Intelligent detection system and method for surface defects of metal coiled material

Abstract

The invention relates to the technical field of metal coiled materials, and provides a metal coiled material surface defect intelligent detection system, which comprises a laser acquisition system, a data detection system, an array formation system, a storage system and a proofreading system, the laser collecting system is used for reflecting laser, the laser collecting system is used for collecting surface data of the metal coiled material through the reflected laser, the data detecting system is used for processing the data collected by the laser collecting system, the array forming system is used for visualizing the data, and the storage system is used for storing the visualized data. And the proofreading system is used for comparing and detecting the visual data in the storage system with new data detected subsequently. High-precision scanning is conducted on the surface of the metal coiled material through the laser collection system, collected data are specially processed through the concavity detection module, the convexity detection module and the color detection module in the data detection system, and various types of surface defects can be carefully recognized.

Description

Technical Field

[0001] The present invention relates to the technical field of metal coils, and in particular to an intelligent detection system and method for surface defects of metal coils. Background Art

[0002] Metal coil is a metal material usually supplied in roll form and is widely used in construction, automotive, aerospace, home appliances, electronics and other industrial fields.

[0003] Metal coils may have various defects during the manufacturing and processing process, such as cracks, holes, scratches, rust, etc. These defects seriously affect the performance and service life of the material. Traditional metal coil defect detection methods mainly rely on manual visual inspection, which is inefficient, easily affected by human factors, and difficult to detect small or hidden defects. Therefore, it is necessary to invent an intelligent detection system and method for metal coil surface defects to achieve automation, reduce manpower, and improve detection efficiency and accuracy. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an intelligent detection system and method for surface defects of metal coils, which solves the problem that the metal coil defect detection method mainly relies on manual visual inspection, which is inefficient, easily affected by human factors, and difficult to detect tiny or hidden defects.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] An intelligent detection system for surface defects of metal coils comprises a laser acquisition system, a data detection system, an array forming system, a storage system and a proofreading system. The laser acquisition system is used to irradiate the surface of the metal coil so as to collect the surface data of the metal coil with the reflected laser. The data detection system is used to process the data collected by the laser acquisition system. The array forming system is used to visualize the data. The storage system is used to store the visualized data. The proofreading system is capable of comparing the visualized data in the storage system with the new data detected subsequently.

[0007] Preferably, the data detection system includes a concavity detection module, a convexity detection module and a color detection module. The concavity detection module has the function of detecting sunken and uneven areas on the surface of the metal coil, the convexity detection module has the function of detecting convex and uneven areas on the surface of the metal coil, and the color detection module has the function of detecting abnormal color areas on the surface of the metal coil due to rust and excessive impurities.

[0008] Preferably, the array forming system includes a grid template module, a grid filling module, an array overlapping module and an array calculation module. The data output by the concavity detection module, the convexity detection module and the color detection module are filled into the grid template module through the grid filling module to form a visual array. The array overlapping module is used to overlap the visual array, and the array calculation module is capable of calculating and extracting range data of the overlapping visual array.

[0009] Preferably, the data output by the concavity detection module, the convexity detection module and the color detection module are multiple groups to fill and generate multiple groups of visualization arrays.

[0010] Preferably, the storage system includes a temporary storage module, a historical storage module and a data export module. The temporary storage module is used to store temporarily established engineering data. The historical storage module is capable of importing the engineering data stored in the temporary storage module into long-term storage. The data export module is capable of exporting the data in the temporary storage module and the historical storage module to transfer data and use it for proofreading work of the proofreading system.

[0011] An intelligent detection method for surface defects of metal coils comprises the following steps:

[0012] Step 1: prepare a batch of metal coils from the same batch, and randomly select several of them to collect surface data using a laser collection system;

[0013] Step 2: The data collected by the laser collection system is classified and grouped by the data detection system, and output to the array formation system for visual array construction;

[0014] Step 3: Visual array construction exports multiple sets of array data, and processes the multiple sets of visual array data to form a detection range;

[0015] Step 4: Use the calibration system to quickly detect the arrays collected from the remaining metal coils of the same batch within the detection range.

