Mold optimization methods for zinc-aluminum alloy die-cast optical modules and aluminum alloy machining molds
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN XIE LI DA PRECISE HARDWARE ELECTRONICS
- Filing Date
- 2025-05-06
- Publication Date
- 2026-05-26
Smart Images
Figure CN120493622B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of aluminum alloy processing technology, specifically to a method for optimizing a die-cast optical module made of zinc-aluminum alloy and an aluminum alloy processing die. Background Technology
[0002] Currently, aluminum alloys are among the most widely used metallic materials in industries such as aerospace. They are extensively used in aircraft structural components (skin, stringers, bulkheads, etc.), engine parts, landing gear, and airborne equipment housings. Therefore, zinc-aluminum alloy die-casting technology is widely applied in the manufacture of precision optical modules. Aluminum alloy parts are lightweight, have good specific stiffness, and are corrosion-resistant, but they also exhibit poor ductility and resilience. Therefore, to improve the production efficiency and product quality of aluminum alloy parts, it is necessary to study aluminum alloy machining molds to improve the precision of aluminum alloy machining processes.
[0003] Existing mold design processes often suffer from problems such as short mold life and low molding quality. The inventors of this application have discovered that traditional mold design relies on trial and error based on experience, which easily leads to problems such as filling defects and thermal stress concentration. While finite element simulation can assist in optimization in existing technologies, it has the following shortcomings:
[0004] 1. It is difficult to balance mesh generation accuracy and computational efficiency; complex curved surfaces are prone to simulation distortion.
[0005] 2. The adjustment of gate parameters lacks quantitative basis and relies on manual experience judgment;
[0006] 3. Insufficient coupling analysis of temperature field and stress field makes it difficult to predict the risk of hot cracking.
[0007] Therefore, there is an urgent need for a mold optimization method that integrates intelligent algorithms and dynamic mesh encryption to adjust mold parameters and improve the product quality of aluminum alloy products. Summary of the Invention
[0008] In view of the above problems, embodiments of the present invention provide a mold optimization method for zinc-aluminum alloy die-cast optical modules and an aluminum alloy processing mold, which are used to solve the problem of low mold design accuracy in the prior art.
[0009] According to one aspect of the present invention, a mold optimization method for a zinc-aluminum alloy die-cast optical module is provided, the method comprising:
[0010] Obtain material property information of the aluminum alloy to be processed and material data of the mold; the material property information includes material flow, springback and stress distribution data; the material data includes physical and mechanical property data and geometric parameters;
[0011] Based on the material data of the aluminum alloy to be processed and the material property information of the mold, a geometric model of the mold is established and meshed; the geometric model includes the cavity, gate, runner, and cooling water channel;
[0012] The die-casting simulation analysis was performed in finite element analysis software to simulate the die-casting process and obtain simulation results. The simulation results include animation of the molten metal flow front, filling process analysis information, solidification information, and mold stress distribution and temperature information.
[0013] The simulation results are input into the parameter optimization model to obtain the adjustment parameters for the mold's gate, runner system, and cooling water circuit.
[0014] The target mold is manufactured based on the adjustment parameters of the mold's gate, runner system, and cooling water circuit.
[0015] In one alternative approach, the material property information of the aluminum alloy to be processed and the material data of the mold are obtained, including:
[0016] The aluminum alloy to be processed is tested to obtain the material property information of the aluminum alloy to be processed;
[0017] Based on the material properties of the aluminum alloy to be processed and the processing requirements, the material data of the mold is determined.
[0018] In one optional approach, the processing technology includes one of CNC machining, cutting machining, and forming machining; determining the material data of the mold based on the material properties and processing requirements of the aluminum alloy to be processed includes:
[0019] Based on the material properties and processing requirements of the aluminum alloy to be processed, the physical and mechanical properties and geometric dimensions of the mold are determined in a preset mold material database. The physical and mechanical properties of the mold include the density, thermal conductivity, specific heat capacity, solid-liquid phase temperature, elastic modulus, Poisson's ratio, and coefficient of thermal expansion of the mold material.
