Detection method and detection device for surface defects of aluminum foil, and slitter

Abstract

This application relates to the field of quality inspection technology, and discloses a detection method, a detection device, and a slitter for defects on the surface of aluminum foil. The detection method includes obtaining the original image information of the aluminum foil surface; performing defect detection on the original image information to obtain a set of defect candidate regions; analyzing the candidate region images in the set of defect candidate regions to obtain a set of defect regions; and identifying the candidate region images in the set of defect regions according to a preset algorithm and outputting a defect identification result. The detection method provided by this disclosure sequentially performs defect detection on the original image information of the aluminum foil surface collected, analyzes the obtained defect region images, and uses a preset algorithm for identification to obtain the defect identification result corresponding to each candidate region image. Compared with the related art, the recognition accuracy of defects on the aluminum foil surface is effectively improved, and thus the detection effect of the surface quality of the aluminum foil is improved.

Description

Technical Field

[0001] The present application relates to the technical field of quality inspection, for example, to a method and device for inspecting surface defects of aluminum foil, and a slitting machine. Background Art

[0002] Aluminum foil refers to a thin sheet with a thickness of less than 0.2mm made of metal aluminum. The aluminum foil needs to be cut longitudinally at the edge and rolled. Therefore, it needs to go through a slitting process to cut the aluminum foil into a specified width. In addition, it is necessary to manually inspect the surface of the aluminum foil for defects. However, manual inspection is inevitably negligent and prone to misdetection.

[0003] In the related art, a detection device for detecting the surface quality of aluminum foil is provided, which uses a first camera to collect images of the surface of the aluminum foil, and transmits the collected data to a control device for identification processing to determine whether there are defects, so that when the surface quality of the aluminum foil is detected, manual visual inspection is not required. At the same time, the second camera collects the image of the aluminum foil for the second time, and it can be determined again whether the aluminum foil has defects, that is, the second camera reviews the defects detected by the first camera.

[0004] The following problems exist in the publicly available implementation process:

[0005] The detection device in the related art compares the image captured by the camera with the defect image to determine whether there is a defect on the surface of the aluminum foil. By comparing the images, the defect images captured in different scenes with the same defect are unique. Therefore, by comparing the captured image with the defect image, the recognition result obtained has the problem of low detection accuracy. Summary of the invention

[0006] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0007] The embodiments of the present disclosure provide a method and a detection device for detecting surface defects of aluminum foil, and a slitting machine, which improve the recognition accuracy of surface defects of aluminum foil, and further improve the detection effect of the surface quality of aluminum foil.

[0008] In some embodiments, a method for detecting surface defects of aluminum foil is provided, including obtaining original image information of the aluminum foil surface; performing defect detection on the original image information to obtain a set of defect candidate areas; analyzing candidate area images in the set of defect candidate areas to obtain a set of defect areas; identifying the candidate area images in the set of defect areas according to a preset algorithm, and outputting a defect identification result.

[0009] In some embodiments, a detection device for surface defects of aluminum foil is provided, including an acquisition unit for acquiring original image information of the aluminum foil surface; a detection unit for performing defect detection on the original image information to obtain a set of defect candidate regions; an analysis unit for analyzing the candidate region images in the set of defect candidate regions to obtain a set of defect regions; and an identification unit for identifying the candidate region images in the set of defect regions according to a preset algorithm and outputting a defect identification result.

[0010] In some embodiments, a detection device for surface defects of aluminum foil is provided, including a processor and a memory storing program instructions, where the processor is configured to execute the detection method for surface defects of aluminum foil as described in any of the above embodiments.

[0011] In some embodiments, a slitter is provided, including: a machine body; a defect detection system disposed on the machine body for detecting original image information of the aluminum foil surface; and the detection device for surface defects of aluminum foil as described in any of the above embodiments, installed on the machine body, and the detection device is connected to the defect detection system.

[0012] The detection method, detection device, and slitter for surface defects of aluminum foil provided by the embodiments of the present disclosure can achieve the following technical effects:

[0013] The detection method provided by the present disclosure is used for aluminum foil surface detection. Specifically, first, original image information of the aluminum foil surface is acquired. By performing defect detection on the original image information, a set of defect candidate regions is obtained. The candidate region images in the set of defect candidate regions are analyzed one by one, and the selected candidate region images form a set of defect regions. A preset algorithm is used to identify the candidate region images in the set of defect regions one by one, and the defect identification result corresponding to each candidate region image is output.

[0014] By adopting the detection method provided by the present disclosure, through the original image information of the aluminum foil surface collected, defect detection is performed in sequence, the obtained defect region images are analyzed, and a preset algorithm is used for identification, and the defect identification result corresponding to each candidate region image is obtained. Compared with the detection result obtained by image comparison in the related art, the defect detection result obtained by using the detection method for aluminum foil surface defects of the present disclosure is more accurate, effectively improving the recognition accuracy of aluminum foil surface defects, and further improving the detection effect of aluminum foil surface quality.

[0015] The above general description and the following description are only exemplary and explanatory, and are not used to limit this application. Description of the Drawings

[0016] One or more embodiments are exemplarily illustrated by corresponding drawings. These exemplary illustrations and the drawings do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and wherein:

[0017] Figure 1 is a schematic structural diagram of a detection system for aluminum foil surface defects provided by an embodiment of the present disclosure;

[0018] Figure 2 is a system framework diagram of a detection system for aluminum foil surface defects provided by an embodiment of the present disclosure;

[0019] Figure 3 is a schematic flowchart of a detection method for aluminum foil surface defects provided by an embodiment of the present disclosure;

[0020] Figure 4 is a schematic flowchart of a detection method for aluminum foil surface defects provided by an embodiment of the present disclosure;

[0021] Figure 5 is a schematic flowchart of a detection method for aluminum foil surface defects provided by an embodiment of the present disclosure;

[0022] Figure 6 is a structural block diagram of a detection device for aluminum foil surface defects provided by an embodiment of the present disclosure;

[0023] Figure 7 is a schematic structural diagram of a slitter provided by an embodiment of the present disclosure;

[0024] Figure 8 is Figure 7 an enlarged structural diagram of part A of the slitter provided by the illustrated embodiment;

