A method and apparatus for online optimization of hot forging process parameters

Abstract

This application discloses an online optimization method and apparatus for hot forging process parameters, applicable to the field of hot forming technology. Based on a full-factor experimental design, this application performs multi-scale simulation of hot forgings to obtain grain size simulation results. Then, it obtains a pre-defined mesh corresponding to the final forging as the base mesh and constructs a rapid grain size prediction dataset based on the grain size simulation results. Next, it constructs a rapid grain size prediction model for hot forgings and a visualization model based on this dataset. The hot forging process parameters are then input into the rapid grain size prediction model to predict real-time grain size data. The real-time grain size data is visualized using the visualization model, thus achieving online visualization prediction of the global grain size of the hot forging. Finally, a biomimetic intelligent optimization algorithm is used to optimize the hot forging process parameters, enabling rapid optimization of process parameters.

Description

Technical Field

[0001] This application relates to the field of hot forming technology, and in particular to a method and apparatus for online optimization of hot forging process parameters. Background Technology

[0002] In related technologies, the grain size of hot forgings has a profound impact on their final performance. From mechanical properties to machining and service performance, grain size control is a key factor in ensuring that materials meet design requirements. In the hot forging process, controlling the grain size through appropriate process parameters can optimize and balance material properties. Currently, methods for optimizing process parameters for hot forgings cannot quickly visualize and predict the grain size across the entire range of hot forgings, nor can they rapidly optimize process parameters.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this application is to propose an online optimization method and apparatus for hot forging process parameters, which can perform online visual prediction of the global grain size of hot forgings and quickly optimize process parameters.

[0005] To achieve the above objectives, one aspect of this application proposes an online optimization method for hot forging process parameters, the method comprising the following steps:

[0006] Multi-scale simulation of hot forgings was conducted based on full factorial experimental design to obtain grain size simulation results.

[0007] Obtain the mesh corresponding to the preset final forging as the base mesh;

[0008] A fast grain size prediction dataset is constructed based on the grain size simulation results and the base grid.

[0009] Based on the aforementioned grain size rapid prediction dataset, a rapid prediction model for the grain size of hot forgings is constructed, along with a visualization model.

[0010] The hot forging process parameters are input into the hot forging grain size rapid prediction model to predict real-time grain size data.

[0011] The real-time grain size data is visualized using the visualization model.

[0012] The process parameters of the hot forging are optimized using a biomimetic intelligent optimization algorithm.

[0013] In some embodiments, the multi-scale simulation of hot forgings based on full factorial experimental design to obtain grain size simulation results includes:

[0014] Construct the constitutive equations of the material;

[0015] A dynamic recrystallization model is constructed based on the constitutive equation of the material.

[0016] After integrating the material constitutive equation and the dynamic recrystallization model into the finite element analysis software, multi-scale simulation of hot forgings was carried out based on full factorial experimental design to obtain the grain size simulation results.

[0017] In some embodiments, the material constitutive equation is formulated as follows:

[0018]

[0019] In the formula, σ is the strain rate; α is the stress factor; σ is the flow stress; Q is the activation energy for hot deformation; R is the molar gas parameter; T is the absolute temperature; and n is a material-related constant of the hot model.

[0020] In some embodiments, the dynamic recrystallization model includes a critical strain model, a volume percentage model, and a grain size model; the formula for the critical strain model is as follows:

[0021]

[0022] In the formula, d0 is the initial grain size; Q1 is the recrystallization activation energy; T is the thermodynamic temperature during deformation; ε p ε represents the peak strain. c The critical strain is n1, m1, and a1, which are constants to be regressed.

[0023] The formula for the volume percentage model is as follows:

[0024]

[0025] In the formula, X drex Percentage of dynamic recrystallization; ε 0.5 h5 is the strain value at which 50% dynamic recrystallization occurs; Q5 is the activation energy corresponding to 50% dynamic recrystallization; h5, m5, k d a5 and β d All represent the constants to be regressed; ε represents the equivalent variation;

[0026] The formula for the grain size model is as follows:

[0027]

[0028] In the formula, d rex is the average grain size for dynamic recrystallization; Q3 is the grain growth activation energy; h3, m3, and a3 are constants to be regressed.

