A Heat Treatment Parameter Optimization Method and System Driven by the Performance Requirements of a Flow Guide Shell

Abstract

The present invention relates to a method and system for optimizing heat treatment parameters driven by the performance requirements of a flow guide shell, which relates to the field of data processing. By inputting the CAD model of the target flow guide shell and performing heat dissipation simulation, after outputting simulation data, multiple heat dissipation characteristic regions are obtained through differential partitioning, heat conduction equations for each region are constructed, differential heat dissipation indexes are predicted based on initial heat treatment parameters, and then a tuning model is established to adjust the parameters. Finally, multiple sets of optimal solutions are output and applied to differential heat treatment, effectively solving the problem of uneven heat dissipation caused by structural differences of the flow guide shell, improving the uniformity and controllability of the heat treatment process, and thus enhancing the forming quality of the flow guide shell.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and particularly to a method and system for optimizing heat treatment parameters driven by the performance requirements of a diversion shell. Background Art

[0002] In the manufacturing field, especially in the production process of parts with complex shapes and high-precision requirements, heat treatment, as one of the key processes, plays a crucial role in the performance and quality of the final product. As a core component widely used in high-end equipment fields such as aviation, aerospace, and automotive engines, the performance of the diversion shell directly affects the operating efficiency and reliability of the entire system.

[0003] However, the existing heat treatment processes often adopt an overall treatment method, that is, the same heat treatment parameters are used for all parts in the same batch. This method can achieve good results when treating parts with simple structures and uniform heat dissipation, but when treating parts with complex structures and uneven heat dissipation such as the diversion shell, obvious limitations are exposed. Due to its special structural form, there are significant differences in the heat dissipation of different parts of the diversion shell. For example, the ventilation is less and the heat dissipation effect is poor in the place where the ring opening is narrow compared to the place where the ring opening is large, resulting in obvious differences in the thermal responses of different parts under the action of the same heat treatment parameters. This difference not only affects the uniformity and controllability of the heat treatment process but also may cause defects such as deformation and cracks in the parts after heat treatment, thereby reducing their forming quality and overall performance. Summary of the Invention

[0004] Aiming at the technical problem in the prior art that the uneven heat dissipation caused by the structural differences of the diversion shell leads to inconsistent thermal responses in the overall heat treatment process and affects the forming quality, the present invention provides a method and system for optimizing heat treatment parameters driven by the performance requirements of the diversion shell to solve this problem.

[0005] The technical solutions of the present invention to solve the above technical problems are as follows:

[0006] In a first aspect, the present invention provides a method for optimizing heat treatment parameters driven by the performance requirements of a flow guide shell, the method comprising: inputting a CAD model of a target flow guide shell, performing a heat dissipation simulation on the CAD model of the target flow guide shell, and outputting heat dissipation simulation data; performing differential partitioning on the heat dissipation simulation data to obtain a plurality of heat dissipation characteristic regions, constructing a heat conduction equation for each heat dissipation characteristic region, and outputting a plurality of regional heat conduction equations; obtaining initial heat treatment parameters, including heating time, cooling method, and cooling rate; predicting differential heat dissipation indexes between the plurality of heat dissipation characteristic regions under the initial heat treatment parameters based on the plurality of regional heat conduction equations; establishing a heat treatment parameter optimization model for the target according to the differential heat dissipation indexes, adjusting the initial heat treatment parameters, and outputting multiple optimal solutions of heat treatment parameters; and performing differential heat treatment on the target flow guide shell according to the multiple optimal solutions of heat treatment parameters.

[0007] In a second aspect, the present invention provides a system for optimizing heat treatment parameters driven by the performance requirements of a flow guide shell, the system comprising: a heat dissipation simulation module, configured to input a CAD model of a target flow guide shell, perform a heat dissipation simulation on the CAD model of the target flow guide shell, and output heat dissipation simulation data; a differential partitioning module, configured to perform differential partitioning on the heat dissipation simulation data to obtain a plurality of heat dissipation characteristic regions, construct a heat conduction equation for each heat dissipation characteristic region, and output a plurality of regional heat conduction equations; a parameter acquisition module, configured to obtain initial heat treatment parameters, including heating time, cooling method, and cooling rate; an index prediction module, configured to predict differential heat dissipation indexes between the plurality of heat dissipation characteristic regions under the initial heat treatment parameters based on the plurality of regional heat conduction equations; a parameter adjustment module, configured to establish a heat treatment parameter optimization model for the target according to the differential heat dissipation indexes, adjust the initial heat treatment parameters, and output multiple optimal solutions of heat treatment parameters; and a heat treatment module, configured to perform differential heat treatment on the target flow guide shell according to the multiple optimal solutions of heat treatment parameters.

[0008] The beneficial effects of the present invention are as follows: By inputting the CAD model of the target flow guide shell and performing a heat dissipation simulation, after outputting the simulation data, differential partitioning is performed to obtain a plurality of heat dissipation characteristic regions, heat conduction equations for each region are constructed, differential heat dissipation indexes are predicted based on the initial heat treatment parameters, and then an optimization model is established to adjust the parameters, and finally multiple optimal solutions are output and applied to differential heat treatment, effectively solving the problem of uneven heat dissipation caused by structural differences of the flow guide shell, improving the uniformity and controllability of the heat treatment process, and thus improving the forming quality of the flow guide shell. Description of the Drawings

[0009] Figure 1 It is a schematic flow chart of a method for optimizing heat treatment parameters driven by the performance requirements of a flow guide shell provided by the present invention.

[0010] Figure 2 Schematic diagram of a heat treatment parameter optimization system driven by the performance requirements of a flow guide shell provided by the present invention.

[0011] Explanation of reference numerals: heat dissipation simulation module 11, differential partition module 12, parameter acquisition module 13, index prediction module 14, parameter adjustment module 15, heat treatment module 16. Detailed implementation manners

[0012] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order to enable any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for purposes of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0015] Embodiment 1:

[0016] As Figure 1 shown, the embodiment of the present invention provides a heat treatment parameter optimization method driven by the performance requirements of a flow guide shell, and the method includes:

[0017] S10: Input the CAD model of the target flow guide shell, perform heat dissipation simulation on the CAD model of the target flow guide shell, and output heat dissipation simulation data.

