Finish machining optimization method and device for non-standard mineral casting

Abstract

The invention provides a finish machining optimization method and device for a non-standard mineral casting, and relates to the technical field of machining parameter optimizing.The method comprises the steps that casting parameters are obtained, an initial finish machining parameter sequence is generated, a casting machining virtual platform is built, simulated casting parameters are obtained, a mapping model is built, and an optimized finish machining parameter sequence is obtained; and machining control is conducted through numerical control machining equipment. The technical problems that in the prior art, due to the fact that accurate machining parameters are lacked, the machining precision is low, and the product quality and the production efficiency are further affected can be solved, meanwhile, due to the fact that effective prediction means are lacked, the machining result cannot be accurately predicted in advance, parameter adjustment in the machining process becomes difficult, and the product quality and the production efficiency are improved. The intelligent level of casting machining is improved, and the product quality is improved.

Description

Technical Field

[0001] This application relates to the field of processing parameter optimization technology, and in particular to a method and apparatus for optimizing the finishing of non-standard mineral castings. Background Technology

[0002] With the continuous development of science and technology and industry, non-standard mineral castings have been widely used in many fields, such as aerospace, automobile manufacturing, and mechanical engineering. However, due to the diverse shapes, dimensions, and performance requirements of non-standard mineral castings...

[0003] Currently, traditional casting processing often requires multiple trials and adjustments to achieve the desired processing results, which often fails to meet the requirements of high precision and high efficiency.

[0004] In summary, the lack of precise processing parameters in existing technologies leads to low processing accuracy, which further affects product quality and production efficiency. At the same time, the lack of effective prediction methods makes it impossible to accurately predict the processing results in advance, making parameter adjustment during the processing process quite difficult. Summary of the Invention

[0005] The purpose of this application is to provide a method and apparatus for optimizing the finishing of non-standard mineral castings, in order to solve the technical problem that the lack of precise processing parameters in the prior art leads to low processing accuracy, which further affects product quality and production efficiency. At the same time, due to the lack of effective prediction methods, it is impossible to accurately predict the processing results in advance, making parameter adjustment during the processing process more difficult.

[0006] In view of the above problems, this application provides a method and apparatus for optimizing the finishing of non-standard mineral castings.

[0007] In a first aspect, this application provides a method for optimizing the finishing of non-standard mineral castings. The method is implemented using a finishing optimization device for non-standard mineral castings. The method includes: determining a target mineral casting; establishing a three-dimensional model of the target mineral casting; constructing target casting parameters based on the three-dimensional model; extracting initial casting parameters of the target mineral casting; generating an initial finishing parameter sequence based on the initial casting parameters and the target casting parameters using a parameter configuration library; building a casting processing virtual platform; importing the initial casting parameters and the initial finishing parameter sequence into the casting processing virtual platform to obtain simulated casting parameters; establishing a mapping model between the initial finishing parameter sequence and the simulated casting parameters; performing parameter mapping between the target casting parameters and the simulated casting parameters; gradually approximating the simulated casting parameters to the target casting parameters based on a preset parameter step size; simultaneously adjusting the initial finishing parameter sequence through the mapping model to obtain an optimized finishing parameter sequence; and inputting the optimized finishing parameter sequence into a CNC machining equipment to perform finishing control on the target mineral casting.