[0025] Figure 9 is Figure 7 a schematic diagram of the detection station distribution of the slitter provided by the illustrated embodiment;

[0026] Figure 10 is Figure 7 a schematic structural diagram of the second detection system of the slitter provided by the illustrated embodiment;

[0027] Figure 11 is Figure 7 a sectional view of the slitter provided by the illustrated embodiment;

[0028] Figure 12 is Figure 7 a schematic installation structure diagram of the first surface inspection camera provided by the illustrated embodiment;

[0029] Figure 13 is Figure 7Schematic diagram of the installation structure of the hole inspection camera provided by the illustrated embodiment;

[0030] Figure 14 is Figure 7 Schematic diagram of the installation structure of the light source provided by the illustrated embodiment;

[0031] Figure 15 is Figure 7 Schematic diagram of the installation structure of the camera provided by the illustrated embodiment;

[0032] Figure 16 is the system block diagram of the detection device for aluminum foil surface defects provided by an embodiment of the present disclosure.

[0033] Reference numerals:

[0034] 10 Detection system;

[0035] 110 First frame; 111 Installation frame; 112 Connecting frame; 113 Connecting beam; 114 First cross beam; 115 Second cross beam; 116 First rod; 117 Second rod; 118 Connecting seat;

[0036] 120 First detection system; 121 Surface inspection component; 122 First surface inspection camera; 123 First surface inspection light source; 124 Hole inspection component; 125 Hole inspection camera; 126 Hole inspection light source;

[0037] 130 Second frame;

[0038] 140 Second detection system; 142 Second surface inspection camera; 144 Second surface inspection light source;

[0039] 150 Cover; 160 Fan;

[0040] 20 Slitter;

[0041] 210 Machine body; 212 Feeding end; 214 Discharging end;

[0042] 220 Sliding component; 222 Slide rail; 2221 Main slide rail; 2222 First sub-slide rail; 2223 Second sub-slide rail; 224 Slide block; 226 Driving part;

[0043] 230 First aluminum foil output part; 240 Second aluminum foil output part; 250 Aluminum foil input part;

[0044] 30 Aluminum foil; a First surface; b Second surface;

[0045] 40 Image processing system; 410 Image processing computer; 420 Detection control computer. Detailed implementation manners

[0046] In order to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The attached drawings are for reference and illustration only, and are not intended to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, numerous details are provided to give a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other instances, well-known structures and devices may be shown in a simplified manner to simplify the drawings.

[0047] In the description of the embodiments of the present disclosure, the terms "first", "second", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0048] Unless otherwise specified, the term "plurality" means two or more.

[0049] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0050] The term "and / or" is an associative relationship describing an object, indicating that there can be three relationships. For example, A and / or B means: A or B, or, A and B these three relationships.

[0051] The term "corresponding" may refer to an associative relationship or a binding relationship. A corresponding to B means that there is an associative relationship or a binding relationship between A and B.

[0052] In some embodiments, in combination with Figure 1 and Figure 2 as shown, a detection system 10 for surface defects of aluminum foil is provided, including: a first detection system 120, a second detection system 140, and an image processing system 40. The first detection system 120 is used to detect the first surface a of the aluminum foil 30. The second detection system 140 is used to detect the second surface b of the aluminum foil 30. The first surface a and the second surface b are two opposite surfaces of the aluminum foil 30. The image processing system 40 is respectively connected to the first detection system 120 and the second detection system 140, and is used to perform image analysis and processing on the original image information detected by the first detection system 120 and the second detection system 140, and output a defect recognition result.

[0053] In combination with Figure 12As shown, the first detection system 120 includes an appearance inspection component 121. The appearance inspection component includes a plurality of first appearance inspection cameras 122 and a first appearance inspection light source 123. The plurality of first appearance inspection cameras 122 and the first appearance inspection light source 123 are located on the same side of the aluminum foil 30. The first detection system 120 further includes a hole inspection component 124. Figure 13 As shown, the hole inspection component 124 includes a plurality of hole inspection cameras 125 and a hole inspection light source 126. The plurality of hole inspection cameras 125 and the hole inspection light source 126 are respectively located on opposite sides of the aluminum foil 30. The hole inspection component 124 is used to detect pinhole defects. The appearance inspection component 121 is used to detect other surface defects except for pinhole defects.

[0054] Combined with Figure 10 As shown, the second detection system 140 includes: a plurality of second appearance inspection cameras 142 and a second appearance inspection light source 144. The plurality of second appearance inspection cameras 142 and the second appearance inspection light source 144 are located on the same side of the aluminum foil 30.

[0055] Optionally, combined with Figure 2 As shown, the image processing system 40 includes an image processing computer 410 and a detection control computer 420. The image processing computer 410 is connected to the cameras in the first detection system 120 and the second detection system 140.

[0056] Optionally, the image processing system includes a processor and a memory storing program instructions. The processor is configured to execute a detection method for surface defects of the aluminum foil when running the program instructions.

[0057] Specifically, combined with Figure 1 and Figure 2 As shown, during the movement of the aluminum foil 30, each camera collects the original image information on the surface of the aluminum foil 30 in real time and transmits it to the image processing computer 410. The image processing computer 410 uses image analysis software to analyze the original image information on the surface of the aluminum foil 30 in real time to obtain the defect detection result, and sends the detection result to the detection control computer 420 in real time. After receiving the detection results of all cameras, the detection control computer 420 displays them on the system control interface in real time. In this way, the detection result on the surface of the aluminum foil 30 can be visually seen.

[0058] Combined with Figure 1 and Figure 2 For the detection system shown, in some embodiments, combined with Figure 3 As shown, a detection method for surface defects of the aluminum foil is provided, including:

[0059] S301, the processor obtains the original image information on the surface of the aluminum foil.

[0060] S302, the processor performs defect detection on the original image information to obtain a set of defect candidate regions.

[0061] In S303, the processor analyzes the candidate region images in the set of defect candidate regions to obtain a set of defect regions.

[0062] In S304, the processor identifies the candidate region images in the set of defect regions according to a preset algorithm and outputs a defect identification result.

