Establishment method and judgment method of detection database of non-ferrous metal rolled product

Abstract

The invention relates to the technical field of detection, and discloses an establishment method and a judgment method of a detection database of a non-ferrous metal rolled product, and the establishment method comprises the steps: obtaining a plurality of detection files related to the non-ferrous metal rolled product from a plurality of detection devices; extracting product numbers of the products from file names of a plurality of detection files; analyzing the defect type, the defect position and the defect size of each defect of the product from the surface defect data of multiple defect types; adding the defect type, the defect position, the defect size and the product number of each defect of the product into a defect data file in a preset file format; and storing the defect data file in a detection database. According to the method, highly-automatic surface quality defect data collection, analysis and judgment of various defect types can be realized, the manual workload in the whole process is greatly reduced, the working time consumption of analysis and judgment is reduced, and the analysis and judgment accuracy can be greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of detection technology, and in particular to a method for establishing a detection database for non-ferrous metal rolled products and a method for determining the same. Background Art

[0002] In the current non-ferrous metal rolling industry, surface quality is a key factor affecting the quality of the final product. By analyzing and determining the surface quality defects of the product, we can find out the impact of the product's production process parameters on the quality of the final product, which is of great significance to improving product quality and reducing production costs, thereby improving customer satisfaction and enhancing the overall competitiveness of the enterprise.

[0003] In recent years, domestic non-ferrous metal rolling enterprises have begun to actively introduce and develop advanced surface quality defect analysis and determination technologies to achieve automatic detection, classification and determination of product surface defects, and improve detection efficiency and accuracy. However, the analysis and determination of surface quality defects are limited by the specialization of the determination equipment. The existing surface defect detection equipment is generally specialized for detecting a certain type of surface defects, and its detection results are stored in the equipment itself or in the host computer. This makes it difficult for quality analysts to combine different types of detection results generated by various devices for unified analysis when analyzing the surface quality defects of products, and thus cannot discover the deep connection between these detection results, which in turn affects the final analysis conclusion.

[0004] In the current non-ferrous metal rolling production practice, the collection and analysis of surface defect data is often completed manually, that is, different special equipment is used to perform the required surface quality defect detection on the same finished product, and the equipment will generate an excel or csv test report file. After the detection is completed, the production staff will take out the test report from the corresponding equipment and hand it over to the analyst to use excel and other office software to perform statistics and analysis of surface defects. Summary of the invention

[0005] The purpose of the present invention is to provide a method for establishing a detection database for non-ferrous metal rolled products and a method for determining the same, which can realize highly automated surface quality defect data collection, analysis and determination of various defect types, greatly reduce the manual workload in the entire process, reduce the time spent on analysis and determination, and avoid errors in product number correspondence, statistical calculations, etc. that may occur when manually screening data, thereby greatly improving the accuracy of analysis and determination.

[0006] In order to achieve the above-mentioned objectives, the first aspect of the present invention provides a method for establishing a detection database for non-ferrous metal rolled products, the establishment method comprising: acquiring multiple detection files about non-ferrous metal rolled products from multiple detection devices, wherein the multiple detection files include surface defect data of multiple defect types, and the file formats of the multiple detection files are different; extracting the product numbers of the non-ferrous metal rolled products from the file names of the multiple detection files; parsing the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product from the surface defect data of the multiple defect types; adding the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product and the product number to a defect data file in a preset file format; and storing the defect data file in the detection database.

[0007] In an embodiment of the present invention, the multiple inspection files also include product pattern inspection data, and the establishment method also includes: parsing the length coordinates of the non-ferrous metal rolled product and the pattern height on the length coordinates from the product pattern inspection data in the multiple inspection files; adding the length coordinates of the non-ferrous metal rolled product, the pattern height on the length coordinates, and the product number to the pattern data file in the preset file format; and storing the pattern data file in the inspection database.

[0008] In an embodiment of the present invention, parsing the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product from the surface defect data in the multiple inspection files includes: parsing the defect type, defect position, defect length and defect width of each defect of the non-ferrous metal rolled product from the surface defect data in the multiple inspection files; comparing the defect length and defect width of each defect of the non-ferrous metal rolled product; and taking the larger value of the defect length and the defect width of each defect as the defect size of the corresponding defect.

[0009] In the embodiment of the present invention, the multiple defect types include: pinholes, black spots, black oil lines, concave and convex spots, and wrinkles.

[0010] Through the above technical scheme, the present invention creatively first obtains multiple inspection files about non-ferrous metal rolled products from multiple inspection devices; secondly, extracts the product number of the product from the file names of the multiple inspection files; then, parses the defect type, defect position and defect size of each defect of the product from the surface defect data of multiple defect types; then, adds the defect type, defect position and defect size of each defect of the product and the product number to a defect data file in a preset file format; finally, stores the defect data file in the inspection database, thereby realizing highly automated surface quality defect data collection of multiple defect types, greatly reducing the manual workload in the entire process, reducing the time-consuming work of collection, and thus providing reliable basic data for the subsequent automated execution of analysis and judgment.