[0008] Secondly, this application also provides a finishing optimization device for non-standard mineral castings, used to execute a finishing optimization method for non-standard mineral castings as described in the first aspect, wherein the device includes: a casting parameter acquisition module, which is used to determine a target mineral casting, establish a three-dimensional model of the target mineral casting, and construct target casting parameters based on the three-dimensional model; a parameter sequence generation module, which is used to extract initial casting parameters of the target mineral casting, and generate an initial finishing parameter sequence through a parameter configuration library based on the initial casting parameters and the target casting parameters; and a mapping model acquisition module, which is used to build a casting processing... A virtual platform is used to import the initial casting parameters and the initial finishing parameter sequence into the casting processing virtual platform to obtain simulated casting parameters and establish a mapping model between the initial finishing parameter sequence and the simulated casting parameters. A finishing parameter sequence acquisition module is used to map the target casting parameters to the simulated casting parameters, gradually approximate the simulated casting parameters to the target casting parameters based on a preset parameter step size, and simultaneously adjust the initial finishing parameter sequence through the mapping model to obtain an optimized finishing parameter sequence. A finishing control module is used to input the optimized finishing parameter sequence into a CNC machining equipment to perform finishing control on the target mineral casting.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: By identifying the target mineral casting, a three-dimensional model of the target mineral casting is established, and target casting parameters are constructed based on the three-dimensional model. Initial casting parameters of the target mineral casting are extracted, and an initial finishing parameter sequence is generated through a parameter configuration library based on the initial casting parameters and the target casting parameters. A casting processing virtual platform is built, and the initial casting parameters and the initial finishing parameter sequence are imported into the casting processing virtual platform to obtain simulated casting parameters, and a mapping model between the initial finishing parameter sequence and the simulated casting parameters is established. The target casting parameters and the simulated casting parameters are matched, and parameters are mapped based on preset parameters. By gradually approximating the target casting parameters with the simulated casting parameters in several steps, and simultaneously adjusting the initial finishing parameter sequence through a mapping model, an optimized finishing parameter sequence is obtained. The optimized finishing parameter sequence is then input into a CNC machining equipment to perform finishing control on the target mineral casting. This effectively solves the technical problem of existing technologies lacking precise machining parameters, resulting in low machining accuracy and further affecting product quality and production efficiency. At the same time, due to the lack of effective prediction methods, it is impossible to accurately predict the machining results in advance, making parameter adjustment during the machining process more difficult. This improves the level of intelligence in casting machining and enhances product quality.

[0010] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating the optimization method for finishing non-standard mineral castings according to this application; Figure 2 This is a schematic diagram of the structure of a finishing optimization device for non-standard mineral castings according to this application.

[0013] Explanation of reference numerals in the attached figures: Module 11 for acquiring casting parameters, module 12 for generating parameter sequences, module 13 for acquiring mapping models, module 14 for acquiring finishing parameter sequences, and module 15 for controlling finishing. Detailed Implementation

[0014] This application provides a method and apparatus for optimizing the finishing of non-standard mineral castings, which solves the technical problem that the lack of precise processing parameters in the prior art leads to low processing accuracy, further affecting product quality and production efficiency. At the same time, due to the lack of effective prediction methods, it is impossible to accurately predict the processing results in advance, making parameter adjustment during the processing more difficult. This improves the level of intelligence in casting processing and enhances product quality.

[0015] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0016] Example 1 Please see the appendix Figure 1 This application provides a method for optimizing the finishing of non-standard mineral castings. The method is applied to a finishing optimization device for non-standard mineral castings, and specifically includes the following steps: S1: Determine the target mineral casting, establish a three-dimensional model of the target mineral casting, and construct the target casting parameters based on the three-dimensional model of the casting; Specifically, the target mineral casting is identified. If a physical sample already exists, detailed dimensional data of the casting is obtained using a 3D scanner or measuring tools such as calipers and micrometers. A 3D modeling software, such as SolidWorks, AutoCAD, or Blender, is then used to create a 3D model of the casting. Based on the collected data, the shape and dimensions of the casting are accurately drawn in the modeling software. The accuracy of the model is ensured, especially the precision of critical dimensions and mating surfaces. Based on the 3D model, key parameters of the casting are determined, such as length, width, height, wall thickness, hole diameter, and the positional accuracy of mating surfaces.

[0017] S2: Extract the initial casting parameters of the target mineral casting, and generate an initial finishing parameter sequence based on the initial casting parameters and the target casting parameters through a parameter configuration library; Specifically, the initial dimensions, shape, and material parameters of the target mineral casting are measured or obtained from its design drawings. These parameters include, but are not limited to, the casting's length, width, height, wall thickness, inner and outer diameters, material hardness, and surface roughness. The extracted initial casting parameters are compared with the target casting parameters to identify which dimensions or characteristics need adjustment to achieve the target parameters. The parameter configuration library is a database or knowledge base containing various combinations of machining parameters, which can recommend corresponding machining parameters based on different initial and target parameters. This library includes finishing-related parameters such as cutting speed, feed rate, depth of cut, tool type, and coolant usage. Based on the differences between the initial and target parameters, and the recommended values ​​in the parameter configuration library, an initial finishing parameter sequence is generated. The initial finishing parameter sequence includes multiple finishing parameter subsequences, corresponding to multiple finishing parameters.