[0016] Preferably, the visualization array construction in step 3 is specifically as follows:

[0017] In the data output by the concavity detection module to the grid filling module, the flat surface is output as 0, and the concave part is output as 1. The grid in the grid template module is filled with black and white, 0 is white, 1 is black, and the black and white array grids A1, A2...A are exported. n ;

[0018] In the data output by the convexity detection module to the grid filling module, the flat surface is output as 0, and the convex part is output as 1. The grid in the grid template module is filled with gray and white, 0 is white, 1 is gray, and the black and white array grids B1, B2...B are exported. n ;

[0019] In the data output by the color detection module to the grid filling module, the normal color area is output as 0, and the color field area is output as 1. The grid in the grid template module is filled with red and white, 0 is white, 1 is red, and the black and white array grids C1, C2...C are exported. n .

[0020] Preferably, the detection range processing method in step 3 is: grids A1, A2...A n , B1, B2...B n and C1, C2...C n Group them and overlap them. Select the high overlap part in multiple groups of grids to regenerate the grid as the detection range. Grids A1, A2...A n Overlap is A α , grid B1, B2...B n Overlap is B α , grids C1, C2...C n Overlap is C α .

[0021] Preferably, in the work of collecting the remaining metal coils of the same batch in step 4: the grid array generated by the concavity detection module is A β , the grid array generated by the convexity detection module is B β The grid array generated by the color detection module is C β .

[0022] Preferably, the detection method in step 4 is: when A α >A β , B α >B β and C α >C β If all three items are met, the metal coil is considered qualified; otherwise, it is unqualified if any one of them is not met.

[0023] The present invention provides an intelligent detection system and method for metal coil surface defects.

[0024] Beneficial effects:

[0025] 1. The present invention uses a laser acquisition system to perform high-precision scanning on the surface of the metal coil. The collected data is specially processed by the concavity detection module, convexity detection module and color detection module in the data detection system, which can carefully identify various types of surface defects. In addition, the generation and overlapping processing technology of multiple sets of data visualization arrays is combined to further enhance the ability to identify the size, shape and distribution of defects, thereby significantly improving the precision and accuracy of detection.

[0026] 2. The present invention greatly reduces the need for manual inspection and the risk of misjudgment caused by human factors through automated data collection, processing and visualization array construction, and can quickly judge the quality of the coiled material and realize an efficient and automated quality control process. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A diagram of an intelligent detection system for surface defects of a metal coil according to the present invention;

[0028] Figure 2 A diagram of a data detection system of the present invention;

[0029] Figure 3 A system diagram for forming an array of the present invention;

[0030] Figure 4 A diagram of a storage system of the present invention;

[0031] Figure 5 The present invention is a flow chart of an intelligent detection method for surface defects of metal coils. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Example:

[0034] As one aspect of this application, please see the attached Figure 1 - Attachment Figure 4An embodiment of the present invention provides an intelligent detection system for surface defects of metal coils, including a laser acquisition system, a data detection system, an array forming system, a storage system and a proofreading system. The laser acquisition system is used to irradiate the surface of the metal coil to collect the surface data of the metal coil with the reflected laser. The data detection system is used to process the data collected by the laser acquisition system. The array forming system is used to visualize the data. The storage system is used to store the visualized data. The proofreading system is capable of comparing and detecting the visualized data in the storage system with the new data detected subsequently.

[0035] The data detection system includes a concavity detection module, a convexity detection module and a color detection module. The concavity detection module has the function of detecting concave and uneven areas on the surface of the metal coil, the convexity detection module has the function of detecting convex and uneven areas on the surface of the metal coil, and the color detection module has the function of detecting abnormal color areas on the surface of the metal coil due to rust and excessive impurities.

