging, multiple ring forging forming motion constraints, and multiple ring blank initial dimensions. This may include: the electronic device determining multiple sets of first process parameters using an orthogonal experimental method based on multiple die geometry parameters corresponding to the ring forging, multiple ring forging forming motion constraints, and multiple ring blank initial dimensions.

[0044] Among them, the orthogonal experimental design method is an efficient experimental design method based on mathematical statistics. Its core lies in using a standardized orthogonal array to scientifically arrange multi-factor and multi-level experiments, aiming to obtain reliable conclusions quickly with the fewest number of experiments, significantly improve experimental efficiency and reduce costs.

[0045] In this embodiment of the application, the electronic device selects the die geometry parameters corresponding to the ring forging, the ring forging forming motion constraints, and the initial size of the ring blank as three factors for orthogonal experimental design. For each factor, multiple test values ​​are prepared (i.e., the values ​​of multiple die geometry parameters, the values ​​of multiple ring forging forming motion constraints, and the values ​​of multiple initial sizes of the ring blank) as several levels corresponding to each factor in the orthogonal experiment. Based on the selected factors and the number of determined levels, a matching orthogonal table is selected. According to the arrangement of the orthogonal table, the different levels of each factor are filled into the corresponding columns. Each row of data in the orthogonal table constitutes a specific set of first process parameters to be tested.

[0046] The entire process utilizes a scientifically designed orthogonal array to select a small number of representative solutions (i.e., multiple sets of first process parameters) from the full factor combination that possess characteristics such as uniform dispersion and comparable uniformity. This allows for a systematic traversal of the entire process space composed of multiple factors, including mold geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank. It enables precise analysis of the primary and secondary effects and interactions of each factor, thereby locking in the optimal parameter range and determining a small number of representative solutions with maximum efficiency. This completely eliminates the inherent blindness and resource waste of traditional trial-and-error methods, and improves the efficiency of determining multiple sets of first process parameters.

[0047] Step 102: For each group of first process parameters, simulate the ring forging process according to the first process parameters to obtain the first forming index and the first material performance index of the ring forging; based on the first forming index, the first material performance index, and the first weight coefficient and the second weight coefficient corresponding to the first process parameters, determine the first comprehensive index of the first process parameters, and use it as the first fitness.

[0048] The ring forging process refers to the entire process in which the ring blank rotates under the drive of the drive roller, while the core roller feeds radially and the axial roller feeds axially, causing continuous plastic deformation of the ring blank, and finally obtaining a ring forging with specified dimensions and cross-sectional shape.

[0049] Forming indices, also known as macroscopic indices, characterize the performance and quality of macroscopic physical quantities such as geometry, load, and temperature of the ring forging when the ring forging process is simulated according to the first process parameters. Optionally, each first forming index may include at least the first cross-sectional filling rate, the first equivalent strain distribution variance, the first maximum rolling force, and the first temperature distribution variance.

[0050] Material performance indicators, also known as microscopic indicators, characterize the internal microstructure (such as recrystallization and grain size) and final mechanical properties of the ring forging when the ring forging process is simulated according to the first process parameters. Optionally, each first material performance indicator may include at least the proportion of a first target region (also known as the proportion of a dynamic recrystallization region) and the variance of a first grain size distribution, wherein the proportion of the first target region is the proportion of the region where the dynamic recrystallization volume fraction exceeds a preset threshold (such as 90%).

[0051] The first weighting coefficient is used to describe the importance of the forming index or the degree of optimization preference.

[0052] The second weighting coefficient is used to describe the importance of material performance indicators or the degree of optimization preference.

[0053] The first comprehensive index, also known as the first fitness, is used to describe the quality of a corresponding set of first process parameters.

[0054] For example, the first cross-sectional fill rate is a cross-sectional fill rate greater than 97.5%; the first equivalent strain distribution variance is an equivalent strain distribution variance less than 0.71; the first maximum rolling force is a rolling force less than the limit of the rolling equipment; the first temperature distribution variance is a temperature distribution variance less than 0.75; the first target region proportion is a region proportion greater than 80%; and the first grain size distribution variance is a grain size distribution variance less than 15.

[0055] It should be noted that the first weighting coefficient is determined based on the first molding index of each of the multiple sets of first process parameters, and the second weighting coefficient is determined based on the first material performance index of each of the multiple sets of first process parameters.

[0056] Optionally, the electronic device simulates the ring forging process according to the first process parameters to obtain the first forming index and the first material performance index of the ring forging. This can include: the electronic device establishing a three-dimensional thermo-mechanical-structural coupled finite element model of the ring forging in finite element software (such as ABAQUS or DEFORM-3D); the electronic device using the first process parameters as input to the finite element model, simulating the ring forging process through thermophysical simulation experiments to obtain the first forming index and the first material performance index of the ring forging.

[0057] The finite element model includes mold geometry parameters, ring forging motion constraints, initial ring blank dimensions and mesh generation, as well as boundary conditions such as interface friction, heat conduction, convection and radiation.

[0058] In this embodiment of the application, a high-precision three-dimensional thermo-mechanical-structural coupling finite element model can be used to simulate the entire process of ring forging with high precision, enabling electronic equipment to obtain the first forming index and the first material performance index comprehensively and accurately, thereby providing a reliable and detailed data foundation for subsequent process parameter optimization.

[0059] Optionally, the method may further include: during the simulation process, the electronic device monitors the outer diameter growth rate of the ring forging in real time; if the outer diameter growth rate is less than a preset speed threshold, a proportional-integral-derivative (PID) algorithm is used to increase the core roller feed speed and / or the main roller rotation speed; if the outer diameter growth rate is greater than or equal to the preset speed threshold, a PID algorithm is used to decrease the core roller feed speed and / or the main roller rotation speed.

[0060] The outer diameter growth rate refers to the amount by which the outer diameter of the ring forging increases per unit time.

[0061] The PID algorithm is the closed-loop control algorithm in the above finite element model.