[0018] S3: Build a virtual platform for casting processing, import the initial casting parameters and the initial finishing parameter sequence into the virtual platform for casting processing, obtain the simulated casting parameters, and establish a mapping model between the initial finishing parameter sequence and the simulated casting parameters; Specifically, the casting machining virtual platform is a virtual platform for simulating machining processes, capable of simulating the casting machining process and outputting the parameters of the simulated casting after machining. The platform's hardware and software environment are configured to ensure stable operation and sufficient computing power to simulate complex machining processes. Initial casting parameters and the generated initial finishing parameter sequence are imported into the virtual platform. The simulated machining process is started on the virtual platform, using the initial finishing parameter sequence to simulate the machining of the initial casting. Changes in various parameters during the simulated machining process, such as cutting force, temperature, and stress distribution, are monitored. After the simulated machining is completed, the parameters of the simulated casting are extracted from the virtual platform. These parameters include the machined dimensions, shape, surface roughness, and hardness. The relationship between the initial finishing parameter sequence and the simulated casting parameters is analyzed. Data analysis and modeling techniques, such as regression analysis and neural networks, are used to establish a mapping model between the two. For example, one parameter in the simulated casting parameters is derived from one finishing parameter, or it can be derived from multiple finishing parameters. This model should be able to predict the parameter state of the casting after machining given a set of finishing parameters.

[0019] S4: Match the target casting parameters with the simulated casting parameters, and gradually approximate the simulated casting parameters with the target casting parameters based on the preset parameter step size. Simultaneously, gradually adjust the initial finishing parameter sequence through the mapping model to obtain the optimized finishing parameter sequence. Specifically, first, ensure a clear correspondence between the target casting parameters and the simulated casting parameters. Each parameter has a corresponding item in both sets of data, such as length corresponding to length, diameter to diameter, etc. Based on machining accuracy requirements, material properties, and the performance of the machining equipment, set the parameter adjustment step size. The step size determines the magnitude of each parameter adjustment; it should be small enough to ensure the accuracy of the approximation process, but not too small to avoid affecting optimization efficiency. For each pair of corresponding parameters, such as size and shape accuracy, compare the differences between the simulated casting parameters and the target casting parameters. Based on the magnitude and direction of the difference, and the preset parameter step size, gradually adjust the simulated casting parameters to approximate the target casting parameters. Whenever the simulated casting parameters are adjusted, use a mapping model to predict the required changes in finishing parameters. Based on the prediction results of the mapping model, synchronously adjust the corresponding parameters in the initial finishing parameter sequence. Repeat the above steps until the simulated casting parameters are sufficiently close to the target casting parameters, or reach the preset iteration limit. When the simulated casting parameters meet the tolerance requirements of the target casting parameters, stop the iteration process. The corresponding finishing parameter sequence at this point is the optimized finishing parameter sequence. If the verification results are not satisfactory, you can go back to the previous steps to further adjust the parameter step size or mapping model to obtain better optimization results.

[0020] S5: Input the optimized finishing parameter sequence into the CNC machining equipment to perform finishing control on the target mineral casting.

[0021] Specifically, the parameters are converted into a format that the CNC machining equipment can recognize and execute, such as G-code. The accuracy and completeness of the parameters during conversion are ensured to avoid data loss or format errors. The converted, optimized finishing parameters are input into the CNC machining equipment via the CNC system interface or data transmission method. The machining program is started. The target mineral casting is correctly clamped on the worktable of the CNC machining equipment, ensuring the stability of the casting and machining accuracy. The appropriate machining mode and parameter settings are selected on the control panel of the CNC machining equipment. The finishing program is started, allowing the CNC machining equipment to automatically machine according to the optimized finishing parameter sequence.

[0022] Furthermore, this application also includes: Acquire historical casting finishing data, determine multiple casting samples based on the historical casting finishing data, and extract the initial casting parameter set, the sample finishing parameter sequence set, and the sample actual casting parameter set based on the multiple casting samples; The initial casting parameter set, the finishing parameter sequence set, and the actual casting parameter set are mapped and stored to generate an actual sample library. Supervised learning training is performed based on the initial casting parameter set, the actual casting parameters, and the finishing parameter sequence set to construct an auxiliary generation network. A parameter configuration library is generated based on the actual sample library and the auxiliary generation network.

