Method, device, equipment, medium and program product for determining aluminum casting mold temperature collection point

Abstract

The application relates to the field of aluminum casting molds, and discloses a method, a device, equipment, a medium and a program product for determining temperature collection points of an aluminum casting mold, the method comprising: simulating a process of manufacturing a target product by using a target aluminum casting mold to obtain simulation temperature time sequence data of manufacturing the target product by using the target aluminum casting mold; performing dimension reduction on the simulation temperature data based on a PCA-UMAP-tSNE dimension reduction algorithm to obtain low-dimensional temperature data; performing cluster analysis on the low-dimensional temperature data to obtain n candidate temperature collection points; matching the n candidate temperature collection points with structural features of the target aluminum casting mold to obtain N target temperature collection points, wherein N<=n, and the target aluminum casting mold is provided with temperature collection points capable of accurately reflecting temperature change conditions of the aluminum casting mold, so that temperature collection and feedback control performed by using the temperature collection points can improve the accuracy and reliability of temperature collection in a casting process, thereby improving the yield of target product casting.

Description

Technical Field

[0001] This disclosure generally relates to the field of aluminum casting molds, and specifically to a method, apparatus, equipment, medium, and program product for determining temperature acquisition points in aluminum casting molds. Background Technology

[0002] As wheel hubs become more precise, complex, and lightweight, the requirements for controllability in the wheel hub production process are increasing. Ultimately, this places higher demands on the stability of the temperature field of the wheel hub mold during production. In addition, to improve casting efficiency, forced cooling of the mold is required during the casting process. Existing mold cooling solutions involve installing air and water cooling channels in the top, bottom, and side molds.

[0003] In related technologies, the selection of temperature measurement points during aluminum wheel casting is primarily based on experience, choosing locations near the mold cooling pipes for temperature measurement. However, this experience-based temperature acquisition method, lacking any data or theoretical basis, results in the selected temperature measurement points failing to accurately reflect the temperature changes in the aluminum casting mold. Consequently, quality problems arising from abnormal temperature control are prone to occur during production. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method, apparatus, equipment, medium and program product for determining the temperature acquisition point of aluminum casting mold, so as to provide the target aluminum casting mold with a temperature acquisition point that can accurately reflect the temperature change of the aluminum casting mold, so that the temperature acquisition and feedback control using the temperature acquisition point can improve the accuracy and reliability of temperature acquisition during the casting process, thereby improving the yield of the target product casting.

[0005] In a first aspect, embodiments of this application provide a method for determining the temperature acquisition points of an aluminum casting mold, including:

[0006] The process of manufacturing a target product using a target aluminum casting mold is simulated to obtain simulated temperature data for manufacturing the target product using the target aluminum casting mold; the simulated temperature data includes a time series of temperature changes over time for multiple grid points corresponding to the simulation space during at least one casting cycle.

[0007] The simulated temperature data is reduced in dimensionality using the PCA-UMAP-tSNE dimensionality reduction algorithm to obtain low-dimensional temperature data.

[0008] Cluster analysis was performed on the low-dimensional temperature data to obtain n candidate temperature acquisition points;

[0009] The n candidate temperature acquisition points are matched with the structural features of the target aluminum casting mold to obtain N target temperature acquisition points, where N≤n.

[0010] In some embodiments, the step of performing cluster analysis on the low-dimensional temperature data to obtain n candidate temperature acquisition points includes:

[0011] A first-level cluster analysis is performed on the low-dimensional temperature data. The elbow rule and silhouette coefficient are used to determine the target number of clusters corresponding to the low-dimensional temperature data, and multiple first-level clusters corresponding to the target number of clusters are obtained.

[0012] Perform secondary clustering analysis on the primary clusters to obtain at least one secondary cluster corresponding to each primary cluster;

[0013] For each of the first-level clusters, the candidate temperature acquisition points corresponding to the first-level clusters are determined based on at least one of the second-level clusters.

[0014] In some embodiments, determining the candidate temperature acquisition point corresponding to the primary cluster based on at least one secondary cluster includes:

[0015] Based on at least one of the secondary clusters, determine the dimensionality reduction feature location points corresponding to the primary cluster;

[0016] The candidate temperature acquisition points are obtained by spatially mapping the reduced-dimensional feature locations.

[0017] In some embodiments, spatially mapping the reduced feature location points to obtain the candidate temperature acquisition points includes:

[0018] Perform a first inverse transformation on the reduced-dimensional feature locations to obtain the original spatial feature points;

[0019] A second inverse transformation is performed on the original spatial feature points to obtain the candidate temperature acquisition points.

[0020] In some embodiments, the secondary clustering analysis includes multiple clustering branches performed based on different numbers of secondary clusters, and determining the dimensionality-reduced feature location points corresponding to the primary cluster based on at least one of the secondary clusters includes:

[0021] For each clustering branch, obtain the temperature change of each secondary clustering reaction;

[0022] By comparing the temperature changes of the secondary clustering reactions in each of the multiple clustering branches, the dimensionality reduction feature location points corresponding to the primary cluster are determined.