[0011] A second aspect of the present invention provides a method for determining the product number and customer identification of a non-ferrous metal rolled product, the determination method comprising: in response to receiving a defect determination instruction including a non-ferrous metal rolled product, obtaining a first standard data file corresponding to the product number of the non-ferrous metal rolled product for the customer identification from a standard database, wherein the first standard data file includes a standard total number of defects and a standard defect size; obtaining a defect data file corresponding to the product number from a detection database established according to the method for establishing a detection database for non-ferrous metal rolled products, and obtaining the total number of defects and the maximum defect size based on the defect data file; comparing the obtained total number of defects and the maximum defect size with the standard total number of defects and the standard defect size, respectively; and determining that the non-ferrous metal rolled product is a qualified product when the obtained total number of defects is less than or equal to the standard total number of defects and the obtained maximum defect size is less than or equal to the standard defect size.

[0012] In an embodiment of the present invention, the first standard data file also includes a standard defect density, a standard number of dense points and / or a standard number of continuous defects, and the determination method also includes: obtaining the defect density, the number of dense points and / or the number of continuous defects according to the defect data file; comparing the acquired defect density with the standard defect density, comparing the number of dense points with the standard number of dense points, and / or comparing the number of continuous defects with the standard number of continuous defects; when the acquired total number of defects is less than or equal to the standard total number of defects, the acquired maximum defect size is less than or equal to the standard defect size, and the acquired defect density is less than or equal to the standard defect density, the acquired number of dense points is less than or equal to the standard number of dense points, and / or the acquired number of continuous defects is less than or equal to the standard number of continuous defects, the non-ferrous metal rolled product is determined to be a qualified product.

[0013] In an embodiment of the present invention, the determination method further includes: in response to receiving a defect display instruction including a product number of a non-ferrous metal rolled product, displaying the data in the defect data file on the same page according to the product number of the non-ferrous metal rolled product, wherein multiple defect types correspond to multiple display colors and the display method of each defect type can be hidden.

[0014] In an embodiment of the present invention, displaying the data in the defect data file on the same page includes: displaying the data in the defect data file on the same page using a scatter plot, wherein the coordinates of each scatter point are the defect coordinates of the corresponding defect, and the area of ​​each scatter point is associated with the defect area of ​​the corresponding defect.

[0015] In an embodiment of the present invention, when the detection database includes a pattern data file, the determination method further includes: in response to receiving a pattern determination instruction including a product number of a non-ferrous metal rolled product and a customer identifier, obtaining a second standard data file corresponding to the product number of the non-ferrous metal rolled product for the customer identifier from the standard database, wherein the second standard data file includes a standard maximum height, a standard minimum height and a standard depression; obtaining a pattern data file corresponding to the product number of the non-ferrous metal rolled product from the detection database, and obtaining a maximum pattern height and a minimum pattern height from the pattern data file; determining a pattern depression according to the maximum pattern height and the minimum pattern height; and determining that the non-ferrous metal rolled product is a pattern qualified product when the maximum pattern height is less than or equal to the standard maximum height, the minimum pattern height is less than or equal to the standard minimum height and the pattern depression is less than or equal to the standard depression.

[0016] In an embodiment of the present invention, the determination method further includes: in response to receiving a pattern display instruction including a product number of a non-ferrous metal rolled product, displaying the data in the pattern data file using a line graph according to the product number of the non-ferrous metal rolled product, wherein the horizontal axis and the vertical axis of the line graph are respectively the length coordinate of the corresponding non-ferrous metal rolled product and the pattern height at the length coordinate.

[0017] In an embodiment of the present invention, the determination method also includes: when the total number of defects obtained is greater than the standard total number of defects or the maximum defect size obtained is greater than the standard defect size, obtaining a new first standard data file corresponding to the product number of the non-ferrous metal rolled product for the new customer identification from the standard database, wherein the new first standard data file includes a new standard total number of defects and a new standard defect size; comparing the total number of defects obtained and the maximum defect size with the new standard total number of defects and the new standard defect size respectively; and when the total number of defects obtained is less than or equal to the new standard total number of defects and the maximum defect size obtained is less than or equal to the new standard defect size, determining that the non-ferrous metal rolled product is a qualified quality product for the new customer identification.

[0018] Through the above technical scheme, the present invention can realize highly automated surface quality defect data collection, display, analysis and judgment, greatly reduce the manual workload in the entire process, reduce the time consumption of analysis and judgment, and at the same time avoid errors in product number correspondence, statistical calculations, etc. that may occur when manually screening data, thereby greatly improving the accuracy of analysis and judgment.