[0062] For example, Figure 3 This is a schematic diagram illustrating the implementation flow of the PID in the ABAQUS algorithm provided in this application embodiment. Figure 3 In the middle, the execution structure is used to receive speed commands (i.e., v) from the PID controller. mandrel(t) The finite element model dynamically adjusts the mandrel feed speed and / or main roll rotation speed to change the rolling state; the physical system, used to simulate the physical process, is the aforementioned finite element model itself, which can calculate the state of the ring forging at the next moment based on the speed adjusted by the actuator, material properties, and thermal boundary conditions; the sensing mechanism is used to extract key data from the physical system, monitor and output the outer diameter growth rate of the ring forging (i.e., v) in real time. argw(t) This feedback is then sent to the PID controller, forming a closed loop.

[0063] In other words, from Figure 3 As can be seen from this, during the simulation process, the electronic equipment can use a sensing mechanism to monitor the outer diameter growth rate of the ring forging in real time, and compare this outer diameter growth rate with a preset speed threshold (i.e., v). rgv(t)The following comparisons are made: If the outer diameter growth rate is less than the preset speed threshold, it indicates that the current plastic deformation rate or rolling efficiency is too low, which may lead to a decrease in production efficiency or excessive cooling of the ring forging. In this case, a PID algorithm can be used, i.e., a PID controller can be used to increase the mandrel feed speed and / or the main roll rotation speed to accelerate the diameter expansion of the ring and ensure rolling efficiency within the process temperature window. If the outer diameter growth rate is greater than or equal to the preset speed threshold, it indicates that the current plastic deformation rate is too fast, which may lead to instability of the ring forging, a decrease in geometric accuracy, or internal structural defects. In this case, a PID algorithm can be used to reduce the mandrel feed speed and / or the main roll rotation speed to stabilize the rolling process of the ring forging and ensure the geometric accuracy and mechanical properties of the formed ring forging.

[0064] The entire process dynamically adjusts the mandrel feed speed and / or main roll rotation speed to ensure that the ring forging grows at an approximately constant speed, thereby effectively suppressing dynamic collisions between the ring forging and the rolls and improving the stability of the ring forging rolling process, that is, improving the stability of the ring forging forming process.

[0065] In some embodiments, the electronic device determines a first comprehensive index of the first process parameter based on a first molding index, a first material performance index, and a first weighting coefficient and a second weighting coefficient corresponding to the first process parameter. This may include: the electronic device using an entropy weight method to determine a first weighting coefficient corresponding to the first process parameter based on the molding fluctuation degree corresponding to multiple first molding indices; and using an entropy weight method to determine a second weighting coefficient corresponding to the first process parameter based on the material performance fluctuation degree corresponding to multiple first material performance indices; wherein the sum of the first weighting coefficient and the second weighting coefficient is 1; for each group of first process parameters, the electronic device performs a weighted summation of the first molding index, the first weighting coefficient, the first material performance index, and the second weighting coefficient of the first process parameter to obtain the first comprehensive index of the first process parameter.

[0066] Among them, the degree of molding fluctuation is used to describe the degree of variation, dispersion or information content of a specific molding index (such as the first cross-section filling rate) among multiple first molding indices.

[0067] The degree of material property fluctuation is used to describe the degree of variation, dispersion, or amount of information of a specific material property indicator (such as the proportion of the first target region) among multiple first material property indicators.

[0068] In this embodiment, the electronic device employs the entropy weight method. First, based on the molding fluctuation levels corresponding to multiple first molding indices, it determines the first weight coefficient corresponding to the first process parameter. Simultaneously, using the entropy weight method, it determines the second weight coefficient corresponding to the first process parameter based on the material performance fluctuation levels corresponding to multiple first material performance indices. This ensures that the weight allocation reflects the actual impact of each index on process optimization. Then, for each group of first process parameters, the electronic device determines the first product of the first molding index and the first weight coefficient, and the second product of the first material performance index and the second weight coefficient. The sum of the first and second products is then used as the first comprehensive index of the first process parameter. Based on this, the electronic device can determine the first comprehensive index for each group of first process parameters.

[0069] It should be noted that the first comprehensive index can successfully unify conflicting macroscopic objectives (such as low rolling force and high precision) and microscopic objectives (such as excellent recrystallization structure and fine grains) into a single numerical index. This allows it to automatically balance the requirements for shape accuracy (i.e., forming index) and internal quality (i.e. material performance index) during the ring forging process, providing data support for the subsequent selection of the optimal process parameters that balance high geometric pass rate and excellent mechanical properties.

[0070] In some embodiments, the electronic device employs the entropy weighting method to determine the first weighting coefficient corresponding to the first process parameter based on the degree of forming fluctuation corresponding to multiple first forming indicators. This may include: the electronic device standardizing multiple first cross-sectional filling rates, multiple first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first temperature distribution variances respectively to obtain multiple second cross-sectional filling rates, multiple second equivalent strain distribution variances, multiple second maximum rolling forces, and multiple second temperature distribution variances; the electronic device determines a first sum of multiple second cross-sectional filling rates, a second sum of multiple second equivalent strain distribution variances, a third sum of multiple second maximum rolling forces, and a fourth sum of multiple second temperature distribution variances; the electronic device then assigns a weighting coefficient to each of the multiple second cross-sectional filling rates. The ratio of the filling rate of each second section to the first sum is taken as the first degree of fluctuation of the filling rate of each second section; the ratio of the variance of each second equivalent variation distribution to the second sum in the multiple second equivalent variation distribution variances is taken as the second degree of fluctuation of the variance of each second equivalent variation distribution; the ratio of each second maximum rolling force to the third sum in the multiple second maximum rolling forces is taken as the third degree of fluctuation of the variance of each second maximum rolling force; and the ratio of each second temperature distribution variance to the fourth sum in the multiple second temperature distribution variances is taken as the fourth degree of fluctuation of the variance of each second temperature distribution; the electronic device takes all the first degree of fluctuation, all the second degree of fluctuation, all the third degree of fluctuation, and all the fourth degree of fluctuation as the forming fluctuation degree, and determines the first weighting coefficient according to the forming fluctuation degree.