[0023] In some embodiments, determining the dimensionality-reduced feature location point corresponding to the first-level cluster by comparing the temperature changes of the secondary clustering reactions of each of the plurality of clustering branches includes:

[0024] Based on the similarity of the temperature changes of the multiple secondary clustering reactions among the multiple clustering branches, a target clustering branch for determining the dimensionality reduction feature location point is determined;

[0025] The dimensionality reduction feature location point is determined based on at least one representative cluster point corresponding to the target clustering branch, and the representative cluster point is the cluster center corresponding to the secondary cluster.

[0026] Secondly, embodiments of this application provide a device for determining the temperature acquisition point of an aluminum casting mold, comprising:

[0027] The simulation module is used to simulate the process of manufacturing a target product using a target aluminum casting mold, and to obtain simulation temperature data for manufacturing the target product using the target aluminum casting mold; the simulation temperature data includes a time series of temperature changes over time for multiple grid points corresponding to the simulation space in at least one casting cycle.

[0028] The dimensionality reduction module is used to reduce the dimensionality of the simulated temperature data based on the PCA-UMAP-tSNE dimensionality reduction algorithm to obtain low-dimensional temperature data.

[0029] The clustering module is used to perform cluster analysis on the low-dimensional temperature data to obtain n candidate temperature acquisition points;

[0030] The matching module is used to match the n candidate temperature acquisition points with the structural features of the target aluminum casting mold to obtain N target temperature acquisition points, where N≤n.

[0031] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in embodiments of this application.

[0032] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in embodiments of this application.

[0033] Fifthly, embodiments of this application provide a computer program product, including a computer program, characterized in that, when the computer program is executed by a processor, it implements the method described in embodiments of this application.

[0034] The method and apparatus for determining temperature acquisition points in aluminum casting molds proposed in this application analyze simulated temperature data from the process of manufacturing target products using the target aluminum casting mold. This allows for accurate identification of target temperature acquisition points that reflect temperature changes during the casting process. Specifically, the PCA-UMAP-tSNE dimensionality reduction algorithm effectively reduces high-dimensional temperature time series data to the target dimension while ensuring the reliability of cluster analysis by maintaining the local data structure of the low-dimensional temperature data. Furthermore, secondary cluster analysis allows for finer-grained analysis of temperature changes in clusters with similar temperature variations, identifying more representative cluster points within the same cluster to improve the accuracy of candidate temperature acquisition points. Additionally, by matching candidate temperature acquisition points with the structural features of the target aluminum casting mold, this application ensures that the final selected target temperature acquisition points are reliable measurement points on the target aluminum casting mold, improving the feasibility of the target temperature acquisition point location.

[0035] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0036] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0037] Figure 1 A flowchart illustrating a method for determining temperature acquisition points of an aluminum casting mold according to an embodiment of this application is shown.

[0038] Figure 2 A flowchart illustrating a further detailed process of step 103 of this application is shown;

[0039] Figure 3 This paper shows a spatial schematic diagram of the dimensionality reduction feature location points provided in an embodiment of this application;

[0040] Figure 4 It shows Figure 3 A schematic diagram of the space inverted to the original space;

[0041] Figure 5 A flowchart illustrating a method for determining temperature acquisition points of an aluminum casting mold according to another embodiment of this application is shown.

[0042] Figure 6 A schematic diagram showing the temperature acquisition points set on an aluminum casting mold according to an embodiment of this application is shown;

[0043] Figure 7This application provides an embodiment of the experimental comparison curve data of temperature and cooling airflow at a mold measuring point near the gate in the bottom mold.

[0044] Figure 8 This application provides a comparative curve of standard deviation experimental data for 100 casting cycle mold measuring points near the gate position in an embodiment of the present application.

[0045] Figure 9 This application provides an embodiment of the experimental comparison curve data of temperature and cooling airflow at the mold measuring point near the spokes of the bottom mold.

[0046] Figure 10 This application provides a comparative curve of experimental standard deviation data for 100 casting cycle mold measuring points near the spokes of the bottom mold according to an embodiment of the present application.

[0047] Figure 11 This application provides an embodiment of a comparative experimental curve showing the temperature and cooling airflow at a mold measuring point near the outer rim of the bottom mold.

[0048] Figure 12 This application provides a comparative curve of standard deviation experimental data for 100 casting cycle mold measuring points near the outer rim of the bottom mold according to an embodiment of the present application.

[0049] Figure 13 This application shows an experimental comparison curve of temperature and cooling airflow at a mold measuring point near the root of the spokes in an embodiment of the present application.

[0050] Figure 14 This application provides a comparative curve of standard deviation experimental data for 100 casting cycle mold measuring points near the spoke root of the top mold according to an embodiment of the present application.

[0051] Figure 15 This application provides an embodiment of a comparative experimental curve showing the temperature and cooling airflow at a mold measuring point near the spokes of the top mold.