[0036] The array forming system includes a grid template module, a grid filling module, an array overlapping module and an array calculation module. The data output by the concavity detection module, the convexity detection module and the color detection module are filled into the grid template module through the grid filling module to form a visual array. The array overlapping module is used to overlap the visual array. The array calculation module has the function of calculating and extracting range data of the overlapping visual array. The data output by the concavity detection module, the convexity detection module and the color detection module are multiple groups, which are used to fill and generate multiple groups of visual arrays to reduce errors and improve accuracy.

[0037] The storage system includes a temporary storage module, a historical storage module and a data export module. The temporary storage module is used to store temporarily established engineering data. The historical storage module has the function of importing the engineering data stored in the temporary storage module into long-term storage. The data export module has the function of exporting the data in the temporary storage module and the historical storage module to transfer data and use it for proofreading work of the proofreading system.

[0038] Based on the above-mentioned intelligent detection system for metal coil surface defects, as another aspect of the present application, please refer to the attached Figure 1 - Attachment Figure 5 , an intelligent detection method for surface defects of metal coils, comprising the following steps:

[0039] Step 1: prepare a batch of metal coils from the same batch, and randomly select several of them to collect surface data using a laser collection system;

[0040] Step 2: The data collected by the laser collection system is classified and grouped by the data detection system, and output to the array formation system for visual array construction;

[0041] Step 3: Visual array construction: Export multiple sets of array data, and process the multiple sets of visual array data in the following way:

[0042] In the data output by the concavity detection module to the grid filling module, the flat surface is output as 0, and the concave part is output as 1. The grid in the grid template module is filled with black and white, 0 is white, 1 is black, and the black and white array grids A1, A2...A are exported. n ;

[0043] In the data output by the convexity detection module to the grid filling module, the flat surface is output as 0, and the convex part is output as 1. The grid in the grid template module is filled with gray and white, 0 is white, 1 is gray, and the black and white array grids B1, B2...B are exported. n ;

[0044] In the data output by the color detection module to the grid filling module, the normal color area is output as 0, and the color field area is output as 1. The grid in the grid template module is filled with red and white, 0 is white, 1 is red, and the black and white array grids C1, C2...C are exported. n ;

[0045] Then the detection range is processed. The detection range is processed as follows: grids A1, A2...A n , B1, B2...B n and C1, C2...C n Group them and overlap them. Select the high overlap part in multiple groups of grids to regenerate the grid as the detection range. Grids A1, A2...A n Overlap is A α , grid B1, B2...B n Overlap is B α , grids C1, C2...C n Overlap is C α ;

[0046] Step 4: Use the calibration system to quickly detect the arrays collected from the remaining metal coils of the same batch using the detection range. The grid array generated by the concavity detection module is A. β , the grid array generated by the convexity detection module is B β The grid array generated by the color detection module is C β , when A α >A β , B α >B β and C α >C βIf all three items are met, the metal coil is considered qualified; otherwise, it is unqualified if any one of them is not met.

[0047] The intelligent detection system uses a laser acquisition system to scan the surface of metal coils with high precision. The collected data is specially processed by the concavity, convexity and color detection modules in the data detection system, and can carefully identify various types of surface defects. The system uses the generation and overlapping processing technology of multiple sets of data visualization arrays to further enhance the ability to identify the size, shape and distribution of defects, thereby significantly improving the meticulousness and accuracy of detection. Through automated data acquisition, processing and visualization array construction, it greatly reduces the need for manual inspection and reduces the risk of misjudgment caused by human factors. The temporary storage and historical storage modules in the storage system, as well as the data export module, provide strong support for data management and analysis. The introduction of the proofreading system makes it possible to quickly detect the same batch of metal coils. By comparing the detection range with the actual collected data, the quality of the coil can be quickly judged, realizing an efficient and automated quality control process.

[0048] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent detection system for surface defects of metal coils, characterized in that: The invention comprises a laser acquisition system, a data detection system, an array forming system, a storage system and a proofreading system. The laser acquisition system is used to irradiate the surface of the metal coil so as to collect the surface data of the metal coil by the reflected laser. The data detection system is used to process the data collected by the laser acquisition system. The array forming system is used to visualize the data. The storage system is used to store the visualized data. The proofreading system is capable of comparing and detecting the visualized data in the storage system with the new data detected subsequently.