[0071] In the embodiments of this application, in order to eliminate the differences in the dimensions and values ​​of different specific forming indicators during the process of determining the first weighting coefficient, the electronic device can first standardize the multiple first cross-sectional filling rates, multiple first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first temperature distribution variances respectively to obtain multiple second cross-sectional filling rates, multiple second equivalent strain distribution variances, multiple second maximum rolling forces, and multiple second temperature distribution variances. This can effectively ensure that all specific forming indicators are on a fair basis for comparison in subsequent calculations.

[0072] Then, the electronic device determines the first sum of multiple second cross-sectional filling rates, the second sum of multiple second equivalent strain distribution variances, the third sum of multiple second maximum rolling forces, and the fourth sum of multiple second temperature distribution variances. These four sums can provide data support and preparation for the information entropy calculation of the entropy weight method.

[0073] Next, the electronic device uses the ratio of each second cross-section filling rate to a first sum among multiple second cross-section filling rates as the first degree of fluctuation of each second cross-section filling rate. This first degree of fluctuation is used to describe the degree of variation, dispersion, or information content of the corresponding second cross-section filling rate, i.e., its relative contribution among all first process parameters. It also uses the ratio of each second equivalent variation distribution variance to a second sum among multiple second equivalent variation distribution variances as the second degree of fluctuation of each second equivalent variation distribution variance. This second degree of fluctuation is used to describe the degree of variation, dispersion, or information content of the corresponding second equivalent variation distribution variance. Furthermore, it uses the ratio of each second maximum rolling force to a third sum among multiple second maximum rolling forces as the third degree of fluctuation of each second maximum rolling force. This third degree of fluctuation is used to describe the degree of variation, dispersion, or information content of the corresponding second maximum rolling force. Finally, it uses the ratio of each second temperature distribution variance to a fourth sum among multiple second temperature distribution variances as the fourth degree of fluctuation of each second temperature distribution variance. This fourth degree of fluctuation is used to describe the degree of variation, dispersion, or information content of the corresponding second temperature distribution variance. The entire process provides a quantitative basis for identifying the amount of information and the degree of dispersion in the data.

[0074] Finally, the electronic device uses all first fluctuation levels, all second fluctuation levels, all third fluctuation levels, and all fourth fluctuation levels as forming fluctuation levels, and determines the first weighting coefficient based on the forming fluctuation levels. This ensures that the ring forging forming process focuses on the key forming indicators that have the greatest impact on the process.

[0075] It should be noted that the process of determining the first weight coefficient of the electronic device adopts the entropy weight method to standardize and quantify the macroscopic indicators in the ring forging process, ensuring that the key forming factors (i.e. key forming indicators) that have the greatest impact on the quality of the ring forging can be accurately identified and focused on in multi-objective optimization.

[0076] In some embodiments, the electronic device uses all first fluctuation levels, all second fluctuation levels, all third fluctuation levels, and all fourth fluctuation levels as molding fluctuation levels, and determines a first weighting coefficient based on the molding fluctuation levels. This may include: the electronic device determining a first information entropy based on all first fluctuation levels; determining a second information entropy based on all second fluctuation levels; determining a third information entropy based on all third fluctuation levels; and determining a fourth information entropy based on all fourth fluctuation levels; the electronic device determining a first redundancy sum value for a first process parameter based on the first information redundancy corresponding to the first information entropy, the second information redundancy corresponding to the second information entropy, the third information redundancy corresponding to the third information entropy, and the fourth information redundancy corresponding to the fourth information entropy; and the electronic device determining a first weighting coefficient based on the first information redundancy, the second information redundancy, the third information redundancy, the fourth information redundancy, and the first redundancy sum value.

[0077] In this embodiment of the application, during the process of determining the first weighting coefficient, the electronic device first determines the first information entropy based on all first fluctuation levels. The first information entropy is used to quantify the dispersion of information provided by the cross-sectional filling rate. The smaller the information entropy value, the greater the fluctuation of the cross-sectional filling rate and the more effective information it contains. Based on all second fluctuation levels, the second information entropy is determined. The second information entropy is used to quantify the dispersion of the variance of the equivalent effect distribution. Based on all third fluctuation levels, the third information entropy is determined. The third information entropy is used to quantify the dispersion of the maximum rolling force. Based on all fourth fluctuation levels, the fourth information entropy is determined. The fourth information entropy is used to quantify the dispersion of the variance of the temperature distribution.

[0078] Then, the electronic device calculates the information redundancy (also known as information validity) corresponding to each of the four information entropies. The larger the redundancy value, the greater the impact of the corresponding specific molding index on process optimization, and the higher its weight should be. At this point, the electronic device can determine the first information redundancy corresponding to the first information entropy, the second information redundancy corresponding to the second information entropy, the third information redundancy corresponding to the third information entropy, and the fourth information redundancy corresponding to the fourth information entropy. That is, it can finally determine the four information redundancies, and then determine the sum of these four information redundancies, which is used as the first redundancy sum to provide data support for subsequent calculations. Among the four information redundancies, the i-th information redundancy is the difference between 1 and the i-th information entropy.

[0079] Finally, the electronic device uses the ratio of the first information redundancy to the sum of the first redundancy values ​​as the first sub-weighting coefficient; the ratio of the second information redundancy to the sum of the second redundancy values ​​as the second sub-weighting coefficient; the ratio of the third information redundancy to the sum of the first redundancy values ​​as the third sub-weighting coefficient; and the ratio of the fourth information redundancy to the sum of the fourth redundancy values ​​as the fourth sub-weighting coefficient. This results in four sub-weighting coefficients, which are then used to construct the first weighting coefficient. Each ratio ensures that the weight allocation is proportional to the actual amount of information in the corresponding specific forming indicator, enabling the electronic device to accurately identify and focus on the key forming factors that have the greatest impact on the quality of the ring forging.

[0080] It should be noted that the entire process calculates the information entropy and information redundancy of macro indicators and allocates weights based on the redundancy ratio, thereby achieving objective weighting of macro indicators and ensuring that key forming factors that provide the most effective information can be accurately identified and focused on in multi-objective optimization.

