Aluminum foil lunch box stamping strength detection method and system

Abstract

The invention discloses a method and system for detecting the strength of stamping of an aluminum foil lunch box, and relates to the field of intelligent detection technology. The method comprises: performing Gaussian filtering and noise reduction on the aluminum foil lunch box point cloud data information scanned by laser, and then performing three-dimensional modeling on the processed point cloud data to generate an aluminum foil lunch box point cloud model; performing stamping space domain segmentation on the aluminum foil lunch box point cloud model to obtain equivalent stamping segmentation area information; constructing a stamping strength detection adaptive classifier based on stamping strength correlation indicators, and respectively analyzing the equivalent stamping segmentation area information based on the stamping strength detection adaptive classifier to obtain the aluminum foil lunch box stamping strength detection result, and then performing stamping parameter optimization on the aluminum foil lunch box stamping strength detection result based on the stamping strength optimization space. The technical effect of realizing intelligent detection of the stamping strength of the aluminum foil lunch box and optimization of stamping parameters, improving the accuracy of the stamping strength detection result and the detection efficiency, and then ensuring the application quality of the aluminum foil lunch box is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent detection technology, and in particular to a method and system for detecting the punching strength of an aluminum foil lunch box. Background Art

[0002] Aluminum foil lunch boxes are a widely used type of tableware. They are lightweight, easy to recycle, and produce no harmful pollutants during the production process. Aluminum lunch box products are mostly used in airline food and cake food retail. They are updated quickly and consumed in large quantities, making them suitable for bulk sales. Stamping is an important production process for aluminum foil lunch boxes. Therefore, in order to ensure the application quality of aluminum foil lunch boxes, their actual stamping strength must be accurately tested and controlled. However, the existing aluminum foil lunch box stamping strength test has a low degree of intelligence, resulting in low accuracy of stamping strength test results and low test efficiency. Summary of the invention

[0003] The present application solves the technical problems in the prior art of low intelligence level of stamping strength detection of aluminum foil lunch boxes, resulting in low accuracy of stamping strength detection results and low detection efficiency, by providing a method and system for detecting the stamping strength of aluminum foil lunch boxes. The application achieves the technical effect of realizing intelligent detection of stamping strength of aluminum foil lunch boxes and optimization of stamping parameters through an adaptive classifier, improving the accuracy of stamping strength detection results and detection efficiency, and thus ensuring the application quality of aluminum foil lunch boxes.

[0004] In view of the above problems, the present invention provides a method and system for detecting the stamping strength of an aluminum foil lunch box.

[0005] In a first aspect, the present application provides a method for detecting the stamping strength of an aluminum foil lunch box, the method comprising: performing spatial scanning of a target aluminum foil lunch box by a laser scanner to obtain point cloud data information of the aluminum foil lunch box; performing Gaussian filtering and noise reduction on the point cloud data information of the aluminum foil lunch box to obtain available point cloud data information of the aluminum foil lunch box; performing three-dimensional modeling based on the available point cloud data information of the aluminum foil lunch box to generate a point cloud model of the aluminum foil lunch box; performing stamping space domain segmentation on the point cloud model of the aluminum foil lunch box to obtain equivalent stamping segmentation area information; obtaining stamping strength correlation indicators, the stamping strength correlation indicators including stamping process, material composition, and lunch box thickness; constructing a stamping strength detection adaptive classifier based on the stamping strength correlation indicators, analyzing the equivalent stamping segmentation area information respectively based on the stamping strength detection adaptive classifier to obtain a stamping strength detection result of the aluminum foil lunch box; obtaining a stamping strength optimization space, and performing stamping parameter optimization on the stamping strength detection result of the aluminum foil lunch box based on the stamping strength optimization space.

[0006] On the other hand, the present application also provides an aluminum foil lunch box stamping strength detection system, the system comprising: a laser space scanning module, used to perform space scanning of a target aluminum foil lunch box through a laser scanner to obtain point cloud data information of the aluminum foil lunch box; a Gaussian filtering and denoising module, used to perform Gaussian filtering and denoising on the aluminum foil lunch box point cloud data information to obtain usable aluminum foil lunch box point cloud data information; a point cloud model generation module, used to perform three-dimensional modeling based on the usable aluminum foil lunch box point cloud data information to generate an aluminum foil lunch box point cloud model; a space domain segmentation module, used to perform stamping space domain segmentation on the aluminum foil lunch box point cloud model to obtain equivalent stamping The invention relates to a method for obtaining a stamping strength detection result of an aluminum foil lunch box and a stamping parameter optimization module, wherein the stamping strength detection result is obtained by constructing a stamping strength detection adaptive classifier based on the stamping strength correlation index, and analyzing the equivalent stamping segmentation area information based on the stamping strength detection adaptive classifier to obtain the stamping strength detection result of the aluminum foil lunch box; and a stamping parameter optimization module, which is used to obtain the stamping strength optimization space and optimize the stamping parameters of the stamping strength detection result of the aluminum foil lunch box based on the stamping strength optimization space.