[0029] In some embodiments, constructing a fast grain size prediction dataset based on the grain size simulation results and the base mesh includes:

[0030] Map the grid vertex values ​​from the grain size simulation results to the vertices of the base grid;

[0031] Using the mold preheating temperature, billet heating temperature, and pressing rate as input values, and the value of the vertex as the output value, a fast grain size prediction dataset is constructed.

[0032] In some embodiments, the formula for the rapid prediction model of grain size in hot forgings is as follows:

[0033]

[0034] In the formula, The predicted value f at the predicted location * The mean; The predicted value f at the predicted location * The variance of ; Y is the output value corresponding to the input value X in the grain size fast prediction dataset; K XX This indicates that for all input values ​​X and the prediction point X * The N*N covariance matrix of the evaluation; K X*X It is K X*X The transpose of K; X*X* This represents the covariance matrix between the new input point sets.

[0035] In some embodiments, the visualization processing of the real-time grain size data through the visualization model includes:

[0036] Read the vertex coordinates and face index data of the base mesh;

[0037] A virtual three-dimensional model of the hot forging is constructed based on the vertex coordinates, facet index data, and real-time grain size data;

[0038] Obtain temperature color mapping data;

[0039] The virtual 3D model is controlled to display the color corresponding to the real-time grain size data based on the temperature color mapping data.

[0040] To achieve the above objectives, another aspect of this application proposes an online optimization device for hot forging process parameters, the device comprising:

[0041] The first module is used to perform multi-scale simulation of hot forgings based on full factorial experimental design to obtain grain size simulation results.

[0042] The second module is used to obtain the mesh corresponding to the preset final forging as the base mesh;

[0043] The third module is used to construct a fast grain size prediction dataset based on the grain size simulation results and the base grid.

[0044] The fourth module is used to construct a rapid grain size prediction model for hot forgings based on the grain size rapid prediction dataset, and to construct a visualization model;

[0045] The fifth module is used to input the hot forging process parameters into the hot forging grain size rapid prediction model to predict real-time grain size data;

[0046] The sixth module is used to visualize the real-time grain size data through the visualization model;

[0047] The seventh module is used to optimize the process parameters of the hot forging through a biomimetic intelligent optimization algorithm.

[0048] To achieve the above objectives, another aspect of this application proposes an online optimization device for hot forging process parameters, comprising:

[0049] At least one processor;

[0050] At least one memory for storing at least one program;

[0051] When the at least one program is executed by the at least one processor, the at least one processor performs the method described above.

[0052] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0053] The embodiments of this application include at least the following beneficial effects: This application provides an online optimization method and apparatus for hot forging process parameters. This scheme obtains the grain size simulation results by performing multi-scale simulation of hot forgings based on full factorial experimental design, obtains the mesh corresponding to the preset final forging as the base mesh, so as to unify the vertex coordinates and facet data of the three-dimensional model of the final forging, and then constructs a grain size rapid prediction dataset based on the grain size simulation results. Next, a hot forging grain size rapid prediction model and a visualization model are constructed based on the grain size rapid prediction dataset. The hot forging process parameters are input into the hot forging grain size rapid prediction model to predict the real-time grain size data. The real-time grain size data is visualized through the visualization model, thereby realizing online visualization prediction of the global grain size of hot forgings. Finally, the hot forging process parameters are optimized through a biomimetic intelligent optimization algorithm, thereby enabling rapid optimization of process parameters. Attached Figure Description

[0054] Figure 1 This is a flowchart of the online optimization method for hot forging process parameters provided in the embodiments of this application;

[0055] Figure 2 This is a schematic diagram of the mold analyzed by the finite element analysis software provided in the embodiments of this application;

[0056] Figure 3 This is a schematic diagram of the control arm model analyzed by the finite element analysis software provided in the embodiments of this application;

