A method, system, equipment and medium for online prediction of quenching of forgings.

Abstract

This invention discloses an online prediction method, system, equipment, and medium for forging quenching equipment, relating to the field of quenching flow field-temperature field-microstructure field analysis and prediction technology. The method includes: acquiring velocity sample data; performing flow field analysis on the velocity sample data according to a fluid dynamics analysis model to obtain a first medium velocity; obtaining the response relationship between the quenching tank stirring parameters and the medium velocity based on the first medium velocity and a proxy model; determining a first heat transfer coefficient based on a solid interpolation model and a set proportional relationship; calculating the temperature data of all grid nodes on the surface of the solid model at different times using a temperature field calculation model based on the first heat transfer coefficient and the solid model to obtain second temperature data; and obtaining the microstructure content of the forging during the cooling process based on the second temperature data and the microstructure field calculation model. This invention improves the system's computing speed and reflects the dynamic changes in medium velocity, forging temperature, and microstructure within the quenching tank in real time.

Description

Technical Field

[0001] This invention relates to the field of quenching flow field-temperature field-microstructure field analysis and prediction technology, and in particular to an online prediction method, system, equipment and medium for forging quenching equipment. Background Technology

[0002] Quenching is a key process for improving the microstructure and mechanical properties of forgings. However, due to the large size of forgings, the quenching process is complex and uncertain, making it difficult to precisely control the forging properties. The flow field distribution of the medium during quenching is one of the key factors affecting quenching quality. By adjusting the stirring parameters of the quenching tank, the flow field state can be improved, thereby optimizing the cooling rate and microstructure at different locations on the forging. However, the quenching process faces systemic challenges such as being "invisible," "difficult to quantify," and "nonlinear." The influence of the stirring parameters of the quenching tank on the flow field, temperature field, and microstructure field is difficult to quantitatively assess, and process control lacks a basis.

[0003] Traditional methods for analyzing the flow field, temperature field, and microstructure field during the quenching process primarily employ numerical simulation. For example, the paper "Simulation of Medium Flow Field in Quenching Tank and Optimization Design of Flow Equalization System" uses Fluent fluid dynamics software to simulate the flow field distribution in a production quenching tank and compares the flow field distribution under different flow equalization system structures. The paper "Coupling Simulation Study of Flow Field, Temperature Field, Microstructure Field, and Stress Field in Heat Treatment Process" proposes a coupled analysis model for the high-pressure gas quenching process. However, these models are relatively slow, requiring significant computation time to obtain the final analysis results. Furthermore, the substantial lag between the analysis results and the acquired data means that the analysis results cannot reflect the dynamic changes in the medium velocity, forging temperature, and microstructure within the quenching tank in real time. Summary of the Invention

[0004] The purpose of this invention is to provide an online prediction method, system, equipment and medium for forging quenching equipment. By changing the model structure, the system's computing speed is improved, thereby enabling real-time reflection of the dynamic changes in medium flow rate, forging temperature and microstructure within the quenching tank.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] In a first aspect, the present invention provides an online prediction method for forging quenching equipment, wherein the forging quenching equipment includes at least a quenching tank and a lifting device, the quenching tank contains a medium, the lifting device has a forging fixed on it, and a propeller or nozzle is provided at the bottom of the quenching tank; the online prediction method includes:

[0007] Acquire velocity sample data; the velocity sample data is the propeller velocity or the nozzle injection velocity.

[0008] A system consisting of the forging quenching equipment, the medium, and the forging is modeled to obtain a geometric model of the forging quenching equipment-medium-forging, and a fluid dynamics analysis model is determined based on the geometric model of the forging quenching equipment-medium-forging.

[0009] The flow field is analyzed based on the velocity sample data according to the fluid dynamics analysis model to obtain the first medium velocity; the first medium velocity is the medium velocity of all grid nodes on the surface of the fluid dynamics analysis model;

[0010] The surrogate model is determined based on the radial basis function, and the response relationship between the stirring parameters of the quenching tank and the medium flow rate is obtained according to the first medium flow rate and the surrogate model.

[0011] A solid model is obtained by modeling the forging, and the first medium flow velocity is interpolated into the mesh nodes on the surface of the solid model to obtain a solid interpolation model;

[0012] The first heat transfer coefficient is determined based on the solid interpolation model and the set proportional relationship; the set proportional relationship is the ratio between the medium flow rate and the heat transfer coefficient of the forging surface; the first heat transfer coefficient is the heat transfer coefficient at different grid nodes on the surface of the solid interpolation model.

[0013] Based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times are calculated using the temperature field calculation equation to obtain the first temperature data; the first temperature data is subjected to intrinsic orthogonal decomposition, and the temperature field calculation equation is subjected to order reduction calculation to obtain the temperature field calculation model;

[0014] Based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times are calculated using the temperature field calculation model to obtain the second temperature data.