[0063] The detection method provided by the present disclosure is used for detecting the surface of aluminum foil. Specifically, first, the original image information of the aluminum foil surface is obtained. By performing defect detection on the original image information, a set of defect candidate regions is obtained. The candidate region images in the set of defect candidate regions are analyzed one by one, and the selected candidate region images form a set of defect regions. A preset algorithm is used to identify the candidate region images in the set of defect regions one by one, and the defect identification result corresponding to each candidate region image is output.

[0064] By adopting the detection method provided by the present disclosure, the original image information of the aluminum foil surface collected is sequentially subjected to defect detection, the obtained defect region images are analyzed, and a preset algorithm is used for identification, and the defect identification result corresponding to each candidate region image is obtained. Compared with the detection result obtained by image comparison in the related art, the defect detection result obtained by using the detection method for the aluminum foil surface defect of the present disclosure is more accurate, effectively improving the identification accuracy of the aluminum foil surface defect, and further improving the detection effect of the aluminum foil surface quality.

[0065] Optionally, the step of performing defect detection on the original image information to obtain a set of defect candidate regions includes: performing difference processing on the original image information to obtain a difference image. Performing segmentation processing on the difference image to obtain region images. Extracting the candidate region images that meet the first preset condition in the region images to form a set of defect candidate regions.

[0066] In this embodiment, difference processing is performed on the collected original image information to reduce the interference caused by the background gray level fluctuation of the original image information to defect detection, so that the gray level characteristics of the defects are highlighted, thereby improving the accuracy of defect detection. By performing segmentation processing on the difference image after the difference processing, a plurality of segmented region images are obtained. The first preset condition is used to screen the plurality of region images, and the region images that meet the first preset condition are extracted as candidate region images for further analysis. The extracted plurality of candidate region images are put into the set of defect candidate regions. Through the embodiment of the present disclosure, the preprocessing of the original image information is realized to improve the accuracy of defect detection. Moreover, by segmenting into a plurality of region images and performing screening one by one, further, the comprehensiveness of defect detection is improved, and the defect omission rate is reduced.

[0067] Optionally, the steps of performing difference processing on the original image information to obtain a difference image include: performing filter preprocessing on the original image information to obtain a preprocessed image, and performing difference processing on the preprocessed image to obtain a difference image.

[0068] In this embodiment, the collected original image information is filtered to filter out high-frequency background interference factors and generate a low-frequency background. The preprocessed image after the filtering process is subjected to difference processing to subtract the low-frequency background generated after filtering, reduce the interference of background gray-scale fluctuations, highlight the gray-scale features of defects, and improve the detection effect of defects.

[0069] Optionally, the filter preprocessing of the original image information is specifically: performing mean filtering through mean filtering kernels of multiple sizes to generate a mean-filtered preprocessed image.

[0070] Optionally, the steps of performing difference processing on the preprocessed image to obtain a difference image include: performing image subtraction on any two images in the preprocessed image to obtain a difference image.

[0071] In this embodiment, pairwise image subtraction is performed on the preprocessed image after mean filtering to generate a difference image. To subtract the low-frequency background generated after filtering, reduce the interference of background gray-scale fluctuations, highlight the gray-scale features of defects, and improve the detection effect of defects.

[0072] Optionally, the first preset condition includes that the image pixels are greater than or equal to a pixel threshold.

[0073] In this embodiment, the difference image after the difference processing is segmented to obtain multiple segmented regional images. The regional images in the multiple regional images whose image pixels are greater than or equal to the pixel threshold are extracted as candidate regional images for further analysis. By filtering the segmented multiple regional images through image pixels, the regional images without defect features are filtered out, thereby reducing the amount of data for image processing and analysis, accelerating the image processing speed, and improving the defect analysis efficiency.

[0074] Optionally, the value range of the pixel threshold is from 10 to 20. Specifically, the pixel threshold is 10, 15 or 20.

[0075] Optionally, the steps of analyzing the candidate regional images in the defect candidate region set to obtain a defect region set include: traversing the defect candidate region set and performing connected component analysis on the candidate regional images in the defect candidate region set to obtain a defect region set.

[0076] In this embodiment, by traversing the candidate region images in the set of defect candidate regions, performing connected component analysis (blob analysis) on the candidate region images, classifying the candidate region images in the set of defect candidate regions into defect images and non-defect images, filtering out the non-defect images, a set of defect regions with a smaller data volume is obtained. Then, for the set of defect regions, a preset algorithm is used to extract and analyze the features of real defects, improving the defect recognition accuracy and recognition efficiency.

[0077] Optionally, the steps of performing connected component analysis on the candidate region images in the set of defect candidate regions to obtain a set of defect regions include: determining the pixel parameters of each candidate region image in the set of defect candidate regions. Filtering the candidate region images in the set of defect candidate regions according to the pixel parameters and the second preset condition to obtain a set of defect regions.

[0078] In this embodiment, through connected component analysis (blob analysis), the pixel parameters of each candidate region image in the set of defect candidate regions are determined. The candidate region images whose pixel parameters of the candidate region images in the set of defect candidate regions satisfy the second preset condition are filtered out to obtain a set of defect regions.

[0079] Optionally, the step of filtering the candidate region images in the set of defect candidate regions according to the pixel parameters and the second preset condition includes: filtering out the candidate region images whose pixel parameters are less than or equal to the parameter threshold.

[0080] In this embodiment, the second preset condition is that the pixel parameter is less than or equal to the parameter threshold. That is, the candidate region images whose pixel parameters of the candidate region images in the set of defect candidate regions are less than or equal to the parameter threshold are filtered out. In this way, a set of defect regions with a smaller data volume is obtained. Then, for the set of defect regions, a preset algorithm is used to extract and analyze the features of real defects, improving the defect recognition accuracy and recognition efficiency.

[0081] Optionally, the pixel parameters include the pixel area, pixel width, and pixel height of the candidate region image. The parameter thresholds include the pixel area threshold, pixel width threshold, and pixel height threshold. Among them. The value range of the pixel area threshold is 25 to 35, the value range of the pixel width threshold is 15 to 25, and the value range of the pixel height threshold is 45 to 55. Specifically, the value of the pixel area threshold is 25, 30, or 35, the value of the pixel width threshold is 15, 20, or 25, and the value of the pixel height threshold is 45, 50, or 55.