[0081] In some embodiments, the electronic device employs the entropy weighting method to determine a second weighting coefficient corresponding to a first process parameter based on the degree of material performance fluctuation corresponding to multiple first material performance indicators. This may include: the electronic device standardizing multiple first target region proportions and multiple first grain size distribution variances to obtain multiple second target region proportions and multiple second grain size distribution variances; the electronic device determining a fifth sum of multiple second target region proportions and a sixth sum of multiple second grain size distribution variances; the electronic device using the ratio of each second target region proportion to the fifth sum as the fifth degree of fluctuation of each second target region proportion; and using the ratio of each second grain size distribution variance to the sixth sum as the sixth degree of fluctuation of each second grain size distribution variance; the electronic device using all fifth and sixth degree of fluctuation as the degree of material performance fluctuation, and determining the second weighting coefficient based on the degree of material performance fluctuation.

[0082] In the embodiments of this application, in order to eliminate the differences in the dimensions and values ​​of different specific material performance indicators during the process of determining the second weighting coefficient, the electronic device can first standardize the proportion of multiple first target regions and the variance of multiple first grain size distribution to obtain the proportion of multiple second target regions and the variance of multiple second grain size distribution. This can effectively ensure that all specific material performance indicators are on a fair basis for comparison in subsequent calculations.

[0083] Then, the electronic device determines a fifth sum of the proportions of multiple second target regions and a sixth sum of the variances of multiple second grain size distributions. These two sums can provide data support and preparation for the information entropy calculation of the entropy weight method.

[0084] Next, the electronic device uses the ratio of each second target region's proportion to a fifth sum as the fifth degree of fluctuation for each second target region's proportion. This fifth degree of fluctuation describes the degree of variation, dispersion, or information content of the corresponding second target region's proportion, i.e., its relative contribution among all first process parameters. It also uses the ratio of each second grain size distribution variance to a sixth sum as the sixth degree of fluctuation for each second grain size distribution variance. This sixth degree of fluctuation describes the degree of variation, dispersion, or information content of the corresponding second grain size distribution variance. This entire process provides a quantitative basis for identifying the information content and dispersion in the data.

[0085] Finally, the variance of the second grain size distribution of the electronic device ensures that the ring forging process focuses on the key material properties that have the greatest impact on the process.

[0086] It should be noted that the process of determining the second weight coefficient of the electronic device also adopts the entropy weight method to standardize and quantify the micro-indicators in the ring forging process, ensuring that the key material performance factors (i.e. key material performance indicators) that have the greatest impact on the quality of the ring forging can be accurately identified and focused on in multi-objective optimization.

[0087] In some embodiments, the electronic device treats all fifth and sixth fluctuation levels as material performance fluctuation levels and determines a second weighting coefficient based on the material performance fluctuation levels. This may include: the electronic device determining a fifth information entropy based on all fifth fluctuation levels; the electronic device determining a sixth information entropy based on all sixth fluctuation levels; the electronic device determining a second redundancy sum value for the first process parameter based on the fifth information redundancy corresponding to the fifth information entropy and the sixth information redundancy corresponding to the sixth information entropy; and the electronic device determining a second weighting coefficient based on the fifth information redundancy, the sixth information redundancy, and the second redundancy sum value.

[0088] In the embodiments of this application, during the process of determining the second weighting coefficient, the electronic device first determines the fifth information entropy based on all the fifth fluctuation degrees. The fifth information entropy is used to quantify the dispersion of information provided by the target area proportion. The smaller the information entropy value, the greater the fluctuation of the target area proportion and the more effective information it contains. Then, based on all the sixth fluctuation degrees, the sixth information entropy is determined. The sixth information entropy is used to quantify the dispersion of the variance of the grain size distribution.

[0089] Then, the electronic device calculates the information redundancy corresponding to each of the two information entropies. The larger the redundancy value, the greater the impact of the corresponding specific material performance indicators on process optimization, and the higher its weight should be. At this point, the electronic device can determine the fifth information redundancy corresponding to the fifth information entropy and the sixth information redundancy corresponding to the sixth information entropy, that is, it can finally determine two information redundancies, and then determine the sum of these two information redundancies, which is used as the second redundancy sum to provide data support for subsequent calculations. Among the two information redundancies, the j-th information redundancy is the difference between 1 and the j-th information entropy.

[0090] Finally, the electronic device uses the ratio of the fifth information redundancy to the sum of the second and third redundancy values ​​as the fifth sub-weighting coefficient, and the ratio of the sixth information redundancy to the sum of the second and third redundancy values ​​as the sixth sub-weighting coefficient. This determines two sub-weighting coefficients, which are then used to construct the second weighting coefficient. Each ratio ensures that the weight allocation is proportional to the actual amount of information in the corresponding specific material performance index, enabling the electronic device to accurately identify and focus on the key material performance factors that have the greatest impact on the quality of the ring forging.

[0091] It should be noted that the entire process calculates the information entropy and information redundancy of micro-indicators and allocates weights based on the redundancy ratio, thereby achieving objective weighting of micro-indicators. This ensures that in multi-objective optimization, the key material performance factors that provide the most effective information can be accurately identified and given priority.

[0092] Step 103: Perform cross-validation and / or variation on the die geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank in the multiple sets of first process parameters to obtain multiple sets of second process parameters; and determine the maximum first fitness in the first fitness of each of the multiple sets of first process parameters, and the maximum second fitness in the second fitness of each of the multiple sets of second process parameters.

[0093] In step 103, the die geometry parameters, the ring forging motion constraints, and the initial dimensions of the ring blank together constitute the design variables for process optimization. To find the optimal solution, the electronic equipment needs to operate on the current parameter combination to generate a new, better combination.

[0094] Specifically, if cross-operation is performed, some parameters in two or more sets of first process parameters can be exchanged or combined. For example, the core roller feed speed of first process parameter A can be combined with the ring preheating temperature of first process parameter B to generate a new set of first process parameters, namely a set of second process parameters.