[0018] Exemplarily, a flow guide shell is a component with a complex shape, usually used in high-end equipment fields such as aviation, aerospace, and automotive engines. Its structural design needs to meet specific hydrodynamic requirements. In terms of shape and structure, the flow guide shell may include features such as an orifice, a channel, and a curved surface. The structural differences in different parts result in uneven heat dissipation performance. For example, the part with a narrow orifice has poorer ventilation than the part with a large orifice, and the heat dissipation effect is affected. This structural characteristic of the flow guide shell makes it prone to uneven temperature distribution during the heat treatment process, thereby affecting the final performance.

[0019] Generally, the performance requirements of a flow guide shell mainly include thermal stability, mechanical strength, hydrodynamic performance, and dimensional accuracy. The requirement for thermal stability is that the flow guide shell needs to maintain stable mechanical properties in a high-temperature or temperature-fluctuating environment to avoid deformation or cracks caused by thermal stress; the requirement for mechanical strength is that the flow guide shell needs to have sufficient strength to withstand the pressure and impact under working conditions; the requirement for hydrodynamic performance is that the internal channel design needs to optimize fluid flow, reduce resistance, and improve efficiency; the dimensional accuracy requires that the dimensional tolerances of the key parts of the flow guide shell need to be strictly controlled to ensure the matching with other components.

[0020] The performance requirements of the flow guide shell are closely related to the heat treatment parameters. Therefore, it is necessary to optimize and control its heat treatment parameters. In terms of thermal stability and heating time / cooling rate, too long heating time or too fast cooling rate may lead to coarse grains or residual stress, affecting thermal stability. Therefore, by optimizing the heating time and cooling rate, the grains can be refined and the residual stress can be reduced, improving thermal stability. Moreover, heat treatment parameters such as quenching temperature and tempering temperature directly affect the phase transformation and microstructure of the material, and thus affect the mechanical strength. Therefore, appropriate quenching and tempering treatments can obtain a flow guide shell structure with a combination of high strength and toughness. At the same time, the temperature uniformity during the heat treatment process is crucial for the dimensional accuracy and surface quality of the internal channels of the flow guide shell. If uneven heat dissipation causes local deformation, it may damage the hydrodynamic performance. By adjusting the differential heat treatment parameters, the temperature gradient can be reduced and the heat treatment uniformity can be improved. In addition, the thermal stress during the heat treatment process may cause the flow guide shell to deform, affecting the dimensional accuracy. By optimizing heat treatment parameters such as the cooling method and cooling rate, the thermal stress distribution can be controlled, deformation can be reduced, and the dimensional accuracy requirements can be met.

[0021] The method for optimizing heat treatment parameters driven by the performance requirements of the flow guide shell proposed in this solution is to optimize the parameters differentially based on the structural influence of the flow guide shell. Specifically, first, accurately input the CAD model of the target flow guide shell into a professional simulation software system. The target flow guide shell is the specific object to be analyzed, and its CAD model represents the accurate geometric structure information of the flow guide shell, including key features such as the outer contour and the internal channel layout. During the input process, it is necessary to ensure the integrity and accuracy of the model data to ensure the reliability of subsequent simulation analysis.

[0022] After the model entry is completed, heat dissipation simulation is carried out on the CAD model of the target flow guide shell. The heat dissipation simulation aims to simulate the heat exchange process between the flow guide shell and the surrounding environment under the actual working conditions. By setting reasonable boundary conditions, such as environmental temperature, heat dissipation medium characteristics, etc., and heat source parameters, such as heating power, heat source distribution, etc., numerical calculation methods are used to simulate the heat transfer modes such as conduction, convection and radiation inside the flow guide shell. For example, if the target flow guide shell is applied to the heat dissipation system of an electronic device, the heat source parameters need to be set according to the heat generation situation of the device during actual operation, and the boundary conditions need to be set considering the temperature conditions of the environment where the device is located.

[0023] Finally, after a series of complex calculations and analyses, heat dissipation simulation data is output. These data cover key indicators such as the surface temperature distribution of the flow guide shell, the internal temperature gradient, and the heat dissipation efficiency, providing a scientific basis for evaluating the heat dissipation performance of the flow guide shell and optimizing its structural design.

[0024] S20: Differentially partition the heat dissipation simulation data to obtain multiple heat dissipation characteristic regions, construct heat conduction equations for each heat dissipation characteristic region, and output multiple regional heat conduction equations.

[0025] Furthermore, differential partitioning operations are carried out on the obtained heat dissipation simulation data. Among them, differential partitioning divides the target flow guide shell into multiple regions with unique heat dissipation characteristics according to key parameters such as the temperature distribution characteristics and heat flux density differences reflected by the heat dissipation simulation data. These regions are the heat dissipation characteristic regions, and each heat dissipation characteristic region shows significant differences in heat dissipation behavior. For example, some regions may have higher temperatures and concentrated heat fluxes due to being close to the heat source, while other regions may have relatively lower temperatures and dispersed heat fluxes due to being at the end of the heat dissipation path. Taking the flow guide shell of an electronic device as an example, its heat dissipation simulation data may show that the temperature at the contact part between the flow guide shell and the heating chip is significantly higher than other regions. Based on this, this contact part and a certain range around it can be divided into a high heat dissipation characteristic region, while the regions with lower temperatures such as the edge of the flow guide shell are divided into low heat dissipation characteristic regions.

[0026] After the partition is completed, a heat conduction equation is constructed for each heat dissipation characteristic region. The heat conduction equation is a mathematical expression that describes the law of heat conduction within an object. When constructing it, factors such as the material properties (such as thermal conductivity) of each heat dissipation characteristic region, geometric dimensions, and boundary conditions (such as the heat exchange situation with the surrounding environment) need to be comprehensively considered. For example, for a high heat dissipation characteristic region, due to its high temperature and concentrated heat flow, when constructing the heat conduction equation, the high thermal conductivity characteristics of the material in this region and the boundary condition of close contact with the heat source need to be accurately considered; while for a low heat dissipation characteristic region, attention should be paid to its relatively low thermal conductivity and the natural convection heat dissipation boundary condition with the surrounding environment. Finally, multiple regional heat conduction equations are output, which provide a mathematical basis for further analyzing the heat dissipation mechanism of each heat dissipation characteristic region and optimizing the heat dissipation design of the diversion shell.