[0007] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The invention adopts a technical scheme of using a laser scanner to perform spatial scanning on the target aluminum foil lunch box, performing Gaussian filtering and noise reduction on the scanned aluminum foil lunch box point cloud data information, and then performing three-dimensional modeling based on the processed available aluminum foil lunch box point cloud data information to generate an aluminum foil lunch box point cloud model; performing stamping space domain segmentation on the aluminum foil lunch box point cloud model to obtain equivalent stamping segmentation area information, and at the same time constructing a stamping strength detection adaptive classifier based on stamping strength correlation indicators, and analyzing the equivalent stamping segmentation area information based on the stamping strength detection adaptive classifier to obtain the aluminum foil lunch box stamping strength detection result, and then optimizing the stamping parameters of the aluminum foil lunch box stamping strength detection result based on the stamping strength optimization space. Thus, the technical effect of realizing intelligent stamping strength detection and stamping parameter optimization of aluminum foil lunch boxes through adaptive classifiers is achieved, improving the accuracy and efficiency of stamping strength detection results, and thus ensuring the application quality of aluminum foil lunch boxes is achieved.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of the process of the strength testing method for the stamping of an aluminum foil lunch box of this application;

[0013] Figure 2 A schematic diagram of the process of generating a point cloud model of an aluminum foil lunch box in the strength detection method of the aluminum foil lunch box stamping of this application;

[0014] Figure 3 This is a schematic diagram of the structure of the strength testing system for the stamping of aluminum foil lunch boxes in this application;

[0015] Figure 4 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0016] Explanation of the accompanying drawings: laser space scanning module 11, Gaussian filtering noise reduction module 12, point cloud model generation module 13, spatial domain segmentation module 14, correlation index acquisition module 15, intensity detection result acquisition module 16, stamping parameter optimization module 17, bus 1110, processor 1120, transceiver 1130, bus interface 1140, memory 1150, operating system 1151, application 1152 and user interface 1160. DETAILED DESCRIPTION

[0017] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0018] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0019] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0020] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0021] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0022] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0024] The present application is described below in conjunction with the drawings in the present application.

[0025] Embodiment 1

[0026] like Figure 1 As shown, the present application provides a method for testing the strength of an aluminum foil lunch box punching, the method comprising:

[0027] Step S1: Scan the target aluminum foil lunch box in space by using a laser scanner to obtain point cloud data information of the aluminum foil lunch box;

[0028] Step S2: performing Gaussian filtering to reduce noise on the aluminum foil lunch box point cloud data information to obtain usable aluminum foil lunch box point cloud data information;

[0029] Specifically, aluminum foil lunch boxes are a widely used tableware. They are lightweight, easy to recycle, and produce no harmful pollutants during the production process. Aluminum lunch box products are mostly used in airline food and cake food retail. They are updated quickly and consumed in large quantities, making them suitable for batch sales. Stamping is an important production process for aluminum foil lunch boxes. Therefore, in order to ensure the application quality of aluminum foil lunch boxes, it is necessary to accurately test and control their actual stamping strength.

[0030] First, the laser scanner is used to perform a spatial scan of the target aluminum foil lunch box to be tested for impact strength. The contour set data of the object can be quickly measured in all directions, and then the aluminum foil lunch box point cloud data information is obtained. The aluminum foil lunch box point cloud data information includes the geometric structure data of the lunch box and the appearance data such as color and surface reflectivity, which provides a data basis for the subsequent construction of the lunch box point cloud model. Due to instrument measurement, environmental interference and other reasons, the point cloud data will produce noise interference signals. Therefore, it is necessary to perform Gaussian filtering and noise reduction on the aluminum foil lunch box point cloud data information. By applying the Gaussian function to perform spatial domain smoothing on the point cloud data, the noise in the image is reduced, and the usable aluminum foil lunch box point cloud data information after filtering preprocessing is obtained. Reduce data noise, enhance the availability of point cloud data, and thus improve the application quality of point cloud data.

[0031] Step S3: performing three-dimensional modeling based on the available aluminum foil lunch box point cloud data information to generate an aluminum foil lunch box point cloud model;

[0032] like Figure 2As shown, further, the step of generating the point cloud model of the aluminum foil lunch box in this application also includes:

[0033] Obtaining a point cloud modeling dimensionality reduction rule, wherein the point cloud modeling dimensionality reduction rule includes an attribute dimensionality reduction rule and a modeling requirement dimensionality reduction rule;

[0034] Based on the attribute dimension reduction rule, feature classification is performed on the available aluminum foil lunch box point cloud data information to obtain point cloud data attribute feature information;

[0035] Clustering and extracting the available aluminum foil lunch box point cloud data information according to the point cloud data attribute feature information to obtain aluminum foil lunch box feature point cloud data information;

[0036] Based on the modeling requirement dimensionality reduction rule, the characteristic point cloud data information of the aluminum foil lunch box is reduced in dimension to obtain the target aluminum foil lunch box point cloud data information;

[0037] The target aluminum foil lunch box point cloud data information is used for visual modeling to generate the aluminum foil lunch box point cloud model.