[0023] Specifically, historical casting finishing data is collected from the company's database, production records, or related documents. This data includes the initial parameters of the casting, the finishing parameters used, and the actual parameters after machining. The historical data is cleaned to remove duplicate, erroneous, or incomplete records, ensuring accuracy and validity. Several representative castings are selected as samples from the historical data. The samples include various casting types, sizes, and materials to ensure diversity and representativeness. The initial parameters of each sample before machining, such as size, shape, and material, are extracted. The parameter sequence used during the finishing process of each sample is extracted, including cutting speed, feed rate, and depth of cut. The actual parameters after machining of each sample are extracted, such as finished size, shape accuracy, and surface roughness. The extracted initial casting parameter set, the sample finishing parameter sequence set, and the sample actual casting parameter set are mapped and stored in a one-to-one correspondence. This ensures that the three sets of parameters for each sample accurately correspond. These mapped data are stored in a structured database, forming a practical sample library. The data in the practical sample library is preprocessed, such as through normalization and standardization. A supervised learning model, such as a neural network or support vector machine, is selected to learn the mapping relationship between initial casting parameters, finishing parameters, and actual casting parameters. The supervised learning model is trained using a sample set of initial casting parameters and a sample set of finishing parameter sequences as input, and a sample set of actual casting parameters as output. The model's performance is optimized by continuously adjusting its parameters and structure. Based on the trained supervised learning model, an auxiliary generative network is constructed. This network can predict the corresponding finishing parameter sequences based on the input initial casting parameters and the desired actual casting parameters. The auxiliary generative network explores the finishing parameter sequences corresponding to different initial casting parameters and desired actual casting parameters. This can be achieved through sampling and prediction within the parameter space. The explored finishing parameter sequences are stored along with their corresponding initial casting parameters and desired actual casting parameters, forming a parameter configuration library. This library can recommend suitable finishing parameter sequences based on the user's input, initial casting parameters, and desired actual casting parameters.

[0024] Furthermore, this application also includes: Input the initial casting parameters and the target casting parameters into the parameter configuration library to activate the actual sample library; By traversing multiple casting samples in the actual sample library, the joint similarity with the target mineral casting is calculated to obtain multiple joint similarities; The joint similarity scores are sorted to obtain the maximum joint similarity score. When the maximum joint similarity score is greater than or equal to a preset similarity threshold, the target casting sample is determined. The sample finishing parameter sequence of the target casting sample is used as the initial finishing parameter sequence.

[0025] Specifically, initial casting parameters and target casting parameters are input into a parameter configuration library. These parameters include characteristics such as size, shape, and material. Inputting parameters triggers a query mechanism in the parameter configuration library, activating data in the actual sample library related to the input parameters. Multiple casting samples in the actual sample library are traversed. Each sample contains initial casting parameters, a sequence of finishing parameters, and actual casting parameters. For each sample, the joint similarity between it and the input target mineral casting is calculated. Joint similarity can be calculated based on multiple dimensions, such as size similarity, shape similarity, and material similarity, and can be calculated using methods such as cosine similarity and Euclidean distance. The joint similarity value between each sample and the target mineral casting is obtained through calculation. The calculated joint similarities are sorted, either from high to low or from low to high. The largest value is selected from the sorted joint similarities. It is then checked whether the largest joint similarity is greater than or equal to a preset similarity threshold. This threshold is set according to actual needs and is used to determine whether the similarity between the sample and the target casting is sufficiently high. If the maximum joint similarity is greater than or equal to a preset similarity threshold, the corresponding sample is determined as the target casting sample. The finishing parameter sequence is extracted from the determined target casting sample. This extracted finishing parameter sequence is used as the initial finishing parameter sequence for subsequent casting finishing processes.

[0026] Furthermore, this application also includes: When the maximum joint similarity is less than a preset similarity threshold, the auxiliary generation network is activated; The initial casting parameters and the target casting parameters are input into the auxiliary generation network, which outputs an initial finishing parameter sequence.