[0095] If a mutation operation is performed, one or more values ​​of a set of first process parameters are randomly changed. For example, the angular velocity of the drive roller in the first process parameter C is randomly adjusted to a new value within a certain range to generate a set of second process parameters.

[0096] By combining cross-validation (utilizing known good information) and variation (exploring unknown information), the electronic device can systematically generate multiple sets of second process parameters with diversity and improvement potential, thereby continuously driving the process optimization process.

[0097] Then, the electronic device determines the maximum first fitness from the first fitness of each of the multiple sets of first process parameters, and determines the maximum second fitness from the second fitness of each of the multiple sets of second process parameters, providing key data support for subsequent optimization algorithm iteration and convergence judgment.

[0098] In some embodiments, after the electronic device obtains multiple sets of second process parameters, the method may further include: for each set of second process parameters, the electronic device simulates the ring forging process according to the second process parameters to obtain the second forming index and the second material performance index of the ring forging; based on the second forming index, the second material performance index, and the third and fourth weighting coefficients corresponding to the second process parameters, a second comprehensive index of the second process parameters is determined and used as the second fitness.

[0099] The third weighting coefficient is used to describe the importance of the forming index or the degree of optimization preference.

[0100] The fourth weighting coefficient is used to describe the importance of material performance indicators or the degree of optimization preference.

[0101] The second comprehensive index, also known as the second fitness, is used to describe the quality of a corresponding set of second process parameters.

[0102] Optionally, each of the second forming parameters may include at least the third cross-sectional filling rate, the third equivalent strain distribution variance, the third maximum rolling force, and the third temperature distribution variance.

[0103] Optionally, each of the second material performance indicators may include at least the proportion of the third target region and the variance of the third grain size distribution, wherein the proportion of the third target region is the proportion of the region where the dynamic recrystallization volume fraction exceeds a preset fraction threshold (e.g., 90%).

[0104] It should be noted that the third weighting coefficient is determined based on the second forming index of each of the multiple sets of second process parameters, and the fourth weighting coefficient is determined based on the second material performance index of each of the multiple sets of second process parameters.

[0105] Furthermore, the process of determining the third weighting coefficient is similar to that of determining the first weighting coefficient, the process of determining the fourth weighting coefficient is similar to that of determining the second weighting coefficient, and the process of determining the second comprehensive index is similar to that of determining the first comprehensive index. These will not be elaborated upon here.

[0106] Step 104: If the rate of change between the maximum first fitness and the maximum second fitness is less than a preset rate of change threshold, take the set of process parameters corresponding to the maximum value between the maximum first fitness and the maximum second fitness as the optimal process parameters.

[0107] The rate of change refers to the relative change between two consecutive optimal fitness values, used to measure the convergence speed and stability of the optimization algorithm. This rate of change is typically the absolute value of the ratio of the difference between the maximum second fitness and the maximum first fitness to the maximum first fitness.

[0108] In step 104, by quantifying the fitness change rate of two adjacent optimal solutions and comparing it with a preset change rate threshold, an objective and efficient stopping criterion is provided for the optimization algorithm, thereby avoiding redundant calculations and ensuring that the final output process parameters are the solution with the best performance after convergence, that is, ensuring that the final output process parameters are the optimal process parameters.

[0109] In some embodiments, after step 104, the method may further include: when the rate of change is greater than or equal to a preset rate of change threshold, the electronic device takes a portion of the second process parameters from the multiple sets of second process parameters as new multiple sets of first process parameters, and repeats the above steps 102-103 until the rate of change between the last determined maximum fitness and the previously determined maximum fitness is less than the preset rate of change threshold, and takes the set of process parameters corresponding to the maximum value in each historical iteration as the optimal process parameters.

[0110] Among them, the second fitness of some of the second process parameters is greater than the preset fitness threshold.

[0111] In this embodiment, when the rate of change is greater than or equal to a preset rate of change threshold, it indicates that the optimization has not yet converged and a next generation, i.e., the next iteration of optimization, is required. At this time, the electronic device can determine the relationship between the second fitness of each of the multiple sets of second process parameters and the preset rate of change threshold, and take the second process parameters corresponding to the second fitness greater than the preset fitness threshold as new multiple sets of first process parameters, and enter the next round of iteration simulation and optimization to achieve the purpose of retaining excellent individuals and accelerating convergence. That is, the above steps 102-103 are repeated until the rate of change between the last determined maximum fitness and the previous determined maximum fitness is less than the preset rate of change threshold. At this time, the optimization convergence is satisfied, and the electronic device then obtains the maximum fitness determined in each historical iteration, and takes the set of process parameters corresponding to the maximum value among all maximum fitness as the optimal process parameters. The whole process reflects the characteristics of global optimization, ensures convergence through iteration, and ensures the stability of the optimal solution by retaining the historical maximum fitness, realizing the rapid and objective determination of the optimal process parameters of the ring forging, thereby significantly improving product quality and production efficiency.

[0112] In the embodiments of this application, the technical solutions described in steps 101-104 above overcome the limitations of traditional methods that rely on experience and isolated analysis by combining simulation to obtain multi-index data, adopting a comprehensive evaluation system that integrates multiple indices, and using evolutionary algorithms for iterative optimization. This enables the rapid and accurate determination of the optimal process parameters for ring forgings that simultaneously meet the requirements of precise geometric shape and excellent microstructure performance.

[0113] The following describes the multi-index fusion ring forging process parameter determination system provided in the embodiments of this application. The multi-index fusion ring forging process parameter determination system described below and the multi-index fusion ring forging process parameter determination method described above can be referred to in correspondence.

[0114] Figure 4 This is a schematic diagram of the system for determining process parameters of ring forgings by fusing multiple indicators, as provided in an embodiment of this application. Figure 4 As shown, the system includes: a process parameter determination module 401 and a fitness determination module 402.

[0115] The process parameter determination module 401 is used to determine multiple sets of first process parameters based on multiple die geometry parameters corresponding to the ring forging, multiple ring forging forming motion constraints, and multiple ring blank initial dimensions. Each set of first process parameters includes a die geometry parameter, a ring forging forming motion constraint, and a ring blank initial dimension.