[0020] In one optional approach, the material property information of the aluminum alloy to be processed includes the finished product size information corresponding to the aluminum alloy to be processed; based on the material data of the aluminum alloy to be processed and the material property information of the mold, a geometric model of the mold is established and meshed, including:
[0021] Based on the finished product size information corresponding to the aluminum alloy to be processed, the basic size of the mold body is determined by CAD modeling and 3D QuickPress optimization of the die casting mold flow channel; wherein, the gate retains a rounded corner with a radius larger than a preset threshold.
[0022] Based on the processing information, determine the cavity and gating system of the mold;
[0023] The physical and mechanical performance data of the mold are applied to the cavity and the mold body to obtain the geometric model of the mold;
[0024] The geometric model is meshed using hybrid network technology to obtain the meshed geometric model.
[0025] In one alternative approach, the geometric model is meshed using hybrid network technology to obtain a meshed geometric model, including:
[0026] Determine the initial coarse mesh; among them, the cavity / flow channel region adopts the hexahedral dominant mesh, the complex curved surface adopts the tetrahedral mesh, and the thin-walled structure adopts the prism layer mesh.
[0027] CNN is used to analyze the simulation results of the initial coarse mesh to identify high gradient regions;
[0028] The mesh density in the high gradient region is increased according to a preset density step size;
[0029] The geometric model after mesh refinement is further analyzed using CNN to analyze the simulation results, and high gradient regions are further identified. The mesh is then dynamically refined until the target accuracy is achieved, resulting in the geometric model after mesh division.
[0030] In one optional approach, the parameter optimization model includes a U-Net model, a parameter optimization model, and a generative adversarial network; the step of inputting the simulation results into the parameter optimization model to obtain the adjustment parameters for the mold's gate, runner system, and cooling water circuit includes:
[0031] The animation of the molten metal flow front is input into the U-Net model to detect information on uneven filling, air entrapment, or short-shot phenomena in the molten metal.
[0032] When uneven filling, air entrapment, or short injection occurs in the molten metal, a prompt message is generated, which includes a prompt indicating the location of the problematic gate or the injection speed.
[0033] In an optional approach, the step of inputting the simulation results into a parameter optimization model to obtain adjustment parameters for the mold's gate, runner system, and cooling water circuit further includes:
[0034] By inputting the stress distribution cloud map and temperature cloud map into the generative adversarial network, high-precision stress distribution cloud map and high-precision temperature cloud map are obtained.
[0035] According to another aspect of the present invention, an aluminum alloy processing mold is provided, which is obtained by processing using the mold optimization process of the zinc-aluminum alloy die-cast optical module.
[0036] This invention, through obtaining the material property information of the aluminum alloy to be processed and the material data of the mold, establishes a geometric model of the mold based on the material data of the aluminum alloy to be processed and the material property information of the mold, and performs mesh generation; performs die-casting simulation analysis in finite element analysis software to simulate the die-casting process and obtain simulation results; inputs the simulation results into a parameter optimization model to obtain adjustment parameters for the mold's gate, runner system, and cooling water channels; and manufactures the target mold based on the adjustment parameters of the mold's gate, runner system, and cooling water channels. This effectively improves the manufacturing accuracy of the mold, making it more reasonable, and thus making it more suitable for the current characteristics of aluminum alloy materials and processing technology when using the mold for aluminum alloy processing, thereby improving manufacturing accuracy.
[0037] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description
[0038] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:
[0039] Figure 1 A schematic flowchart of the mold optimization method for zinc-aluminum alloy die-cast optical modules provided in an embodiment of the present invention is shown.
[0040] Figure 2 This diagram illustrates the process of establishing a geometric model in the mold optimization method for zinc-aluminum alloy die-cast optical modules provided in this embodiment of the invention. Detailed Implementation
[0041] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.
[0042] Figure 1 A flowchart illustrating the mold optimization method for a zinc-aluminum alloy die-cast optical module provided in an embodiment of the present invention is shown. Figure 1 As shown, the method includes the following steps:
[0043] Step 110: Obtain the material properties of the aluminum alloy to be processed and the material data of the mold.