[0027] Specifically, since the maximum joint similarity did not reach the preset threshold, instead of relying on historical data from the actual sample library, an auxiliary generation network is activated to generate the required finishing parameters. The initial casting parameters and target casting parameters undergo necessary preprocessing to adapt to the input format of the auxiliary generation network. This includes data normalization, standardization, or conversion to a format that the network can process. The processed initial casting parameters and target casting parameters are then passed as input data to the auxiliary generation network. The auxiliary generation network performs internal calculations and processing on the received input data, predicting a sequence of finishing parameters that matches the input parameters based on its learned mapping relationships. The auxiliary generation network ultimately outputs an initial finishing parameter sequence. This sequence is generated based on the patterns and rules learned by the network from the training data, specifically for the input initial casting parameters and target casting parameters.

[0028] Furthermore, this application also includes: Interact with the CNC machining equipment to determine the adjustable range of the finishing parameters, and configure a parameter adjustment space based on the adjustable range as the first parameter space; Obtain the material properties of the target mineral casting, and configure the material constraint space of the finishing parameters based on the material properties as the second parameter space; By merging the first parameter space and the second parameter space, a target finishing parameter space is generated; Using the target finishing parameter space as a constraint, the initial finishing parameter sequence is gradually adjusted to obtain an optimized finishing parameter sequence.

[0029] Specifically, the adjustable range of finishing parameters supported by the CNC machining equipment is queried through its interface or control panel. These parameters include cutting speed, feed rate, and depth of cut. Based on the adjustable range provided by the CNC machining equipment, a parameter adjustment space is configured. This space represents all possible parameter combinations within the equipment's capabilities and is called the first parameter space. The material properties of the target mineral casting, such as hardness, toughness, and thermal conductivity, are queried from a material database or relevant documents. Based on these material properties, a material constraint space for finishing parameters is configured. This space reflects the range of finishing parameters that can be safely used without impairing material properties or causing excessive wear and is called the second parameter space. The first parameter space, the equipment capabilities range, the second parameter space, and the material constraint range are then merged. The intersection of the two spaces is found, which is the range of finishing parameters that simultaneously satisfies both the equipment capabilities and material constraints. The merged space is the target finishing parameter space, representing the range of finishing parameters that can be safely and effectively used in actual machining. An initial sequence of finishing parameters obtained from a real sample library or predicted by an auxiliary generative network is used as the starting point. Under the constraints of the target finishing parameter space, each parameter in the initial finishing parameter sequence is gradually adjusted to seek the optimal machining effect. After a series of adjustments and tests, an optimized finishing parameter sequence is finally obtained, which can provide better machining effect and quality while meeting the equipment capacity and material constraints.

[0030] Furthermore, this application also includes: Interact with the CNC machining equipment to determine the transition limits of the finishing parameters, and configure parameter variation prohibitions based on the transition limits; Constrained by the target finishing parameter space and the parameter variation taboo, the initial finishing parameter sequence is gradually adjusted to obtain an optimized finishing parameter sequence.

[0031] Specifically, by communicating with the control system of the CNC machining equipment, the transient constraints of the equipment when adjusting finishing parameters are obtained. These constraints include the rate and magnitude of parameter adjustments, as well as dependencies between certain parameters. It is determined which parameter adjustments lead to equipment overload, vibration, or other adverse effects, thus identifying which parameter changes should be avoided. The transient constraint information obtained from the CNC machining equipment is analyzed to identify which finishing parameter adjustments might trigger adverse consequences. Based on the analysis results, taboo rules for parameter changes are established. For example, some parameters may not be allowed to be adjusted significantly in a short period, or the adjustment of some parameters must be coordinated with the adjustment of other parameters. During the adjustment of the initial finishing parameter sequence, the established parameter change taboos are strictly followed to avoid triggering the equipment's transient constraints. Under the dual constraints of the target finishing parameter space and parameter change taboos, the initial finishing parameter sequence is gradually adjusted. This includes multiple iterations and tests to ensure that each adjustment meets all constraints. After each parameter adjustment, the machining effect and equipment status are evaluated to ensure that no transient constraints are triggered and the machining quality meets expectations. Ultimately, an optimized finishing parameter sequence that meets both the requirements of the target finishing parameter space and the parameter change taboos is obtained.