[0019] The third aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for establishing a detection database for non-ferrous metal rolled products and the method for determining non-ferrous metal rolled products are implemented.

[0020] Other features and advantages of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0022] Figure 1 It is a flow chart of a method for establishing a detection database for non-ferrous metal rolled products provided by one embodiment of the present invention;

[0023] Figure 2 It is a flow chart of a method for determining a non-ferrous metal rolled product provided by one embodiment of the present invention;

[0024] Figure 3 is a flow chart of a process for determining surface quality defects provided by an embodiment of the present invention; and

[0025] Figure 4 It is a line graph of the template data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0027] Figure 1 FIG. 1 is a flow chart of a method for establishing a detection database for nonferrous metal rolled products provided by an embodiment of the present invention. Figure 1 As shown, the establishment method includes: step S101, acquiring multiple inspection files about non-ferrous metal rolled products from multiple inspection devices, wherein the multiple inspection files include surface defect data of multiple defect types, and the file formats of the multiple inspection files are different; step S102, extracting the product numbers of the non-ferrous metal rolled products from the file names of the multiple inspection files; step S103, parsing the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product from the surface defect data of the multiple defect types; step S104, adding the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product and the product number to a defect data file of a preset file format; and step S105, storing the defect data file in the inspection database.

[0028] The following explains and illustrates each of the above steps.

[0029] Step S101, obtaining multiple inspection files about non-ferrous metal rolled products from multiple inspection devices.

[0030] The multiple inspection files include surface defect data of multiple defect types, and the multiple inspection files have different file formats.

[0031] The various defect types may include: pinholes, black spots, black oil lines, concave and convex spots, and wrinkles. The pinholes are hole defects, while the others are non-hole defects.

[0032] Use multiple detection devices to detect defects of multiple defect types of the same non-ferrous metal rolled product. Each detection device will generate surface defect data about one defect type, for example, detection device 1 generates surface defect data about pinholes, detection device 2 generates surface defect data about concave and convex points, and detection device 3 generates surface defect data about wrinkles. Among them, the surface defect data may include defect location (for example, horizontal coordinate, vertical coordinate), defect type, defect length, and defect width. Each detection device saves the surface defect data of the corresponding defect type in a csv (Comma-Separated Values) or non-csv (for example, excel or xls) file, that is, forms a corresponding detection file. Thus, multiple detection devices will generate surface defect data of multiple defect types for the same non-ferrous metal rolled product, forming multiple detection files, wherein the file formats of the multiple detection files are different, for example, some are in csv format and some are in excel format.

[0033] In this embodiment, the surface quality defect data is automatically collected: the test result data file is automatically obtained from the test equipment and stored persistently.

[0034] Step S102: extracting the product number of the non-ferrous metal rolled product from the file names of the multiple detection files.

[0035] The file names of multiple inspection files for the same non-ferrous metal rolled product all involve the product number of the same non-ferrous metal rolled product, and this information is extracted from the file name when performing data parsing.

[0036] Step S103, analyzing the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product from the surface defect data of the multiple defect types.

[0037] For step S103, parsing the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product from the surface defect data in the multiple inspection files includes: parsing the defect type, defect position, defect length and defect width of each defect of the non-ferrous metal rolled product from the surface defect data in the multiple inspection files; comparing the defect length and defect width of each defect of the non-ferrous metal rolled product; and taking the larger value of the defect length and the defect width of each defect as the defect size of the corresponding defect.

[0038] Since the inspection file includes surface defect data, which may include defect location (e.g., horizontal coordinate, vertical coordinate), defect type, defect length, and defect width, any existing method can be used to directly parse the defect type, defect location (e.g., horizontal coordinate, vertical coordinate), defect length, and defect width of each defect of the product from the surface defect data of each inspection file. The defect size is calculated using the defect width and defect length obtained by the analysis, and the larger value of the length and width is taken as the size.

[0039] Step S104, adding the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product and the product number to a defect data file in a preset file format.

[0040] Among them, the preset file format can be csv.

[0041] At least the defect type, defect position and defect size of each defect of the non-ferrous metal rolled product obtained in step S104 and the product number obtained in step S102 may be added to the defect data file. The file format of the defect data file may be csv.

[0042] Of course, in addition to the above data, data such as defect length, defect width and / or defect area of ​​each defect may also be added to the defect data file.

[0043] Step S105: storing the defect data file in the detection database.

[0044] That is to say, a detection database (ie, surface defect database) is established for pinhole and non-hole defect detection data.

[0045] Since the test results of general surface quality defect detection equipment are stored in the form of different text files, the above embodiment realizes the collection and unified storage of test data, automatically collects and analyzes the data files generated by the detection equipment, and stores the data in the database. Before collection, a surface defect database and a corresponding judgment standard database (i.e., a standard database) can be constructed in advance based on the content and data structure contained in the text data output by the detection equipment. For example, using data ETL technology, the data in the file is analyzed and extracted and stored in the warehouse.