[0052] Figure 16 This application provides a comparative curve of experimental standard deviation data for 100 casting cycle mold measuring points near the spokes of the top mold according to an embodiment of the present application.

[0053] Figure 17 This application provides an embodiment of a comparative experimental curve showing the temperature and cooling airflow at a mold measuring point near the inner rim of the mold.

[0054] Figure 18 This application provides an embodiment of the standard deviation experimental comparison curve data of 100 casting cycle mold measuring points near the inner rim of the side mold;

[0055] Figure 19This application provides an embodiment of a comparative experimental curve showing the temperature and cooling airflow at a mold measuring point near the outer rim of the mold.

[0056] Figure 20 This application provides an embodiment of the standard deviation experimental comparison curve data of 100 casting cycle mold measuring points near the outer rim of the edge mold;

[0057] Figure 21 A block diagram of a device for determining the temperature acquisition point of an aluminum casting mold according to an embodiment of this application is shown;

[0058] Figure 22 A schematic diagram of the structure of a computer system suitable for implementing an electronic device or server according to embodiments of this application is shown. Detailed Implementation

[0059] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0060] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0061] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation instruction steps as shown in the following embodiments or drawings, the method may include more or fewer operation instruction steps based on conventional or non-creative effort. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application. In actual processing or when the device executes the method, it may be executed sequentially or in parallel according to the method shown in the embodiments or drawings.

[0062] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for determining temperature acquisition points in an aluminum casting mold according to an embodiment of this application is shown. Figure 1 As shown, the method includes:

[0063] Step 101: Simulate the process of manufacturing the target product using the target aluminum casting mold to obtain simulation temperature data for manufacturing the target product using the target aluminum casting mold; the simulation temperature data includes the temperature time series of multiple grid points corresponding to the simulation space as a function of time in at least one casting cycle.

[0064] It should be noted that the embodiments of this application are applied to the process of simulating and predicting the manufacturing process of the target product in order to form a reasonable and reliable preparation scheme before manufacturing the target product using the target aluminum casting mold.

[0065] In other words, before casting the target product, the target aluminum casting mold is meshed using casting process simulation software, and the casting process of the target product is simulated to obtain the temperature sequence of multiple grid points in the grid space where the target aluminum casting mold and the target product are located over time in at least one casting cycle.

[0066] For example, the temperature time series set of the mold grid points is L = (L1, L2, ..., L...). j , ...L i );L j =(L j 1 L j 2 , ..., L j k , ...L j m ),j=1,2,…,i;k=1,2,…,m;L j This is a list of temperature time series corresponding to the j-th mold grid point in the m-th casting cycle; L j k This is a list of temperature time series corresponding to the j-th mold grid point in the k-th casting cycle, where i is the number of mold grid points.

[0067] In one specific embodiment, the casting process simulation software can be ProCAST finite element casting process simulation software, which can simulate the fluid flow during mold filling and the stress of fully coupled temperature field calculations (thermodynamics). Based on this, the temperature time series of the process of manufacturing the target product using the target aluminum casting mold can be obtained using ProCAST software. When the target product is an aluminum alloy wheel, 552,322 mesh points can be obtained. These mesh points include, but are not limited to, the mold mesh points corresponding to the target aluminum casting mold, the product mesh points corresponding to the target product, and other mesh points, which are not specifically limited in this application. Then, the temperature time series of at least one casting cycle of manufacturing the aluminum alloy wheel using the target aluminum casting mold is obtained, for example, the temperature time series of the 5th to 15th casting cycles. In some embodiments, in order to reduce the number of temperature time series, only the temperature time series of one casting cycle can be selected, for example, the temperature time series of the 10th casting cycle.

[0068] Step 102: The simulated temperature data is reduced in dimensionality using the PCA-UMAP-tSNE dimensionality reduction algorithm to obtain low-dimensional temperature data.

[0069] It should be noted that the PCA-UMAP-tSNE dimensionality reduction algorithm is a combination of PCA (Principal Component Analysis), UMAP (Uniform Manifold Approximation and Projection), and t-SNE (t-Distributed Stochastic Neighbor Embedding).

[0070] It should be understood that the most important aspect of data dimensionality reduction is reducing the dimensionality of the data while preserving as much of the original information as possible. PCA is relatively fast, but it suffers from losing a lot of low-level structural information after data reduction. tSNE can preserve the low-level structure of the data, but it is very slow. UMAP, on the other hand, can achieve the speed advantage of PCA while retaining as much data information as possible. Based on this, this application combines PCA, UMAP, and t-SNE to leverage the complementary advantages of different algorithms in the data dimensionality reduction process, achieving high-speed dimensionality reduction while preserving data structure.

