Die material defect inspection method and system

Abstract

This invention discloses a method, a defect inspection method, and a system for generating defect information in die-cutting materials. The method for generating defect information in die-cutting materials includes: acquiring first-view images, second-view images, and third-view images from a first-view, second-view, and third-view perspective respectively, in a specified scene. The specified scene includes at least: a cutter, a die-cutting material target, and a support mechanism carrying the die-cutting material target. The first-view image includes at least: a first detection image of defect detection in the die-cutting material target after die-cutting; the second-view image includes at least: a second detection image of defect detection in the die-cutting material target after die-cutting; and the third-view image includes at least: a third detection image of defect detection in the die-cutting material target after die-cutting. Based on the first detection image, the second detection image, and the third detection image, the method analyzes whether the die-cutting material target has defect features and generates the defect information.

Description

[0001] This application is a divisional application of the invention patent application filed on December 15, 2021, entitled "Method, Apparatus and System for Defect Inspection of Die-cut Materials Based on Cloud Data Sharing" with application number 202111527967. Technical Field

[0002] This invention relates to the field of die-cutting technology, and in particular to a method and system for inspecting defects in die-cutting materials. Background Technology

[0003] Traditional die-cutting production uses die-cutting blades assembled into a die-cutting plate according to the product design requirements. Under pressure, the printed material or other sheet-like blanks are cut into the desired shape or with serrations. In recent years, with the rapid development of the electronics industry, die-cutting technology has been widely used in the production of auxiliary materials for consumer electronics products. It is used to process die-cut materials in various consumer electronics products, such as rubber, single-sided tape, double-sided tape, foam, plastic, vinyl, metal strips, metal sheets, optical films, protective films, mesh, hot melt adhesive tape, OCA optical adhesive, etc. Although die-cutting technology is widely used and has a large market demand, many manufacturers in the industry still rely on visual inspection to judge the quality of die-cut products. This inspection method requires a lot of manpower and resources and is prone to missed inspections.

[0004] With the global and Chinese transformation and upgrading of industrial manufacturing towards intelligent manufacturing, die-cutting technology is also evolving from traditional methods requiring significant manpower and resources towards automation and intelligence. Recently, the die-cutting industry has seen the adoption of machine vision for die-cutting inspection, and even the use of AI algorithms. This indicates, to some extent, that die-cutting technology is moving towards intelligent manufacturing, and also suggests that die-cutting equipment will become increasingly intelligent. Existing technology CN106770332A (title: A method for detecting defects in electronic die-cutting materials based on machine vision, publication date: May 31, 2017) discloses a method for detecting defects in electronic die-cutting materials based on machine vision, mainly including: (a) loading the detection template, (b) transmitting the detection target, (c) sensor monitoring, (d) image capture, and (e) target recognition: first, a triangle matching algorithm is used for feature extraction, achieving efficient extraction of product defect features. The extracted features include texture feature extraction, shape feature extraction, and color feature extraction. Then, Blob analysis is used for image recognition to separate and detect the target from the image background, achieving target shape and defect identification, and calculating the target area. Finally, LBP algorithm is used for texture recognition to identify the surface texture processing technology of the die-cut material target. Although the above method detects defects visually, it essentially requires a large amount of image processing. Moreover, it mainly focuses on extracting defect features of the product after die-cutting, without considering the condition of the cutting blade during die-cutting, such as blade damage or cutting angle deviation, or factors such as displacement deviation and transmission speed of the conveying mechanism during product transport, all of which affect the product die-cutting effect. Furthermore, the defect detection of die-cut products after die-cutting only screens for whether the product has defects, without considering aspects closely related to product defects, such as the posture of the cutting blade during die-cutting and the condition of the cutting blade itself. The above-mentioned existing technology also mentions that the industrial control system transmits the detection site data to the industrial control cloud big data analysis platform in real time for statistical analysis. In summary, the aforementioned existing technologies mainly mention using machine vision to detect product defects and then sending various data to an industrial control cloud big data analysis platform for analysis, involving a large amount of image processing. However, they do not address how to correct the entire die-cutting process after defects are identified, thus failing to improve product yield (low yield can be caused by issues such as foreign object adhesion in addition to cutting by the cutter). Moreover, they primarily focus on the process control of a single die-cutting machine, without considering the in-depth analysis and sharing of defect detection and correction data when multiple die-cutting machines are cutting multiple identical products in batches in a factory's mass production. Technical problems encountered on one machine may also be encountered on other die-cutting machines. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method and system for defect inspection and correction of die-cut materials, in order to solve the technical problem in the prior art that die-cutting equipment does not combine product defect detection with correction of defect problems.