[0038] Furthermore, the step of obtaining the characteristic point cloud data information of the aluminum foil lunch box also includes:

[0039] Based on the point cloud data attribute feature information, obtaining point cloud space attribute feature information and point cloud surface attribute feature information;

[0040] Perform clustering feature configuration according to the point cloud spatial attribute feature information and the point cloud surface attribute feature information, and determine the point cloud feature clustering strategy;

[0041] Clustering the available aluminum foil lunch box point cloud data information based on the point cloud feature clustering strategy to obtain a point cloud feature clustering result;

[0042] The point cloud feature clustering result is used to screen and extract the available aluminum foil lunch box point cloud data information to obtain the aluminum foil lunch box feature point cloud data information.

[0043] Furthermore, the step of obtaining the target aluminum foil lunch box point cloud data information also includes:

[0044] Determine the precision of the target model based on the modeling requirement dimensionality reduction rule;

[0045] Performing point cloud density analysis according to the target model fineness to obtain modeling point cloud density requirement information;

[0046] Obtaining point cloud density distribution information of characteristic point cloud data information of the aluminum foil lunch box;

[0047] The point cloud density distribution information is uniformly enhanced based on the modeling point cloud density requirement information, and the target aluminum foil lunch box point cloud data information is obtained by dimensionality reduction.

[0048] Specifically, three-dimensional modeling is performed based on the available aluminum foil lunch box point cloud data information. Since the amount of modeling point cloud data is large, point cloud modeling dimensionality reduction rules are formulated. The point cloud modeling dimensionality reduction rules are used to reduce the dimensionality of point cloud data, including attribute dimensionality reduction rules and modeling requirement dimensionality reduction rules. First, based on the attribute dimensionality reduction rules, the available aluminum foil lunch box point cloud data information is feature classified to obtain the corresponding point cloud data attribute feature information after attribute feature classification, wherein the attribute dimensionality reduction rules are the basis for feature dimensionality reduction according to the point cloud data attributes, including the spatial attribute features, color attribute features, reflectivity attribute features, etc. of the point cloud data. Cluster extraction is performed on the available aluminum foil lunch box point cloud data information based on the point cloud data attribute feature information, and point cloud data related to the attribute features are extracted, thereby reducing the amount of point cloud data, improving data processing efficiency, and realizing data attribute feature dimensionality reduction.

[0049] The attribute dimension reduction is specifically to obtain the point cloud spatial attribute feature information and point cloud surface attribute feature information of the point cloud data, including surface attribute features such as color and reflectivity, based on the attribute feature information of the point cloud data. Then, clustering feature configuration is performed based on the point cloud spatial attribute feature information and the point cloud surface attribute feature information, and the point cloud feature clustering strategy is determined. The point cloud feature clustering strategy is the basis for clustering feature screening and can be configured by itself. Exemplarily, only the spatial attribute features and color attribute features of the point cloud data are clustered and screened. Then, based on the point cloud feature clustering strategy, the point cloud data information of the usable aluminum foil lunch box is clustered, that is, the point cloud data is calculated based on the clustering features in the strategy, and the point cloud data with the same attribute feature category is clustered into one category to obtain the point cloud feature clustering result. The point cloud feature clustering result is used to screen and extract the available aluminum foil lunch box point cloud data information, that is, point cloud data extraction is implemented according to the clustering result, and unconfigured attribute features, such as reflectivity attribute features, and point cloud data that have not been clustered are reduced in dimension and removed to obtain the corresponding aluminum foil lunch box feature point cloud data information after data attribute reduction is implemented.

[0050] In order to further improve the efficiency of point cloud data modeling, the characteristic point cloud data information of the aluminum foil lunch box is reduced in dimension based on the modeling requirement dimensionality reduction rule, wherein the modeling requirement dimensionality reduction rule is the basis for data dimensionality reduction according to the modeling accuracy of the point cloud model. First, based on the modeling requirement dimensionality reduction rule, the target model fineness is determined. The target model fineness is the modeling fineness of the point cloud model, which is measured by the model resolution. The larger the resolution, the higher the model fineness and the more realistic the hierarchical details. It can be set and determined by yourself. Then, according to the target model fineness, the point cloud density analysis is performed, that is, the spatial distribution density of the point cloud data is matched and analyzed, and the modeling point cloud density demand information is obtained according to the historical demand for modeling data. Then, the point cloud density distribution information of the characteristic point cloud data information of the aluminum foil lunch box is obtained, and the point cloud density distribution information is uniformly enhanced based on the modeling point cloud density demand information, that is, the current point cloud data in each region is uniformly reduced in dimension, so that the enhanced point cloud density meets the required point cloud density, and the target aluminum foil lunch box point cloud data information is obtained by dimension reduction. Finally, the target aluminum foil lunch box point cloud data information is used for visual modeling to generate an aluminum foil lunch box point cloud model with a preset model precision. This achieves personalized point cloud data dimensionality reduction, reduces the amount of modeling point cloud data, and thus improves the point cloud modeling efficiency and ensures the precision of the point cloud model.