[0116] The fitness determination module 402 is used to simulate the ring forging process according to the first process parameters for each group of first process parameters to obtain the first forming index and the first material performance index of the ring forging; and to determine the first comprehensive index of the first process parameter based on the first forming index, the first material performance index, and the first weight coefficient and the second weight coefficient corresponding to the first process parameter, and use it as the first fitness.

[0117] The process parameter determination module 401 is further configured to perform cross- and / or variation of the mold geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank in the multiple sets of first process parameters to obtain multiple sets of second process parameters; and determine the maximum first fitness among the first fitness of each of the multiple sets of first process parameters, and the maximum second fitness among the second fitness of each of the multiple sets of second process parameters; if the rate of change between the maximum first fitness and the maximum second fitness is less than a preset rate of change threshold, the set of process parameters corresponding to the maximum value of the maximum first fitness and the maximum second fitness is taken as the optimal process parameters.

[0118] Optionally, the fitness determination module 402 is specifically used to determine the first weight coefficient corresponding to the first process parameter based on the molding fluctuation degree corresponding to multiple first molding indices using the entropy weight method; and to determine the second weight coefficient corresponding to the first process parameter based on the material performance fluctuation degree corresponding to multiple first material performance indices using the entropy weight method; wherein the sum of the first weight coefficient and the second weight coefficient is 1; for each group of first process parameters, the first molding index, the first weight coefficient, the first material performance index, and the second weight coefficient of the first process parameter are weighted and summed to obtain the first comprehensive index of the first process parameter.

[0119] Optionally, each first forming index includes at least a first cross-section filling rate, a first equivalent strain distribution variance, a first maximum rolling force, and a first temperature distribution variance; the fitness determination module 402 is specifically used to standardize the multiple first cross-section filling rates, multiple first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first temperature distribution variances respectively to obtain multiple second cross-section filling rates, multiple second equivalent strain distribution variances, multiple second maximum rolling forces, and multiple second temperature distribution variances; determine the first sum of the multiple second cross-section filling rates, the second sum of the multiple second equivalent strain distribution variances, the third sum of the multiple second maximum rolling forces, and the fourth sum of the multiple second temperature distribution variances; and determine the first sum of the multiple second cross-section filling rates, the second sum of the multiple second equivalent strain distribution variances, the third sum of the multiple second maximum rolling forces, and the fourth sum of the multiple second temperature distribution variances; and determine the first sum of the multiple second cross-section filling rates, the second cross-section filling rate, and the second temperature distribution variance. The ratio of the filling rate to the first sum is taken as the first fluctuation degree of the filling rate of each second section; the ratio of the variance of each second equivalent variation distribution to the second sum is taken as the second fluctuation degree of the variance of each second equivalent variation distribution; the ratio of the variance of each second maximum rolling force to the third sum is taken as the third fluctuation degree of the variance of each second maximum rolling force; the ratio of the variance of each second temperature distribution to the fourth sum is taken as the fourth fluctuation degree of the variance of each second temperature distribution; all the first fluctuation degree, all the second fluctuation degree, all the third fluctuation degree, and all the fourth fluctuation degree are taken as the forming fluctuation degree, and the first weighting coefficient is determined according to the forming fluctuation degree.

[0120] Optionally, the fitness determination module 402 is specifically used to determine a first information entropy based on all the first fluctuation degrees; determine a second information entropy based on all the second fluctuation degrees; determine a third information entropy based on all the third fluctuation degrees; and determine a fourth information entropy based on all the fourth fluctuation degrees; determine a first redundancy value of the first process parameter based on the first information redundancy corresponding to the first information entropy, the second information redundancy corresponding to the second information entropy, the third information redundancy corresponding to the third information entropy, and the fourth information redundancy corresponding to the fourth information entropy; and determine a first weighting coefficient based on the first information redundancy, the second information redundancy, the third information redundancy, the fourth information redundancy, and the first redundancy value.

[0121] Optionally, each first material performance index includes at least a first target region proportion and a first grain size distribution variance, wherein the first target region proportion is the region proportion whose dynamic recrystallization volume fraction exceeds a preset threshold; the fitness determination module 402 is specifically used to standardize the multiple first target region proportions and multiple first grain size distribution variances respectively to obtain multiple second target region proportions and multiple second grain size distribution variances; determine the fifth sum of the multiple second target region proportions and the sixth sum of the multiple second grain size distribution variances; use the ratio of each second target region proportion to the fifth sum as the fifth fluctuation degree of each second target region proportion; use the ratio of each second grain size distribution variance to the sixth sum as the sixth fluctuation degree of each second grain size distribution variance; use all fifth fluctuation degrees and all sixth fluctuation degrees as the material performance fluctuation degree, and determine the second weighting coefficient based on the material performance fluctuation degree.

[0122] Optionally, the fitness determination module 402 is specifically used to determine the fifth information entropy based on all the fifth fluctuation degrees; determine the sixth information entropy based on all the sixth fluctuation degrees; determine the second redundancy sum value of the first process parameter based on the fifth information redundancy corresponding to the fifth information entropy and the sixth information redundancy corresponding to the sixth information entropy; and determine the second weighting coefficient based on the fifth information redundancy, the sixth information redundancy and the second redundancy sum value.

[0123] Optionally, the process parameter determination module 401 is further configured to, when the rate of change is greater than or equal to the preset rate of change threshold, take a portion of the second process parameters from the plurality of second process parameters as the new plurality of first process parameters, and repeat the above steps S2-S3 until the rate of change between the last determined maximum fitness and the previously determined maximum fitness is less than the preset rate of change threshold, and take the set of process parameters corresponding to the maximum value in each historical iteration as the optimal process parameters; wherein, the second fitness of each of the portion of second process parameters is greater than the preset fitness threshold.