[0032] Furthermore, this application also includes: Based on the target finishing parameter space and the parameter variation taboos, generate equipment operating constraints for the CNC machining equipment; The optimized finishing parameter sequence is input into the CNC machining equipment, and the finishing control of the target mineral casting is executed based on the equipment's working constraints.

[0033] Specifically, the target finishing parameter space and parameter variation restrictions are integrated into a clear equipment operating constraint file or instruction set. This file serves as the operating specification for the CNC machining equipment during finishing. The equipment operating constraint file or instruction set is input into the CNC machining equipment's control system. It is ensured that the equipment can recognize and comply with these constraints, automatically checking and adjusting parameters during machining. Before inputting, the optimized finishing parameter sequence is verified again to ensure it meets all conditions within the equipment operating constraints. Each adjustment in the parameter sequence is ensured to conform to the previously set target finishing parameter space and parameter variation restrictions. The verified optimized finishing parameter sequence is input into the CNC machining equipment through its user interface or control system interface. The CNC machining equipment initializes according to the input optimized finishing parameter sequence. The equipment status is checked to ensure all components are in normal working order. After ensuring all preparations are complete and the equipment is in good condition, the finishing process is started. The CNC machining equipment will automatically perform machining based on the input optimized finishing parameter sequence and equipment operating constraints. During machining, the CNC machining equipment monitors various parameters in real time to ensure they remain within the equipment operating constraints. If any situation exceeds the constraints, the equipment should be able to automatically adjust or stop processing to prevent equipment damage or degradation of processing quality. The finishing process ends when the CNC machining equipment completes all steps according to the optimized finishing parameter sequence.

[0034] In summary, the finishing optimization method for non-standard mineral castings provided in this application has the following technical effects: By identifying the target mineral casting, a three-dimensional model of the target mineral casting is established, and target casting parameters are constructed based on the three-dimensional model. Initial casting parameters of the target mineral casting are extracted, and an initial finishing parameter sequence is generated through a parameter configuration library based on the initial casting parameters and the target casting parameters. A casting processing virtual platform is built, and the initial casting parameters and the initial finishing parameter sequence are imported into the casting processing virtual platform to obtain simulated casting parameters, and a mapping model between the initial finishing parameter sequence and the simulated casting parameters is established. The target casting parameters and the simulated casting parameters are matched, and parameters are mapped based on preset parameters. By gradually approximating the target casting parameters with the simulated casting parameters in several steps, and simultaneously adjusting the initial finishing parameter sequence through a mapping model, an optimized finishing parameter sequence is obtained. The optimized finishing parameter sequence is then input into a CNC machining equipment to perform finishing control on the target mineral casting. This effectively solves the technical problem of existing technologies lacking precise machining parameters, resulting in low machining accuracy and further affecting product quality and production efficiency. At the same time, due to the lack of effective prediction methods, it is impossible to accurately predict the machining results in advance, making parameter adjustment during the machining process more difficult. This improves the level of intelligence in casting machining and enhances product quality.

[0035] Example 2 Based on the same inventive concept as the finishing optimization method for non-standard mineral castings described in the foregoing embodiments, this application also provides a finishing optimization device for non-standard mineral castings. Please refer to the appendix. Figure 2 The device includes: The casting parameter acquisition module 11 is used to determine the target mineral casting, establish a three-dimensional model of the target mineral casting, and construct the target casting parameters based on the three-dimensional model of the casting. The parameter sequence generation module 12 is used to extract the initial casting parameters of the target mineral casting, and generate an initial finishing parameter sequence based on the initial casting parameters and the target casting parameters through a parameter configuration library. The mapping model acquisition module 13 is used to build a casting processing virtual platform, import the initial casting parameters and the initial finishing parameter sequence into the casting processing virtual platform, obtain the simulated casting parameters, and establish a mapping model between the initial finishing parameter sequence and the simulated casting parameters. The finishing parameter sequence acquisition module 14 is used to match the target casting parameters with the simulated casting parameters, gradually approximate the simulated casting parameters to the target casting parameters based on a preset parameter step size, and simultaneously adjust the initial finishing parameter sequence through a mapping model to obtain an optimized finishing parameter sequence. The finishing control module 15 is used to input the optimized finishing parameter sequence into the CNC machining equipment to perform finishing control on the target mineral casting.