[0051] Step S4: performing stamping space domain segmentation on the aluminum foil lunch box point cloud model to obtain equivalent stamping segmentation area information;

[0052] Step S5: Obtaining stamping strength related indicators, wherein the stamping strength related indicators include stamping process, material composition, and lunch box thickness;

[0053] Specifically, the aluminum foil lunch box point cloud model is segmented in the stamping space domain, that is, the stamping force analysis is performed according to the spatial attribute characteristics of the lunch box point cloud data, and the areas with the same stamping force surface are divided into the same segmented area, so as to obtain the equivalent stamping segmented area information after the division. At the same time, the stamping strength correlation index is formulated, which is an influencing index related to the stamping strength of the aluminum foil lunch box, including the stamping process, such as cold rolling or hot rolling; material composition, such as 3004 aluminum foil, 8011 aluminum foil, etc.; and lunch box thickness, etc. The stamping strength correlation index value of the aluminum foil lunch box is different, and its corresponding stamping strength also changes accordingly.

[0054] Step S6: constructing a stamping strength detection adaptive classifier based on the stamping strength associated index, and analyzing the equivalent stamping segmentation area information based on the stamping strength detection adaptive classifier to obtain a stamping strength detection result of the aluminum foil lunch box;

[0055] Furthermore, the steps of constructing the stamping strength detection adaptive classifier in this application also include:

[0056] Acquire a stamping strength test database by using data mining technology, wherein the stamping strength test database includes stamping strength related index data and stamping strength test data of historical aluminum foil lunch boxes;

[0057] Classifying and integrating the stamping strength detection database according to the stamping strength related indexes to obtain a stamping strength index detection sample data set;

[0058] The stamping strength index detection sample data sets are trained respectively by using a deep learning network structure to obtain a basic stamping strength detection branch network set;

[0059] The branch networks in the basic stamping strength detection branch network set are fused to generate the stamping strength detection adaptive classifier.

[0060] Furthermore, the step of fusing the branch networks in the basic punching strength detection branch network set also includes:

[0061] Performing principal component analysis on the attribute information of the punching strength related index to obtain dimension-reduced punching strength attribute information;

[0062] Based on factor analysis of the reduced-dimensional stamping strength attribute information, stamping strength weight distribution information is obtained;

[0063] According to the punching strength weight distribution information, fusion parameters are assigned to the basic punching strength detection branch network set, branch network fusion factor information is determined, and each branch network is fused based on the branch network fusion factor information.

[0064] Specifically, in order to realize intelligent stamping strength detection, a stamping strength detection adaptive classifier is constructed based on the stamping strength related index. First, a stamping strength detection database is searched and collected through data mining technology. The stamping strength detection database includes the stamping strength related index data of historical aluminum foil lunch boxes and the stamping strength detection data corresponding to its index value. The stamping strength detection database is classified and integrated according to the stamping strength related index, that is, the detection data in the database is divided according to the related index type, and the detection data of the same index type are integrated into one category to obtain the integrated stamping strength index detection sample data set. Then, the stamping strength index detection sample data sets are trained separately using a deep learning network structure, and the stamping strength related index data is used as input data and the corresponding stamping strength detection data is used as identification data. The basic stamping strength detection branch network set is trained to obtain the basic stamping strength detection branch network set, which is a neural network model used to predict the stamping strength of lunch boxes based on each stamping strength index.

[0065] Since the prediction accuracy of the basic stamping strength detection branch network is low, the branch networks in the basic stamping strength detection branch network set are fused. First, the attribute information of the stamping strength related indicators is subjected to principal component analysis, that is, the multiple variable attributes related to each stamping strength related indicator are subjected to dimensionality reduction processing, and the important attribute characteristics are clearly displayed to obtain attribute information with a strong correlation with the stamping strength, namely, the reduced-dimensional stamping strength attribute information. Then, based on the factor analysis of the reduced-dimensional stamping strength attribute information, that is, the common features in each detection attribute are extracted, and the attribute information with the same nature is classified into one attribute information. The attribute information with more common factors has a larger corresponding weight, and the attribute information with fewer common factors has a smaller corresponding weight, thereby obtaining the weight distribution result of the attribute factors, namely, the stamping strength weight distribution information.

[0066] According to the stamping strength weight distribution information, the basic stamping strength detection branch network set is assigned fusion parameters, that is, the larger the weight, the larger the branch network fusion parameter corresponding to the index, and the index weight is determined as the branch network fusion factor information, and the branch networks are fused based on the branch network fusion factor information. The larger the fusion factor, the greater the prediction voting right of the branch network in the final adaptive classifier, and then the fusion generates a stamping strength detection adaptive classifier with higher prediction accuracy, which is used to predict the stamping strength of the aluminum foil lunch box. Based on the stamping strength detection adaptive classifier, the equivalent stamping segmentation area information is predicted and analyzed respectively, and the stamping strength detection results corresponding to the equivalent stamping segmentation area information in the aluminum foil lunch box are obtained, and then the stamping strength detection results of the aluminum foil lunch box are obtained. Intelligent analysis and detection of the stamping strength of the aluminum foil lunch box is realized to improve the accuracy and efficiency of the stamping strength detection results.