[0071] In one specific embodiment, the simulated temperature data can first be reduced from its original dimension to a P-dimensional principal component space using the PCA algorithm, retaining approximately 85% of the original data variance. Then, the UMAP algorithm is used for further nonlinear dimensionality reduction, reducing the data to U dimensions while preserving local topological structure. Finally, the t-SNE algorithm is used to reduce the U-dimensional data to T dimensions, resulting in low-dimensional temperature data that highlights local data structure and is suitable for cluster analysis. Here, P, U, and T can be determined based on the casting process of manufacturing the target product using the target aluminum casting mold. For example, when the target product is an aluminum alloy wheel, P is 100, U is 20, and T is 2.

[0072] Therefore, compared with the traditional methods of data dimensionality reduction using PCA or PCA-tSNE algorithms, the PCA-UMAP-tSNE dimensionality reduction algorithm proposed in this application can better preserve the data structure characteristics of temperature changes during the casting process, especially after the mold is forcibly cooled during casting. This provides a reliable data foundation for subsequent data clustering analysis and improves the rationality and accuracy of clustering analysis and temperature acquisition point selection.

[0073] Step 103: Perform cluster analysis on the low-dimensional temperature data to obtain n candidate temperature acquisition points.

[0074] It should be understood that the purpose of cluster analysis on low-dimensional temperature data is to identify points that reflect temperature changes throughout the entire casting cycle. These changes should correspond to the temperature changes during the casting process, especially after cooling of the target aluminum casting mold or the target product. In other words, candidate temperature acquisition points should reflect the temperature changes of the target casting mold or the target product as the casting process progresses, rather than simply being points that guarantee temperature acquisition or only being key structural points of the target product.

[0075] In one feasible embodiment, such as Figure 2 As shown, cluster analysis was performed on the low-dimensional temperature data to obtain n candidate temperature acquisition points, including:

[0076] Step 1031: Perform first-level cluster analysis on the low-dimensional temperature data. The first-level cluster analysis can use the K-means clustering algorithm. Use the elbow rule and silhouette coefficient to determine the target number of clusters corresponding to the low-dimensional temperature data, and obtain multiple first-level clusters corresponding to the target number of clusters.

[0077] It should be noted that the elbow method is a commonly used technique for determining the number of clusters. The silhouette coefficient is an indicator for evaluating the clustering effect, used to measure the density and separation of data points within a cluster. In other words, in this embodiment, the elbow method and silhouette coefficient can be used to determine the number of candidate temperature sampling points applied to the target casting mold. In other words, first-level clustering can identify the number of regions that reflect significant temperature changes during the casting process of the target product using the target aluminum casting mold, especially after cooling, and obtain a class of data with a consistent temperature change trend—that is, a first-level cluster.

[0078] Step 1032: Perform secondary clustering analysis on the primary clusters to obtain at least one secondary cluster corresponding to each primary cluster.

[0079] It should be understood that the purpose of using two-level cluster analysis in this application is to capture subtle differences in temperature behavior within each first-level cluster.

[0080] Step 1033: For each primary cluster, determine the candidate temperature acquisition points corresponding to the primary cluster based on at least one secondary cluster.

[0081] In other words, in this embodiment of the application, a first-level cluster analysis is used to determine the number of regions that can reflect the significant temperature changes during the casting process of manufacturing the target product using the target aluminum casting mold, especially after cooling. Then, a second-level cluster analysis is used to identify subtle differences in temperature behavior and to determine candidate temperature acquisition points for setting up temperature acquisition devices (e.g., thermocouples) in each region.

[0082] Therefore, this application is able to identify measurement points that are truly representative of temperature changes based on a secondary clustering strategy.

[0083] In a feasible embodiment, determining candidate temperature acquisition points corresponding to a primary cluster based on at least one secondary cluster includes: determining dimensionality-reduced feature location points corresponding to the primary cluster based on at least one secondary cluster, and spatially mapping the dimensionality-reduced feature location points to obtain candidate temperature acquisition points.

[0084] It should be understood that low-dimensional temperature data is obtained through multiple dimensionality reduction steps. Since the initial dimensionality reduction uses the PCA algorithm, the resulting low-dimensional temperature data remains within the PCA space. Therefore, it is necessary to determine the dimensionality reduction feature points corresponding to the primary clusters based on the secondary clustering; these are representative points that reflect the temperature change characteristics of the data clusters within that primary cluster. For example, such as... Figure 3 As shown in the figure, the color chart on the right side of the figure shows the color labels used for the 10 first-level clusters in the graphic space, and the PCA space shows the dimensionality reduction feature location points corresponding to each first-level cluster.

[0085] Therefore, after obtaining the dimensionality-reduced feature location points, it is necessary to further spatially map the dimensionality-reduced feature location points to obtain candidate temperature acquisition points.

[0086] Specifically, the reduced-dimensional feature location points are spatially mapped to obtain candidate temperature acquisition points, including: performing a first inverse transformation on the reduced-dimensional feature location points to obtain the original spatial feature points, and performing a second inverse transformation on the original spatial feature points to obtain candidate temperature acquisition points.

[0087] The first inverse transform is the PCA pseudo-inverse matrix transform, and the second inverse transform is the normalizer inverse transform.