[0046] In one embodiment, the plurality of detection files also include product pattern detection data. Accordingly, the establishment method further includes: parsing the length coordinate of the non-ferrous metal rolled product and the pattern height on the length coordinate from the product pattern detection data in the plurality of detection files; adding the length coordinate of the non-ferrous metal rolled product and the pattern height on the length coordinate and the product number to the pattern data file in the preset file format; and storing the pattern data file in the detection database.

[0047] In addition to the surface defect data, the product pattern detection data can also be collected in parallel. Each detected file includes surface defect data of a defect type and product pattern detection data. Among them, the product pattern detection data includes the length coordinate of the non-ferrous metal rolled product and the pattern height on the length coordinate. The length coordinate of the product and the pattern height on the length coordinate can be directly parsed from the product pattern detection data of each detection file in any existing way. The length coordinate of the non-ferrous metal rolled product obtained by this step and the pattern height on the length coordinate and the product number obtained by step S102 can be added to the pattern data file, and then the pattern data file is also added to the detection database (i.e., the surface defect database).

[0048] Of course, the defect data files (or the defect data files and the pattern data files) of different non-ferrous metal rolled products with different product numbers are added to the detection database in the above manner.

[0049] To summarize, the present invention creatively first obtains multiple inspection files about non-ferrous metal rolled products from multiple inspection devices; secondly, extracts the product number of the product from the file names of the multiple inspection files; then, parses the defect type, defect position and defect size of each defect of the product from the surface defect data of multiple defect types; then, adds the defect type, defect position and defect size of each defect of the product and the product number to a defect data file in a preset file format; finally, stores the defect data file in the inspection database, thereby realizing highly automated surface quality defect data collection of multiple defect types, greatly reducing the manual workload in the entire process, reducing the time-consuming work of collection, and thus providing reliable basic data for the subsequent automated execution of analysis and judgment.

[0050] Figure 2 FIG. 1 is a flow chart of a method for determining a nonferrous metal rolled product according to an embodiment of the present invention. Figure 2As shown, the determination method includes: step S201, in response to receiving a defect determination instruction including a product number of a non-ferrous metal rolled product and a customer identifier, obtaining a first standard data file corresponding to the product number of the non-ferrous metal rolled product for the customer identifier from a standard database, wherein the first standard data file includes a standard total number of defects and a standard defect size; step S202, obtaining a defect data file corresponding to the product number from a detection database established according to the method for establishing a detection database for non-ferrous metal rolled products, and obtaining a total number of defects and a maximum defect size according to the defect data file; step S203, comparing the obtained total number of defects and the maximum defect size with the standard total number of defects and the standard defect size, respectively; and step S204, when the obtained total number of defects is less than or equal to the standard total number of defects and the obtained maximum defect size is less than or equal to the standard defect size, determining that the non-ferrous metal rolled product is a qualified product.

[0051] Before executing the determination process, surface defect determination standard rules for different product numbers (e.g., a first standard data file) may be maintained in a standard database based on the product standards required by different customers. The first standard data file may include the total number of standard defects and the standard defect size for each defect type for different product numbers.

[0052] When a defect determination instruction regarding a certain product number and customer identification is received, the product number and customer identification that require surface quality defect analysis are used as entry points, and a first standard data file corresponding to the product number for the customer identification is associated and queried in the standard database; at the same time, the product number is used as an entry point, and a defect data file corresponding to the product number is associated and queried from the inspection database; since the defect data file includes the defect type, defect position and defect size as well as the product number, the total number of defects can be determined according to the defect type and the defect position by any existing method, and the maximum defect size can be determined according to the defect size; the total number of defects obtained is compared with the standard total number of defects, and the maximum defect size is compared with the standard defect size, so as to determine whether the product meets the standard required by the customer; if both data are less than or equal to the corresponding standard data, it is determined that the surface quality of the product is qualified for the customer with the customer identification.

[0053] In one embodiment, the first standard data file also includes a standard defect density, a standard number of dense points, and / or a standard number of continuous defects. Accordingly, the determination method further includes: obtaining the defect density, the number of dense points, and / or the number of continuous defects according to the defect data file; comparing the obtained defect density with the standard defect density, comparing the number of dense points with the standard number of dense points, and / or comparing the number of continuous defects with the standard number of continuous defects; when the total number of defects obtained is less than or equal to the standard total number of defects, the maximum defect size obtained is less than or equal to the standard defect size, and the defect density obtained is less than or equal to the standard defect density, the number of dense points obtained is less than or equal to the standard number of dense points, and / or the number of continuous defects obtained is less than or equal to the standard number of continuous defects, the non-ferrous metal rolled product is determined to be a qualified product.