[0057] Figure 4 This is a schematic diagram of key parts of the blank provided in the embodiments of this application;

[0058] Figure 5 This is a schematic diagram of the online optimization device for hot forging process parameters provided in the embodiments of this application;

[0059] Figure 6 This is a schematic diagram of the hardware structure of the online optimization device for hot forging process parameters provided in the embodiments of this application. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0062] Before providing a detailed description of the embodiments of this application, some of the nouns and terms used in the embodiments of this application will be explained first. The nouns and terms used in the embodiments of this application shall be interpreted as follows:

[0063] Forgings are metal objects that are shaped by applying pressure and plastic deformation to achieve the required shape or appropriate compressive force.

[0064] Cold forging: refers to the process of processing metal at room temperature.

[0065] Hot forging: A process of processing metal at a temperature higher than the recrystallization temperature of the billet metal.

[0066] This application provides an online optimization method and apparatus for hot forging process parameters. After obtaining grain size simulation results through multi-scale simulation of hot forgings based on full-factor experimental design, a pre-defined mesh corresponding to the final forging is obtained as the base mesh to unify the vertex coordinates and facet data of the final forging's 3D model. Then, a rapid grain size prediction dataset is constructed based on the grain size simulation results. Next, a rapid grain size prediction model and a visualization model are constructed based on the rapid grain size prediction dataset. The hot forging process parameters are input into the rapid grain size prediction model to predict real-time grain size data. The real-time grain size data is then visualized using the visualization model, thereby achieving online visualization prediction of the global grain size of the hot forging. Finally, a biomimetic intelligent optimization algorithm is used to optimize the hot forging process parameters, thus enabling rapid optimization of the process parameters.

[0067] The online optimization method for hot forging process parameters provided in this application relates to the field of hot forming technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the online optimization method for hot forging process parameters, but is not limited to the above forms.

[0068] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0069] Figure 1 This is an optional flowchart of the online optimization method for hot forging process parameters provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S110 to S180:

[0070] Step S110: Perform multi-scale simulation of hot forgings based on full factorial experimental design to obtain grain size simulation results;

[0071] Step S120: Obtain the mesh corresponding to the preset final forging as the base mesh;

[0072] Step S130: Construct a fast grain size prediction dataset based on the grain size simulation results and the base mesh;

[0073] Step S140: Construct a fast prediction model for the grain size of hot forgings based on the grain size fast prediction dataset, and construct a visualization model;

[0074] Step S150: Input the hot forging process parameters into the hot forging grain size rapid prediction model to predict real-time grain size data;

[0075] Step S160: Visualize the real-time grain size data using the visualization model;

[0076] Step S170: Optimize the process parameters of the hot forging using a biomimetic intelligent optimization algorithm.

[0077] In this embodiment, the material constitutive equation and dynamic recrystallization model can be obtained by combining hot compression experiments and metallographic observation of high-temperature hot compression samples. These equations and models are then integrated into finite element analysis software, and a full-factor experimental design table is designed. The die preheating temperature, billet heating temperature, and reduction rate are selected as factors in the design table. Finally, multi-scale simulation of the hot forging process is performed with different parameter combinations to obtain the grain size simulation results. It is understood that the constitutive relationship can be described using a hyperbolic sine Arrhenius relation, where the formula for the material constitutive equation is as follows:

[0078]

[0079] In the formula, σ is the strain rate; a is the stress factor; σ is the flow stress; Q is the activation energy for thermal deformation; R is the molar gas parameter; T is the absolute temperature; n is a material-related constant of the thermal model; A is a constant.

[0080] It is understandable that dynamic recrystallization models include critical strain models, volume percentage models, and grain size models; the formula for the critical strain model is as follows:

[0081]

[0082] In the formula, d0 is the initial grain size; Q1 is the recrystallization activation energy; T is the thermodynamic temperature during deformation; ε p ε represents the peak strain. c The critical strain is n1, m1, and a1, which are constants to be regressed.