[0067] Step S7: Obtain a stamping strength optimization space, and optimize stamping parameters of the stamping strength test result of the aluminum foil lunch box based on the stamping strength optimization space.

[0068] Furthermore, the application steps also include:

[0069] Quantify the strength standard of the target aluminum foil lunch box application scenario to obtain the target application stamping strength benchmark;

[0070] Determine a target stamping strength optimization coefficient according to the difference between the stamping strength test result of the aluminum foil lunch box and the target application stamping strength benchmark;

[0071] Optimizing the stamping strength optimization space based on the target stamping strength optimization coefficient to generate a stamping strength parameter memory library;

[0072] A stamping fitness function is used to perform global optimization in the stamping strength parameter memory library, and stamping process optimization parameter information is output. Based on the stamping process optimization parameter information, aluminum foil lunch box optimization production is performed.

[0073] Specifically, the stamping strength optimization space is obtained through the historical stamping process data of the aluminum foil lunch box. The stamping strength optimization space is the optimization range space of the stamping strength process parameters, including stamping strength-related process parameters, including stamping force, stamping frequency, temperature, etc., and stamping strength size data corresponding to the process parameters. Based on the stamping strength optimization space, the stamping parameters of the aluminum foil lunch box stamping strength test results are optimized. First, the application scenario of the target aluminum foil lunch box is quantified for strength standards. Aluminum foil lunch boxes are widely used in take-out, fast food, bento and other occasions. The application strength and structure of the lunch boxes required for different application scenarios are also different, and the corresponding stamping strength also changes accordingly. The target application stamping strength benchmark of the aluminum foil lunch box to be applied is obtained through the historical experience data of the aluminum foil lunch box application scenario, that is, the actual stamping strength standard corresponding to the target application scenario.

[0074] The difference between the stamping strength test result of the aluminum foil lunch box and the stamping strength benchmark of the target application is used as the target stamping strength optimization coefficient to indicate the optimization degree of the stamping strength. Then, the stamping strength optimization space is optimized based on the target stamping strength optimization coefficient, that is, the data space is screened for the corresponding stamping strength level according to the actual stamping strength optimization degree, and a stamping strength parameter memory library is generated to reduce the amount of optimization data, thereby improving the parameter optimization efficiency. The stamping fitness function can be empirically formulated based on the stamping strength value and the stamping cost to evaluate the pros and cons of the stamping strength process parameters. The stamping fitness function is used to perform global optimization in the stamping strength parameter memory library, and the search is optimized to a preset number of iterations, and the stamping process optimization parameter information with the best fitness evaluation is output. The aluminum foil lunch box is optimized for production based on the stamping process optimization parameter information to achieve timely adjustability of optimized production, ensure that the actual stamping strength of the aluminum foil lunch box meets the standard, and then ensure the application quality of the aluminum foil lunch box.

[0075] In summary, the method and system for detecting the strength of aluminum foil lunch box stamping provided by the present application have the following technical effects:

[0076] The invention adopts a technical scheme of using a laser scanner to perform spatial scanning on the target aluminum foil lunch box, performing Gaussian filtering and noise reduction on the scanned aluminum foil lunch box point cloud data information, and then performing three-dimensional modeling based on the processed available aluminum foil lunch box point cloud data information to generate an aluminum foil lunch box point cloud model; performing stamping space domain segmentation on the aluminum foil lunch box point cloud model to obtain equivalent stamping segmentation area information, and at the same time constructing a stamping strength detection adaptive classifier based on stamping strength correlation indicators, and analyzing the equivalent stamping segmentation area information based on the stamping strength detection adaptive classifier to obtain the aluminum foil lunch box stamping strength detection result, and then optimizing the stamping parameters of the aluminum foil lunch box stamping strength detection result based on the stamping strength optimization space. Thus, the technical effect of realizing intelligent stamping strength detection and stamping parameter optimization of aluminum foil lunch boxes through adaptive classifiers is achieved, improving the accuracy and efficiency of stamping strength detection results, and thus ensuring the application quality of aluminum foil lunch boxes is achieved.