[0082] In some embodiments, as shown in Figure 4 a method for detecting defects on the surface of aluminum foil is provided, including:

[0083] S401, the processor obtains the original image information of the aluminum foil surface.

[0084] S402, the processor performs defect detection on the original image information to obtain a set of defect candidate regions.

[0085] S403, the processor analyzes the candidate region images in the set of defect candidate regions to obtain a set of defect regions.

[0086] S404, the processor takes screenshots in the original image information according to the candidate region images in the set of defect regions to obtain defect sub-images.

[0087] S405, the processor inputs the defect sub-images into a preset deep learning model for defect recognition and outputs the defect recognition result.

[0088] In this embodiment, traverse the set of defect regions, and intercept each candidate region image from the original image information according to the image information of the candidate region image to generate a defect sub-image. And send the defect sub-image into a preset deep learning model that has been trained for defect recognition and output the defect recognition result.

[0089] Optionally, the detection method further includes constructing an initial learning model. Input a large amount of processed defect image data to train the initial learning model to obtain a pre-trained model. The pre-training content includes defect object detection, defect object classification, semantic segmentation, and key point detection. Train and learn the trained pre-trained model to output a preset deep learning model.

[0090] Optionally, the preset deep learning model includes an Alexnet deep learning model to improve the defect recognition efficiency and accuracy.

[0091] Optionally, the preset deep learning model includes a machine learning decision tree (Decision Tree) model, which uses the length, width, area, gray scale, and texture features of the defect image as inputs for learning and training to identify defects.

[0092] Optionally, the preset deep learning model includes an artificial neural network model, which uses the length, width, area, gray scale, and texture features of the defect image as inputs for learning and training to identify defects.

[0093] Optionally, the defect recognition result includes one or more of the following: defect sub-image, defect location, defect area, defect length, and defect width.

[0094] Optionally, the detection method further includes: saving and displaying the defect recognition result.

[0095] Optionally, the detection method further includes: obtaining the size information of the aluminum foil. According to the size information of the aluminum foil, an X-Y coordinate map of the aluminum foil surface is constructed; the width of the aluminum foil is the X-axis, and the length of the aluminum foil is the Y-axis. According to the defect recognition result, a defect thumbnail is displayed in real time at the corresponding position on the X-Y coordinate map.

[0096] In this embodiment, during the movement of the aluminum foil, real-time image detection is performed on the surface of the aluminum foil, and according to the detected original image information, defect detection is performed, and the detected defect recognition result is displayed in real time on the display interface to facilitate the staff to intuitively view the detection result.

[0097] Specifically, a type mark can be set according to the defect type, and the type mark corresponding to the defect thumbnail is displayed in real time at the corresponding position on the X-Y coordinate map, further intuitively displaying the distribution of the defects.

[0098] Optionally, according to the number of occurrences of the same defect type or the continuously occurring size in the defect recognition result, an alarm reminder is issued to remind the staff to check the aluminum foil site in time.

[0099] In some embodiments, as shown in Figure 5 a detection method for defects on the surface of aluminum foil is provided, including:

[0100] S501, the processor obtains the original image information of the aluminum foil surface.

[0101] S502, the processor performs filtering preprocessing on the original image information to obtain a preprocessed image.

[0102] S503, the processor subtracts any two images in the preprocessed image to obtain a difference image.

[0103] S504, the processor performs segmentation processing on the difference image to obtain a region image.

[0104] S505, the processor extracts the candidate region images that meet the first preset condition in the region image to form a defect candidate region set.

[0105] S506, the processor traverses the defect candidate region set to determine the pixel parameters of each candidate region image in the defect candidate region set.

[0106] S507, the processor filters out the candidate region images whose pixel parameters are less than or equal to the parameter threshold to obtain a defect region set.

[0107] S508, the processor takes a screenshot of the original image information according to the candidate region images in the defect region set to obtain a defect thumbnail.

[0108] S509. The processor inputs the defective small image into a preset deep learning model for defect recognition and outputs the defect recognition result.

[0109] In some embodiments, in combination with Figure 16 As shown, a detection device 1600 for aluminum foil surface defects is provided, including an acquisition unit 1602 for acquiring the original image information of the aluminum foil surface; a detection unit 1604 for performing defect detection on the original image information to obtain a set of defect candidate regions; an analysis unit 1606 for analyzing the candidate region images in the set of defect candidate regions to obtain a set of defect regions; and an identification unit 1608 for identifying the candidate region images in the set of defect regions according to a preset algorithm and outputting the defect recognition result.

[0110] Optionally, the detection unit 1604 is specifically configured to perform difference processing on the original image information to obtain a difference image; perform segmentation processing on the difference image to obtain a region image; and extract the candidate region images in the region image that meet the first preset condition to form a set of defect candidate regions.

[0111] Optionally, the analysis unit 1606 is specifically configured to traverse the set of defect candidate regions and perform connected component analysis on the candidate region images in the set of defect candidate regions to obtain a set of defect regions.

[0112] Optionally, the identification unit 1608 is specifically configured to capture a defective small image from the original image information according to the candidate region images in the set of defect regions, input the defective small image into a preset deep learning model for defect recognition, and output the defect recognition result. The defect recognition result includes one or more of the following: defective small image, defect position, defect area, defect length, and defect width.

[0113] In combination with Figure 6 As shown, an embodiment of the present disclosure provides a detection device 60 for aluminum foil surface defects, including a processor 600 and a memory 601. Optionally, the device 60 may further include a communication interface 602 and a bus 603. Among them, the processor 600, the communication interface 602, and the memory 601 can complete mutual communication through the bus 603. The communication interface 602 can be used for information transmission. The processor 600 can call the logical instructions in the memory 601 to execute the above-described method for detecting aluminum foil surface defects.

[0114] In addition, when the logical instructions in the above-mentioned memory 601 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0115] The memory 601, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 100 executes functional applications and data processing by running the program instructions / modules stored in the memory 601, that is, implements the detection method for aluminum foil surface defects in the above embodiments.

[0116] The memory 601 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal device, etc. In addition, the memory 601 may include a high-speed random access memory and may also include a non-volatile memory.