[0027] S30: Obtain initial heat treatment parameters, including heating time, cooling method, and cooling rate.

[0028] Next, it is necessary to obtain the initial heat treatment parameters, which are the key factors determining the heat treatment effect and material properties, mainly including heating time, cooling method, and cooling rate.

[0029] Among them, the heating time refers to the duration during which the material to be treated is heated from the initial temperature to the specified heat treatment temperature. It is affected by various factors such as the material type, size specifications, and target heat treatment effect. For example, for large metal castings, due to their large volume and high heat capacity, compared with small metal parts, a longer heating time is required to ensure that the temperature inside the material evenly reaches the heat treatment required temperature to avoid heat treatment defects caused by uneven temperature.

[0030] The cooling method refers to the specific method used for the material to be cooled after heating. Common cooling methods include air cooling, oil cooling, water cooling, etc. Different cooling methods have different cooling characteristics and are suitable for different materials and heat treatment purposes. For example, for some high-alloy steels, to prevent cracks from occurring during quenching, oil cooling is often used because its cooling rate is relatively slow, which can effectively reduce the thermal stress inside the material; while for some carbon steel parts with extremely high hardness requirements and not prone to cracking, water cooling may be selected to achieve rapid cooling to obtain a high-hardness structure.

[0031] The cooling rate represents the speed at which the temperature of the material drops during the cooling process. It is closely related to the cooling method and is also affected by factors such as the temperature of the cooling medium and the surface state of the material. For example, when using water cooling, if the temperature of the cooling water is low and the water flow rate is fast, the cooling rate of the material will be significantly accelerated; while if there are impurities such as scale on the surface of the material, it may hinder heat transfer and result in an actual cooling rate lower than the theoretical value.

[0032] Obtaining accurate initial heat treatment parameters is an important prerequisite for formulating a reasonable heat treatment process and ensuring that the material obtains ideal performance.

[0033] S40: Predicting differential heat dissipation indicators between the plurality of heat dissipation characteristic zones under the initial heat treatment parameters based on the plurality of regional heat conduction equations.

[0034] Preferably, in the heat treatment process simulation and performance prediction link, the differential heat dissipation indicators between multiple heat dissipation characteristic areas under the initial heat treatment parameters are predicted based on the constructed multiple regional heat conduction equations. The regional heat conduction equation, as a mathematical model describing the heat conduction law of each heat dissipation characteristic area, covers key information such as the unique material properties, geometric structure and boundary conditions of each area, and is the basis for accurately predicting heat dissipation indicators. Initial heat treatment parameters, such as heating time, cooling method and cooling rate, set specific boundaries and constraints for solving the heat conduction equation. Different parameter combinations will cause the temperature field and heat flow field distribution in each heat dissipation characteristic area to change significantly. The differentiated heat dissipation index is used to quantify the differential characteristics of each heat dissipation characteristic area during the heat dissipation process, such as temperature gradient, heat dissipation rate, etc. These indicators can intuitively reflect the pros and cons of the heat dissipation performance of different areas.

[0035] Taking the guide shell of a mechanical structure as an example, its different heat dissipation characteristic zones vary due to factors such as material thickness and distance from the heat source. Given initial heat treatment parameters, such as a heating time of 30 minutes, air cooling, and a cooling rate set according to material properties, the temperature gradient of each heat dissipation characteristic zone can be predicted by solving the heat conduction equation for each zone. Regions closer to the heat source and with thicker materials may have larger temperature gradients, indicating drastic temperature fluctuations and greater heat dissipation difficulty. In contrast, regions farther from the heat source and with thinner materials have relatively smaller temperature gradients, resulting in more uniform heat dissipation. Regarding heat dissipation rates, some heat dissipation characteristic zones may have higher heat dissipation rates due to the direct effects of the cooling method, while others may have lower heat dissipation rates due to longer heat conduction paths or poorer material thermal conductivity. Predicting these differentiated heat dissipation indicators provides a scientific basis for optimizing heat treatment processes and improving the overall heat dissipation performance of the material.

[0036] S50: Establishing a heat treatment parameter tuning model based on the differentiated heat dissipation index as a target, adjusting the initial heat treatment parameters, and outputting multiple sets of heat treatment parameter optimal solutions.

[0037] Specifically, when optimizing the heat treatment process, based on the predicted differential heat dissipation index, a heat treatment parameter tuning model is constructed for a specific target. The differential heat dissipation index, as a key parameter reflecting the heat dissipation performance differences in each heat dissipation characteristic region, such as temperature gradient, heat dissipation rate, etc., provides a quantitative basis for the construction of the tuning model, and the specific targets include achieving the best overall heat dissipation uniformity of the material, reducing the risk of local overheating to improve the material performance stability, etc.

[0038] The heat treatment parameter tuning model is an intelligent model constructed based on mathematical algorithms and optimization theory. It can comprehensively consider the mutual influence among multiple heat treatment parameters, such as heating time, cooling method, cooling rate, etc., and their complex relationships with the differential heat dissipation index. For example, when the target is to reduce the maximum temperature gradient inside the material, the tuning model will analyze that too long heating time may lead to too high overall temperature of the material, thus increasing the temperature difference between different regions, and too fast cooling rate may cause the temperature in some heat dissipation characteristic regions to drop sharply, exacerbating the temperature gradient; at the same time, different cooling methods also have different effects on the heat dissipation rates of each region.

[0039] Furthermore, based on the relationship analysis between heat treatment parameters and the differential heat dissipation index, the tuning model will perform parameter adjustment operations on the initial heat treatment parameters. By continuously adjusting the parameter combinations, optimization algorithms (such as genetic algorithms, particle swarm algorithms, etc.) are used to search for the optimal solution in the parameter space. During the parameter adjustment process, the model will calculate the differential heat dissipation index of each heat dissipation characteristic region under different parameter combinations in real time and compare and evaluate it with the target.