[0088] In other words, in this embodiment, the first inverse transformation restores the dimensionality-reduced feature points in PCA space to the original space, and the second inverse transformation further maps the dimensionality-reduced feature points to the original physical space coordinate system. It should be understood that in this embodiment, the original physical space coordinate system is a simulation space coordinate system generated in the casting process simulation software, using the target aluminum casting mold to manufacture the target product. In this coordinate system, some coordinates correspond one-to-one with the various positions of the target aluminum casting mold, and some coordinates correspond one-to-one with the various positions of the target product. For example, as shown... Figure 4 As shown, Figure 3 The diagram illustrates the inverse transformation of the dimensionality-reduced feature points in the image to their positions in the original space.

[0089] In a preferred embodiment, the secondary clustering analysis includes multiple clustering branches performed based on different numbers of secondary clusters. That is, in this embodiment, when performing secondary clustering, the optimal number of categories is not determined using methods such as the elbow rule and silhouette coefficient for the data contained in the primary clusters before clustering analysis. Instead, clustering is performed separately according to multiple preset numbers of clusters, resulting in multiple clustering branches based on different numbers of sub-clusters.

[0090] The number of clusters can be determined based on the required precision for manufacturing the target product using the target aluminum casting mold, and this application does not impose specific limitations. Taking the manufacturing of aluminum alloy wheels as an example, the number of sub-clusters can include 1 and 3. That is, for each primary cluster, a secondary clustering analysis is performed once with 1 sub-cluster and once with 3 sub-clusters, for a total of two secondary clustering analyses, resulting in 1 sub-cluster and 3 sub-clusters respectively, i.e., 1 secondary cluster and 3 secondary clusters respectively.

[0091] Furthermore, when the secondary clustering analysis includes multiple clustering branches executed based on different numbers of secondary clusters, the dimensionality reduction feature location points corresponding to the primary clusters are determined based on at least one secondary cluster. This includes: for each clustering branch, obtaining the temperature change of each secondary clustering reaction, comparing the temperature change of each secondary clustering reaction in multiple clustering branches, and determining the dimensionality reduction feature location points corresponding to the primary clusters.

[0092] It should be understood that each clustering branch corresponds to a number of secondary clusters, and the result of a clustering branch is the number of secondary clusters corresponding to that number. Continuing with the above embodiment, the clustering branch can be a first clustering branch with 1 sub-cluster (secondary cluster) and a second clustering branch with 3 sub-clusters (secondary clusters).

[0093] In one specific embodiment, a target clustering branch for determining the dimensionality reduction feature location point is determined based on the similarity of temperature changes in multiple secondary clustering reactions among multiple clustering branches, and the dimensionality reduction feature location point is determined based on at least one representative clustering point corresponding to the target clustering branch.

[0094] For example, the temperature change of one secondary clustering reaction in the first clustering branch and the temperature change of three secondary clustering reactions in the second clustering branch are analyzed separately. Then, the secondary clusters in the two clustering branches are compared. For example, the similarity of the temperature change of one secondary clustering reaction in the first clustering branch and the temperature change of three secondary clustering reactions in the second clustering branch is compared to determine the target clustering branch.

[0095] In this application, the target clustering branch can be a clustering branch whose similarity to other clustering branches is greater than a preset threshold, or a clustering branch whose similarity to other clustering branches is greater than a preset number. This application does not make any specific limitations.

[0096] In a preferred embodiment, when multiple clustering branches have the same similarity, the clustering branch containing the fewest secondary clusters is selected as the target clustering branch. For example, if the temperature change corresponding to one secondary cluster in the first clustering branch is consistent with that of three secondary clusters in the second clustering branch, then the first clustering branch is selected as the target clustering branch.

[0097] Then, based on at least one representative point corresponding to the target clustering branch, the dimensionality reduction feature location points are determined, including but not limited to using the average position of at least one representative point corresponding to a secondary cluster as the dimensionality reduction feature location point. For example, for the first clustering branch, the representative point of the only secondary cluster contained in the first clustering branch can be directly used as the dimensionality reduction feature location point; for the second clustering branch, the average position (center position) of the representative points of the three secondary clusters in the second clustering branch can be used as the dimensionality reduction feature location point.

[0098] It should be understood that the aforementioned scheme can be used to convert the dimensionality-reduced feature location points into candidate temperature acquisition points, and this application will not elaborate on it here.

[0099] Step 104: Match the n candidate temperature acquisition points with the structural features of the target aluminum casting mold to obtain N target temperature acquisition points, where N≤n.

[0100] Specifically, the coordinate range of each region of the target aluminum casting mold can be obtained, and the candidate temperature acquisition point can be matched with the coordinate range of each region of the target aluminum casting mold. When the match is successful, the matching point on the target aluminum casting mold is used as the target temperature acquisition point.