[0015] The microstructure field calculation model is determined based on the Avrami equation and the KM equation, and the pearlite content, bainite content and martensite content of the forging during the cooling process are obtained based on the second temperature data and the microstructure field calculation model.

[0016] Optionally, a fluid dynamics analysis model is determined based on the geometric model of the forging quenching equipment-medium-forging, specifically including:

[0017] Mesh the geometric model of the forging quenching equipment-medium-forging;

[0018] By setting the material parameters and first boundary conditions of the geometric model of the forging quenching equipment-medium-forging after mesh generation, a fluid dynamics analysis model is obtained; the material parameters include the density, viscosity, thermal conductivity and specific heat capacity of the medium; the first boundary condition is determined based on the propeller speed or nozzle velocity.

[0019] Optionally, flow field analysis is performed on the velocity sample data according to the fluid dynamics analysis model to obtain the first medium velocity, specifically including:

[0020] The propeller speed or nozzle velocity in the fluid dynamics analysis model is changed according to the rate sample data.

[0021] Fluid dynamics simulation was performed on the fluid dynamics analysis model after changing the propeller speed or nozzle velocity to obtain the first medium velocity.

[0022] Optionally, the proxy model is:

[0023]

[0024] In the formula, x new For the prediction point, Let n be the first medium velocity at the prediction point, n be the number of samples, and ω be the velocity. i Let r represent the response relationship between the stirring parameters of the quenching tank and the medium flow rate corresponding to the i-th sample point. i Let Euclidean distance be the predicted point and the i-th sample point. These are radial basis functions.

[0025] Optionally, based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times is calculated using the temperature field calculation model to obtain the second temperature data, specifically including:

[0026] The material parameters and second boundary conditions of the solid model are set; the material parameters include the density, viscosity, thermal conductivity and specific heat capacity of the medium; the second boundary conditions are determined based on the first heat transfer coefficient.

[0027] Based on the first heat transfer coefficient and the configured solid model, the temperature data of all grid nodes on the surface of the solid model at different times are calculated using the temperature field calculation model to obtain the second temperature data; the temperature field calculation model is as follows:

[0028]

[0029] In the formula, T represents the second temperature data, and k represents the thermal conductivity of the forging. Here, t is the Laplace operator, Q is the internal heat source, ρ is the density of the forging, and c is the internal heat source. p This refers to the specific heat capacity of the forging.

[0030] Optionally, the tissue field calculation model specifically includes: a first Avrami equation, a second Avrami equation, and a KM equation;

[0031] The first Avrami equation is:

[0032]

[0033] In the formula, f1 is the pearlite content, b1 is the first transformation kinetic parameter of pearlite, t is the cooling time, and t s During the incubation period, n1 is the kinetic parameter of the second transformation of pearlite;

[0034] The second Avrami equation is:

[0035]

[0036] In the formula, f2 is the bainite content, b2 is the first transformation kinetic parameter of bainite, and n2 is the second transformation kinetic parameter of bainite.

[0037] The KM equation is:

[0038] f3=1-exp(-a(M s -T));

[0039] In the formula, f3 is the martensite content, a is the martensite transformation kinetic parameter, and M... s T represents the temperature at which the martensitic transformation begins, and T is the second temperature data.

[0040] Secondly, the present invention provides an online prediction system for forging quenching equipment, the system comprising:

[0041] The sample data acquisition module is used to acquire velocity sample data; the velocity sample data is the propeller velocity or the nozzle injection velocity.

[0042] The fluid dynamics analysis model determination module is used to model the system composed of the forging quenching equipment, the medium and the forging, to obtain the geometric model of the forging quenching equipment-medium-forging, and to determine the fluid dynamics analysis model based on the geometric model of the forging quenching equipment-medium-forging.

[0043] The first medium velocity generation module is used to perform flow field analysis on the velocity sample data according to the fluid dynamics analysis model to obtain the first medium velocity; the first medium velocity is the medium velocity of all grid nodes on the surface of the fluid dynamics analysis model;

[0044] The response relationship determination module is used to determine the surrogate model based on the radial basis function, and to obtain the response relationship between the stirring parameters of the quenching tank and the medium flow rate according to the first medium flow rate and the surrogate model.

[0045] The solid interpolation model determination module is used to model the forging to obtain a solid model, and interpolate the first medium flow velocity into the mesh nodes on the surface of the solid model to obtain a solid interpolation model;

[0046] The first heat transfer coefficient generation module is used to determine the first heat transfer coefficient based on the solid interpolation model and a set proportional relationship; the set proportional relationship is the ratio between the medium flow rate and the heat transfer coefficient of the forging surface; the first heat transfer coefficient is the heat transfer coefficient at different grid nodes on the surface of the solid interpolation model.