[0117] In some embodiments, in combination with Figures 7 to 11 As shown, a slitter 20 is provided, including: a machine body 210. A defect detection system disposed on the machine body 210 for detecting the original image information on the surface of the aluminum foil. And a detection device 60 for aluminum foil surface defects as described in any of the above embodiments, installed on the machine body 210, and the detection device 60 is connected to the defect detection system.

[0118] The slitter 20 provided by the present disclosure includes a machine body 210, a defect detection system, and a detection device 60 for the aluminum foil surface as described in any of the above embodiments. The detection device 60 is installed on the machine body 210, and the detection device 60 is connected to the defect detection system. For the slitter 20 provided by the present disclosure, the detection device 60 for the aluminum foil surface as described in any of the above embodiments is used to detect the surface of the aluminum foil. Specifically, first, the original image information on the surface of the aluminum foil is obtained. By performing defect detection on the original image information, a set of defect candidate regions is obtained. Each candidate region image in the set of defect candidate regions is analyzed one by one, and the selected candidate region images form a set of defect regions. A preset algorithm is used to identify each candidate region image in the set of defect regions one by one, and the defect recognition result corresponding to each candidate region image is output.

[0119] By adopting the detection method provided by the present disclosure, through the original image information on the surface of the collected aluminum foil, defect detection is performed in sequence, the obtained defect region images are analyzed, and a preset algorithm is used for identification, and the defect recognition result corresponding to each candidate region image. Compared with the detection results obtained by image comparison in the related art, using the detection method for aluminum foil surface defects of the present disclosure, the obtained defect detection results are more accurate, effectively improving the recognition accuracy of aluminum foil surface defects, and further improving the detection effect of aluminum foil surface quality.

[0120] Optionally, the defect detection system includes the detection system 10 for surface defects of the aluminum foil 30 provided in any of the above embodiments. It includes: a first detection system 120, a second detection system 140, and an image processing system. The first detection system 120 is used to detect the first surface of the aluminum foil 30. The second detection system 140 is used to detect the second surface of the aluminum foil 30. The first surface and the second surface are two opposite surfaces of the aluminum foil 30. The image processing system is respectively connected to the first detection system 120 and the second detection system 140, and is used to perform image analysis and processing on the original image information detected by the first detection system 120 and the second detection system 140, and output a defect recognition result.

[0121] Further, in combination with Figure 7 As shown, the machine body 210 includes a feeding end 212 and a discharging end 214. The first detection system 120 is arranged at the discharging end 214 and is used to detect the defects on the first surface a of the aluminum foil 30. The second detection system 140 is arranged at the feeding end 212 and is used to detect the defects on the second surface b on the other side of the aluminum foil 30.

[0122] The present disclosure provides that the slitter 20 can simultaneously detect the first surface a and the second surface b of the aluminum foil 30 by respectively arranging the second detection system 140 and the first detection system 120 at the feeding end 212 and the discharging end 214 for detecting the second surface b and the first surface a of the aluminum foil 30 respectively. In this way, during the slitting process of the slitter 20, the defects on the opposite first surface a and second surface b of the aluminum foil 30 can be detected in real time, thereby improving the comprehensiveness of the detection of the aluminum foil 30 and reducing the defect miss detection rate. Moreover, during the slitting process, the detection of the first surface a and the second surface b is realized synchronously, improving the detection efficiency of the surface of the aluminum foil 30 and simplifying the detection process.

[0123] Optionally, the slitter further includes: a first frame 110 and a second frame 130. The first detection system 120 is arranged on the first frame 110. The second detection system 140 is arranged on the second frame 130.

[0124] In this embodiment, by arranging the first frame 110 and the second frame 130 for installing the first detection system 120 and the second detection system 140, excessive improvement of the machine body of the slitter is avoided, reducing the modification cost and modification difficulty.

[0125] Optionally, in combination with Figure 12 and Figure 14 As shown, the surface inspection component 121 is arranged on the first frame 110. The surface inspection component includes a plurality of first surface inspection cameras 122 and a first surface inspection light source 123, and the plurality of first surface inspection cameras 122 and the first surface inspection light source 123 are located on the same side of the aluminum foil 30.

[0126] In this embodiment, the first detection system 120 includes a surface inspection component 121 disposed on the first frame 110. The surface inspection component 121 is used to detect other surface defects of the first surface a except for pinhole defects. The surface inspection component 121 includes a plurality of first surface inspection cameras 122 and a first surface inspection light source 123 disposed on the same side of the aluminum foil 30, and the surface image of the aluminum foil 30 is captured by a reflection method.

[0127] Optionally, the first frame 110 includes: a first cross beam 114 and a second cross beam 115. A plurality of first surface inspection cameras 122 are disposed on the first cross beam 114. Moreover, the plurality of first surface inspection cameras 122 can rotate and / or move relative to the first cross beam 114. The first surface inspection light source 123 is disposed on the second cross beam 115, and the first surface inspection light source 123 can rotate and / or move relative to the second cross beam 115.

[0128] In this embodiment, the first frame 110 includes a first cross beam 114 for mounting a plurality of first surface inspection cameras 122, and a second cross beam 115 for mounting the first surface inspection light source 123. The plurality of first surface inspection cameras 122 can rotate relative to the first cross beam 114 to adjust the shooting angle of the first surface inspection cameras 122. And the plurality of first surface inspection cameras 122 can move along the first cross beam 114 to adjust the distance between two adjacent first surface inspection cameras 122 to meet the detection requirements of aluminum foils 30 of different widths. The first surface inspection light source 123 can rotate and / or move relative to the second cross beam 115 to cooperate with the shooting angles of the plurality of first surface inspection cameras 122 to improve the shooting effect of the first surface inspection cameras 122.

[0129] Optionally, as shown in combination with Figure 11 and Figure 13 , a hole inspection component 124 is disposed on the first frame 110. The hole inspection component 124 includes a plurality of hole inspection cameras 125 and a hole inspection light source 126. The plurality of hole inspection cameras 125 and the hole inspection light source 126 are respectively located on opposite sides of the aluminum foil 30.