[0083] The formula for the volume percentage model is as follows:

[0084]

[0085] In the formula, X drex Percentage of dynamic recrystallization; ε 0.5 h5 is the strain value at which 50% dynamic recrystallization occurs; Q5 is the activation energy corresponding to 50% dynamic recrystallization; h5, m5, k d a5 and β d All represent the constants to be regressed; ε represents the equivalent variation;

[0086] The formula for the grain size model is as follows:

[0087]

[0088] In the formula, d rex is the average grain size for dynamic recrystallization; Q3 is the grain growth activation energy; h3, m3, and a3 are constants to be regressed.

[0089] In this embodiment, when constructing a fast grain size prediction dataset, a section of the forging mesh can be selected as the base mesh, and key parts of the billet within that mesh can be selected as vertices to unify the vertex coordinates and facet data of the forging's 3D model. Then, the KNN algorithm and RBF model are used to map the mesh vertex values ​​from the grain size simulation results to the vertices of the base mesh. Finally, the die preheating temperature, billet heating temperature, and pressing rate are used as input values, and the vertex values ​​are used as output values ​​to construct the fast grain size prediction dataset.

[0090] In this embodiment, a Gaussian process regression model can be constructed to quickly predict the grain size of hot forgings. The Gaussian process is represented by a mean function and a covariance function, as shown in the following formula:

[0091]

[0092] Where m(x) is the mean function and k(x, x′) is the covariance function, i.e., f(x) ~ N(m(x), k(x, x′)).

[0093] In a Gaussian process regression model, the relationship between the output value and the input value is as follows:

[0094] y(X) = f(X) + ε;

[0095] Where X represents the input vector, f(X) represents the latent function, y(X) represents the output function, and ε is a Gaussian noise random variable.

[0096] The key prediction equation of Gaussian process regression is used as a fast prediction model for grain size of hot forgings, and its formula is as follows:

[0097]

[0098] In the formula, The predicted value f at the predicted location * The mean; The predicted value f at the predicted location * The variance of ; Y is the output value corresponding to the input value X in the grain size fast prediction dataset; K XX This indicates that for all input values ​​X and the prediction point X * The N*N covariance matrix of the evaluation; K X*X It is K X*X The transpose of K; X*X* This represents the covariance matrix between the new input point sets.

[0099] Simultaneously, the parameters of the hot forging are visualized through a visualization model. Specifically, this embodiment can read the vertex coordinates and patch index data of the base mesh, construct a virtual three-dimensional model of the hot forging based on the vertex coordinates, patch index data, and real-time grain size data, and after obtaining the temperature color mapping data, control the virtual three-dimensional model to display the color corresponding to the real-time grain size data, thereby displaying the parameter change process of the forging in real time in the virtual three-dimensional model.

[0100] In this embodiment, the process parameters of hot forging can also be optimized using a biomimetic intelligent optimization algorithm. It is understood that the whale optimization algorithm is selected as the biomimetic intelligent optimization algorithm. This algorithm is characterized by its simplicity and efficiency, and can find the global optimum in a complex high-dimensional space. Specifically, the whale optimization algorithm first identifies the location of the prey and gradually approaches it. The mathematical formula can be expressed as follows:

[0101]

[0102] In the formula, This is the whale's current location. It is the optimal solution found in the current iteration. and It is a coefficient vector used to control position updates.

[0103] When approaching prey, humpback whales will form a spiral trajectory around it, which can be represented by the following formula:

[0104]

[0105] In the formula, Let represent the distance between the i-th whale and its prey, i.e., the current optimal solution, where b is a constant and l is a random number.

[0106] To avoid local optima, whales randomly select other locations to search, thereby enhancing their global search capabilities. The mathematical model is as follows:

[0107]

[0108] In the formula, It is a randomly selected position vector that helps the whale explore the entire search space.

[0109] By identifying the die preheating temperature, billet heating temperature, and pressing rate as design variables, and the average grain size at key locations of the hot forging and the global average grain size as optimization objectives, the multi-objective optimization is transformed into a single-objective optimization by assigning weights, and a fitness function is designed based on a grain size prediction model. The number of humpback whale individuals is initialized, the range of design variables is determined, and the maximum number of iterations is set, thereby optimizing the hot forging process parameters.