[0047] The temperature field calculation model determination module is used to calculate the temperature data of all grid nodes on the surface of the solid model at different times based on the first heat transfer coefficient and the solid model, and obtain the first temperature data by using the temperature field calculation equation; perform intrinsic orthogonal decomposition on the first temperature data, and perform order reduction calculation on the temperature field calculation equation to obtain the temperature field calculation model;

[0048] The second temperature data generation module is used to calculate the temperature data of all grid nodes on the surface of the solid model at different times based on the first heat transfer coefficient and the solid model, and to obtain the second temperature data.

[0049] The microstructure content determination module is used to determine the microstructure field calculation model based on the Avrami equation and the KM equation, and to obtain the pearlite content, bainite content and martensite content of the forging during the cooling process based on the second temperature data and the microstructure field calculation model.

[0050] Optionally, the fluid dynamics analysis model determination module specifically includes:

[0051] The mesh generation module is used to perform mesh generation on the geometric model of the forging quenching equipment-medium-forging.

[0052] The model setting module is used to set the material parameters and first boundary conditions of the geometric model of the forging quenching equipment-medium-forging after meshing, so as to obtain the fluid dynamics analysis model; the material parameters include the density, viscosity, thermal conductivity and specific heat capacity of the medium; the first boundary condition is determined according to the propeller speed or nozzle spray speed.

[0053] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the online prediction method for forging quenching equipment described in the first aspect.

[0054] Fourthly, the present invention provides a computer-readable storage medium, characterized in that it stores a computer program, which, when executed by a processor, implements the online prediction method for forging quenching equipment as described in the first aspect.

[0055] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0056] The proxy model in this invention uses radial basis functions to establish the response relationship between the stirring parameters of the quenching tank and the medium flow rate, avoiding complex and time-consuming flow field calculations. The temperature field calculation model performs order reduction processing for large-scale finite element calculations, significantly reducing the solution scale of the partial differential equation system and greatly improving the efficiency of transient field solutions while maintaining high solution accuracy. Using these two models, the coupled solution operations of the flow field, temperature field, and microstructure field, which take hours to complete, can be compressed to the second level. Simultaneously, the medium flow rate is obtained through the fluid dynamics analysis model, the forging temperature data is obtained through the temperature field calculation model, and the microstructure content of pearlite, bainite, and martensite is obtained through the microstructure field calculation model, reflecting in real time the dynamic changes of the medium flow rate, forging temperature, and microstructure within the quenching tank. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A flowchart of the online prediction method for forging quenching equipment provided in an embodiment of the present invention;

[0059] Figure 2 This is a structural diagram of the online prediction system for forging quenching equipment provided in an embodiment of the present invention;

[0060] Figure 3 This is a modeling diagram of the forging quenching equipment provided in an embodiment of the present invention;

[0061] Figure 4 This is a bottom cross-sectional view of the quenching tank provided in an embodiment of the present invention;

[0062] Figure 5 A solid model diagram based on forging provided in an embodiment of the present invention;

[0063] Figure 6 A flow velocity distribution diagram on the workpiece surface provided by the fluid dynamics analysis model in an embodiment of the present invention;

[0064] Figure 7 The flow velocity distribution diagram on the surface of the workpiece after interpolation of the solid model provided in the embodiment of the present invention.

[0065] Symbol explanation:

[0066] Quenching tank-1, lifting tool-2, lower end forging-3, agitator-4, base plate-5. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0068] The purpose of this invention is to provide an online prediction method, system, equipment and medium for forging quenching equipment. By changing the model structure, the system's computing speed is improved, thereby enabling real-time reflection of the dynamic changes in medium flow rate, forging temperature and microstructure within the quenching tank.

[0069] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0070] Example 1

[0071] This embodiment provides an online prediction method for forging quenching equipment, such as... Figure 1 As shown, it includes:

[0072] Step 100: Obtain rate sample data. The rate sample data refers to either propeller rate or nozzle injection rate.

[0073] In one example, a single propeller or nozzle can be used as a rate sample variable, or multiple propellers or nozzles can be grouped together as a rate sample variable. The Latin hypercube algorithm is used to design rate samples, ensuring that the number of designed rate samples is greater than 10*N (where N is the number of rate sample variables).

[0074] Step 200: Model the system consisting of forging quenching equipment, medium and forging to obtain the geometric model of forging quenching equipment-medium-forging, and determine the fluid dynamics analysis model based on the geometric model of forging quenching equipment-medium-forging.

[0075] In one example, 3D CAD software is used to model a system consisting of forging quenching equipment, media, and forgings.