[0077] Embodiment 2

[0078] Based on the same inventive concept as the strength detection method for punching an aluminum foil lunch box in the aforementioned embodiment, the present invention also provides a strength detection system for punching an aluminum foil lunch box, such as Figure 3 As shown, the system comprises:

[0079] The laser space scanning module 11 is used to perform space scanning on the target aluminum foil lunch box through a laser scanner to obtain point cloud data information of the aluminum foil lunch box;

[0080] A Gaussian filtering and denoising module 12 is used to perform Gaussian filtering and denoising on the aluminum foil lunch box point cloud data information to obtain usable aluminum foil lunch box point cloud data information;

[0081] A point cloud model generating module 13 is used to perform three-dimensional modeling based on the available aluminum foil lunch box point cloud data information to generate an aluminum foil lunch box point cloud model;

[0082] A space domain segmentation module 14 is used to perform stamping space domain segmentation on the aluminum foil lunch box point cloud model to obtain equivalent stamping segmentation area information;

[0083] A correlation index obtaining module 15 is used to obtain a stamping strength correlation index, wherein the stamping strength correlation index includes a stamping process, a material composition, and a lunch box thickness;

[0084] A strength detection result obtaining module 16 is used to construct a stamping strength detection adaptive classifier based on the stamping strength associated index, and analyze the equivalent stamping segmentation area information based on the stamping strength detection adaptive classifier to obtain the stamping strength detection result of the aluminum foil lunch box;

[0085] The stamping parameter optimization module 17 is used to obtain a stamping strength optimization space, and optimize the stamping parameters of the stamping strength test result of the aluminum foil lunch box based on the stamping strength optimization space.

[0086] Furthermore, the system also includes:

[0087] A dimensionality reduction rule acquisition unit, used to acquire a point cloud modeling dimensionality reduction rule, wherein the point cloud modeling dimensionality reduction rule includes an attribute dimensionality reduction rule and a modeling requirement dimensionality reduction rule;

[0088] A point cloud feature classification unit, used to perform feature classification on the usable aluminum foil lunch box point cloud data information based on the attribute dimension reduction rule to obtain point cloud data attribute feature information;

[0089] A point cloud clustering extraction unit, used for clustering and extracting the available aluminum foil lunch box point cloud data information according to the point cloud data attribute feature information, to obtain the aluminum foil lunch box feature point cloud data information;

[0090] A point cloud data dimensionality reduction unit, used to reduce the dimension of the aluminum foil lunch box feature point cloud data information based on the modeling requirement dimensionality reduction rule to obtain target aluminum foil lunch box point cloud data information;

[0091] The visual modeling unit is used to perform visual modeling using the target aluminum foil lunch box point cloud data information to generate the aluminum foil lunch box point cloud model.

[0092] Furthermore, the system also includes:

[0093] A point cloud attribute feature obtaining unit, used for obtaining point cloud space attribute feature information and point cloud surface attribute feature information based on the point cloud data attribute feature information;

[0094] A clustering feature configuration unit, configured to perform clustering feature configuration according to the point cloud spatial attribute feature information and the point cloud surface attribute feature information, and determine a point cloud feature clustering strategy;

[0095] A point cloud data clustering unit, used for clustering the available aluminum foil lunch box point cloud data information based on the point cloud feature clustering strategy to obtain a point cloud feature clustering result;

[0096] The point cloud screening and extraction unit is used to screen and extract the available aluminum foil lunch box point cloud data information by using the point cloud feature clustering result to obtain the aluminum foil lunch box feature point cloud data information.

[0097] Furthermore, the system also includes:

[0098] A model precision determination unit, used to determine the precision of a target model based on the modeling requirement dimensionality reduction rule;

[0099] A point cloud density analysis unit, used to perform point cloud density analysis according to the precision of the target model and obtain the point cloud density requirement information for modeling;

[0100] A density distribution information acquisition unit, used to acquire point cloud density distribution information of the characteristic point cloud data information of the aluminum foil lunch box;

[0101] The density uniformity enhancement unit is used to uniformly enhance the point cloud density distribution information based on the modeling point cloud density requirement information, and reduce the dimension to obtain the target aluminum foil lunch box point cloud data information.

[0102] Furthermore, the system also includes:

[0103] A detection database acquisition unit, used to acquire a stamping strength detection database by using data mining technology, wherein the stamping strength detection database includes stamping strength associated index data and stamping strength detection data of historical aluminum foil lunch boxes;

[0104] A database classification and integration unit, used to classify and integrate the stamping strength detection database according to the stamping strength related index, and obtain a stamping strength index detection sample data set;

[0105] A sample training unit, used to train the stamping strength index detection sample data set respectively using a deep learning network structure to obtain a basic stamping strength detection branch network set;

[0106] The branch network fusion unit is used to fuse the branch networks in the basic stamping strength detection branch network set to generate the stamping strength detection adaptive classifier.

[0107] Furthermore, the system also includes:

[0108] A principal component analysis unit, used to perform principal component analysis on the attribute information of the punching strength related index to obtain dimension-reduced punching strength attribute information;

[0109] A factor analysis unit, configured to obtain punching strength weight distribution information based on factor analysis of the reduced-dimensional punching strength attribute information;

[0110] A fusion parameter assigning unit is used to assign fusion parameters to the basic stamping strength detection branch network set according to the stamping strength weight distribution information, determine the branch network fusion factor information, and fuse the branch networks based on the branch network fusion factor information.