[0110] In some embodiments, the method of this application is applied to... Figure 2 The mold shown is used to prepare the following: Figure 3 The study focuses on a car control arm model, employing multi-scale simulation modeling, artificial intelligence algorithms, and computer graphics to achieve online, rapid, and visual prediction of grain size and optimization of hot forging process parameters. The specific implementation process includes, but is not limited to, the following steps:

[0111] Step 1: Perform multi-scale simulation of the hot forging process and construct a dataset using a base mesh.

[0112] Step 1.1: Taking an aluminum alloy control arm as an example, samples are taken for hot compression and metallographic experiments. The material constitutive equation and dynamic recrystallization equation are fitted based on the experimental data. In this example, using 6082 aluminum alloy, the corresponding material constitutive equation under high-temperature rheological conditions is as follows:

[0113]

[0114] The critical strain model for dynamic recrystallization of 6082 aluminum alloy is as follows:

[0115]

[0116] The dynamic recrystallization volume percentage model for 6082 aluminum alloy is as follows:

[0117]

[0118] The dynamic recrystallization grain size model for 6082 aluminum alloy is as follows:

[0119]

[0120] This embodiment uses Deform simulation software to simulate the hot forging process at multiple scales. In the preprocessing interface, the obtained constitutive equation of 6082 aluminum alloy and the parameters solved by the dynamic recrystallization model are imported into the integrated model of the software to perform macroscopic and mesoscopic multi-scale hot forging simulations. Each simulation mainly includes two processes: pre-forging and final forging. The friction coefficient between the die and the billet is 0.3, the heat transfer coefficient between the billet and the die is 11 N / s / mm / ℃, the environmental convective heat transfer coefficient is 0.02 N / s / mm / ℃, and the initial grain size is 105 micrometers. A full factorial experimental design is performed, and the levels and factors are shown in Table 1. According to the table, 27 sets of process parameters are obtained, and 27 sets of hot forging simulations can be performed.

[0121] Table 1

[0122]

[0123] Step 1.2: In the 27 simulations, the hot forging part with the fewest meshes after the hot forging simulation is selected, and its mesh is extracted as the base mesh. Then, the global average grain size results obtained from simulations with different parameter combinations are attached to this base mesh. Taking a certain set of parameter simulations as an example, firstly, the vertex coordinates of the base mesh, the vertex coordinates of the hot forging part in this set of simulations, and the vertex values ​​are extracted. Here, the vertex values ​​refer to the values ​​at the mesh vertices when the variable in the Deform post-processing is the average grain size. Then, the KNN algorithm is used to obtain the indices of the 15 points closest to each vertex of the base mesh in the vertex coordinates of the final hot forging part in this set of simulations. Based on these indices, the coordinates of these 15 vertices and their corresponding vertex values ​​are obtained. Then, the RBF model is trained with these 15 vertex coordinates as input and the 15 vertex values ​​as output, thereby interpolating the result corresponding to each vertex of the base mesh. The above processing is performed on all 27 sets of simulation results to obtain the input and output sizes of a unified dataset. The input of the dataset is the hot forging process parameters, namely the die preheating temperature, the billet heating temperature, and the pressing rate, and the output is the vertex values ​​of all the base meshes. Finally, to eliminate differences between different units of measurement, the min-max normalization method was used for data preprocessing.

[0124] Step 2: Establish a rapid prediction model and visualization model for grain size of hot forgings.

[0125] Step 2.1: Based on the grain size rapid prediction dataset constructed in 1.2, establish multiple Gaussian process regression models. For small sample data, GPR can effectively capture the complex patterns and uncertainties of the data, and provide accurate predictions and uncertainty measures. In this embodiment, a Gaussian process regression model is created for all vertices of the base mesh. Assuming there are m nodes, it can be represented as follows:

[0126]

[0127] Each prediction model is trained and tested using 27 data samples. Each sample contains three inputs (die preheating temperature, billet heating temperature, and reduction rate) and one output (grain size). The final result is that feeding a set of input parameters into the Gaussian process regression model instantly yields a set of grain size values ​​corresponding to the base grid (real-time grain size data).