[0076] In this embodiment, the fluid dynamics analysis model is determined based on the geometric model of the forging quenching equipment-medium-forging, specifically including:

[0077] Step 201: Mesh the geometric model of the forging quenching equipment-medium-forging.

[0078] Step 202: Set the material parameters and first boundary conditions for the meshed forging quenching equipment-medium-forging geometry model to obtain the fluid dynamics analysis model. The material parameters include the density, viscosity, thermal conductivity, and specific heat capacity of the medium. The first boundary condition is determined based on the propeller speed or nozzle velocity.

[0079] Step 300: Perform flow field analysis on the velocity sample data based on the fluid dynamics analysis model to obtain the first medium velocity. The first medium velocity is the medium velocity at all grid nodes on the surface of the fluid dynamics analysis model.

[0080] In this embodiment, step 300 specifically includes:

[0081] Step 301: Change the propeller speed or nozzle velocity in the fluid dynamics analysis model according to the rate sample data.

[0082] Step 302: Perform fluid dynamics simulation on the fluid dynamics analysis model after changing the propeller speed or nozzle speed to obtain the first medium flow velocity.

[0083] In one example, flow field simulation is performed using software such as Fluent and Flow3D.

[0084] Step 400: Determine the surrogate model based on the radial basis function, and obtain the response relationship between the stirring parameters of the quenching tank and the medium flow rate according to the first medium flow rate and the surrogate model.

[0085] Specifically, the proxy model is as follows:

[0086]

[0087] In the formula, x new For the prediction point, Let n be the first medium velocity at the prediction point, n be the number of samples, and ω be the velocity. i Let r represent the response relationship between the stirring parameters of the quenching tank and the medium flow rate corresponding to the i-th sample point. i Let Euclidean distance be the predicted point and the i-th sample point. These are radial basis functions.

[0088] The formula for calculating the Euclidean distance between the predicted point and the i-th sample point is:

[0089] r i =||x new -x i || 2 ;

[0090] In the formula, x i Let be the i-th sample point. The radial basis function is:

[0091]

[0092] In the formula, σ is the shape factor.

[0093] Step 500: Model the forging to obtain a solid model, and interpolate the first medium flow velocity into the mesh nodes on the surface of the solid model to obtain a solid interpolation model.

[0094] In one example, a 3D CAD software is used to model the forging, and a finite element spatial interpolation method is used to interpolate the first medium velocity into the mesh nodes on the surface of the solid model.

[0095] Step 600: Determine the first heat transfer coefficient based on the solid interpolation model and the set proportional relationship. The set proportional relationship is the ratio between the medium flow rate and the heat transfer coefficient of the forging surface, and the first heat transfer coefficient is the heat transfer coefficient at different grid nodes on the surface of the solid interpolation model.

[0096] In one example, the proportional relationship between the medium flow velocity and the heat transfer coefficient of the forging surface can be obtained through literature review or experimental methods. For instance, the experimental method involves collecting the heat transfer coefficients of the forging surface at different medium flow velocities, and then using a linear regression equation to linearly fit the different medium flow velocities and their corresponding heat transfer coefficients. The coefficients of the linearly fitted equation are then obtained, and the proportional relationship between the medium flow velocity and the heat transfer coefficient of the forging surface can be determined. Once the medium flow velocity is known, the heat transfer coefficient of the forging surface can be quickly determined using this proportional relationship.

[0097] Step 700: Based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times is calculated using the temperature field calculation equation to obtain the first temperature data. The first temperature data is then subjected to intrinsic orthogonal decomposition, and the temperature field calculation equation is reduced in order to obtain the temperature field calculation model.

[0098] Specifically, the equation for calculating the temperature field is:

[0099]

[0100] In the formula, T *Here is the first temperature data, and k is the thermal conductivity of the forging. Here, t is the Laplace operator, Q is the internal heat source, ρ is the density of the forging, and c is the internal heat source. p This refers to the specific heat capacity of the forging.

[0101] Further, a temperature snapshot matrix A is established based on the acquired first temperature data. Each row of the temperature snapshot matrix A contains the temperature values ​​of a certain grid node at all times, and each column contains the temperature values ​​of all grid nodes at a certain time. Then, the established temperature snapshot matrix A needs to be subjected to eigenvalue orthogonal decomposition and valence reduction calculation. The results of the eigenvalue orthogonal decomposition and valence reduction calculation are used to optimize and train the temperature field calculation equation, resulting in a temperature field calculation model.

[0102] Step 800: Based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times is calculated using the temperature field calculation model to obtain the second temperature data.