[0044] In this embodiment of the invention, the material property information includes material flow, springback, and stress distribution data; the material data includes physical and mechanical property data and geometric parameters.
[0045] Specifically, the aluminum alloy to be processed is tested to obtain its material properties; based on the material properties and processing requirements of the aluminum alloy, the material data of the mold is determined. In this embodiment of the invention, the processing technology includes one of CNC machining, cutting machining, and forming machining. Specifically, based on the material properties and processing requirements of the aluminum alloy to be processed, the physical and mechanical properties and geometric dimensions of the mold are determined from a preset mold material database; the physical and mechanical properties of the mold include the density, thermal conductivity, specific heat capacity, solid-liquid phase temperature, elastic modulus, Poisson's ratio, and coefficient of thermal expansion of the mold material. For example, in one embodiment of the invention, the material to be processed is ZL101A aluminum alloy (measured parameters: liquidus 615℃, solidus 555℃, dynamic viscosity 2.8 Pa·s). Correspondingly, the mold material is H13 hot work die steel (thermal conductivity 24.3 W / m·K, yield strength 1450 MPa). The springback coefficient of the aluminum alloy was measured to be 0.12 by a high-temperature tensile testing machine, and the latent heat of solidification data was obtained by DSC analysis.
[0046] Step 120: Based on the material data of the aluminum alloy to be processed and the material property information of the mold, establish the geometric model of the mold and perform mesh generation.
[0047] In this embodiment of the invention, the geometric model of the mold includes a mold body, which comprises a cavity, a gate, runners, and cooling water channels. The cavity is the hollow part of the mold used to shape the product; it is the core part of the mold and determines the final product's shape and dimensional accuracy. The gate is the channel connecting the runners and the cavity, serving as the inlet for molten metal to enter the cavity and controlling the flow rate and direction of the molten metal. For example, the size and shape of the gate can adjust the filling speed of the molten metal, avoiding problems such as air entrapment, splashing, or insufficient filling caused by excessively rapid filling. It also reduces turbulence in the molten metal and needs to facilitate subsequent cleaning; the gate is typically designed with an easy-to-cut shape to facilitate the removal of any gate residue after product molding, improving the product's appearance quality and dimensional accuracy. The material property information of the aluminum alloy to be processed includes the finished product's dimensional information. For example, the aluminum alloy casting is a module housing with external dimensions of 80mm × 50mm × 10mm and a wall thickness of 1.2mm. The corresponding mold dimensions are 200mm×150mm×80mm, with a 20mm machining allowance on each side.
[0048] Among them, such as Figure 2 As shown, the embodiments of the present invention include the following steps:
[0049] Step 210: Based on the finished product size information corresponding to the aluminum alloy to be processed, the basic size of the mold body is determined by CAD modeling and 3D QuickPress optimization of the die casting mold flow channel; wherein, the gate retains a rounded corner with a radius larger than a preset threshold.
[0050] Step 220: Based on the processing information, determine the cavity and gating system of the mold. Assign the physical and mechanical performance data of the mold to the cavity and mold body to obtain the geometric model of the mold. Mesh the geometric model using hybrid network technology to obtain the meshed geometric model. In this embodiment of the invention, CAD software is used to create the geometric model of the mold, including the cavity, gate, runner, cooling water channels, etc., ensuring the accuracy and completeness of the model. In one embodiment of the invention, the cooling water channels are designed as straight-through channels with a diameter of φ8mm, 15mm from the cavity surface, and a spacing of 30mm; a spiral water channel is added at the hot spot in special areas, with a pitch of 12mm and a diameter of φ6mm. The ejection system uses ejector pins with a diameter of φ3mm, spaced 25mm apart at the edge of the casting and the root of the reinforcing ribs; a 10mm safety margin is reserved for the ejection stroke.