[0130] In this embodiment, the first detection system 120 further includes a hole inspection component 124 for detecting pinhole defects. The hole inspection component 124 includes a plurality of hole inspection cameras 125 and a hole inspection light source 126. Based on the characteristics of pinhole defects, the plurality of hole inspection cameras 125 and the hole inspection light source 126 are respectively disposed on opposite sides of the aluminum foil 30, and the pinholes are captured by a transmission method to improve the detection of pinhole defects. Compared with the related art in which the camera and the light source are disposed on the same side to detect the aluminum foil 30, the present disclosure expands the detection range of defect types, thereby improving the detection effect of defects.

[0131] Optionally, the first frame 110 includes: a first rod 116 and a second rod 117. A plurality of hole inspection cameras 125 are disposed on the first rod 116, and the plurality of hole inspection cameras 125 can rotate and / or move relative to the first rod 116. A hole inspection light source 126 is disposed on the second rod 117, and the hole inspection light source 126 can rotate and / or move relative to the second rod 117.

[0132] In this embodiment, a plurality of hole inspection cameras 125 are disposed on the first rod 116 and can rotate or move relative to the first rod 116 to adjust the shooting angle and setting position. The hole inspection light source 126 is disposed on the second rod 117 and can rotate relative to the second rod 117 to be oppositely disposed with the hole inspection camera 125, improving the detection accuracy of pinhole defects.

[0133] Optionally, in combination with Figure 11 As shown, a plurality of second surface inspection cameras 142 are disposed on the second frame 130, and the plurality of second surface inspection cameras 142 can rotate and / or move relative to the second frame 130. A second surface inspection light source 144 is disposed on the second frame 130, and the second surface inspection light source 144 can rotate and / or move relative to the second frame 130. Among them, the plurality of second surface inspection cameras 142 and the second surface inspection light source 144 are located on the same side of the aluminum foil 30.

[0134] In this embodiment, the second detection system 140 includes a plurality of second surface inspection cameras 142 disposed on the second frame 130. The plurality of second surface inspection cameras 142 are distributed at intervals along the width of the aluminum foil 30. The second surface inspection light source 144 and the plurality of second surface inspection cameras 142 are located on the same side of the aluminum foil 30 and are used to detect defects on the second surface b of the aluminum foil 30.

[0135] Among them, the types of surface defects of the aluminum foil 30 include oil spots, pockmarks, black lines, foreign object indentation, roller marks, scratches, holes, mosquitoes, etc. The types of defects detected by the surface inspection assembly 121 and the second detection system 140 include but are not limited to: oil spots, pockmarks, black lines, foreign object indentation, roller marks, scratches, mosquitoes. The hole inspection assembly 124 detects hole defects.

[0136] Optionally, in combination with Figure 15 As shown, the detection system 10 further includes a plurality of covers 150. Each first surface inspection camera 122, each needle inspection camera, and each second surface inspection camera 142 are respectively provided with a cover 150. By disposing the camera in the cover 150, the protection of the camera is realized.

[0137] Optionally, in combination with Figure 15As shown, the detection system 10 further includes a plurality of fans 160. The number of fans 160 is the same as that of the cover bodies 150. Each cover body 150 is provided with a fan 160. The fan 160 is used to supply air to the camera inside the cover body 150 to perform dust removal operation on the surface of the camera and improve the clarity of the captured image of the camera.

[0138] Optionally, in combination with Figure 14 As shown, the first surface inspection light source 123, the hole inspection light source 126, and the second surface inspection light source 144 all adopt strip-shaped light sources to simplify the installation process.

[0139] Optionally, in combination with Figure 7 and Figure 8 As shown, the slitter 20 further includes: a sliding assembly 220. The sliding assembly 220 is arranged on the machine body 210. The first frame 110 is connected to the sliding assembly 220, and the sliding assembly 220 is used to drive the first frame 110 to move relative to the machine body 210.

[0140] In this embodiment, by arranging the sliding assembly 220 on the machine body 210, the first frame 110 can be moved relative to the machine body 210. In this way, during the slitting process of the aluminum foil 30, the first frame 110 is located at the discharge end 214 so that the first detection system 120 can collect an image of the first surface a of the aluminum foil 30 at the discharge end 214. After the slitting operation is completed and when blanking is required, the first frame 110 will affect the normal progress of the blanking process, and then the sliding assembly 220 drives the first frame 110 to move to a position beside the discharge end 214 relative to the machine body 210. In this way, the smoothness of the process completion of the slitter 20 can be improved. And by arranging the sliding assembly 220, the first frame 110 and the first detection system 120 are moved to the side space of the discharge end 214, improving the compactness of the overall equipment layout and reducing the space occupancy rate.

[0141] Optionally, in combination with Figure 7 As shown, the sliding assembly 220 includes: a slide rail 222, a slider 224, and a driving member 226. The slide rail 222 is arranged on the machine body 210. The slider 224 is slidably connected to the slide rail 222, and the first frame 110 is connected to the slide rail 222. The driving member 226 is connected to the slider 224, and the driving member 226 is used to drive the slider 224 to move along the slide rail 222 to adjust the relative position between the first frame 110 and the machine body 210.

[0142] In this embodiment, a slide rail 222 is provided on the machine body 210, and the slide rail 222 extends along the width direction of the discharge end 214. The slider 224 is slidably connected to the slide rail 222. The first frame 110 is provided with the slide rail 222. The driving member 226 is disposed on the machine body 210. The output end of the driving member 226 is connected to the slider 224, and the driving member 226 is configured to drive the slider 224 to move along the slide rail 222 to adjust the relative position between the first frame 110 and the machine body 210.

[0143] Specifically, when the discharging process needs to be performed at the discharging end 214, the driving member 226 drives the slider 224 to move, so as to drive the first frame 110 to move relative to the machine body 210 to a position beside the discharging end 214. When detection is required, the driving member 226 drives the slider 224 to move in the reverse direction, so as to drive the first frame 110 to move relative to the machine body 210 to the discharging end 214 to perform a detection operation on the aluminum foil 30.

[0144] Optionally, the driving member 226 includes a motor.