[0040] After multiple rounds of iterative calculations, multiple sets of optimal solutions of heat treatment parameters are finally output. These optimal solutions are parameter combinations that meet the specific target and perform well in multiple dimensions. The multiple sets of optimal solutions of heat treatment parameters output are used to match the heat dissipation capabilities of different heat dissipation characteristic regions. Regions with strong heat dissipation capabilities are matched with relatively mild treatment conditions, while regions with weak heat dissipation capabilities use stronger cooling or extended time treatment. For example, a set of optimal solutions may be to adjust the heating time to 25 minutes, select oil cooling with a specific ratio as the cooling method, and control the cooling rate within a suitable range on the premise of ensuring that the overall hardness of the material meets the requirements, so that the temperature gradient of each heat dissipation characteristic region of the material is greatly reduced and the heat dissipation uniformity is significantly improved, providing multiple feasible optimization schemes for the actual heat treatment process.

[0041] S60: Perform differential heat treatment on the target guide shell according to the multiple sets of optimal solutions of heat treatment parameters.

[0042] Specifically, based on the obtained optimal solutions of multiple groups of heat treatment parameters, differential heat treatment operations are carried out on the target flow guide shell. The optimal solutions of multiple groups of heat treatment parameters are the results obtained by optimizing the heat treatment parameter optimization model based on differential heat dissipation indexes and specific targets. Each group of parameter optimal solutions includes specific combinations of key parameters such as heating time, cooling method, and cooling rate. These combinations have been proven in simulation analysis to be able to effectively improve the heat dissipation performance of the target flow guide shell, such as reducing the risk of local overheating and improving heat dissipation uniformity.

[0043] Differential heat treatment refers to the targeted heat treatment process of the target flow guide shell according to the characteristics of different parameter optimal solutions. Since there are differences in heating time, cooling method, etc. among different parameter optimal solutions, this will lead to different temperature change curves and tissue transformation conditions of the flow guide shell during the heat treatment process. When implementing the differential heat treatment corresponding to the parameters, it is necessary to precisely control the heating duration of the heating equipment to ensure that the flow guide shell reaches the specified heat treatment temperature within the specified time. In the cooling stage, the heated flow guide shell is quickly immersed in a coolant with a specific ratio to achieve a specific cooling rate, so that the internal tissue of the flow guide shell changes as expected.

[0044] By carrying out differential heat treatment on the target flow guide shell according to multiple groups of heat treatment parameter optimal solutions, heat treatment samples with different heat dissipation performances and tissue characteristics can be obtained, providing rich experimental data and selection basis for subsequent screening of the optimal heat treatment plan and meeting the heat dissipation requirements under different working conditions.

[0045] In a preferred embodiment, a heat dissipation simulation is performed on the CAD model of the target flow guide shell, and heat dissipation simulation data is output, including: performing a structural mesh division on the CAD model of the target flow guide shell to obtain a CAD mesh model; wherein, the CAD model includes the structural parameters and material properties of the target flow guide shell, and the material properties include density, specific heat capacity, and thermal conductivity; configuring heat treatment working condition parameters, and using Ansys to perform a heat conduction simulation on the CAD mesh model under the heat treatment working condition parameters, and outputting heat dissipation simulation data, and the heat dissipation simulation data includes the temperature change curve in each grid area.

[0046] Optionally, during the process of analyzing the heat dissipation performance of the target flow deflector housing, a structural mesh generation operation is first performed on the CAD model of the target flow deflector housing. The CAD model of the target flow deflector housing completely covers two types of key information, namely its structural parameters and material properties. The structural parameters detail geometric features such as the external dimensions and internal channel layout of the flow deflector housing, while the material properties include important physical parameters such as density, specific heat capacity, and thermal conductivity. These parameters have a direct impact on the heat dissipation performance of the flow deflector housing. For example, if the flow deflector housing is made of a metal material with a high thermal conductivity, its heat conduction ability will be significantly better than that of a material with a low thermal conductivity. Structural mesh generation discretizes the CAD model into a series of regular mesh elements for subsequent numerical calculations. The CAD mesh model obtained after the mesh generation operation provides a discretized calculation basis for the subsequent heat conduction simulation.

[0047] Subsequently, the heat treatment condition parameters are configured. These parameters simulate the environmental conditions of the flow deflector housing during actual operation or heat treatment, such as ambient temperature, heat source power, heating time, etc.

[0048] After determining the heat treatment condition parameters, a heat conduction simulation is performed on the CAD mesh model using the professional finite element analysis software Ansys. Ansys can use numerical calculation methods to simulate the heat conduction process inside the flow deflector housing based on the configured condition parameters, as well as the structural parameters and material properties in the CAD mesh model. During the simulation, the software calculates the temperature change in each mesh area in real time and finally outputs the heat dissipation simulation data, which mainly includes the temperature change curve in each mesh area. Among them, the temperature change curve intuitively shows the dynamic temperature change process of the flow deflector housing at different positions and different times, providing key data support for evaluating the heat dissipation performance of the flow deflector housing and discovering potential heat problem areas. For example, by analyzing the temperature change curve, the areas with too high temperature on the flow deflector housing can be determined, and then its structural design or material selection can be optimized accordingly to improve the overall heat dissipation effect.

[0049] In a preferred embodiment, the heat dissipation simulation data is differentially partitioned to obtain multiple heat dissipation characteristic regions, including: statistically analyzing the temperature change characteristics of each mesh area in the heat dissipation simulation data, including the average temperature change rate, the maximum temperature gradient, and the area heat flux; calculating heat dissipation indexes based on the temperature change characteristics, clustering the temperature change characteristics of all mesh areas according to the calculation results of the heat dissipation indexes, and outputting the first clustering result; performing discrete mesh area identification on the first clustering result, and reconstructing the identified discrete mesh areas to output the second clustering result, which is multiple heat dissipation characteristic regions.

[0050] Furthermore, in the heat dissipation performance analysis stage, differentiated partitioning operations are carried out on the obtained heat dissipation simulation data. First, the temperature change characteristics of each grid area in the heat dissipation simulation data are comprehensively statistically analyzed. These characteristics cover key indicators such as the average temperature change rate, the maximum temperature gradient, and the regional area heat flux. Among them, the average temperature change rate reflects the speed of the temperature change of the grid area within a certain period of time. For example, some grid areas close to the heat source may have a higher average temperature change rate due to direct heating; the maximum temperature gradient reflects the unevenness of the temperature distribution in the grid area. At the edge of the guide shell or the internal structure mutation, the maximum temperature gradient may be larger; and the regional area heat flux represents the heat passing through the unit area, which is closely related to factors such as the thermal conductivity of the material and boundary conditions.