[0103] In this embodiment, step 800 specifically includes:

[0104] Step 801: Set the material parameters and second boundary conditions for the solid model. The material parameters include the density, viscosity, thermal conductivity, and specific heat capacity of the medium. The second boundary conditions are determined based on the first heat transfer coefficient.

[0105] Step 802: Based on the first heat transfer coefficient and the set solid model, use the temperature field calculation model to calculate the temperature data of all grid nodes on the surface of the solid model at different times, and obtain the second temperature data.

[0106] The temperature field calculation model is as follows:

[0107]

[0108] In the formula, T represents the second temperature data.

[0109] Step 900: Determine the microstructure field calculation model based on the Avrami equation and the KM equation, and obtain the pearlite content, bainite content and martensite content during the cooling process of the forging based on the second temperature data and the microstructure field calculation model.

[0110] The tissue field calculation model specifically includes: the first Avrami equation, the second Avrami equation, and the KM equation. The first Avrami equation is:

[0111]

[0112] In the formula, f1 is the pearlite content, b1 is the first transformation kinetic parameter of pearlite, t is the cooling time, and t sDuring the incubation period, n1 is the kinetic parameter of the second transformation of pearlite.

[0113] The second Avrami equation is:

[0114]

[0115] In the formula, f2 is the bainite content, b2 is the first transformation kinetic parameter of bainite, and n2 is the second transformation kinetic parameter of bainite.

[0116] The KM equation is:

[0117] f3=1-exp(-a(M s -T));

[0118] In the formula, f3 is the martensite content, a is the martensite transformation kinetic parameter, and M... s T represents the temperature at which the martensitic transformation begins, and T is the second temperature data.

[0119] Furthermore, the first transformation kinetic parameters of pearlite, bainite, and martensite can all be determined according to the first calculation formula for transformation kinetic parameters. The first calculation formula for transformation kinetic parameters is as follows:

[0120]

[0121] In the formula, b is the first transformation kinetic parameter, f1 is the first transformation variable in the Time Temperature Transformation (TTT) curve of supercooled austenite, t1 is the isothermal time corresponding to the first transformation variable in the TTT curve, and t s，1 n represents the gestation period corresponding to the first transition variable in the TTT curve. * This is the second transformation kinetic parameter.

[0122] The second transformation kinetic parameters of pearlite and bainite can both be determined using the second calculation formula for transformation kinetic parameters. The second calculation formula for transformation kinetic parameters is as follows:

[0123]

[0124] In the formula, f2 is the second transition variable in the TTT curve, t2 is the isothermal time corresponding to the second transition variable in the TTT curve, and t s，2 This represents the gestation period corresponding to the second transition variable in the TTT curve.

[0125] This embodiment can realize real-time simulation and prediction of medium flow rate, forging temperature and microstructure in quenching tank by collecting stirring parameters in real time, and visualize the calculation results of medium flow rate and heat transfer coefficient of forging surface.

[0126] Example 2

[0127] To implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, this embodiment provides an online prediction system for forging quenching equipment, such as... Figure 2 As shown, it includes:

[0128] The sample data acquisition module 31 is used to acquire rate sample data; the rate sample data is the propeller rate or the nozzle injection rate.

[0129] The fluid dynamics analysis model determination module 32 is used to model the system consisting of forging quenching equipment, medium and forging, to obtain the geometric model of forging quenching equipment-medium-forging, and to determine the fluid dynamics analysis model based on the geometric model of forging quenching equipment-medium-forging.

[0130] The first medium velocity generation module 33 is used to perform flow field analysis on the velocity sample data according to the fluid dynamics analysis model to obtain the first medium velocity; the first medium velocity is the medium velocity of all grid nodes on the surface of the fluid dynamics analysis model.

[0131] The response relationship determination module 34 is used to determine the surrogate model based on the radial basis function, and to obtain the response relationship between the stirring parameters of the quenching tank and the medium flow rate according to the first medium flow rate and the surrogate model.

[0132] The solid interpolation model determination module 35 is used to model the forging to obtain a solid model, and interpolate the first medium flow velocity into the mesh nodes on the surface of the solid model to obtain the solid interpolation model.

[0133] The first heat transfer coefficient generation module 36 is used to determine the first heat transfer coefficient based on the solid interpolation model and the set proportional relationship; the set proportional relationship is the proportional relationship between the medium flow rate and the heat transfer coefficient of the forging surface; the first heat transfer coefficient is the heat transfer coefficient at different grid nodes on the surface of the solid interpolation model.

[0134] The temperature field calculation model determination module 37 is used to calculate the temperature data of all grid nodes on the surface of the solid model at different times based on the first heat transfer coefficient and the solid model, and to obtain the first temperature data; to perform intrinsic orthogonal decomposition on the first temperature data, and to perform order reduction calculation on the temperature field calculation equation to obtain the temperature field calculation model.