[0145] Optionally, in combination Figure 7 As shown, the slide rail 222 includes a main slide rail 2221, a first sub-slide rail 2222, and a second sub-slide rail 2223. The main slide rail 2221 is disposed on the top of the machine body 210, and the slider 224 is slidably connected to the main slide rail 2221. The motor is connected to the slider 224. The first sub-slide rail 2222 and the second sub-slide rail 2223 are both disposed on the side wall of the machine body 210. And, along the height direction of the machine body 210, the first sub-slide rail 2222 is located above the second sub-slide rail 2223. The connecting beam 113 located at the upper part of the first frame 110 is slidably connected to the first sub-slide rail 2222. The connecting seat 118 located at the lower part of the first frame 110 is slidably connected to the second sub-slide rail 2223. By providing the first sub-slide rail 2222 and the second sub-slide rail 2223 which are arranged at intervals up and down on the side wall of the machine body 210, the stability of the first frame 110 during the movement relative to the machine body 210 is improved.

[0146] Optionally, in combination Figure 9 As shown, the slitter 20 further includes: a first aluminum foil output member 230 and a second aluminum foil output member 240. The first aluminum foil output member 230 is disposed at the discharging end 214 of the machine body 210. The second aluminum foil output member 240 is disposed at the discharging end 214 of the machine body 210, and the first aluminum foil output member 230 and the second aluminum foil output member 240 are arranged at intervals. The number of the first detection systems 120 is two groups, and the two groups of first detection systems 120 are respectively used to detect the output aluminum foil 30 of the first aluminum foil output member 230 and the output aluminum foil 30 of the second aluminum foil output member 240.

[0147] In this embodiment, a first aluminum foil output member 230 and a second aluminum foil output member 240 are provided at the discharge end 214 of the machine body 210. First detection systems 120 are respectively provided on the first aluminum foil output member 230 and the second aluminum foil output member 240. The two groups of first detection systems 120 are respectively used to collect surface images of the first surface a of the aluminum foil 30 wound into the first aluminum foil output member 230 and the second aluminum foil output member 240, for detecting defects on the first surface a.

[0148] Further, a surface inspection component 121 and a hole inspection component 124 are provided for the first aluminum foil output member 230. The surface inspection component 121 is used to collect surface images of the first surface a of the aluminum foil 30 wound into the first aluminum foil output member 230, for detecting defects on the first surface a. The hole inspection component 124 is used to collect surface images of the first surface a of the aluminum foil 30 wound into the first aluminum foil output member 230, for detecting pinhole defects on the first surface a.

[0149] Further, a surface inspection component 121 and a hole inspection component 124 are provided for the second aluminum foil output member 240. The surface inspection component 121 is used to collect surface images of the first surface a of the aluminum foil 30 wound into the second aluminum foil output member 240, for detecting defects on the first surface a. The hole inspection component 124 is used to collect surface images of the first surface a of the aluminum foil 30 wound into the second aluminum foil output member 240, for detecting pinhole defects on the first surface a.

[0150] Optionally, as shown in Figure 8 The first frame body 110 includes a mounting frame body 111, a connecting frame body 112, a connecting beam 113, a first cross beam 114 and a second cross beam 115, a first rod body 116 and a second rod body 117. The connecting frame body 112 is slidably connected to the main slide rail 2221 located at the top of the machine body 210. The mounting frame body 111 is connected to the connecting frame body 112. The connecting beam 113 is disposed in the mounting frame body 111, and a connecting seat 118 is disposed at the bottom corners of the mounting frame body 111. Two groups of the first cross beam 114 and the second cross beam 115 are provided on the mounting frame body 111, respectively for mounting a plurality of first surface inspection cameras 122 and strip-shaped light sources. Two first rod bodies 116 are provided on the mounting frame body 111, and a plurality of hole inspection cameras 125 are respectively provided on the two rod bodies. The two ends of the second rod body 117 are respectively connected to the two ends of the machine body 210, and the second rod body 117 is used to mount a light source disposed opposite to the hole inspection camera 125.

[0151] Optionally, the slitter 20 further includes an aluminum foil input member 250. The aluminum foil input member 250 is provided at the feed end 212 of the machine body 210. The number of the second detection systems 140 is two groups, and the two groups of second detection systems 140 are respectively provided on opposite sides of the input aluminum foil 30 of the aluminum foil input member 250.

[0152] In this embodiment, in combination with Figure 10 As shown, an aluminum foil input member 250 is provided at the feeding end 212 of the machine body 210. Two sets of second detection systems 140 are provided for the aluminum foil input member 250. The two sets of second detection systems 140 are respectively located on both sides of the aluminum foil input member 250, and image acquisition is performed on the second surface b of the double-layer aluminum foil 30 output from the aluminum foil input member 250 for detecting defects on the second surface b.

[0153] Exemplarily, in combination with Figure 7 and Figure 9 As shown, taking the vertical slitter 20 of the double-layer rolling process as an example of the type of the slitter 20, surface detection of two bright surfaces is realized at the feeding end 212 of the slitter 20, that is, the two second surfaces b as shown in Figure 9 As shown, surface detection of two dark surfaces and pinhole detection in the transmission imaging mode are realized at the discharging end 214, that is, the two first surfaces a as shown in Figure 9 As shown.

[0154] In this way, in combination with Figure 9 As shown, 6 detection stations are added to the slitter 20. By setting a second frame body 130 at the feeding end 212, a set of second detection systems 140 is respectively arranged on the upper and lower sides of the second frame body 130, that is, 2 surface inspection stations above and below. And, a first frame body 110 is arranged at the discharging end 214. The first frame body 110 is provided with 4 cross beams from top to bottom. The 4 cross beams are used to install 2 sets of first detection systems 120. Each set of first detection systems 120 respectively includes a surface inspection component 121 and a hole inspection component 124. In this way, 4 detection stations are arranged on the 4 cross beams to improve the compactness of the overall equipment layout.

[0155] Further, in order to meet the detection accuracy requirements for surface defects of the aluminum foil 30, 4 4K linear array cameras are arranged at a single station in the transverse direction of the aluminum foil 30. That is, 4 cameras are arranged on each rod body above and below the second frame body 130, and the 4 cameras are spaced apart. Two first cross beams 114 are arranged at intervals on the first frame body 110, and 4 cameras are arranged on each first cross beam 114, and the 4 cameras are spaced apart.

[0156] In order to meet the detection accuracy requirements for pinhole defects, 6 8K high-speed linear array cameras are required for the pinhole detection station of a single aluminum foil 30 in the transverse direction of the aluminum foil 30. Two first rod bodies 116 are arranged at intervals on the first frame body 110, and 6 cameras are arranged on each first rod body 116, and the 6 cameras are spaced apart.