[0101] In some embodiments, when the Euclidean distance between the candidate temperature acquisition point and the reference point on the target aluminum casting mold is less than a preset distance threshold, the reference point on the target aluminum casting mold is determined as the target temperature acquisition point. The reference point on the target aluminum casting mold can be any position on the outer edge of the target aluminum casting mold. Optionally, the reference point on the target aluminum casting mold can be a point on the outer edge of the target aluminum casting mold that does not affect the casting of the target product. Preferably, the reference point on the target aluminum casting mold can be multiple points or a range of points selected by technicians according to the spatial requirements for deploying thermocouples.

[0102] Therefore, the method for determining temperature acquisition points of aluminum casting molds proposed in this application can accurately identify target temperature acquisition points that reflect temperature changes during the casting process by analyzing simulated temperature data from the process of manufacturing the target product using the target aluminum casting mold. Specifically, the PCA-UMAP-tSNE dimensionality reduction algorithm effectively reduces high-dimensional temperature time series data to the target dimension while ensuring the reliability of cluster analysis by maintaining the local data structure of the low-dimensional temperature data. Furthermore, secondary cluster analysis allows for finer-grained analysis of temperature changes in clusters with similar temperature variations, identifying more representative cluster points that reflect temperature changes within the same cluster and improving the accuracy of candidate temperature acquisition points. Additionally, by matching candidate temperature acquisition points with the structural features of the target aluminum casting mold, this application ensures that the finally selected target temperature acquisition points are reliable measurement points on the target aluminum casting mold, improving the feasibility of the target temperature acquisition point location.

[0103] It should be understood that after determining the target temperature acquisition point by implementing the method for determining the temperature acquisition point of the aluminum casting mold proposed in the embodiments of this application, thermocouples can be installed on the target aluminum casting mold according to the target temperature acquisition point to collect temperature data in real time during the casting process. This facilitates the staff to monitor the status of the casting process, achieve precise control of the casting process, and thus improve the yield of the target product.

[0104] In one specific embodiment, such as Figure 5As shown, the casting process simulation software is launched to simulate the process of manufacturing the target product using the target aluminum casting mold. Temperature time-series data of all temperature measurement points (grid points) are acquired. Then, principal component analysis (reduced to P-dimensionality), unified manifold approximation and projection (reduced to U-dimensionality), and t-distribution random nearest neighbor (reduced to T-dimensionality) are performed sequentially on the temperature time-series data. k-means clustering analysis is performed to determine the optimal number of clusters n, and secondary clustering is performed. For each category obtained from the first-level clustering analysis, secondary clustering analysis is performed on a single representative point and k representative points of the subcategory. The single representative point and k representative points of the subcategory are compared and analyzed to determine the corresponding cluster representative point. PCA is performed on the final n cluster representative points for inverse matrix space mapping, followed by dimensionality reduction feature to physical space inverse transformation. The actual measurement point closest to the Euclidean cluster in the physical space is found, and the actual installation position of the mold temperature measurement point is designed in the mold diagram.

[0105] For example, based on Figure 3 and Figure 4 The clustering results, through analysis, yield the measurement point data shown in Table 1:

[0106] Table 1

[0107]

[0108] Furthermore, based on the measuring point locations in Table 1, the settings in the target aluminum casting mold are as follows: Figure 6 As shown in Table 1, the locations of the 10 temperature measuring points, combined with the structural features and manufacturing process of the mold itself, ensure that the four temperature measuring points of the side mold are located on two adjacent side molds. Specifically, 1 / 3 of the temperature measuring points are located at the top and bottom of the first side mold, 2 / 4 of the temperature measuring points are located at the top and bottom of the second side mold, temperature measuring points 5 / 6 / 7 are located in the top mold, and temperature measuring points 8 / 9 / 10 are located in the bottom mold.

[0109] According to such Figure 6 The spatial coordinates of the target temperature acquisition points are shown. Thermocouples are installed at the corresponding positions on the physical mold, and temperature acquisition and control are performed during the actual casting process. The results are compared with temperature acquisition and control during the actual casting process based on temperature measurement points selected empirically for the mold, as shown below. Figures 7-20 The comparison results are shown. Among them, Figures 7-12 The results show the comparison of temperature measurement points at the bottom mold. Figures 13-16 The results of the temperature measurement points of the top mold are shown. Figures 17-20The comparison results of the temperature measurement points on the mold side are shown. It can be seen that, according to the method proposed in this patent, the target temperature acquisition points exhibit more drastic temperature changes during a single casting cycle, showing temperature variations corresponding to the cooling opening and closing during the casting process. Furthermore, the mold temperature control based on the method proposed in this patent is more precise, with the standard deviation of mold temperature changes across multiple casting cycles being lower than the results obtained from temperature measurement points selected based on experience.

[0110] It should be noted that although the operation of the method of the present invention is described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in that specific order, or that all the operations shown must be performed in order to achieve the desired result.

[0111] Figure 21 A block diagram of a device for determining the temperature acquisition point of an aluminum casting mold according to an embodiment of this application is shown.