[0054] If the product standards required by the customer also include standard defect density and standard number of dense points, before executing the determination process, the surface defect determination standard rules for different product numbers can be maintained in the standard database (for example, the first standard data file) according to the product standards required by different customers. The first standard data file may include the total number of standard defects, standard defect size, standard defect density and standard number of dense points for each defect type for different product numbers. Among them, the number of standard dense points refers to the standard number of multiple defect points that exist simultaneously within a certain area range (which can be set according to actual requirements and its value is relatively small).

[0055] Since the defect data file includes the defect type, defect location, defect size and the product number, the total number of defects can be determined according to the defect type and the defect location by any existing method, and the defect density can be determined according to the size of the product, and the number of dense points can be determined according to the defect type and the defect location by any existing method; the total number of defects obtained is compared with the standard total number of defects, the maximum defect size is compared with the standard defect size, the defect density obtained is compared with the standard defect density, and the number of dense points obtained is compared with the standard number of dense points to determine whether the product meets the customer's requirements; if the four data are all less than or equal to the corresponding standard data, the surface quality of the product is determined to be qualified.

[0056] If the product standards required by the customer also include standard defect density and standard continuous defect quantity, before executing the determination process, the surface defect determination standard rules for different product numbers (e.g., the first standard data file) can be maintained in the standard database according to the product standards required by different customers. The first standard data file may include the total number of standard defects, standard defect size, standard defect density, and standard continuous defect quantity for each defect type of different product numbers. Among them, the standard continuous defect quantity refers to the standard number of surface quality defect points that are continuous in spatial distribution (i.e., the spatial distance is less than a distance threshold).

[0057] Since the defect data file includes the defect type, defect location, defect size and the product number, the total number of defects can be determined according to the defect type and the defect location by any existing method, and the defect density can be determined according to the size of the product, and the number of continuous defects can be determined according to the defect type and the defect location by any existing method; the total number of defects obtained is compared with the standard total number of defects, the maximum defect size is compared with the standard defect size, the defect density is compared with the standard defect density, and the continuous number of defects obtained is compared with the standard continuous number of defects to determine whether the product meets the standards required by the customer; if the four data are all less than or equal to the corresponding standard data, the surface quality of the product is determined to be qualified.

[0058] For other embodiments, the product standard required by the customer also includes standard defect density, standard number of dense points, or standard number of continuous defects, or also includes standard defect density, standard number of dense points and standard number of continuous defects, or also includes standard number of dense points and standard number of continuous defects, etc. Before executing the determination process, according to the product standards required by different customers, surface defect determination standard rules for different product numbers (for example, the first standard data file) can be maintained in the standard database. The specific content of the first standard data file will not be described here, and you can refer to the relevant description above.

[0059] For the determination of the spatial distribution characteristics of surface quality defects such as continuous pinholes and dense pinholes, two-dimensional sliding windows, convolutional neural networks, and graph convolutional neural networks are used to complete the determination.

[0060] Surface quality defect data (such as the maximum size and density of surface quality defects, etc.) are judged using the surface quality judgment standards maintained in the standard database. If the actual data exceeds the judgment standard threshold, it is considered unqualified. Surface quality defect judgment is performed on a product basis and the judgment result details are given.

[0061] In one embodiment, the determination method further includes: in response to receiving a defect display instruction including a product number of a non-ferrous metal rolled product, displaying the data in the defect data file on the same page according to the product number of the non-ferrous metal rolled product, wherein multiple defect types correspond to multiple display colors and the display method of each defect type can be hidden.

[0062] The displaying of the data in the defect data file on the same page includes: displaying the data in the defect data file on the same page using a scatter plot, wherein the coordinates of each scatter point are the defect coordinates of the corresponding defect, and the area of ​​each scatter point is associated with the defect area of ​​the corresponding defect.

[0063] In order to display different defects more intuitively, when a defect display instruction for a certain product number is received, the data in the defect data file is displayed on the same page. For example, different colors are used for display of different types of defects, and the defect types that need to be displayed can be dynamically selected, while other defect types that do not need to be displayed are hidden.

[0064] For example, the distribution of surface quality defects on the surface of the finished product is displayed in the form of a scatter plot. The maximum value of the horizontal axis of the scatter plot represents the width of the product, and the maximum value of the vertical axis represents the length of the product. Each point in the figure represents a defect at that position, and its horizontal and vertical coordinates are the position of the defect point on the surface. The size of the point represents the area of ​​the defect, and different types of defects are distinguished by different colors. The strategy for determining the size of the point is: first obtain the minimum size of each type of defect of the product, and set the area of ​​the corresponding point in the scatter plot to 1, and the display area of ​​each remaining point in the scatter plot is: (the area of ​​the defect corresponding to the point / minimum area)*1. In the scatter plot, the selected specific area can be enlarged to more clearly show the location distribution of defects in a small area; the surface quality defect category displayed in the scatter plot can be selected, and the defect category that does not need to be analyzed temporarily can be hidden. Therefore, even if there are two types of defects at the same position, all defects can be better displayed, thereby avoiding the overlapping display of defect points. At the same time, for each category of defects whose size exceeds the upper limit standard, it will be highlighted in the scatter plot for quick positioning.