[0051] After calculating the temperature variation characteristics, the heat dissipation index is calculated based on these characteristics. The heat dissipation index comprehensively considers the different performance of each grid area during the heat dissipation process, providing a quantitative basis for subsequent cluster analysis. Based on the heat dissipation index calculation results, a clustering algorithm is used to cluster the temperature variation characteristics of all grid areas. The core purpose of clustering is to divide the boundaries of different areas based on the similarity of heat dissipation performance, grouping grid areas with similar heat dissipation characteristics together, and outputting the first clustering result.

[0052] However, the first clustering result may have discrete grid areas. Although these discrete areas have certain similarities in heat dissipation performance, they are relatively scattered in spatial distribution, which is not conducive to subsequent unified analysis and processing. Therefore, the first clustering result is identified as discrete grid areas, and these discrete grid areas are identified through specific algorithms or rules, and then reconstructed. The reconstruction process aims to integrate discrete grid areas into continuous areas, making them more reasonable in space, and finally output the second clustering result, which is a plurality of heat dissipation characteristic areas. For example, in the heat dissipation simulation data analysis of a certain diversion shell, after clustering and reconstruction, a heat dissipation characteristic area close to the heat source with drastic temperature changes, and another heat dissipation characteristic area far away from the heat source with relatively gentle temperature changes may be obtained. These heat dissipation characteristic areas provide a clear division basis for further analysis of the heat dissipation mechanism of the diversion shell and optimization of the heat dissipation design.

[0053] In a preferred embodiment, after performing structural mesh division on the CAD model of the target guide shell to obtain the CAD mesh model, it also includes: dividing the multiple heat dissipation feature areas to obtain labeled heat dissipation feature areas, wherein the labeled heat dissipation feature areas are areas where the heat dissipation index is less than a preset threshold; after accessing the CAD mesh model, encrypting the mesh of the labeled heat dissipation feature area using local encryption rules to update the CAD mesh model.

[0054] In detail, after completing the structural mesh division of the target guide shell CAD model and obtaining the CAD mesh model, further refined processing of the heat dissipation characteristic area is carried out. Specifically, an in-depth analysis is conducted on the multiple heat dissipation characteristic areas that have been divided, and the labeled heat dissipation characteristic areas are screened out based on the preset heat dissipation index threshold. These labeled heat dissipation characteristic areas refer to areas where the heat dissipation index is less than the preset threshold. The heat dissipation index usually comprehensively considers factors such as the temperature change rate, temperature gradient, and heat flux of the area. For example, in the guide shell, some areas with poor heat dissipation performance due to complex structure or material characteristics may have a heat dissipation index lower than the preset threshold, and are thus determined to be labeled heat dissipation characteristic areas.

[0055] After integrating the CAD mesh model, local mesh densification is applied to the mesh in the heat dissipation feature areas of the label to improve the accuracy of subsequent heat conduction simulations, especially in critical heat dissipation areas. This local mesh densification is based on the need for higher-resolution simulations in heat dissipation-sensitive areas. For example, in areas with thinner walls, where heat dissipation behavior is more complex and temperature fluctuations may be more dramatic, a higher mesh density can more accurately capture subtle changes in the temperature and thermal flow fields.

[0056] Through encryption processing, the grid density of the label heat dissipation feature area is improved, thereby updating the CAD grid model. The updated CAD grid model has a finer grid division in the label heat dissipation feature area, which can provide a more accurate data basis for subsequent heat conduction simulations, help to more accurately evaluate the heat dissipation performance of the target guide shell, identify potential heat dissipation problem areas, and provide strong support for optimizing the design of the guide shell. For example, in the simulation of a certain guide shell, the encrypted model can more clearly show the temperature distribution and changes in the thinner wall area during the heat treatment process, providing an important basis for improving the structural design of this area.

[0057] In a preferred embodiment, predicting the differentiated heat dissipation indicators between the multiple heat dissipation characteristic zones under the initial heat treatment parameters based on the multiple regional heat conduction equations includes: applying the initial heat treatment parameters to the respective regional heat conduction equations, and outputting heat dissipation simulation prediction data for the respective zones, wherein the expressions of the regional heat conduction equations include: ;in, is the density of region i, is the specific heat capacity of region i, is the thermal conductivity of region i, is the temperature field distribution of region i at time t under coordinate x, is the divergence operator, The heat absorbed by region i at coordinate x at time t; the differential heat dissipation indexes of the multiple heat dissipation characteristic regions are obtained according to the heat dissipation simulation prediction data of each region, and the differential heat dissipation indexes characterize the magnitude of the differences in the temperature change characteristics among regions.

[0058] Specifically, in the heat treatment process simulation and analysis stage, the differential heat dissipation indexes among multiple heat dissipation characteristic regions are predicted based on the heat conduction equations of multiple regions. First, the temperature boundary conditions, heat source conditions, etc. implied by the initial heat treatment parameters, such as heating time, cooling method, etc., are applied to the heat conduction equations of each region. The heat conduction equation of a region is a mathematical expression that describes the heat conduction law in a specific region, specifically: . Its expression contains multiple key parameters, such as the density (ρᵢ), specific heat capacity (cᵢ), and thermal conductivity (kᵢ) of region i. These parameters reflect the material properties of region i and have a direct impact on heat conduction; Tᵢ(x,t) represents the temperature field distribution of region i at coordinate x at time t, which describes the spatial and temporal variations of temperature within the region; ∇ represents the divergence operator, which is used to describe the diffusion of heat within the region; Qᵢ(x,t) represents the heat absorbed by region i at coordinate x at time t, which may come from external heat sources or heat transfer between regions.

[0059] By substituting the initial heat treatment parameters into the equation and combining the material properties and boundary conditions of each region, the heat dissipation simulation prediction data of each region can be solved, and this data includes information such as temperature values at different positions and different times. For example, in the heat treatment simulation of a certain flow guide shell, if the material density of a certain heat dissipation characteristic region is large and the specific heat capacity is high, under the same initial heat treatment parameters, its temperature change may be relatively gentle, and the heat dissipation simulation prediction data will reflect this characteristic.