[0112] like Figure 21 As shown, the device 10 for determining the temperature acquisition point of the aluminum casting mold includes:

[0113] Simulation module 11 is used to simulate the process of manufacturing a target product using a target aluminum casting mold, and obtain simulation temperature data of manufacturing the target product using the target aluminum casting mold; the simulation temperature data includes a time series of temperature changes over time for multiple grid points corresponding to the simulation space in at least one casting cycle.

[0114] Dimensionality reduction module 12 is used to reduce the dimensionality of the simulated temperature data based on the PCA-UMAP-tSNE dimensionality reduction algorithm to obtain low-dimensional temperature data;

[0115] Clustering module 13 is used to perform clustering analysis on the low-dimensional temperature data to obtain n candidate temperature acquisition points;

[0116] The matching module 14 is used to match the n candidate temperature acquisition points with the structural features of the target aluminum casting mold to obtain N target temperature acquisition points, where N≤n.

[0117] In some embodiments, clustering module 13 is specifically used for:

[0118] A first-level cluster analysis is performed on the low-dimensional temperature data. The elbow rule and silhouette coefficient are used to determine the target number of clusters corresponding to the low-dimensional temperature data, and multiple first-level clusters corresponding to the target number of clusters are obtained.

[0119] Perform secondary clustering analysis on the primary clusters to obtain at least one secondary cluster corresponding to each primary cluster;

[0120] For each of the first-level clusters, the candidate temperature acquisition points corresponding to the first-level clusters are determined based on at least one of the second-level clusters.

[0121] In some embodiments, clustering module 13 is specifically used for:

[0122] Based on at least one of the secondary clusters, determine the dimensionality reduction feature location points corresponding to the primary cluster;

[0123] The candidate temperature acquisition points are obtained by spatially mapping the reduced-dimensional feature locations.

[0124] In some embodiments, clustering module 13 is specifically used for:

[0125] Perform a first inverse transformation on the reduced-dimensional feature locations to obtain the original spatial feature points;

[0126] A second inverse transformation is performed on the original spatial feature points to obtain the candidate temperature acquisition points.

[0127] In some embodiments, the secondary clustering analysis includes multiple clustering branches executed based on different numbers of secondary clusters. The clustering module 13 is specifically used for:

[0128] For each clustering branch, obtain the temperature change of each secondary clustering reaction;

[0129] By comparing the temperature changes of the secondary clustering reactions in each of the multiple clustering branches, the dimensionality reduction feature location points corresponding to the primary cluster are determined.

[0130] In some embodiments, clustering module 13 is specifically used for:

[0131] Based on the similarity of the temperature changes of the multiple secondary clustering reactions among the multiple clustering branches, a target clustering branch for determining the dimensionality reduction feature location point is determined;

[0132] The dimensionality reduction feature location point is determined based on at least one representative cluster point corresponding to the target clustering branch, and the representative cluster point is the cluster center corresponding to the secondary cluster.

[0133] It should be understood that the modules or modules described in the aluminum casting mold temperature acquisition point determination device 10 are related to the reference... Figure 1The steps in the described method correspond accordingly. Therefore, the operations and features described above for the method are also applicable to the device 10 for determining the temperature acquisition point of the aluminum casting mold and the modules contained therein, and will not be repeated here. The device 10 for determining the temperature acquisition point of the aluminum casting mold can be pre-implemented in the browser or other secure applications of an electronic device, or it can be loaded into the browser or other secure applications of an electronic device through download or other means. The corresponding modules in the device 10 for determining the temperature acquisition point of the aluminum casting mold can cooperate with the modules in the electronic device to implement the solution of the embodiments of this application.

[0134] The division of modules or units mentioned in the detailed description above is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0135] The following is for reference. Figure 22 , Figure 22 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of this application is shown.

[0136] like Figure 22 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 902 or programs loaded from storage section 908 into random access memory (RAM) 903. RAM 903 also stores various programs and data required for the system's operating instructions. CPU 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0137] The following components are connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 910 as needed so that computer programs read from it can be installed into storage section 908 as needed.

[0138] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 2The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program contains program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 909, and / or installed from removable medium 911. When the computer program is executed by central processing unit (CPU) 901, it performs the functions defined in the system of this application.

[0139] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operational instructions of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two connected blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified functions or operational instructions, or using a combination of dedicated hardware and computer instructions.

[0141] The units or modules described in the embodiments of this application can be implemented in software or hardware. The described units or modules can also be housed in a processor; for example, a processor can be described as including a simulation module, a dimensionality reduction module, a clustering module, and a matching module. The names of these units or modules do not necessarily limit the specific unit or module itself. For example, a simulation module can also be described as "simulating the process of manufacturing a target product using a target aluminum casting mold, obtaining simulation temperature data for manufacturing the target product using the target aluminum casting mold; the simulation temperature data includes a time series of temperature changes over time for multiple grid points corresponding to the simulation space during at least one casting cycle."

[0142] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not assembled into the electronic device. The computer-readable storage medium stores one or more programs that, when used by one or more processors, execute the method for determining the temperature acquisition point of the aluminum casting mold described in this application.