[0111] Furthermore, the system also includes:

[0112] A strength standard quantification unit, used to quantify the strength standard of the target aluminum foil lunch box application scenario and obtain a target application stamping strength benchmark;

[0113] An optimization coefficient determination unit, used to determine a target stamping strength optimization coefficient according to a difference between the stamping strength test result of the aluminum foil lunch box and the target application stamping strength benchmark;

[0114] A stamping strength parameter memory library generating unit, configured to optimize the stamping strength optimization space based on the target stamping strength optimization coefficient and generate a stamping strength parameter memory library;

[0115] The lunch box optimization production unit is used to use the stamping fitness function to perform global optimization in the stamping strength parameter memory library, output stamping process optimization parameter information, and optimize the production of aluminum foil lunch boxes based on the stamping process optimization parameter information.

[0116] The foregoing Figure 1 The various variations and specific examples of the strength detection method for stamping an aluminum foil lunch box in Example 1 are also applicable to the strength detection system for stamping an aluminum foil lunch box in this embodiment. Through the above detailed description of the strength detection method for stamping an aluminum foil lunch box, those skilled in the art can clearly know the implementation method of the strength detection system for stamping an aluminum foil lunch box in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0117] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method embodiment for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0118] Exemplary Electronic Devices

[0119] For details, see Figure 4 As shown, the present application also provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .

[0120] In the present application, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned method embodiment for controlling output data is implemented.

[0121] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .

[0122] In the present application, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges. Bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150 .

[0123] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Such architectures include, by way of example and not limitation, an Industry Standard Architecture bus, a Micro Channel Architecture bus, an expansion bus, a Video Electronics Standards Association, a Peripheral Component Interconnect bus.

[0124] The processor 1120 may be an integrated circuit chip having signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processors include: a general-purpose processor, a central processing unit, a network processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, a complex programmable logic device, a programmable logic array, a microcontroller unit or other programmable logic device, a discrete gate, a transistor logic device, and a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in this application may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located on multiple different chips.

[0125] Processor 1120 may be a microprocessor or any conventional processor. The method steps disclosed in the present application may be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a readable storage medium known in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, a register, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0126] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, this application will not further describe them.

[0127] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, or a stylus.

[0128] It should be understood that in the present application, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above network may be a self-organizing network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the Internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless network, a wireless fidelity network, and a combination of two or more of the above networks. For example, the cellular telephone network and the wireless network may be a global mobile communication device, a code division multiple access device, a global microwave interconnection access device, a general packet radio service device, a wideband code division multiple access device, a long term evolution device, a LTE frequency division duplex device, a LTE time division duplex device, an advanced long term evolution device, a universal mobile communication device, an enhanced mobile broadband device, a massive machine type communication device, an ultra-reliable low latency communication device, and the like.

[0129] It should be understood that the memory 1150 in the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory.

[0130] Volatile memory includes random access memory, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously linked dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in the present application includes, but is not limited to, the above and any other suitable types of memory.

[0131] In the present application, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0132] Specifically, the operating system 1151 includes various device programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various application programs, such as a media player and a browser, which are used to implement various application services. The program implementing the method of the present application may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer device executable instructions that perform specific tasks or implement specific abstract data types.

[0133] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0134] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for testing the strength of aluminum foil lunch box stamping, characterized in that: The method comprises: Use a laser scanner to perform spatial scanning on the target aluminum foil lunch box to obtain point cloud data information of the aluminum foil lunch box; Performing Gaussian filtering and noise reduction on the aluminum foil lunch box point cloud data information to obtain usable aluminum foil lunch box point cloud data information; Perform three-dimensional modeling based on the available aluminum foil lunch box point cloud data information to generate an aluminum foil lunch box point cloud model; The aluminum foil lunch box point cloud model is segmented in the stamping space domain to obtain equivalent stamping segmentation area information, that is, stamping force analysis is performed according to the spatial attribute characteristics of the lunch box point cloud data, and areas with the same stamping force surface are divided into the same segmentation area, so as to obtain equivalent stamping segmentation area information after division; Obtaining stamping strength related indicators, wherein the stamping strength related indicators include stamping process, material composition, and lunch box thickness; Based on the stamping strength correlation index, a stamping strength detection adaptive classifier is constructed, and based on the stamping strength detection adaptive classifier, the equivalent stamping segmentation area information is analyzed respectively to obtain the stamping strength detection result of the aluminum foil lunch box; A stamping strength optimization space is obtained, and stamping parameters are optimized for the stamping strength test result of the aluminum foil lunch box based on the stamping strength optimization space.

2. The method according to claim 1, characterized in that The step of generating a point cloud model of an aluminum foil lunch box comprises: Obtaining a point cloud modeling dimensionality reduction rule, wherein the point cloud modeling dimensionality reduction rule includes an attribute dimensionality reduction rule and a modeling requirement dimensionality reduction rule; Based on the attribute dimension reduction rule, feature classification is performed on the available aluminum foil lunch box point cloud data information to obtain point cloud data attribute feature information; Clustering and extracting the available aluminum foil lunch box point cloud data information according to the point cloud data attribute feature information to obtain aluminum foil lunch box feature point cloud data information; Based on the modeling requirement dimensionality reduction rule, the characteristic point cloud data information of the aluminum foil lunch box is reduced in dimension to obtain the target aluminum foil lunch box point cloud data information; The target aluminum foil lunch box point cloud data information is used for visual modeling to generate the aluminum foil lunch box point cloud model.