[0135] The second temperature data generation module 38 is used to calculate the temperature data of all grid nodes on the surface of the solid model at different times based on the first heat transfer coefficient and the solid model, using a temperature field calculation model, to obtain the second temperature data.

[0136] The microstructure content determination module 39 is used to determine the microstructure field calculation model based on the Avrami equation and the KM equation, and to obtain the pearlite, bainite and martensite content during the cooling process of the forging based on the second temperature data and the microstructure field calculation model.

[0137] In this embodiment, the fluid dynamics analysis model determination module 32 specifically includes:

[0138] Mesh generation module 321 is used to perform mesh generation on the geometric model of forging quenching equipment-medium-forging.

[0139] The model setting module 322 is used to set the material parameters and first boundary conditions of the geometric model of the forging quenching equipment-medium-forging after meshing, so as to obtain the fluid dynamics analysis model. The material parameters include the density, viscosity, thermal conductivity and specific heat capacity of the medium. The first boundary condition is determined according to the propeller speed or nozzle spray speed.

[0140] Example 3

[0141] This embodiment provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to execute the online prediction method for forging quenching equipment of Embodiment 1.

[0142] Alternatively, the aforementioned electronic device may be a server.

[0143] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the online prediction method for forging quenching equipment of Embodiment 1.

[0144] Example 4

[0145] This embodiment provides a practical application scenario for an online prediction method for forging quenching equipment, specifically including:

[0146] The lower head forging 3 is heated and then subjected to the following process: Figure 3 The forging quenching equipment shown is used for water quenching. The forging quenching equipment includes: a quenching tank 1, a lifting device 2, a lower end forging 3, a stirrer 4, and a base plate 5. (Example) Figure 4As shown, 13 agitators 4 are installed at the bottom of the quenching tank 1. The agitators 4 are divided into four groups: the first group is the one in the middle, the second group is the four agitators 4 in the middle ring, the third group is the four agitators 4 distributed on the outermost dotted line, and the fourth group is the remaining four agitators 4 in the outermost ring. The four groups of agitators 4 are controlled by a group to control the rotation speed, with a maximum speed of 600 r / min.

[0147] Step 41: Model the system consisting of the quenching equipment for the lower head forging, the medium, and the forging. Establish a fluid dynamics analysis model and conduct flow field analysis to obtain the medium velocity. Then, establish proxy models between four sets of agitator speed and medium velocity.

[0148] Step 411: Consider the stirring rate of the 4 sets of stirrers 4 as four design variables. The value range of each design variable is 0-600 r / min. Then the number of design variables is 4. Based on the Latin hypercube algorithm, design 50 design samples. Each sample is a combination of the four design variables.

[0149] Step 412: Use Fluent software to create... Figure 4 The system shown consists of a 3D geometric model of the quenching equipment, medium, and forging of the lower end forging. The model is divided into tetrahedral meshes to obtain a fluid dynamics analysis model. Data such as density, viscosity, thermal conductivity, and specific heat of the cooling water in the quenching tank are input, and the quenching equipment and forging are set as rigid bodies.

[0150] Step 413: Based on the 50 design samples in Step 411, set different agitator speeds in the fluid dynamics analysis model in Step 412, and then conduct flow field analysis to obtain the flow velocity values ​​at all nodes.

[0151] Step 415: Based on the results of step 413, a proxy model between the stirring parameters of the quenching tank and the medium flow rate is established using a radial basis function model to achieve rapid response calculation of the bottom propeller stirring rate and the medium flow rate.

[0152] Step 42: Establish the solid model required for temperature field-microstructure field analysis of the lower head forging. Use the finite element spatial interpolation method to interpolate the flow velocity data in the fluid dynamics analysis model into the mesh of the solid model. Based on the correspondence between the medium flow velocity and the heat transfer coefficient of the forging surface, calculate the heat transfer coefficient at different locations on the forging surface.

[0153] Step 421: Use CAD software to create a three-dimensional geometric model of the forging and perform hexahedral mesh generation to obtain the following... Figure 5 The solid model required for temperature field-tissue field analysis is shown.

[0154] Step 422: Using the finite element spatial interpolation method, the flow velocity values ​​on the surface nodes of all design samples obtained in step 413 are interpolated to the nodes on the surface of the solid model. Figure 6 The workpiece surface flow velocity is given for four sets of fluid dynamic analysis models at rotational speeds of 300, 150, 300, and 0 r / min. Figure 7 The surface velocity of the workpiece after interpolation of the solid model.

[0155] Step 423: Refer to the literature "Numerical Simulation and Experimental Study on Heat Transfer of Water at Different Flow Rates and the Heat Transfer Relationship between Flow Rates" to obtain the heat transfer coefficient of water at different flow rates. Based on the heat transfer relationship, calculate the heat transfer coefficient at different nodes on the surface of the solid model.