[0124] Optionally, the process parameter determination module 401 is further configured to simulate the ring forging process according to the second process parameters for each group of second process parameters, and obtain the second forming index and the second material performance index of the ring forging; and determine the second comprehensive index of the second process parameters based on the second forming index, the second material performance index, and the third and fourth weighting coefficients corresponding to the second process parameters, and use it as the second fitness.

[0125] Figure 5 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 5As shown, the electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540. The processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions from the memory 530 to execute a method for determining the process parameters of ring forgings using multi-index fusion.

[0126] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0127] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the multi-index fusion method for determining the process parameters of ring forging provided by the above methods.

[0128] In another aspect, embodiments of this application also provide a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a method for determining process parameters of ring forgings by multi-index fusion as provided by the methods described above.

[0129] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0130] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A multi-index fused ring forging process parameter determination method, characterized in that, include: S1. Based on the multiple die geometry parameters, multiple ring forging motion constraints and multiple ring blank initial dimensions corresponding to the ring forging, determine multiple sets of first process parameters. Each set of first process parameters includes a die geometry parameter, a ring forging motion constraint and a ring blank initial dimension. S2. For each set of first process parameters, the ring forging process is simulated according to the first process parameters to obtain the first forming index and the first material performance index of the ring forging. Each first forming index includes at least the first cross-sectional filling rate, the first equivalent strain distribution variance, the first maximum rolling force, and the first temperature distribution variance. Each first material performance index includes at least the first target region proportion and the first grain size distribution variance. The first target region proportion is the proportion of the region where the dynamic recrystallization volume fraction exceeds a preset threshold. Based on the first forming index, the first material performance index, and the first weighting coefficient and the second weighting coefficient corresponding to the first process parameters, the first comprehensive index of the first process parameters is determined and used as the first fitness. The step S2, which involves determining the first comprehensive index of the first process parameter based on the first molding index, the first material performance index, and the first and second weighting coefficients corresponding to the first process parameter, includes: The entropy weight method is used to determine the first weight coefficient corresponding to the first process parameter based on the degree of molding fluctuation corresponding to multiple first molding indicators; and the entropy weight method is used to determine the second weight coefficient corresponding to the first process parameter based on the degree of material performance fluctuation corresponding to multiple first material performance indicators; wherein, the sum of the first weight coefficient and the second weight coefficient is 1. For each group of first process parameters, the first forming index, the first weighting coefficient, the first material performance index, and the second weighting coefficient of the first process parameter are weighted and summed to obtain the first comprehensive index of the first process parameter. The method of using entropy weighting to determine the first weighting coefficient corresponding to the first process parameter based on the degree of molding fluctuation corresponding to multiple first molding indicators includes: The multiple first cross-section filling rates, multiple first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first temperature distribution variances are standardized to obtain multiple second cross-section filling rates, multiple second equivalent strain distribution variances, multiple second maximum rolling forces, and multiple second temperature distribution variances. A first sum of the multiple second cross-section filling rates, a second sum of the multiple second equivalent strain distribution variances, a third sum of the multiple second maximum rolling forces, and a fourth sum of the multiple second temperature distribution variances are determined. The ratio of each second cross-section filling rate to the first sum is taken as the first fluctuation degree of each second cross-section filling rate. The ratio of each second equivalent variation distribution variance to the second sum in the second equivalent variation distribution variance is taken as the second fluctuation degree of each second equivalent variation distribution variance; the ratio of each second maximum rolling force to the third sum in the plurality of second maximum rolling forces is taken as the third fluctuation degree of each second maximum rolling force; and the ratio of each second temperature distribution variance to the fourth sum in the plurality of second temperature distribution variances is taken as the fourth fluctuation degree of each second temperature distribution variance; all first fluctuation degrees, all second fluctuation degrees, all third fluctuation degrees, and all fourth fluctuation degrees are taken as the forming fluctuation degree, and the first weighting coefficient is determined according to the forming fluctuation degree; S3. Perform cross-validation and / or variation on the die geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank in the multiple sets of first process parameters to obtain multiple sets of second process parameters; and determine the maximum first fitness among the first fitness of each of the multiple sets of first process parameters, and the maximum second fitness among the second fitness of each of the multiple sets of second process parameters. S4. If the rate of change between the maximum first fitness and the maximum second fitness is less than a preset rate of change threshold, the set of process parameters corresponding to the maximum value of the maximum first fitness and the maximum second fitness shall be taken as the optimal process parameters.

2. The method for determining process parameters of ring forgings by multi-index fusion according to claim 1, characterized in that, The step of taking all first fluctuation levels, all second fluctuation levels, all third fluctuation levels, and all fourth fluctuation levels as the forming fluctuation level, and determining the first weighting coefficient based on the forming fluctuation level, includes: Based on all the first fluctuation levels, determine the first information entropy; based on all the second fluctuation levels, determine the second information entropy; based on all the third fluctuation levels, determine the third information entropy; and based on all the fourth fluctuation levels, determine the fourth information entropy. The first redundancy and value of the first process parameter are determined based on the first information redundancy corresponding to the first information entropy, the second information redundancy corresponding to the second information entropy, the third information redundancy corresponding to the third information entropy, and the fourth information redundancy corresponding to the fourth information entropy. The first weighting coefficient is determined based on the first information redundancy, the second information redundancy, the third information redundancy, the fourth information redundancy, and the sum of the first redundancy values.

3. The multi-criteria integrated ring- forging process parameter determination method of claim 1, wherein, The step of using the entropy weight method to determine the second weighting coefficient corresponding to the first process parameter based on the degree of material performance fluctuation corresponding to multiple first material performance indicators includes: The proportions of multiple first target regions and the variances of multiple first grain size distributions are standardized to obtain the proportions of multiple second target regions and the variances of multiple second grain size distributions. Determine the fifth sum of the proportions of the plurality of second target regions, and the sixth sum of the variances of the plurality of second grain size distributions; The ratio of each proportion of the plurality of second target regions to the fifth sum is taken as the fifth fluctuation degree of each proportion of the second target regions; and the ratio of each variance of the plurality of second grain size distributions to the sixth sum is taken as the sixth fluctuation degree of each variance of the second grain size distribution. All fifth and sixth fluctuation levels are taken as the material property fluctuation levels, and the second weighting coefficient is determined based on the material property fluctuation levels.