[0143] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for determining the temperature acquisition points of an aluminum casting mold, characterized in that, include: The process of manufacturing the target product using the target aluminum casting mold was simulated to obtain the simulated temperature data of manufacturing the target product using the target aluminum casting mold. The simulated temperature data includes a time series of temperature changes over time at multiple grid points corresponding to the simulation space during at least one casting cycle. The simulated temperature data is reduced in dimensionality using the PCA-UMAP-tSNE dimensionality reduction algorithm to obtain low-dimensional temperature data. Cluster analysis was performed on the low-dimensional temperature data to obtain n candidate temperature acquisition points; The n candidate temperature acquisition points are matched with the structural features of the target aluminum casting mold to obtain N target temperature acquisition points, where N≤n; The step of performing cluster analysis on the low-dimensional temperature data to obtain n candidate temperature acquisition points includes: A first-level cluster analysis is performed on the low-dimensional temperature data. The elbow rule and silhouette coefficient are used to determine the target number of clusters corresponding to the low-dimensional temperature data, and multiple first-level clusters corresponding to the target number of clusters are obtained. Perform secondary cluster analysis on the primary clusters to obtain at least one secondary cluster corresponding to each primary cluster; For each of the first-level clusters, the candidate temperature acquisition points corresponding to the first-level clusters are determined based on at least one of the second-level clusters; The step of determining the candidate temperature acquisition point corresponding to the primary cluster based on at least one of the secondary clusters includes: Based on at least one of the secondary clusters, determine the dimensionality reduction feature location points corresponding to the primary cluster; The candidate temperature acquisition points are obtained by spatially mapping the reduced-dimensional feature locations.

2. The method for determining the temperature acquisition points of aluminum casting molds according to claim 1, characterized in that, The step of spatially mapping the reduced-dimensional feature locations to obtain the candidate temperature acquisition points includes: Perform a first inverse transformation on the reduced-dimensional feature locations to obtain the original spatial feature points; The original spatial feature points are subjected to a second inverse transformation to obtain the candidate temperature acquisition points.

3. The method for determining the temperature acquisition points of aluminum casting molds according to claim 2, characterized in that, The secondary clustering analysis includes multiple clustering branches executed based on different numbers of secondary clusters. The step of determining the dimensionality-reduced feature location points corresponding to the primary cluster based on at least one of the secondary clusters includes: For each clustering branch, obtain the temperature change of each secondary clustering reaction; By comparing the temperature changes of the secondary clustering reactions in each of the multiple clustering branches, the dimensionality reduction feature location points corresponding to the primary cluster are determined.

4. The method for determining the temperature acquisition points of aluminum casting molds according to claim 3, characterized in that, The step of comparing the temperature changes of each of the secondary clustering reactions in multiple clustering branches to determine the dimensionality-reduced feature location points corresponding to the primary cluster includes: Based on the similarity of the temperature changes of the multiple secondary clustering reactions among the multiple clustering branches, a target clustering branch for determining the dimensionality reduction feature location point is determined; The dimensionality reduction feature location point is determined based on at least one representative cluster point corresponding to the target clustering branch, and the representative cluster point is the cluster center corresponding to the secondary cluster.

5. A device for determining the temperature acquisition point of an aluminum casting mold, characterized in that, include: The simulation module is used to simulate the process of manufacturing a target product using a target aluminum casting mold, and to obtain simulation temperature data for manufacturing the target product using the target aluminum casting mold; the simulation temperature data includes a time series of temperature changes over time for multiple grid points corresponding to the simulation space in at least one casting cycle. The dimensionality reduction module is used to reduce the dimensionality of the simulated temperature data based on the PCA-UMAP-tSNE dimensionality reduction algorithm to obtain low-dimensional temperature data. The clustering module is used to perform cluster analysis on the low-dimensional temperature data to obtain n candidate temperature acquisition points; The matching module is used to match the n candidate temperature acquisition points with the structural features of the target aluminum casting mold to obtain N target temperature acquisition points, where N ≤ n. The clustering module is specifically used for: A first-level cluster analysis is performed on the low-dimensional temperature data. The elbow rule and silhouette coefficient are used to determine the target number of clusters corresponding to the low-dimensional temperature data, and multiple first-level clusters corresponding to the target number of clusters are obtained. Perform secondary cluster analysis on the primary clusters to obtain at least one secondary cluster corresponding to each primary cluster; For each of the first-level clusters, the candidate temperature acquisition points corresponding to the first-level clusters are determined based on at least one of the second-level clusters; and Based on at least one of the secondary clusters, determine the dimensionality reduction feature location points corresponding to the primary cluster; The candidate temperature acquisition points are obtained by spatially mapping the reduced-dimensional feature locations.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for determining the temperature acquisition point of the aluminum casting mold as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, this program implements the method for determining the temperature acquisition point of the aluminum casting mold as described in any one of claims 1-4.

8. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method for determining the temperature acquisition point of the aluminum casting mold as described in any one of claims 1-4.

Images