[0060] Subsequently, based on the heat dissipation simulation prediction data of each region, the differential heat dissipation indexes of the multiple heat dissipation characteristic regions are further obtained. The differential heat dissipation indexes are used to quantify the magnitude of the differences in the temperature change characteristics among regions. For example, these indexes can be obtained by calculating the differences in parameters such as the temperature change amplitude and temperature gradient of different regions within a specific time period. Taking two heat dissipation characteristic regions as an example, if the temperature of one region rises rapidly during the heating process while the temperature of the other region rises slowly, then the differential heat dissipation indexes of these two regions will reflect the significant differences in their temperature change rates. These differential heat dissipation indexes provide an important quantitative basis for evaluating the heat dissipation performance of each heat dissipation characteristic region and optimizing the heat treatment process.

[0061] In a preferred embodiment, a heat treatment parameter tuning model is established based on the differential heat dissipation index as the target, and the initial heat treatment parameters are adjusted to output multiple sets of optimal solutions for heat treatment parameters, including: taking the minimization of the differential heat dissipation index as the target, using the initial heat treatment parameters as input variables, and using the optimal solutions for heat treatment parameters as output variables to construct a heat treatment parameter tuning model; performing Bayesian optimization on each differential heat dissipation index according to the heat treatment parameter tuning model, and calculating the real-time differential heat dissipation index under the current multiple sets of heat treatment parameters; when the real-time differential heat dissipation index converges, output the current multiple sets of heat treatment parameters as the optimal solution.

[0062] Preferably, to achieve the goal of making the thermal responses in different regions more consistent after heat treatment, a heat treatment parameter tuning model is constructed based on the differential heat dissipation index.

[0063] In a specific embodiment, taking the minimization of the differential heat dissipation index as the core goal, the differential heat dissipation index can characterize the difference in temperature change characteristics between each heat dissipation characteristic region, such as the difference in parameters such as the temperature change amplitude and temperature gradient in each region. By minimizing this index, the thermal responses in each region can be made to converge.

[0064] Using the initial heat treatment parameters, such as the heating time, the parameters corresponding to the cooling method, etc. as input variables, these parameters are the key factors affecting heat transfer and distribution during heat treatment; using the optimal solutions for heat treatment parameters as output variables, and the optimal solution is the parameter combination that can minimize the differential heat dissipation index. Based on the above goals, input variables, and output variables, a heat treatment parameter tuning model is constructed, which can comprehensively consider the interaction between various parameters and their complex relationship with the differential heat dissipation index.

[0065] Subsequently, according to the constructed heat treatment parameter tuning model, the Bayesian optimization algorithm is used to optimize the parameters for each differential heat dissipation index. The Bayesian optimization algorithm efficiently searches for the optimal solution in the parameter space by continuously sampling and updating the probability model. During the optimization process, the real-time differential heat dissipation index under the current multiple sets of heat treatment parameters is calculated, and these real-time indexes reflect the degree of thermal response difference in each heat dissipation characteristic region under the current parameter combination.

[0066] For example, in the optimization of the heat treatment parameters of a certain flow guide shell, the Bayesian optimization algorithm is used to continuously adjust parameters such as heating time and cooling rate, and the corresponding differential heat dissipation index is calculated in real time. When the real-time differential heat dissipation index is in a converged state, it means that within the current parameter search range, further adjustment of the parameters is difficult to significantly reduce the differential heat dissipation index. At this time, the current multiple sets of heat treatment parameters are output as the optimal solutions. These optimal solutions provide multiple feasible parameter options for the actual heat treatment process, helping to improve the heat treatment quality, making the thermal responses of different regions more consistent after heat treatment, and meeting specific engineering requirements.

[0067] In a preferred embodiment, calculating the real-time differential heat dissipation index under the current multiple sets of heat treatment parameters further includes: when the real-time differential heat dissipation index does not converge, updating the multiple sets of heat treatment parameters according to the Bayesian adjustment parameters, where the Bayesian adjustment parameters include the expected improvement value or the upper confidence bound; and outputting the optimal solutions of the multiple sets of heat treatment parameters until the real-time differential heat dissipation index is in a converged state.

[0068] Specifically, when it is calculated that the real-time differential heat dissipation index does not converge, it indicates that the current multiple sets of heat treatment parameters have not yet made the thermal responses of each heat dissipation characteristic region reach a relatively consistent state. At this time, it is necessary to update the multiple sets of heat treatment parameters according to the Bayesian adjustment parameters.

[0069] The Bayesian adjustment parameters are an important part of the Bayesian optimization algorithm. The expected improvement value (EI) is used to measure the degree of performance improvement that may be brought about by exploring new parameters based on the current parameters, that is, how much the differential heat dissipation index is expected to be reduced; the upper confidence bound (UCB) comprehensively considers the historical performance and uncertainty of the parameters, guiding the algorithm to balance exploration and exploitation and avoiding falling into local optima. For example, in the scenario of optimizing the heat treatment parameters of a certain flow guide shell, if the real-time differential heat dissipation index is large under the current parameter combination, it indicates that the thermal responses of each region are significantly different. The algorithm will search for new parameter combinations that may bring greater performance improvement in the parameter space according to the Bayesian adjustment parameters such as the expected improvement value or the upper confidence bound, such as adjusting parameters such as heating time and cooling rate.

[0070] Iterate continuously in this way until the real-time differential heat dissipation index is in a converged state. At this time, it means that within the current parameter search range, the thermal responses of each heat dissipation characteristic region have reached a relatively consistent degree, and further adjustment of the parameters is difficult to significantly reduce the differential heat dissipation index. Finally, the current multiple sets of heat treatment parameters are output as the optimal solutions. These optimal solutions provide effective parameter options for the actual heat treatment process, helping to improve the heat treatment quality and meet the engineering requirements.