[0128] Step 2.2: Combining computer graphics technology, the grain size prediction results are displayed intuitively in real time as a cloud map. First, the vertex and face index data of the base mesh are read, and the grain size prediction results output by Gaussian process regression are extracted. Using the Mesh3d object from the Plotly library, a 3D mesh graphic object is created by passing in parameters such as vertex coordinates, face indices, and grain size values. To convert the grain size values ​​into color for display, a temperature color map is defined. This color map maps different colors according to the size of the grain size to more intuitively display the grain size distribution.

[0129] Step 3: Optimize the hot forging process parameters using a biomimetic intelligent optimization algorithm. A linear weighted method is used to transform the multi-objective optimization problem into a single-objective optimization problem. The weight coefficients of the objective function are determined based on the importance of the problem analysis. In this embodiment, taking the average grain size at critical locations and the global average grain size as examples where their importance is equivalent, the weight factors for both are set to 0.5. For the global average grain size, the mean of the predicted results can be used for calculation; for the average grain size at critical locations, the mean of the predicted results can be used for calculation. Figure 4 Taking the mid-position as an example, the vertex order of the base mesh at key positions is obtained in advance. After the prediction model outputs the prediction results, the prediction results at key positions can be directly extracted using programming, and the mean can be directly calculated. First, a set of whale positions are randomly generated, ensuring they are within a given boundary range. The fitness of each whale's current position is evaluated, and the global optimum is updated. The position of each whale is gradually updated according to the strategies of hunting prey, bubble net attacks, and exploring prey, ensuring that the updated position is within a predefined boundary range (this boundary is the boundary value of the factors in Table 1). The maximum number of iterations is set to 100. After reaching this number, the optimal process parameters can be obtained.

[0130] In summary, the method provided in this application combines digital twin technologies such as multi-scale modeling, machine learning, and 3D visualization with parameter optimization, thereby improving the efficiency of hot forging process parameter optimization and providing reliable technical support for the manufacturing of high-performance hot forgings.

[0131] Reference Figure 5 This application provides an online optimization device for hot forging process parameters, the device comprising:

[0132] The first module 510 is used to perform multi-scale simulation of hot forgings based on full factorial experimental design to obtain grain size simulation results.

[0133] The second module 520 is used to obtain the mesh corresponding to the preset final forging as the base mesh;

[0134] The third module 530 is used to construct a fast grain size prediction dataset based on the grain size simulation results and the base grid.

[0135] Module 540 is used to build a fast prediction model for the grain size of hot forgings based on the grain size fast prediction dataset, and to build a visualization model;

[0136] The fifth module 550 is used to input hot forging process parameters into the hot forging grain size rapid prediction model to predict real-time grain size data;

[0137] Module 6, 560, is used to visualize real-time grain size data through a visualization model.

[0138] Module 7, 570, is used to optimize the process parameters of hot forgings using a biomimetic intelligent optimization algorithm.

[0139] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0140] This application also provides an online optimization device for hot forging process parameters. The device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned online optimization method for hot forging process parameters. This online optimization device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0141] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0142] Please see Figure 6 , Figure 6 The hardware structure of an online hot forging process parameter optimization device according to another embodiment is illustrated. The online hot forging process parameter optimization device includes:

[0143] The processor 610 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0144] The memory 620 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 620 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 620 and called by the processor 610 to execute the online optimization method for hot forging process parameters of the embodiments of this application.

[0145] The input / output interface 630 is used to realize information input and output;

[0146] The communication interface 640 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0147] Bus 650 transmits information between various components of the device (e.g., processor 610, memory 620, input / output interface 630, and communication interface 640);

[0148] The processor 610, memory 620, input / output interface 630 and communication interface 640 are connected to each other within the device via bus 650.

[0149] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described online optimization method for hot forging process parameters.