[0156] Step 43: Establish a temperature field-microstructure field calculation model for the forging during the cooling process.

[0157] Step 431: Set the material parameters of the solid model to 5083 steel, set the boundary conditions of the solid model to the surface heat transfer coefficient of water, simulate the water cooling process of the solid model, and obtain the temperature data of all nodes on the surface of the solid model at different times.

[0158] Step 432: Based on the temperature data obtained in Step 431, construct a snapshot matrix A for the model. Each row of this matrix represents the temperature value of a node at all times, and each column represents the temperature value of all nodes at a certain time. Perform eigenorthogonal decomposition on A and establish a temperature field calculation model.

[0159] Step 433: Based on the temperature value calculated in Step 432, a microstructure field calculation model is established using the Avrami equation and the KM equation to calculate the content of pearlite, bainite, and martensite in the cooling process.

[0160] Finally, the above model was deployed in a large forging quenching equipment. By real-time acquisition of the bottom propeller rotation speed, the flow rate of the medium in the quenching tank, the temperature of the forging, and the microstructure were predicted rapidly in real time. Abnormal stirring devices were visually alerted, and their impact on the cooling rate and microstructure was determined. This method can acquire the stirring parameters of the quenching tank in real time and perform real-time simulation and prediction of the medium flow field, temperature field, and microstructure field of the forging quenching equipment. Compared with traditional finite element numerical simulation, this method has a faster calculation speed and can achieve real-time online simulation and prediction of the flow field, temperature field, and microstructure field.

[0161] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0162] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An online prediction method for forging quenching equipment, characterized in that, The forging quenching equipment includes at least a quenching tank and a lifting device. The quenching tank contains a medium, and the forging is fixed on the lifting device. A propeller or nozzle is provided at the bottom of the quenching tank. The online prediction method includes: Acquire velocity sample data; the velocity sample data is the propeller velocity or the nozzle injection velocity. A system consisting of the forging quenching equipment, the medium, and the forging is modeled to obtain a geometric model of the forging quenching equipment-medium-forging, and a fluid dynamics analysis model is determined based on the geometric model of the forging quenching equipment-medium-forging. The flow field is analyzed based on the velocity sample data according to the fluid dynamics analysis model to obtain the first medium velocity; the first medium velocity is the medium velocity of all grid nodes on the surface of the fluid dynamics analysis model; The surrogate model is determined based on the radial basis function, and the response relationship between the stirring parameters of the quenching tank and the medium flow rate is obtained according to the first medium flow rate and the surrogate model. A solid model is obtained by modeling the forging, and the first medium flow velocity is interpolated into the mesh nodes on the surface of the solid model to obtain a solid interpolation model; The first heat transfer coefficient is determined based on the solid interpolation model and the set proportional relationship; the set proportional relationship is the ratio between the medium flow rate and the heat transfer coefficient of the forging surface; the first heat transfer coefficient is the heat transfer coefficient at different grid nodes on the surface of the solid interpolation model. Based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times are calculated using the temperature field calculation equation to obtain the first temperature data; the first temperature data is subjected to intrinsic orthogonal decomposition, and the temperature field calculation equation is subjected to order reduction calculation to obtain the temperature field calculation model; Based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times are calculated using the temperature field calculation model to obtain the second temperature data. The microstructure field calculation model is determined based on the Avrami equation and the KM equation, and the pearlite content, bainite content and martensite content of the forging during the cooling process are obtained based on the second temperature data and the microstructure field calculation model.

2. The online prediction method for forging quenching equipment according to claim 1, characterized in that, The fluid dynamics analysis model is determined based on the geometric model of the forging quenching equipment-medium-forging, specifically including: Mesh the geometric model of the forging quenching equipment-medium-forging; By setting the material parameters and first boundary conditions of the geometric model of the forging quenching equipment-medium-forging after mesh generation, a fluid dynamics analysis model is obtained; the material parameters include the density, viscosity, thermal conductivity and specific heat capacity of the medium; the first boundary condition is determined based on the propeller speed or nozzle velocity.

3. The online prediction method for forging quenching equipment according to claim 2, characterized in that, Based on the fluid dynamics analysis model, flow field analysis is performed on the velocity sample data to obtain the first medium velocity, specifically including: The propeller speed or nozzle velocity in the fluid dynamics analysis model is changed according to the rate sample data. Fluid dynamics simulation was performed on the fluid dynamics analysis model after changing the propeller speed or nozzle velocity to obtain the first medium velocity.