[0065] The defect detection data originally stored in the detection database in the form of detailed items are displayed in the same page in the form of charts, which more intuitively describes the distribution characteristics of surface defects and the spatial distribution relationship between different surface quality defects.

[0066] by Figure 3 Take the example to illustrate the process of determining surface quality defects.

[0067] S1: Unified collection and analysis of text data.

[0068] S2: Establish surface quality database.

[0069] The surface quality database includes a detection database (including defect data files) and a standard database.

[0070] S3: Associate test data by product number.

[0071] S4: Graphical display of surface defects.

[0072] S5: Statistical analysis of surface defect data.

[0073] Conduct statistical analysis on the surface quality defect detection result data, calculate the total number and distribution characteristics of each type of surface defects, and display them in the form of tables and statistical graphs to facilitate more intuitive viewing and analysis of the detection result data.

[0074] S6: Surface defect determination details.

[0075] S7: Display of surface defect determination details.

[0076] This embodiment collects the surface quality defect data of non-ferrous metal rolled products, takes each finished product as the analysis object, realizes the automatic correlation query, visual display and statistical analysis of surface quality defect data, and online determination of surface quality, thereby improving the efficiency and accuracy of surface quality analysis and determination. This embodiment mainly aims at the goal of surface quality defect analysis and determination in the non-ferrous metal rolling industry, and realizes intuitive, accurate and efficient surface quality defect analysis and determination functions.

[0077] The present invention can realize highly automated computer collection, display, analysis and judgment of surface quality defect data, greatly reduce the manual workload in the whole process, and reduce the time consumed in analysis and judgment. The time consumed in data collection, analysis and judgment of a single surface quality analysis and judgment is reduced from several hours that may be consumed manually to a maximum of 30 minutes. At the same time, errors in product number correspondence, statistical calculations, etc. that may occur when manually screening data are avoided, and the accuracy of analysis and judgment is greatly improved.

[0078] In one embodiment, when the detection database includes a pattern data file, the determination method further includes: in response to receiving a pattern determination instruction including a product number of a non-ferrous metal rolled product and a customer identifier, obtaining a second standard data file corresponding to the product number of the non-ferrous metal rolled product for the customer identifier from the standard database, wherein the second standard data file includes a standard maximum height, a standard minimum height, and a standard droop; obtaining a pattern data file corresponding to the product number of the non-ferrous metal rolled product from the detection database, and obtaining a maximum pattern height and a minimum pattern height from the pattern data file; determining a pattern droop based on the maximum pattern height and the minimum pattern height; and determining that the non-ferrous metal rolled product is a pattern qualified product when the maximum pattern height is less than or equal to the standard maximum height, the minimum pattern height is less than or equal to the standard minimum height, and the pattern droop is less than or equal to the standard droop.

[0079] If the detection database includes a pattern data file, when a pattern determination instruction regarding a certain product number and customer identification is received, the product number and customer identification that require pattern analysis are used as entries, and a second standard data file corresponding to the product number for the customer identification is associated and queried in the standard database; at the same time, the pattern data file corresponding to the product number is associated and queried from the detection database using the product number as an entry; since the pattern data file includes a length coordinate, a pattern height on the length coordinate, and the product number, the maximum pattern height and the minimum pattern height can be determined by any existing method based on the pattern height on the length coordinate, and the pattern droop amount can be further determined; the maximum pattern height is compared with the standard maximum height, the minimum pattern height is compared with the standard minimum height, and the pattern droop amount is compared with the standard droop amount; if the three data are all less than or equal to the corresponding standard values, it is determined that the pattern of the product is qualified for the customer with the customer identification.

[0080] In one embodiment, the determination method further includes: in response to receiving a pattern display instruction including a product number of a non-ferrous metal rolled product, displaying the data in the pattern data file using a line graph according to the product number of the non-ferrous metal rolled product, wherein the horizontal axis and the vertical axis of the line graph are respectively the length coordinate of the corresponding non-ferrous metal rolled product and the pattern height at the length coordinate.