[0006] In a first aspect, the present invention provides a method for defect verification of die-cut materials, the method comprising:

[0007] First-view, second-view, and third-view images of a specified scene are acquired from a first-view, second-view, and third-view perspective, respectively. The specified scene includes at least: a cutter, a die-cutting material target, and a support mechanism that carries the die-cutting material target. The first-view, second-view, and third-view perspectives are at different angles during image acquisition, and the time intervals between the acquisition of the first-view, second-view, and third-view perspectives are within a preset range.

[0008] The first perspective image includes at least: a first detection image of the die-cut material target object after die-cutting;

[0009] The second perspective image includes at least: a second detection image of the die-cut material target object after die-cutting;

[0010] The third-view image includes at least: a third detection image of the die-cut material target object after die-cutting;

[0011] Based on the first detection image, the second detection image, and the third detection image, analyze whether the die-cutting material target has defect features and generate defect information;

[0012] The defect is corrected based on the defect information, and corresponding correction information is generated;

[0013] The defect information and the correction information are sent to the server so that the server can build a die-cutting model of the die-cutting material target and distribute the die-cutting model to several die-cutting devices.

[0014] The defect information is used to characterize the defects present in the die-cutting material target;

[0015] The correction information is parameter information generated when correcting defects based on the defect information;

[0016] The die-cutting model includes at least one of the following: the operating parameters of the die-cutting equipment, the control parameters of the cutter, and the shape, size, and thickness of the die-cutting material target.

[0017] Furthermore, the first perspective image also includes a first pre-cut image of the target material being transferred before die-cutting;

[0018] The second perspective image also includes a second pre-cut image of the target material being transferred before die-cutting;

[0019] The third-view image also includes a third pre-cut image of the target material being transferred before die-cutting;

[0020] The method further includes: analyzing, based on the first pre-cutting image, the second pre-cutting image, and the third pre-cutting image, whether the die-cutting material target object has foreign objects attached during transmission, whether it is arranged at a preset interval, whether the movement trajectory of the carrying mechanism is normal, and whether it is located at a designated position on the carrying mechanism.

[0021] Furthermore, the first perspective image also includes a first cutting-time image of the scene where the cutting blade cuts the die-cutting material target during the first die-cutting process;

[0022] The second perspective image also includes a second cutting-time image of the scene where the die-cutting blade cuts the die-cutting material target object;

[0023] The third-view image also includes: a third cutting-time image of the scene where the die-cutting blade is cutting the die-cutting material target object;

[0024] The method further includes: analyzing, based on the first cutting time image, the second cutting time image, and the third cutting time image, whether there are foreign objects on the cutter when the cutter is cutting the die-cutting material target, the initial position information of the cutter, and whether the die-cutting material target is shifted during cutting.

[0025] Furthermore, the step of analyzing whether the die-cutting material target has defect features based on the first detection image, the second detection image, and the third detection image, and generating the defect information, includes:

[0026] When the analysis based on the first detection image, the second detection image and the third detection image indicates that the die-cutting material target has defect features, the feeding and die-cutting work of the die-cutting material target shall be stopped immediately.

[0027] Record defect information of the die-cut material target.

[0028] Furthermore, the defect information includes at least one of the following: the defect location information, defect severity, defect cause information of the die-cutting material target object, and the working parameters of the die-cutting material target object involved in the entire process from feeding to waste separation.

[0029] Furthermore, the correction information includes at least one of the following: control correction parameters of the cutter, conveying speed correction parameters of the die-cutting material target, initial position correction parameters when cutting the die-cutting material target, and relative position correction parameters between the die-cutting material target and the support mechanism.

[0030] Furthermore, the operating parameters of the die-cutting model equipment include: the transmission speed of the die-cutting equipment and the offset angle range of the die-cutting equipment.