[0036] Furthermore, the system also includes an auxiliary network construction module, which is used for: Acquire historical casting finishing data, determine multiple casting samples based on the historical casting finishing data, and extract the initial casting parameter set, the sample finishing parameter sequence set, and the sample actual casting parameter set based on the multiple casting samples; The initial casting parameter set, the finishing parameter sequence set, and the actual casting parameter set are mapped and stored to generate an actual sample library. Supervised learning training is performed based on the initial casting parameter set, the actual casting parameters, and the finishing parameter sequence set to construct an auxiliary generation network. A parameter configuration library is generated based on the actual sample library and the auxiliary generation network.

[0037] Furthermore, the system also includes a similarity acquisition module, which is used for: Input the initial casting parameters and the target casting parameters into the parameter configuration library to activate the actual sample library; By traversing multiple casting samples in the actual sample library, the joint similarity with the target mineral casting is calculated to obtain multiple joint similarities; The joint similarity scores are sorted to obtain the maximum joint similarity score. When the maximum joint similarity score is greater than or equal to a preset similarity threshold, the target casting sample is determined. The sample finishing parameter sequence of the target casting sample is used as the initial finishing parameter sequence.

[0038] Furthermore, the system also includes a finishing parameter sequence acquisition module, which is used for: When the maximum joint similarity is less than a preset similarity threshold, the auxiliary generation network is activated; The initial casting parameters and the target casting parameters are input into the auxiliary generation network, which outputs an initial finishing parameter sequence.

[0039] Furthermore, the system also includes an optimized finishing sequence acquisition module, which is used for: Interact with the CNC machining equipment to determine the adjustable range of the finishing parameters, and configure a parameter adjustment space based on the adjustable range as the first parameter space; Obtain the material properties of the target mineral casting, and configure the material constraint space of the finishing parameters based on the material properties as the second parameter space; By merging the first parameter space and the second parameter space, a target finishing parameter space is generated; Using the target finishing parameter space as a constraint, the initial finishing parameter sequence is gradually adjusted to obtain an optimized finishing parameter sequence.

[0040] Furthermore, the system also includes a change taboo acquisition module, which is used for: Interact with the CNC machining equipment to determine the transition limits of the finishing parameters, and configure parameter variation prohibitions based on the transition limits; Constrained by the target finishing parameter space and the parameter variation taboo, the initial finishing parameter sequence is gradually adjusted to obtain an optimized finishing parameter sequence.

[0041] Furthermore, the system also includes a processing control module, which is used for: Based on the target finishing parameter space and the parameter variation taboos, generate equipment operating constraints for the CNC machining equipment; The optimized finishing parameter sequence is input into the CNC machining equipment, and the finishing control of the target mineral casting is executed based on the equipment's working constraints.

[0042] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The finishing optimization method and specific examples for non-standard mineral castings in Example 1 are also applicable to the finishing optimization apparatus for non-standard mineral castings in this embodiment. Through the foregoing detailed description of the finishing optimization method for non-standard mineral castings, those skilled in the art can clearly understand the finishing optimization apparatus for non-standard mineral castings in this embodiment; therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0043] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0044] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for optimizing the finishing of non-standard mineral castings, characterized in that, The method further includes: Identify the target mineral casting, establish a three-dimensional model of the target mineral casting, and construct the target casting parameters based on the three-dimensional model of the casting; Extract the initial casting parameters of the target mineral casting, and generate an initial finishing parameter sequence based on the initial casting parameters and the target casting parameters through a parameter configuration library; A virtual platform for casting processing is built. The initial casting parameters and the initial finishing parameter sequence are imported into the virtual platform to obtain the simulated casting parameters, and a mapping model between the initial finishing parameter sequence and the simulated casting parameters is established. The parameters of the target casting and the parameters of the simulated casting are mapped to each other. Based on the preset parameter step size, the parameters of the simulated casting are gradually approximated to the parameters of the target casting. At the same time, the initial finishing parameter sequence is gradually adjusted through the mapping model to obtain the optimized finishing parameter sequence. The optimized finishing parameter sequence is input into the CNC machining equipment to perform finishing control on the target mineral casting.