[0150] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0151] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0152] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0153] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0154] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; 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.

[0155] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0156] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0157] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0159] The units described above 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0160] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0161] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it 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 all or part 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 multiple 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0162] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for online optimization of hot forging process parameters, characterized in that, The method includes the following steps: Multi-scale simulation of hot forgings was conducted based on full factorial experimental design to obtain grain size simulation results. Obtain the mesh corresponding to the preset final forging as the base mesh; A fast grain size prediction dataset is constructed based on the grain size simulation results and the base grid. Based on the aforementioned grain size rapid prediction dataset, a rapid prediction model for the grain size of hot forgings is constructed, along with a visualization model. The hot forging process parameters are input into the hot forging grain size rapid prediction model to predict real-time grain size data. The real-time grain size data is visualized using the visualization model. The process parameters of the hot forging are optimized using a biomimetic intelligent optimization algorithm.

2. The method according to claim 1, characterized in that, The multi-scale simulation of hot forgings based on full factorial experimental design yields grain size simulation results, including: Construct the constitutive equations of the material; A dynamic recrystallization model is constructed based on the constitutive equation of the material. After integrating the material constitutive equation and the dynamic recrystallization model into the finite element analysis software, multi-scale simulation of hot forgings was carried out based on full factorial experimental design to obtain the grain size simulation results.

3. The method according to claim 2, characterized in that, The formula for the constitutive equation of the material is as follows: ； In the formula, For strain rate; Stress factor; For flow stress; It is the activation energy for thermal deformation; For molar gas parameters; is the absolute temperature; n is a constant related to the material of the hot mold; A is a constant.

4. The method according to claim 3, characterized in that, The dynamic recrystallization model includes a critical strain model, a volume percentage model, and a grain size model; the formula for the critical strain model is as follows: ； ； In the formula, This represents the initial grain size; This is the activation energy for recrystallization; The thermodynamic temperature at which deformation occurs; Peak strain; The critical strain; , and All are constants to be regressed; The formula for the volume percentage model is as follows: ； ； In the formula, Percentage of dynamic recrystallization; This is the strain value at which 50% dynamic recrystallization occurs; This corresponds to the activation energy for 50% dynamic recrystallization. , , , and All represent constants to be regressed; Indicates equivalent change; The formula for the grain size model is as follows: ； In the formula, This represents the average grain size during dynamic recrystallization. It is the activation energy for grain growth; , and All of these are constants to be regressed.

5. The method according to claim 1, characterized in that, The step of constructing a fast grain size prediction dataset based on the grain size simulation results and the base grid includes: Map the grid vertex values ​​from the grain size simulation results to the vertices of the base grid; Using the mold preheating temperature, billet heating temperature, and pressing rate as input values, and the value of the vertex as the output value, a fast grain size prediction dataset is constructed.

6. The method according to claim 1, characterized in that, The visualization processing of the real-time grain size data through the visualization model includes: Read the vertex coordinates and face index data of the base mesh; A virtual three-dimensional model of the hot forging is constructed based on the vertex coordinates, facet index data, and real-time grain size data; Obtain temperature color mapping data; The virtual 3D model is controlled to display the color corresponding to the real-time grain size data based on the temperature color mapping data.

7. An online optimization device for hot forging process parameters, characterized in that, The device comprises: The first module is used to perform multi-scale simulation of hot forgings based on full factorial experimental design to obtain grain size simulation results. The second module is used to obtain the mesh corresponding to the preset final forging as the base mesh; The third module is used to construct a fast grain size prediction dataset based on the grain size simulation results and the base grid. The fourth module is used to construct a rapid grain size prediction model for hot forgings based on the grain size rapid prediction dataset, and to construct a visualization model; The fifth module is used to input the hot forging process parameters into the hot forging grain size rapid prediction model to predict real-time grain size data; The sixth module is used to visualize the real-time grain size data through the visualization model; The seventh module is used to optimize the process parameters of the hot forging through a biomimetic intelligent optimization algorithm.

8. An online optimization device for hot forging process parameters, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images