[0051] Step 230: After designing the basic geometric model, import the CAD-format geometric model into the finite element analysis software and then perform mesh generation. In this embodiment of the invention, an appropriate mesh type (such as tetrahedral mesh, hexahedral mesh, etc.) and mesh density are selected based on the complexity of the geometric model and the required analysis accuracy. After meshing the geometric model, a finite element mesh is generated. For areas such as the gate and thick-walled sections, the mesh is appropriately densified using a progressively denser meshing method to improve analysis accuracy. Specifically, an initial coarse mesh is determined; hexahedral meshes are used as the dominant mesh for cavities and flow channels, tetrahedral meshes are used for complex curved surfaces, and prismatic layer meshes are used for thin-walled structures. The simulation results of the initial coarse mesh are analyzed using CNN to identify high-gradient regions; the mesh density of these high-gradient regions is then increased according to a preset density step size; the geometric model after mesh densification is further analyzed using CNN to identify more high-gradient regions and dynamically densify the mesh until the target accuracy is achieved, resulting in the meshed geometric model. The mesh quality can be checked; when the distortion is less than 0.85, the aspect ratio is less than 15, and the cell volume mutation rate is less than 30%, the mesh quality is considered acceptable. In this embodiment, feature samples are constructed, including mold samples and labels for the regions to be refined. The feature sample data is used to train the CNN to obtain a trained CNN. The model's feature parameters are input into the trained CNN, and the simulation results of the initial coarse mesh are analyzed to obtain the high-gradient regions of the current mold. The mesh in these high-gradient regions is then refined. By setting the model to dynamically adjust the mesh, the workload of manually adjusting the mesh can be effectively reduced, improving the accuracy of the simulation.
[0052] Step 130: Perform die-casting simulation analysis in finite element analysis software to simulate the die-casting process and obtain simulation results.
[0053] The simulation results include animation of the molten metal flow front, filling process analysis information, solidification information, and stress distribution and temperature information of the mold.
[0054] Specifically, in this embodiment of the invention, flow analysis utilizes a VOF (Volume of Fluid) model to track the flow front of the molten metal. Heat transfer analysis is coupled with the release of latent heat of solidification, setting interfacial thermal resistance, and a mold-casting interface heat transfer coefficient of 5000 W / m²·K. Stress analysis utilizes an elastoplastic model, considering the thermo-mechanical coupling effect between the mold and the casting. The filling process analysis involves observing the molten metal filling sequence through flow front animation, identifying "stagnant zones" and "jet flows," where stagnant zones are areas with a filling time difference greater than 10%, and jet flows are areas with a flow velocity greater than 40 m / s. Gas entrapment distribution maps are extracted to locate porosity risk areas, where areas with a gas volume fraction greater than 5% are defined as porosity risk areas. Solidification and stress analysis involves drawing temperature gradient cloud maps to identify hot spots and shrinkage risk areas, where hot spots are areas with a cooling rate less than 50℃ / s. Mold stress distribution is extracted, and the maximum equivalent stress area is marked; areas exceeding 800 MPa require structural optimization.
[0055] Step 140: Input the simulation results into the parameter optimization model to obtain the adjustment parameters of the mold's gate, runner system, and cooling water circuit.
[0056] The parameter optimization model is trained based on historical aluminum alloy processing data and historical mold parameters. In this embodiment of the invention, the parameter optimization model includes a U-Net model, a parameter optimization model, and a generative adversarial network. The historical aluminum alloy processing data includes animation samples of the molten metal flow front, stress distribution cloud map samples, temperature cloud map samples, and simulation data samples.
[0057] The process involves inputting the animation of the molten metal flow front into a U-Net model to detect uneven filling, air entrapment, or short-shot phenomena in the molten metal. The U-Net model is pre-trained based on samples of the molten metal flow front animation. When uneven filling, air entrapment, or short-shot phenomena occur, a prompt message is generated, indicating the problematic gate location or injection speed. If the flow front does not reach the end of the cavity synchronously, the gate location is adjusted using a "flow balance index."
[0058] The stress distribution cloud map and temperature cloud map are respectively input into the generative adversarial network to obtain high-precision stress distribution cloud map and high-precision temperature cloud map; wherein the generative adversarial network is pre-trained based on stress distribution cloud map samples and temperature cloud map samples.