4. The multi-criteria, fusion, ring- forging process parameter determination method of claim 3, wherein, The step of taking all fifth and sixth fluctuation levels as the material property fluctuation levels and determining the second weighting coefficient based on the material property fluctuation levels includes: Based on all the aforementioned fifth fluctuation levels, determine the fifth information entropy; Based on all the aforementioned sixth fluctuation levels, determine the sixth information entropy; Based on the fifth information redundancy corresponding to the fifth information entropy and the sixth information redundancy corresponding to the sixth information entropy, the second redundancy and value of the first process parameter are determined; The second weighting coefficient is determined based on the fifth information redundancy, the sixth information redundancy, and the second redundancy sum.

5. The multi-criteria, fusion- ring process parameter determination method of any of claims 1-4, wherein, The method further includes: If the rate of change is greater than or equal to the preset rate of change threshold, some of the second process parameters in the multiple sets of second process parameters are used as the new multiple sets of first process parameters, and the above steps S2-S3 are repeated until the rate of change between the last determined maximum fitness and the previous determined maximum fitness is less than the preset rate of change threshold, and the set of process parameters corresponding to the maximum value in each historical iteration is used as the optimal process parameters. In this context, the second fitness of each of the aforementioned second process parameters is greater than a preset fitness threshold.

6. The method for determining process parameters of ring forgings by multi-index fusion according to any one of claims 1-4, characterized in that, The method further includes: For each group of second process parameters, the ring forging process is simulated according to the second process parameters to obtain the second forming index and the second material performance index of the ring forging; based on the second forming index, the second material performance index, and the third and fourth weighting coefficients corresponding to the second process parameters, the second comprehensive index of the second process parameters is determined and used as the second fitness.

7. A system for determining process parameters of ring forgings by integrating multiple indices, characterized in that, include: The process parameter determination module is used to determine multiple sets of first process parameters based on multiple die geometry parameters corresponding to the ring forging, multiple ring forging forming motion constraints, and multiple ring blank initial dimensions. Each set of first process parameters includes a die geometry parameter, a ring forging forming motion constraint, and a ring blank initial dimension. The fitness determination module is used to simulate the ring forging process according to the first process parameters for each group of first process parameters, and obtain the first forming index and the first material performance index of the ring forging. Each first forming index includes at least the first cross-sectional filling rate, the first equivalent strain distribution variance, the first maximum rolling force, and the first temperature distribution variance. Each first material performance index includes at least the first target region proportion and the first grain size distribution variance. The first target region proportion is the proportion of the region where the dynamic recrystallization volume fraction exceeds a preset fraction threshold. Based on the first forming index, the first material performance index, and the first weighting coefficient and the second weighting coefficient corresponding to the first process parameters, a first comprehensive index of the first process parameters is determined and used as the first fitness. The method for determining the first comprehensive index of the first process parameter based on the first forming index, the first material performance index, and the first weighting coefficient and second weighting coefficient corresponding to the first process parameter includes: using the entropy weight method to determine the first weighting coefficient corresponding to the first process parameter based on the forming fluctuation degree corresponding to multiple first forming indices; and using the entropy weight method to determine the second weighting coefficient corresponding to the first process parameter based on the material performance fluctuation degree corresponding to multiple first material performance indices; wherein the sum of the first weighting coefficient and the second weighting coefficient is 1; for each group of first process parameters, the first forming index, the first weighting coefficient, the first material performance index, and the second weighting coefficient of the first process parameter are weighted and summed to obtain the first comprehensive index of the first process parameter; wherein, using the entropy weight method to determine the first weighting coefficient corresponding to the first process parameter based on the forming fluctuation degree corresponding to multiple first forming indices includes: standardizing multiple first cross-sectional filling rates, multiple first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first temperature distribution variances respectively to obtain multiple second ... first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first temperature distribution variances respectively to obtain multiple first equivalent strain distribution variances, multiple first maximum rolling forces, and multiple first maximum rolling forces, and multiple first minimum rolling forces, and multiple first minimum rolling forces, and multiple first minimum rolling forces, and obtaining multiple first average weighting coefficients, multiple first maximum rolling forces, and multiple first minimum rolling forces The method considers the surface filling rate, multiple second equivalent strain distribution variances, multiple second maximum rolling forces, and multiple second temperature distribution variances; it determines the first sum of the multiple second section filling rates, the second sum of the multiple second equivalent strain distribution variances, the third sum of the multiple second maximum rolling forces, and the fourth sum of the multiple second temperature distribution variances; it uses the ratio of each second section filling rate to the first sum as the first fluctuation degree of each second section filling rate; and it uses the ratio of each second equivalent strain distribution variance to the second sum. The ratio is used as the second degree of fluctuation of the variance of each second equivalent variation distribution; the ratio of each second maximum rolling force to the third sum is used as the third degree of fluctuation of each second maximum rolling force; the ratio of each second temperature distribution variance to the fourth sum is used as the fourth degree of fluctuation of each second temperature distribution variance; all first degrees of fluctuation, all second degrees of fluctuation, all third degrees of fluctuation, and all fourth degrees of fluctuation are used as the forming fluctuation degree, and the first weighting coefficient is determined according to the forming fluctuation degree; The process parameter determination module is further configured to perform cross- and / or variation on the mold geometry parameters, ring forging motion constraints, and initial dimensions of the ring blank in the plurality of first process parameters to obtain a plurality of second process parameters; and determine the maximum first fitness among the first fitness of each of the plurality of first process parameters, and the maximum second fitness among the second fitness of each of the plurality of second process parameters; if the rate of change between the maximum first fitness and the maximum second fitness is less than a preset rate of change threshold, the set of process parameters corresponding to the maximum value of the maximum first fitness and the maximum second fitness is taken as the optimal process parameters.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for determining the process parameters of ring forging by multi-index fusion as described in any one of claims 1 to 6.

Images