2. The method for optimizing the finishing of non-standard mineral castings according to claim 1, characterized in that, The method further includes: Obtain historical casting finishing data, determine multiple casting samples based on the historical casting finishing data, and extract the initial casting parameter set, the sample finishing parameter sequence set, and the sample actual casting parameter set based on the multiple casting samples; The initial casting parameter set, the finishing parameter sequence set, and the actual casting parameter set are mapped and stored to generate an actual sample library. Supervised learning training is performed based on the initial casting parameter set, the actual casting parameters, and the finishing parameter sequence set to construct an auxiliary generation network. A parameter configuration library is generated based on the actual sample library and the auxiliary generation network.

3. The method for optimizing the finishing of non-standard mineral castings according to claim 2, characterized in that, Based on the initial casting parameters and the target casting parameters, an initial finishing parameter sequence is generated through a parameter configuration library, including: Input the initial casting parameters and the target casting parameters into the parameter configuration library to activate the actual sample library; By traversing multiple casting samples in the actual sample library, the joint similarity with the target mineral casting is calculated to obtain multiple joint similarities; The joint similarity scores are sorted to obtain the maximum joint similarity score. When the maximum joint similarity score is greater than or equal to a preset similarity threshold, the target casting sample is determined. The sample finishing parameter sequence of the target casting sample is used as the initial finishing parameter sequence.

4. The method for optimizing the finishing of non-standard mineral castings according to claim 3, characterized in that, The method further includes: When the maximum joint similarity is less than a preset similarity threshold, the auxiliary generation network is activated; The initial casting parameters and the target casting parameters are input into the auxiliary generation network, which outputs an initial finishing parameter sequence.

5. The method for optimizing the finishing of non-standard mineral castings according to claim 1, characterized in that, The method includes: Interact with the CNC machining equipment to determine the adjustable range of the finishing parameters, and configure a parameter adjustment space based on the adjustable range as the first parameter space; Obtain the material properties of the target mineral casting, and configure the material constraint space of the finishing parameters based on the material properties as the second parameter space; By merging the first parameter space and the second parameter space, a target finishing parameter space is generated; Using the target finishing parameter space as a constraint, the initial finishing parameter sequence is gradually adjusted to obtain an optimized finishing parameter sequence.

6. The method for optimizing the finishing of non-standard mineral castings according to claim 5, characterized in that, The method further includes: Interact with the CNC machining equipment to determine the transition limits of the finishing parameters, and configure parameter variation prohibitions based on the transition limits; Constrained by the target finishing parameter space and the parameter variation taboo, the initial finishing parameter sequence is gradually adjusted to obtain an optimized finishing parameter sequence.

7. The method for optimizing the finishing of non-standard mineral castings according to claim 6, characterized in that, The optimized finishing parameter sequence is input into a CNC machining equipment to perform finishing control on the target mineral casting, including: Based on the target finishing parameter space and the parameter variation taboos, generate equipment operating constraints for the CNC machining equipment; The optimized finishing parameter sequence is input into the CNC machining equipment, and the finishing control of the target mineral casting is executed based on the equipment's working constraints.

8. A finishing optimization device for non-standard mineral castings, characterized in that, The apparatus is used to perform a finishing optimization method for non-standard mineral castings according to any one of claims 1 to 7, the apparatus comprising: A casting parameter acquisition module is used to determine the target mineral casting, establish a three-dimensional model of the target mineral casting, and construct the target casting parameters based on the three-dimensional model of the casting. A parameter sequence generation module is used to extract the initial casting parameters of the target mineral casting, and generate an initial finishing parameter sequence based on the initial casting parameters and the target casting parameters through a parameter configuration library. The mapping model acquisition module is used to build a virtual platform for casting processing, import the initial casting parameters and the initial finishing parameter sequence into the virtual platform for casting processing, obtain the simulated casting parameters, and establish a mapping model between the initial finishing parameter sequence and the simulated casting parameters. The finishing parameter sequence acquisition module is used to match the parameters of the target casting with the parameters of the simulated casting, gradually approximate the parameters of the simulated casting with the parameters of the target casting based on a preset parameter step size, and simultaneously adjust the initial finishing parameter sequence through a mapping model to obtain an optimized finishing parameter sequence. A finishing control module is used to input the optimized finishing parameter sequence into a CNC machining equipment to perform finishing control on the target mineral casting.

Images