[0157] In this way, one high-brightness LED light source is configured for each detection station, and a total of 6 strip-shaped LED light sources are required.

[0158] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are configured to execute the above-mentioned method for detecting defects on the aluminum foil surface.

[0159] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The foregoing storage medium may be a non-transitory storage medium, such as: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., which are various media that can store program codes.

[0160] The above description and drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process, and other changes. Embodiments merely represent possible variations. Unless explicitly required, separate components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or substituted for parts and features of other embodiments. Moreover, the terms used in this application are only for describing embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element. In this article, what each embodiment focuses on may be the differences from other embodiments, and the same or similar parts among the various embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

[0161] Those skilled in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner may depend on the specific application and design constraints of the technical solution. The skilled person can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The skilled person can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0162] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.

[0163] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A slitter, characterized in that, Comprising: Machine body; A detection system for surface defects of aluminum foil, the detection system includes: a first detection system, a second detection system and an image processing system, the detection system is arranged on the machine body; the image processing system is respectively connected to the first detection system and the second detection system, and is used for receiving the original image information detected by the first detection system and the second detection system; the image processing system includes a processor and a memory storing program instructions, and the processor is configured to execute a detection method for surface defects of aluminum foil; the detection method includes: obtaining the original image information of the aluminum foil surface; performing difference processing on the original image information to obtain a difference image; performing segmentation processing on the difference image to obtain a region image; extracting candidate region images in the region image that satisfy the image pixel being greater than or equal to the pixel threshold to form a defect candidate region set; analyzing the candidate region images in the defect candidate region set to obtain a defect region set; identifying the candidate region images in the defect region set according to a preset algorithm and outputting a defect identification result; The machine body includes a feeding end and a discharging end, the first detection system is arranged at the discharging end and is used for detecting defects on the first surface of the aluminum foil; the second detection system is arranged at the feeding end and is used for detecting defects on the second surface of the aluminum foil; the first surface and the second surface are two opposite surfaces of the aluminum foil; The first detection system includes a surface inspection component and a hole inspection component, the hole inspection component is used for detecting pinhole defects, and the surface inspection component is used for detecting other surface defects except pinhole defects; the number of the first detection systems is two groups, and the two groups of first detection systems are respectively used for collecting surface images of the first surface of the rolled-in aluminum foil; The number of the second detection systems is two groups, and the two groups of second detection systems are respectively arranged on opposite sides of the input aluminum foil and are used for collecting surface images of the second surface of the aluminum foil.

2. The slitter according to claim 1, characterized in that, Further comprising: A first aluminum foil output member, arranged at the discharging end of the machine body; A second aluminum foil output member, arranged at the discharging end of the machine body, and the first aluminum foil output member and the second aluminum foil output member are arranged at intervals; The two groups of first detection systems are respectively used for detecting the output aluminum foil of the first aluminum foil output member and the output aluminum foil of the second aluminum foil output member.

3. The slitter according to claim 1, characterized in that, Further comprising: An aluminum foil input member, arranged at the feeding end of the machine body; The two groups of second detection systems are respectively arranged on opposite sides of the input aluminum foil of the aluminum foil input member.

4. The slitter according to any one of claims 1 to 3, characterized in that, The surface inspection component is arranged on the first frame, and the surface inspection component includes a plurality of first surface inspection cameras and a plurality of first surface inspection light sources, and the plurality of first surface inspection cameras and the plurality of first surface inspection light sources are located on the same side of the aluminum foil.

5. The slitter according to any one of claims 1 to 3, characterized in that, The hole inspection component is arranged on the first frame, and the hole inspection component includes a plurality of hole inspection cameras and a plurality of hole inspection light sources, and the plurality of hole inspection cameras and the plurality of hole inspection light sources are respectively located on opposite sides of the aluminum foil.

6. The slitter according to any one of claims 1 to 3, characterized in that, The second detection system includes: A plurality of second surface inspection cameras, arranged on the second frame, and the plurality of second surface inspection cameras can rotate and / or move relative to the second frame; A plurality of second surface inspection light sources, arranged on the second frame, and the plurality of second surface inspection light sources can rotate and / or move relative to the second frame; Wherein, the plurality of second surface inspection cameras and the plurality of second surface inspection light sources are located on the same side of the aluminum foil.

7. The slitter according to any one of claims 1 to 3, characterized in that, The steps of performing difference processing on the original image information to obtain a difference image include: Perform filtering preprocessing on the original image information to obtain a preprocessed image; Perform difference processing on the preprocessed image to obtain a difference image.

8. The slitter according to claim 7, characterized in that, The steps of performing difference processing on the preprocessed image to obtain a difference image include: Perform image subtraction on any two images in the preprocessed image to obtain a difference image.

9. The slitter according to any one of claims 1 to 3, characterized in that, The steps of analyzing the candidate region images in the defect candidate region set to obtain a defect region set include: Traverse the defect candidate region set, perform connected component analysis on the candidate region images in the defect candidate region set, and obtain a defect region set.

10. The slitter according to claim 9, characterized in that, The steps of performing connected component analysis on the candidate region images in the defect candidate region set to obtain a defect region set include: Determine the pixel parameters of each candidate region image in the defect candidate region set; Filter the candidate region images in the defect candidate region set according to the pixel parameters and the second preset condition to obtain a defect region set.

11. The slitter according to claim 10, wherein, The steps of filtering the candidate region images in the defect candidate region set according to the pixel parameters and the second preset condition include: Filter out the candidate region images with pixel parameters less than or equal to the parameter threshold.

12. The slitter according to any one of claims 1 to 3, wherein, The steps of identifying the candidate region images in the defect region set according to a preset algorithm and outputting a defect recognition result include: Take a screenshot of the original image information based on the candidate region images in the defect region set to obtain a defect thumbnail; Input the defect thumbnail into a preset deep learning model for defect recognition and output a defect recognition result.

13. The slitter according to claim 12, wherein, The defect recognition result includes one or more of the following: defect thumbnail, defect location, defect area, defect length, and defect width.

Images