[0081] When receiving a layout display instruction for a certain product number, the layout detection data is displayed in the form of a line graph. The maximum value of the horizontal axis of the line graph represents the length of the product, and the maximum value of the vertical axis represents the layout height of the product at the corresponding length position, such as Figure 4As shown. In the line chart, the pattern curve is first drawn according to the pattern detection data. At the same time, according to the upper and lower limits of the pattern height entered in the standard, it is displayed in the line chart as a colored dotted line to determine whether the pattern height at each length position is qualified. The pattern droop is obtained by calculating the difference (absolute value) between the maximum and minimum values ​​of the pattern detection data, and the pattern droop is compared with the standard droop to determine whether it is qualified. Only when both the pattern height and the droop are qualified, the product pattern is judged to be qualified.

[0082] After two rounds of judgment, the judgment results are output. The judgment results are listed in a detailed judgment table by product, including basic information such as product number, production time, specifications, the total number of various surface defects such as pinholes and wrinkles, the calculation results of the plate sag, and the final judgment result (qualified / unqualified). On one page, the surface quality defects such as pinholes and wrinkles and various surface quality defect data such as plate detection are displayed in the form of charts.

[0083] For products that are judged as unqualified after the two rounds of judgment described above, other standards can be selected for secondary judgment to determine whether the product does not meet the requirements of the originally selected judgment standard but meets the lower judgment requirements, thereby avoiding the direct scrapping of the product after the first judgment is unqualified. The secondary judgment is completed based on the judgment result. For example, after modifying the customer on the judgment result query page, the system will automatically judge the product according to the judgment standard of the newly selected customer and update the judgment result.

[0084] In an embodiment of the present invention, the determination method also includes: when the total number of defects obtained is greater than the standard total number of defects or the maximum defect size obtained is greater than the standard defect size, obtaining a new first standard data file corresponding to the product number of the non-ferrous metal rolled product for the new customer identification from the standard database, wherein the new first standard data file includes a new standard total number of defects and a new standard defect size; comparing the total number of defects obtained and the maximum defect size with the new standard total number of defects and the new standard defect size respectively; and when the total number of defects obtained is less than or equal to the new standard total number of defects and the maximum defect size obtained is less than or equal to the new standard defect size, determining that the non-ferrous metal rolled product is a qualified quality product for the new customer identification.

[0085] An embodiment of the present invention establishes a surface quality defect database, collects surface defects such as pinholes and pattern detection data, realizes graphical visualization and statistical analysis of surface quality defect data of different categories on the same page, judges the surface quality in combination with the corresponding judgment standards of the product, realizes automated judgment result production, analysis of unqualified surface defects, and supports secondary re-judgment.

[0086] In summary, the present invention creatively realizes highly automated surface quality defect data collection, display, analysis and judgment, greatly reduces the manual workload in the entire process, reduces the time spent on analysis and judgment, and at the same time avoids errors in product number correspondence, statistical calculations, etc. that may occur when manually screening data, thereby greatly improving the accuracy of analysis and judgment.

[0087] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for establishing a detection database for non-ferrous metal rolled products and the method for determining non-ferrous metal rolled products are implemented.

[0088] An embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the method for establishing a detection database for non-ferrous metal rolled products and the method for determining non-ferrous metal rolled products.

[0089] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, a variety of simple modifications can be made to the technical solution of the present invention, and these simple modifications all belong to the protection scope of the present invention.

[0090] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

[0091] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0092] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the present invention, they should also be regarded as the contents disclosed by the present invention.

Claims

1. A method for establishing a detection database for non-ferrous metal rolled products, characterized in that: The establishment method comprises: Acquire multiple inspection files about non-ferrous metal rolled products from multiple inspection devices, wherein the multiple inspection files include surface defect data of multiple defect types, and the multiple inspection files have different file formats; Extracting the product number of the non-ferrous metal rolled product from the file names of the multiple detection files; Analyzing the defect type, defect location and defect size of each defect of the non-ferrous metal rolled product from the surface defect data of the multiple defect types; adding the defect type, defect location and defect size of each defect of the non-ferrous metal rolled product and the product number to a defect data file in a preset file format; and The defect data file is stored in the detection database.

2. The establishment method according to claim 1, characterized in that: The plurality of inspection files also include product pattern inspection data, and the establishment method further includes: Parsing the length coordinate of the non-ferrous metal rolled product and the height of the pattern on the length coordinate from the product pattern detection data in the plurality of detection files; Adding the length coordinate of the non-ferrous metal rolled product, the pattern height on the length coordinate, and the product number to the pattern data file in the preset file format; and The pattern data file is stored in the detection database.

3. The establishment method according to claim 1 or 2, characterized in that: Analyzing the defect type, defect location and defect size of each defect of the non-ferrous metal rolled product from the surface defect data in the plurality of inspection files includes: Analyzing the defect type, defect position, defect length and defect width of each defect of the non-ferrous metal rolled product from the surface defect data in the plurality of inspection files; comparing the defect length and the defect width of each defect of the non-ferrous metal rolled product; and The larger value between the defect length and the defect width of each defect is taken as the defect size of the corresponding defect.