2. The intelligent detection system for metal coil surface defects according to claim 1 is characterized in that: The data detection system includes a concavity detection module, a convexity detection module and a color detection module. The concavity detection module has the function of detecting concave and uneven areas on the surface of the metal coil, the convexity detection module has the function of detecting convex and uneven areas on the surface of the metal coil, and the color detection module has the function of detecting abnormal color areas on the surface of the metal coil due to rust and excessive impurities.

3. The intelligent detection system for metal coil surface defects according to claim 2, characterized in that: The array forming system includes a grid template module, a grid filling module, an array overlapping module and an array calculation module. The data output by the concavity detection module, the convexity detection module and the color detection module are filled into the grid template module through the grid filling module to form a visual array. The array overlapping module is used to overlap the visual array. The array calculation module is capable of calculating and extracting range data of the overlapping visual array.

4. The intelligent detection system for metal coil surface defects according to claim 3 is characterized in that: The data output by the concavity detection module, the convexity detection module and the color detection module are multiple groups, so as to fill and generate multiple groups of visualization arrays.

5. The intelligent detection system for metal coil surface defects according to claim 1, characterized in that: The storage system includes a temporary storage module, a historical storage module and a data export module. The temporary storage module is used to store temporarily established engineering data. The historical storage module is capable of importing the engineering data stored in the temporary storage module into long-term storage. The data export module is capable of exporting the data in the temporary storage module and the historical storage module to transfer data and use it for proofreading work of the proofreading system.

6. An intelligent detection method for metal coil surface defects, using an intelligent detection system for metal coil surface defects as claimed in any one of claims 1 to 5, characterized in that: The following steps are involved: Step 1: prepare a batch of metal coils from the same batch, and randomly select several of them to collect surface data using a laser collection system; Step 2: The data collected by the laser collection system is classified and grouped by the data detection system, and output to the array formation system for visual array construction; Step 3: Visual array construction exports multiple sets of array data, and processes the multiple sets of visual array data to form a detection range; Step 4: Use the detection range to quickly detect the arrays collected from the remaining metal coils of the same batch through the calibration system.

7. The intelligent detection method for surface defects of metal coils according to claim 6, characterized in that: The visualization array construction in step 3 is specifically as follows: In the data output by the concavity detection module to the grid filling module, the flat surface is output as 0, and the concave part is output as 1. The grid in the grid template module is filled with black and white, 0 is white, 1 is black, and the black and white array grids A1, A2...A are exported. n ; In the data output by the convexity detection module to the grid filling module, the flat surface is output as 0, and the convex part is output as 1. The grid in the grid template module is filled with gray and white, 0 is white, 1 is gray, and the black and white array grids B1, B2...B are exported. n ; In the data output by the color detection module to the grid filling module, the normal color area is output as 0, and the color field area is output as 1. The grid in the grid template module is filled with red and white, 0 is white, 1 is red, and the black and white array grids C1, C2...C are exported. n .

8. The intelligent detection method for surface defects of metal coils according to claim 7, characterized in that: The detection range processing method in step 3 is: grid A1, A2...A n , B1, B2...B n and C1, C2...C n Group them and overlap them. Select the high overlap part in multiple groups of grids to regenerate the grid as the detection range. Grids A1, A2...A n Overlap is A α , grid B1, B2...B n Overlap is B α , grids C1, C2...C n Overlap is C α .

9. The intelligent detection method for surface defects of metal coils according to claim 8, characterized in that: In the work of collecting the remaining metal coils of the same batch in step 4: the grid array generated by the concavity detection module is A β , the grid array generated by the convexity detection module is B β The grid array generated by the color detection module is C β .

10. The intelligent detection method for surface defects of metal coils according to claim 9, characterized in that: The detection method of step 4 is: when A α >A β , B α >B β and C α >C β If all three items are met, the metal coil is considered qualified; otherwise, it is unqualified if any one of them is not met.

Images