[0031] Secondly, the present invention provides a defect inspection system for die-cut materials, characterized in that the system comprises: a server, a main die-cutting device, and a plurality of slave die-cutting devices, wherein the server, the main die-cutting device, and the plurality of slave die-cutting devices are communicatively connected to each other, wherein the main die-cutting device is used for:

[0032] First-view, second-view, and third-view images of a specified scene are acquired from a first-view, second-view, and third-view perspective, respectively. The specified scene includes at least: a cutter, a die-cutting material target, and a support mechanism that carries the die-cutting material target. Furthermore, the first-view, second-view, and third-view perspectives are at different angles during image acquisition, and the time intervals between the acquisition of the first-view, second-view, and third-view perspectives are within a preset range.

[0033] The first perspective image includes at least: a first detection image of the die-cut material target object after die-cutting;

[0034] The second perspective image includes at least: a second detection image of the die-cut material target object after die-cutting;

[0035] The third-view image includes at least: a third detection image of the die-cut material target object after die-cutting;

[0036] Based on the first detection image, the second detection image, and the third detection image, analyze whether the die-cutting material target has defect features and generate defect information;

[0037] The defect is corrected based on the defect information, and corresponding correction information is generated;

[0038] Send the defect information and the correction information to the server;

[0039] The server is used to: receive the defect information and the correction information, establish a die-cutting model of the die-cutting material target, and distribute the die-cutting model to several die-cutting devices;

[0040] The die-cutting equipment adjusts its own die-cutting control parameters according to the die-cutting model;

[0041] The defect information is used to characterize the defects present in the die-cutting material target;

[0042] The correction information is parameter information generated when correcting defects based on the defect information;

[0043] The die-cutting model includes at least one of the following: the operating parameters of the die-cutting equipment, the control parameters of the cutter, and the shape, size, and thickness of the die-cutting material target.

[0044] In summary, the beneficial effects of the present invention are as follows:

[0045] The die-cutting material defect detection method and system provided in this invention comprehensively considers the defect detection process from material loading to post-die-cutting product defect detection, corrects defects in a timely manner, and establishes a die-cutting model based on the entire process. This model can then be replicated and shared with die-cutting equipment that cuts similar die-cutting materials. In this way, other die-cutting equipment can directly use the verified and compliant die-cutting model to control its operation, greatly improving the yield of die-cutting materials. It also reduces the previous problem of over-reliance on the experience of die-cutting workers, avoids the waste of die-cutting materials, and significantly reduces the manufacturing cost of large-scale die-cutting in factories. Furthermore, it achieves data sharing and reduces the over-reliance on worker experience factors in die-cutting detection and calibration. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, and these are all within the protection scope of the present invention.

[0047] Figure 1 This is a schematic diagram of the structure of the die-cutting material defect inspection system based on cloud data sharing according to Embodiment 1 of the present invention.

[0048] Figure 2 yes Figure 1 The diagram shows the structure of the main die-cutting equipment.

[0049] Figure 3 yes Figure 2 The diagram shows the structure of the cutter and image acquisition mechanism of the main die-cutting equipment.

[0050] Figure 4 This is a flowchart illustrating the defect inspection method for die-cutting materials based on cloud data sharing in Embodiment 1 of the present invention.

[0051] Figure 5 This is a schematic diagram of the structure of the die-cutting material defect inspection device based on cloud data sharing in Embodiment 2 of the present invention. Detailed Implementation

[0052] The features and exemplary embodiments of various aspects of the present invention will now be described in detail. To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the invention.

[0053] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0054] Example 1

[0055] Please see Figures 1 to 3 The cloud-based data sharing-based die-cutting material defect inspection system provided in Embodiment 1 of this invention mainly includes: a main die-cutting device 10, a server 20, and at least one slave die-cutting device 30. The main die-cutting device 10, the server 20, and each slave die-cutting device 30 can communicate via wired or wireless means to achieve data sharing. The main application scenario is for large-scale cutting of die-cutting materials of the same type, such as die-cutting materials composed of foam, adhesive, and backing paper, die-cutting materials composed of backing paper, foam, adhesive, and backing paper, etc., which are achieved through large-scale cutting using die-cutting technology. For some large enterprises or office addresses (such as large-scale die-cutting service providers) distributed in multiple locations, the demand for die-cutting equipment will be large. Several die-cutting devices are distributed and interact with each other through the server. Of course, one die-cutting device can also interact with another die-cutting device.