4. The establishment method according to claim 1 or 2, characterized in that: The various defect types include: pinholes, black spots, black oil lines, concave and convex spots, and wrinkles.

5. A method for determining non-ferrous metal rolled products, characterized in that: The determination method comprises: In response to receiving a defect determination instruction including a product number of a non-ferrous metal rolled product and a customer identifier, acquiring a first standard data file corresponding to the product number of the non-ferrous metal rolled product for the customer identifier from a standard database, wherein the first standard data file includes a standard defect total number and a standard defect size; Obtaining a defect data file corresponding to the product number from a detection database established by the method for establishing a detection database for non-ferrous metal rolled products according to any one of claims 1 to 4, and obtaining a total number of defects and a maximum defect size according to the defect data file; Comparing the obtained total number of defects and maximum defect size with the standard total number of defects and the standard defect size respectively; and When the total number of defects obtained is less than or equal to the standard total number of defects and the maximum defect size obtained is less than or equal to the standard defect size, the non-ferrous metal rolled product is determined to be a product of qualified quality.

6. The determination method according to claim 5, characterized in that: The first standard data file also includes a standard defect density, a standard number of dense points and / or a standard number of continuous defects, and the determination method also includes: Acquire defect density, number of dense points and / or number of continuous defects according to the defect data file; Comparing the obtained defect density with the standard defect density, comparing the number of dense points with the standard number of dense points, and / or comparing the number of continuous defects with the standard number of continuous defects; When the total number of defects obtained is less than or equal to the standard total number of defects, the maximum defect size obtained is less than or equal to the standard defect size, the defect density obtained is less than or equal to the standard defect density, the number of dense points obtained is less than or equal to the standard number of dense points, and / or the number of continuous defects obtained is less than or equal to the standard number of continuous defects, the non-ferrous metal rolled product is judged to be a qualified quality product.

7. The determination method according to claim 5, characterized in that: The determination method further comprises: In response to receiving a defect display instruction including a product number of a non-ferrous metal rolled product, the data in the defect data file is displayed on the same page according to the product number of the non-ferrous metal rolled product, wherein multiple defect types correspond to multiple display colors and the display method of each defect type can be hidden.

8. The determination method according to claim 7, characterized in that: The displaying of the data in the defect data file on the same page includes: On the same page, a scatter plot is used to display the data in the defect data file, wherein the coordinates of each scatter point are the defect coordinates of the corresponding defect, and the area of ​​each scatter point is associated with the defect area of ​​the corresponding defect.

9. The determination method according to claim 5, characterized in that: In the case where the detection database includes a pattern data file, the determination method further includes: In response to receiving a version determination instruction including a product number of a non-ferrous metal rolled product and a customer identifier, obtaining a second standard data file corresponding to the product number of the non-ferrous metal rolled product for the customer identifier from the standard database, wherein the second standard data file includes a standard maximum height, a standard minimum height, and a standard setback; Acquire a pattern data file corresponding to the product number of the non-ferrous metal rolled product from the detection database, and acquire a maximum pattern height and a minimum pattern height from the pattern data file; Determining the amount of template depression according to the maximum template height and the minimum template height; and When the maximum pattern height is less than or equal to the standard maximum height, the minimum pattern height is less than or equal to the standard minimum height, and the pattern depression is less than or equal to the standard depression, the non-ferrous metal rolled product is determined to be a pattern qualified product.

10. The determination method according to claim 9, characterized in that: The determination method further comprises: In response to receiving a pattern display instruction including a product number of a non-ferrous metal rolled product, the data in the pattern data file is displayed using a line graph according to the product number of the non-ferrous metal rolled product, wherein the horizontal axis and the vertical axis of the line graph are respectively the length coordinate of the corresponding non-ferrous metal rolled product and the pattern height at the length coordinate.

11. The determination method according to any one of claims 5 to 10, characterized in that: The determination method further comprises: When the total number of defects obtained is greater than the standard total number of defects or the maximum defect size obtained is greater than the standard defect size, a new first standard data file corresponding to the product number of the non-ferrous metal rolled product identified by the new customer is obtained from the standard database, wherein the new first standard data file includes a new standard total number of defects and a new standard defect size; Comparing the obtained total number of defects and maximum defect size with the new standard total number of defects and the new standard defect size respectively; and When the total number of defects obtained is less than or equal to the new standard total number of defects and the maximum defect size obtained is less than or equal to the new standard defect size, the non-ferrous metal rolled product is determined to be a qualified product for the new customer identification.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for establishing a detection database for non-ferrous metal rolled products as described in any one of claims 1 to 4 and the method for determining non-ferrous metal rolled products as described in any one of claims 5 to 11.

Images