3. The method according to claim 2, characterized in that The obtained feature point cloud data information of the aluminum foil lunch box includes: Based on the point cloud data attribute feature information, obtaining point cloud space attribute feature information and point cloud surface attribute feature information; Perform clustering feature configuration according to the point cloud spatial attribute feature information and the point cloud surface attribute feature information, and determine the point cloud feature clustering strategy; Clustering the available aluminum foil lunch box point cloud data information based on the point cloud feature clustering strategy to obtain a point cloud feature clustering result; The point cloud feature clustering result is used to screen and extract the available aluminum foil lunch box point cloud data information to obtain the aluminum foil lunch box feature point cloud data information.

4. The method according to claim 2, characterized in that The step of obtaining the target aluminum foil lunch box point cloud data information includes: Determine the precision of the target model based on the modeling requirement dimensionality reduction rule; Performing point cloud density analysis according to the target model fineness to obtain modeling point cloud density requirement information; Obtaining point cloud density distribution information of characteristic point cloud data information of the aluminum foil lunch box; The point cloud density distribution information is uniformly enhanced based on the modeling point cloud density requirement information, and the target aluminum foil lunch box point cloud data information is obtained by dimensionality reduction.

5. The method according to claim 1, characterized in that The method of constructing a stamping strength detection adaptive classifier comprises: Acquire a stamping strength test database by using data mining technology, wherein the stamping strength test database includes stamping strength related index data and stamping strength test data of historical aluminum foil lunch boxes; Classifying and integrating the stamping strength detection database according to the stamping strength related indexes to obtain a stamping strength index detection sample data set; The stamping strength index detection sample data sets are trained respectively by using a deep learning network structure to obtain a basic stamping strength detection branch network set; The branch networks in the basic stamping strength detection branch network set are fused to generate the stamping strength detection adaptive classifier.

6. The method according to claim 5, characterized in that The step of fusing the branch networks in the basic stamping strength detection branch network set includes: Performing principal component analysis on the attribute information of the punching strength related index to obtain dimension-reduced punching strength attribute information; Based on factor analysis of the reduced-dimensional stamping strength attribute information, stamping strength weight distribution information is obtained; According to the punching strength weight distribution information, fusion parameters are assigned to the basic punching strength detection branch network set, branch network fusion factor information is determined, and each branch network is fused based on the branch network fusion factor information.

7. The method according to claim 1, characterized in that The method comprises: Quantify the strength standard of the target aluminum foil lunch box application scenario to obtain the target application stamping strength benchmark; Determine a target stamping strength optimization coefficient according to the difference between the stamping strength test result of the aluminum foil lunch box and the target application stamping strength benchmark; Optimizing the stamping strength optimization space based on the target stamping strength optimization coefficient to generate a stamping strength parameter memory library; A stamping fitness function is used to perform global optimization in the stamping strength parameter memory library, and stamping process optimization parameter information is output. Based on the stamping process optimization parameter information, aluminum foil lunch box optimization production is performed.

8. Aluminum foil lunch box stamping strength detection system, characterized in that: The system comprises: A laser space scanning module is used to perform space scanning on the target aluminum foil lunch box through a laser scanner to obtain point cloud data information of the aluminum foil lunch box; A Gaussian filtering and denoising module is used to perform Gaussian filtering and denoising on the aluminum foil lunch box point cloud data information to obtain usable aluminum foil lunch box point cloud data information; A point cloud model generation module, used for performing three-dimensional modeling based on the available aluminum foil lunch box point cloud data information to generate an aluminum foil lunch box point cloud model; A spatial domain segmentation module is used to perform stamping spatial domain segmentation on the aluminum foil lunch box point cloud model to obtain equivalent stamping segmentation area information, that is, to perform stamping force analysis according to the spatial attribute characteristics of the lunch box point cloud data, and divide the areas with the same stamping force surface into the same segmentation area, so as to obtain the equivalent stamping segmentation area information after division; A correlation index obtaining module, used to obtain a stamping strength correlation index, wherein the stamping strength correlation index includes a stamping process, a material composition, and a lunch box thickness; A strength detection result acquisition module is used to construct a stamping strength detection adaptive classifier based on the stamping strength associated index, and analyze the equivalent stamping segmentation area information based on the stamping strength detection adaptive classifier to obtain the stamping strength detection result of the aluminum foil lunch box; The stamping parameter optimization module is used to obtain the stamping strength optimization space and optimize the stamping parameters of the stamping strength test result of the aluminum foil lunch box based on the stamping strength optimization space.

9. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method for detecting the stamping strength of an aluminum foil lunch box as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method for detecting the strength of the aluminum foil lunch box punching as described in any one of claims 1 to 7 are implemented.

Images