4. The online prediction method for forging quenching equipment according to claim 1, characterized in that, The proxy model is as follows: ； In the formula, For the prediction point, The first medium velocity at the prediction point, For the sample size, For the first i The response relationship between the stirring parameters of the quenching tank and the flow rate of the medium at each sample point. For the prediction point and the first i Euclidean distance between sample points These are radial basis functions.

5. The online prediction method for forging quenching equipment according to claim 1, characterized in that, Based on the first heat transfer coefficient and the solid model, the temperature data of all grid nodes on the surface of the solid model at different times is calculated using the temperature field calculation model to obtain the second temperature data, which specifically includes: The material parameters and second boundary conditions of the solid model are set; the material parameters include the density, viscosity, thermal conductivity and specific heat capacity of the medium; the second boundary conditions are determined based on the first heat transfer coefficient. Based on the first heat transfer coefficient and the configured solid model, the temperature data of all grid nodes on the surface of the solid model at different times are calculated using the temperature field calculation model to obtain the second temperature data; the temperature field calculation model is as follows: ； In the formula, This is the second temperature data. For the thermal conductivity of the forging, Cooling time, As an internal heat source, For the density of the forging, This refers to the specific heat capacity of the forging.

6. The online prediction method for forging quenching equipment according to claim 1, characterized in that, The tissue field calculation model specifically includes: the first Avrami equation, the second Avrami equation, and the KM equation; The first Avrami equation is: ； In the formula, Pearlite content, These are the kinetic parameters for the first transformation of pearlite. Cooling time, During the gestation period, These are the kinetic parameters for the second transformation of pearlite; The second Avrami equation is: ； In the formula, Bainite content, These are the kinetic parameters for the first transformation of bainite. These are the kinetic parameters for the second transformation of bainite; The KM equation is: ； In the formula, Martensite content, These are the kinetic parameters for martensitic transformation. This is the temperature at which the martensitic transformation begins. This is the second temperature data.

7. An online prediction system for forging quenching equipment, characterized in that, The system includes: The sample data acquisition module is used to acquire velocity sample data; the velocity sample data is the propeller velocity or the nozzle injection velocity. The fluid dynamics analysis model determination module is used to model the system consisting of forging quenching equipment, medium and forging, to obtain the geometric model of forging quenching equipment-medium-forging, and to determine the fluid dynamics analysis model based on the geometric model of forging quenching equipment-medium-forging. The first medium velocity generation module is used to perform flow field analysis on the velocity sample data according to the fluid dynamics analysis model to obtain the first medium velocity; the first medium velocity is the medium velocity of all grid nodes on the surface of the fluid dynamics analysis model; The response relationship determination module is used to determine the surrogate model based on the radial basis function, and to obtain the response relationship between the stirring parameters of the quenching tank and the medium flow rate according to the first medium flow rate and the surrogate model. The solid interpolation model determination module is used to model the forging to obtain a solid model, and interpolate the first medium flow velocity into the mesh nodes on the surface of the solid model to obtain a solid interpolation model; The first heat transfer coefficient generation module is used to determine the first heat transfer coefficient based on the solid interpolation model and a set proportional relationship; the set proportional relationship is the ratio between the medium flow rate and the heat transfer coefficient of the forging surface; the first heat transfer coefficient is the heat transfer coefficient at different grid nodes on the surface of the solid interpolation model. The temperature field calculation model determination module is used to calculate the temperature data of all grid nodes on the surface of the solid model at different times based on the first heat transfer coefficient and the solid model, and obtain the first temperature data by using the temperature field calculation equation; perform intrinsic orthogonal decomposition on the first temperature data, and perform order reduction calculation on the temperature field calculation equation to obtain the temperature field calculation model; The second temperature data generation module is used to calculate the temperature data of all grid nodes on the surface of the solid model at different times based on the first heat transfer coefficient and the solid model, and to obtain the second temperature data. The microstructure content determination module is used to determine the microstructure field calculation model based on the Avrami equation and the KM equation, and to obtain the pearlite content, bainite content and martensite content of the forging during the cooling process based on the second temperature data and the microstructure field calculation model.

8. The online prediction system for forging quenching equipment according to claim 7, characterized in that, The fluid dynamics analysis model determination module specifically includes: The mesh generation module is used to perform mesh generation on the geometric model of the forging quenching equipment-medium-forging. The model setting module is used to set the material parameters and first boundary conditions of the geometric model of the forging quenching equipment-medium-forging after meshing, so as to obtain the fluid dynamics analysis model; the material parameters include the density, viscosity, thermal conductivity and specific heat capacity of the medium; the first boundary condition is determined according to the propeller speed or nozzle spray speed.

9. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the online prediction method for forging quenching equipment as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the online prediction method for forging quenching equipment as described in any one of claims 1 to 6.

Images