[0059] The filling process analysis information, solidification information, high-precision stress distribution cloud map, and high-precision temperature cloud map are input into the multi-task analysis model to obtain the porosity, thermal cracking probability, and shrinkage risk analysis results; the multi-task analysis model is pre-trained based on simulation data samples.
[0060] The embodiments of the present invention utilize a parameter optimization model, enabling more efficient and accurate adjustment of mold structure parameters based on simulation results.
[0061] Step 150: Based on the adjustment parameters of the mold's gate, runner system, and cooling water circuit, the target mold is manufactured.
[0062] High-precision CNC machining equipment, such as CNC milling machines or EDM machines, is used to precisely machine the gate according to the design drawings. It is ensured that the cross-sectional area, length, and angle of the gate meet the optimized parameter requirements, and the machining accuracy is controlled within the allowable error range. For complex gate shapes, such as tangential feed gates, multi-axis machining technology may be required to ensure machining accuracy and surface quality.
[0063] In this embodiment of the invention, CNC machining equipment is used to process the flow channels, including circular flow channels, trapezoidal flow channels, and "T-shaped balancers" at the flow channel branches. Based on adjustment parameters, the cross-sectional shape, size, and position of the flow channels are precisely controlled to ensure that the processed flow channels meet the optimized parameter requirements. For the added arc-shaped guide blocks, CNC milling machines or EDM equipment are used to process them, ensuring that their shape and size meet the design requirements and that they are perfectly integrated with the flow channels.
[0064] For conventional cooling water channels, CNC machining equipment is used for drilling and milling to ensure that the diameter, spacing, and position of the channels meet design requirements. During machining, attention is paid to controlling machining accuracy and surface roughness to ensure unobstructed flow and effective cooling. For special water channel structures, such as spiral cooling water channels and variable cross-section water channels, this embodiment of the invention uses additive manufacturing or laser processing. This method allows for the creation of complex water channel shapes and structures, improving the machining accuracy and quality of the cooling water channels.
[0065] In this embodiment of the invention, after the target mold is manufactured, it is also debugged, including debugging of the gating system and the cooling system. If defects or performance failures are found in the mold, the gating gate, runner system, or cooling water channel of the mold are locally adjusted or redesigned and processed according to the type and location of the defects.
[0066] This invention, through obtaining the material property information of the aluminum alloy to be processed and the material data of the mold, establishes a geometric model of the mold based on the material data of the aluminum alloy to be processed and the material property information of the mold, and performs mesh generation; performs die-casting simulation analysis in finite element analysis software to simulate the die-casting process and obtain simulation results; inputs the simulation results into a parameter optimization model to obtain adjustment parameters for the mold's gate, runner system, and cooling water channels; and manufactures the target mold based on the adjustment parameters of the mold's gate, runner system, and cooling water channels. This effectively improves the manufacturing accuracy of the mold, making it more reasonable, and thus making it more suitable for the current characteristics of aluminum alloy materials and processing technology when using the mold for aluminum alloy processing, thereby improving manufacturing accuracy.
[0067] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages is for the purpose of disclosing the best mode of implementation of the invention.
[0068] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.
[0069] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.
[0070] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.
[0071] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.