[0071] A heat treatment parameter optimization method driven by the performance requirements of a diversion shell provided by an embodiment of the present invention has at least the following technical effects:

[0072] 1. By differentiating and partitioning the heat dissipation simulation data, multiple heat dissipation characteristic regions are obtained, and heat conduction equations are constructed for each heat dissipation characteristic region, enabling more accurate analysis and simulation of the heat dissipation characteristics of different regions of the diversion shell, avoiding the problem of insufficient accuracy caused by using a unified model, and providing a more accurate basis for subsequent heat treatment parameter optimization.

[0073] 2. A heat treatment parameter optimization model is established with the differentiated heat dissipation index as the goal, and the initial heat treatment parameters are adjusted. By quantifying the heat dissipation performance differences between different heat dissipation characteristic regions and using this as the optimization goal, it is possible to more effectively find the combination of heat treatment parameters that makes the thermal responses of each region tend to be consistent. Compared with empirical parameter adjustment, the pertinence and efficiency of parameter adjustment are significantly improved, which helps to improve the overall heat treatment quality of the diversion shell.

[0074] 3. During the parameter adjustment process, the Bayesian optimization algorithm is used to optimize the differentiated heat dissipation index, and a local refinement rule is introduced to refine the grid of the key regions of heat dissipation performance. The Bayesian optimization algorithm can efficiently search for the optimal solution in a complex parameter space, while local grid refinement improves the simulation accuracy, especially in the heat dissipation performance sensitive regions. The combination of the two enables more accurate capture of the temperature changes and heat flux distribution of the diversion shell during the heat treatment process while ensuring the calculation efficiency, providing strong support for the performance optimization of the diversion shell.

[0075] Embodiment 2:

[0076] As Figure 2 shown, based on the same inventive concept as the heat treatment parameter optimization method driven by the performance requirements of a diversion shell provided in Embodiment 1, an embodiment of the present invention further provides a heat treatment parameter optimization system driven by the performance requirements of a diversion shell, and the system includes:

[0077] A heat dissipation simulation module 11, configured to input the CAD model of the target diversion shell, perform heat dissipation simulation on the CAD model of the target diversion shell, and output heat dissipation simulation data.

[0078] A difference partitioning module 12, configured to perform differentiated partitioning on the heat dissipation simulation data to obtain multiple heat dissipation characteristic regions, construct heat conduction equations for each heat dissipation characteristic region, and output multiple regional heat conduction equations.

[0079] A parameter acquisition module 13, configured to acquire initial heat treatment parameters, including heating time, cooling method, and cooling rate.

[0080] An index prediction module 14, configured to predict a differential heat dissipation index between the multiple heat dissipation characteristic regions under the initial heat treatment parameters based on the multiple regional heat conduction equations.

[0081] A parameter adjustment module 15, configured to establish a heat treatment parameter optimization model for a target based on the differential heat dissipation index, adjust the initial heat treatment parameters, and output multiple optimal solutions of heat treatment parameters.

[0082] A heat treatment module 16, configured to perform differential heat treatment on the target flow guide shell according to the multiple optimal solutions of heat treatment parameters.

[0083] Furthermore, the heat dissipation simulation module 11 is further configured to perform the following steps:

[0084] Perform structural mesh division on the CAD model of the target flow guide shell to obtain a CAD mesh model; wherein, the CAD model includes the structural parameters and material properties of the target flow guide shell, and the material properties include density, specific heat capacity, and thermal conductivity; configure heat treatment condition parameters, and use Ansys to perform heat conduction simulation on the CAD mesh model under the heat treatment condition parameters, and output heat dissipation simulation data, where the heat dissipation simulation data includes the temperature change curve in each grid region.

[0085] Furthermore, the differential partition module 12 is further configured to perform the following steps:

[0086] Statistically analyze the temperature change characteristics of each grid region in the heat dissipation simulation data, including the average temperature change rate, the maximum temperature gradient, and the area heat flux of the region; calculate the heat dissipation index according to the temperature change characteristics, cluster the temperature change characteristics of all grid regions according to the heat dissipation index calculation result, and output a first clustering result; perform discrete grid region identification on the first clustering result, and reconstruct the identified discrete grid regions to output a second clustering result, where the second clustering result is multiple heat dissipation characteristic regions.

[0087] Furthermore, the heat dissipation simulation module 11 is further configured to perform the following steps:

[0088] Divide the multiple heat dissipation characteristic regions to obtain labeled heat dissipation characteristic regions, where the labeled heat dissipation characteristic regions are regions with a heat dissipation index less than a preset threshold; after accessing the CAD mesh model, use a local refinement rule to refine the grids of the labeled heat dissipation characteristic regions and update the CAD mesh model.

[0089] Furthermore, the index prediction module 14 is further configured to perform the following steps:

[0090] Apply the initial heat treatment parameters to each regional heat conduction equation, and output the heat dissipation simulation prediction data for each region. The expression of the regional heat conduction equation includes: ; where is the density of region i, is the specific heat capacity of region i, is the thermal conductivity of region i, is the temperature field distribution of region i at time t under coordinate x, is the divergence operator, is the heat absorbed by region i at time t under coordinate x; Obtain the differential heat dissipation index of the multiple heat dissipation characteristic regions according to the heat dissipation simulation prediction data of each region. The differential heat dissipation index characterizes the difference in the temperature change characteristics between regions.

[0091] Furthermore, the parameter adjustment module 15 is also used to perform the following steps:

[0092] Taking the minimization of the differential heat dissipation index as the goal, using the initial heat treatment parameters as input variables, and the optimal solution of heat treatment parameters as output variables, construct a heat treatment parameter optimization model; Perform Bayesian optimization on each differential heat dissipation index according to the heat treatment parameter optimization model, and calculate the real-time differential heat dissipation index under the current multiple sets of heat treatment parameters; When the real-time differential heat dissipation index converges, output the current multiple sets of heat treatment parameters as the optimal solution.

[0093] Furthermore, the parameter adjustment module 15 is also used to perform the following steps:

[0094] When the real-time differential heat dissipation index does not converge, update multiple sets of heat treatment parameters according to the Bayesian adjustment parameters. Among them, the Bayesian adjustment parameters include the expected improvement value or the upper confidence bound; Output the optimal solution of multiple sets of heat treatment parameters until the real-time differential heat dissipation index converges.