Claims
1. A method for optimizing the mold of a zinc-aluminum alloy die-cast optical module, characterized in that, The method includes: Obtaining material property information of the aluminum alloy to be processed and material data of the mold includes: testing the aluminum alloy to be processed to obtain its material property information; determining the material data of the mold based on the material property information of the aluminum alloy to be processed and processing requirements; the processing method includes one of CNC machining, cutting machining, and forming machining; determining the material data of the mold based on the material property information of the aluminum alloy to be processed and processing requirements includes: determining the physical and mechanical property data and geometric dimensions of the mold in a preset mold material database based on the material property information of the aluminum alloy to be processed and processing requirements; the physical and mechanical property data of the mold includes the density, thermal conductivity, specific heat capacity, solid-liquid phase temperature, elastic modulus, Poisson's ratio, and coefficient of thermal expansion of the mold material; the material property information includes material flow, springback, and stress distribution data; the material data includes physical and mechanical property data and geometric parameters. Based on the material data of the aluminum alloy to be processed and the material property information of the mold, a geometric model of the mold is established and meshed. The geometric model includes a cavity, gate, runner, and cooling water channel. The material property information of the aluminum alloy to be processed includes the finished product size information corresponding to the aluminum alloy to be processed. The process of establishing the geometric model of the mold and meshing it includes: determining the basic dimensions of the mold body by using CAD modeling based on the finished product size information corresponding to the aluminum alloy to be processed, and optimizing the die-casting mold runner using 3D QuickPress; wherein, a fillet with a radius larger than a preset threshold is retained at the gate; determining the cavity and gating system of the mold based on the processing information; assigning the physical and mechanical performance data of the mold to the cavity and mold body to obtain the geometric model of the mold; and meshing the geometric model using hybrid network technology to obtain the meshed geometric model. The die-casting simulation analysis was performed in finite element analysis software to simulate the die-casting process and obtain simulation results. The simulation results include animation of the molten metal flow front, filling process analysis information, solidification information, and mold stress distribution and temperature information. The simulation results are input into the parameter optimization model to obtain the adjustment parameters for the mold's gate, runner system, and cooling water circuit; the parameter optimization model is trained based on historical aluminum alloy processing data and historical mold parameters. The target mold is manufactured based on the adjustment parameters of the mold's gate, runner system, and cooling water circuit.
2. The method according to claim 1, characterized in that, The geometric model is meshed using hybrid network technology to obtain a meshed geometric model, including: Determine the initial coarse mesh; among them, the cavity / flow channel region adopts the hexahedral dominant mesh, the complex curved surface adopts the tetrahedral mesh, and the thin-walled structure adopts the prism layer mesh. CNN is used to analyze the simulation results of the initial coarse mesh to identify high gradient regions; The mesh density in the high gradient region is increased according to a preset density step size; The geometric model after mesh refinement is further analyzed using CNN to analyze the simulation results, and high gradient regions are further identified. The mesh is then dynamically refined until the target accuracy is achieved, resulting in the geometric model after mesh division.
3. The method according to claim 1, characterized in that, The parameter optimization model includes a U-Net model, a parameter optimization model, and a generative adversarial network; the step of inputting the simulation results into the parameter optimization model to obtain the adjustment parameters for the mold's gate, runner system, and cooling water circuit includes: The animation of the molten metal flow front is input into the U-Net model to detect information on uneven filling, air entrapment, or short-shot phenomena in the molten metal; wherein, the U-Net model is pre-trained based on samples of the molten metal flow front animation; When uneven filling, air entrapment, or short injection occurs in the molten metal, a prompt message is generated, which includes a prompt indicating the location of the problematic gate or the injection speed.
4. The method according to claim 3, characterized in that, The step of inputting the simulation results into the parameter optimization model to obtain the adjustment parameters for the mold's gate, runner system, and cooling water circuit also includes: The stress distribution cloud map and temperature cloud map are respectively input into the generative adversarial network to obtain high-precision stress distribution cloud map and high-precision temperature cloud map; wherein, the generative adversarial network is trained in advance based on stress distribution cloud map samples and temperature cloud map samples.
5. The method according to claim 4, characterized in that, The simulation results are input into the parameter optimization model to obtain the adjustment parameters for the mold's gate, runner system, and cooling water circuit. This also includes: The filling process analysis information, solidification information, high-precision stress distribution cloud map, and high-precision temperature cloud map are input into the multi-task analysis model to obtain the porosity, thermal cracking probability, and shrinkage risk analysis results; wherein, the multi-task analysis model is pre-trained based on the simulation data sample.
6. An aluminum alloy machining mold, characterized in that, The aluminum alloy processing mold is obtained by using the mold optimization process of the zinc-aluminum alloy die-casting optical module as described in any one of claims 1-5.