[0095] Through the foregoing detailed description of a method for optimizing heat treatment parameters driven by the performance requirements of a guide shell in this specification, those skilled in the art can clearly know a system for optimizing heat treatment parameters driven by the performance requirements of a guide shell in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0096] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing heat treatment parameters driven by the performance requirements of a diversion shell, characterized in that, The method includes: Inputting the CAD model of the target flow guide shell, performing heat dissipation simulation on the CAD model of the target flow guide shell, and outputting heat dissipation simulation data; Performing differential partitioning on the heat dissipation simulation data to obtain multiple heat dissipation characteristic regions, constructing heat conduction equations for each heat dissipation characteristic region, and outputting multiple regional heat conduction equations; Obtaining initial heat treatment parameters, including heating time, cooling method, and cooling rate; Predicting the differential heat dissipation indexes between the multiple heat dissipation characteristic regions under the initial heat treatment parameters based on the multiple regional heat conduction equations; Establishing a heat treatment parameter optimization model based on the differential heat dissipation indexes for the target, adjusting the initial heat treatment parameters, and outputting multiple optimal solutions of heat treatment parameters; Performing differential heat treatment on the target flow guide shell according to the multiple optimal solutions of heat treatment parameters; Among them, performing heat dissipation simulation on the CAD model of the target flow guide shell and outputting heat dissipation simulation data includes: Performing structural mesh division on the CAD model of the target flow guide shell to obtain a CAD mesh model; Among them, the CAD model includes the structural parameters and material properties of the target flow guide shell, and the material properties include density, specific heat capacity, and thermal conductivity; Configuring heat treatment condition parameters, and using Ansys to perform heat conduction simulation on the CAD mesh model under the heat treatment condition parameters, and outputting heat dissipation simulation data, where the heat dissipation simulation data includes the temperature change curve in each mesh region; Among them, performing differential partitioning on the heat dissipation simulation data to obtain multiple heat dissipation characteristic regions includes: Counting the temperature change characteristics of each mesh region in the heat dissipation simulation data, including the average temperature change rate, the maximum temperature gradient, and the area heat flux of the region; Calculating heat dissipation indexes according to the temperature change characteristics, clustering the temperature change characteristics of all mesh regions according to the heat dissipation index calculation results, and outputting a first clustering result; Performing discrete mesh region identification on the first clustering result, reconstructing the identified discrete mesh regions, and outputting a second clustering result, where the second clustering result is multiple heat dissipation characteristic regions.

2. The heat treatment parameter optimization method driven by the performance requirements of the flow guide shell according to claim 1, characterized in that, After performing structural mesh division on the CAD model of the target flow guide shell to obtain a CAD mesh model, it further includes: Dividing the multiple heat dissipation characteristic regions to obtain labeled heat dissipation characteristic regions, where the labeled heat dissipation characteristic regions are regions with heat dissipation indexes less than a preset threshold; After accessing the CAD mesh model, encrypting the meshes of the labeled heat dissipation characteristic regions using local encryption rules, and updating the CAD mesh model.

3. The heat treatment parameter optimization method driven by the performance requirements of the diversion shell as described in claim 1, characterized in that Predicting the differential heat dissipation indexes between the multiple heat dissipation characteristic regions under the initial heat treatment parameters based on the multiple regional heat conduction equations includes: Applying the initial heat treatment parameters to each regional heat conduction equation, and outputting heat dissipation simulation prediction data for each region. The expression of the regional heat conduction equation includes: ； Among them, is the density of region i, is the specific heat capacity of region i, is the thermal conductivity of region i, is the temperature field distribution of region i at time t under coordinate x, is the divergence operator, is the heat absorbed by region i at time t under coordinate x; Obtaining the differential heat dissipation indexes of the multiple heat dissipation characteristic regions according to the heat dissipation simulation prediction data of each region, where the differential heat dissipation indexes characterize the difference in temperature change characteristics between regions.

4. The heat treatment parameter optimization method driven by the performance requirements of the diversion shell according to claim 3, wherein, Establish a heat treatment parameter optimization model based on the differential heat dissipation index as the target, adjust the initial heat treatment parameters, and output multiple optimal solutions of heat treatment parameters, including: Construct a heat treatment parameter optimization model with the goal of minimizing the differential heat dissipation index, using the initial heat treatment parameters as input variables and the optimal solutions of heat treatment parameters as output variables; Perform Bayesian optimization on each differential heat dissipation index according to the heat treatment parameter optimization model, and calculate the real-time differential heat dissipation index under the current multiple sets of heat treatment parameters; When the real-time differential heat dissipation index converges, output the current multiple sets of heat treatment parameters as the optimal solution.

5. The heat treatment parameter optimization method driven by the performance requirements of the diversion shell as described in claim 4, wherein, Calculating the real-time differential heat dissipation index under the current multiple sets of heat treatment parameters further includes: When the real-time differential heat dissipation index does not converge, update the multiple sets of heat treatment parameters according to the Bayesian adjustment parameters, where the Bayesian adjustment parameters include the expected improvement value or the upper confidence bound; Output multiple optimal solutions of heat treatment parameters until the real-time differential heat dissipation index converges.

6. A heat treatment parameter optimization system driven by the performance requirements of a diversion shell, characterized in that, For implementing the heat treatment parameter optimization method driven by the performance requirements of the flow guide shell according to any one of claims 1-5, the system includes: A heat dissipation simulation module for inputting the CAD model of the target flow guide shell, performing heat dissipation simulation on the CAD model of the target flow guide shell, and outputting heat dissipation simulation data; A differential partitioning module for differentially partitioning the heat dissipation simulation data to obtain multiple heat dissipation characteristic regions, constructing heat conduction equations for each heat dissipation characteristic region, and outputting multiple regional heat conduction equations; A parameter acquisition module for acquiring initial heat treatment parameters, including heating time, cooling method, and cooling rate; An index prediction module for predicting the differential heat dissipation index between the multiple heat dissipation characteristic regions under the initial heat treatment parameters based on the multiple regional heat conduction equations; A parameter adjustment module for establishing a heat treatment parameter optimization model with the differential heat dissipation index as the target, adjusting the initial heat treatment parameters, and outputting multiple optimal solutions of heat treatment parameters; A heat treatment module for performing differential heat treatment on the target flow guide shell according to the multiple optimal solutions of heat treatment parameters.

Images