[0056] In embodiments of the present invention, a die-cutting device is selected as the main die-cutting device. The main die-cutting device includes a die-cutting machine and a host computer. The host computer can be a PC, an all-in-one computer with a display, or a tablet computer. The host computer is equipped with vision processing software that analyzes images acquired by the die-cutting machine from different perspectives. For ease of control, the PLC controller that controls the die-cutting machine can even be integrated into the host computer, so that the die-cutting machine can be controlled directly through the host computer. In addition, all die-cutting devices can be centrally controlled through a central control console (thus enabling remote control). The central control console serves as both a server and the controller of the entire system, controlling the data communication of the entire system and the operation of each die-cutting device (main die-cutting device and slave die-cutting devices). Furthermore, when visually inspecting the die-cutting material target object, the defects of visual inspection mainly include whether the die-cutting material target object has misalignment, angular deviation, positional deviation, burrs or other foreign matter adhering to the product, which affect the use of the finished die-cutting material target object.

[0057] like Figure 2 and Figure 3 As shown, the die-cutting machine of the main die-cutting equipment in Embodiment 1 of the present invention mainly includes: a die-cutting machine body 100, a feeding mechanism 200, a cutting mechanism 300, an unloading mechanism 400, and a material rack mechanism 500 disposed on the die-cutting machine body 100. The die-cutting machine body 100 can be equipped with a PLC controller and some drive mechanisms such as motors. It can have a manual control console, or it can be integrated into a host computer instead. The main working principle is that the feeding mechanism 200 feeds the die-cutting material target object, and then the conveying mechanism conveys it to the support platform carrying the die-cutting material target object. Some can use belt conveyor, that is, during feeding, the support platform is fixed on the belt, the die-cutting material target object is placed on the support platform, and then the belt conveys the support platform carrying the die-cutting material target object to the area below the cutting mechanism for direct cutting.

[0058] The cutting mechanism 300 includes a cutting platform 320 and a cutting assembly 310. The cutting assembly 310 is as follows: Figure 3As shown, the device includes: a cutter mounting base, a cutter mounting position on one side of the cutter (as shown in the mounting hole 311), or other structures that facilitate cutter mounting, such as mounting grooves or fasteners like screws or clips. Since these are common practices in the prior art, this invention does not limit them. Three or more cameras, referred to as the first camera 312, the second camera 313, the third camera 314, and the fourth camera 315, are positioned around the cutter mounting hole 311 to capture images of the cutter cutting the target material from different angles. The cutter mounting position is provided on the cutter mounting base because the die-cutting machine needs to use different types of cutters when cutting different materials; otherwise, the cutter may be damaged, affecting production. Furthermore, the first camera 312, the second camera 313, the third camera 314, and the fourth camera 315 can rotate relative to the cutter mounting base or adjust to the relative distance between the target material and the die-cutting material.

[0059] like Figure 4 As shown, the foregoing description mainly illustrates the hardware implementation environment of the cloud data sharing-based die-cutting material defect inspection method provided by the present invention. With at least three of the following cameras—first camera 312, second camera 313, third camera 314, and fourth camera 315—installed on the die-cutting machine, the cloud data sharing-based die-cutting material defect inspection method of the present invention mainly includes the following steps based on images acquired from different perspectives:

[0060] S10: Acquire first-view, second-view, and third-view images of a specified scene from a first-view, second-view, and third-view perspective, respectively. The specified scene includes at least: a cutter, a die-cutting material target, and a support mechanism carrying the die-cutting material target. The angles of the first-view, second-view, and third-view perspectives during image acquisition are different, and the time intervals between the acquisition of the first-view, second-view, and third-view perspectives are within a preset range. The different acquisition angles are mainly to allow image acquisition of multiple surfaces of the die-cutting material target (which has a certain three-dimensionality, such as OCA with a certain thickness). Typically, when installing cameras, it is necessary to ensure that three or four or more cameras can respectively capture different surfaces of the die-cutting material target. Moreover, acquiring images from different perspectives can reduce the influence of external environmental factors on the accuracy of detection, such as uneven lighting in the environment where the die-cutting equipment is located, or the presence of certain obstacles that affect image acquisition. Furthermore, the preset time interval in this invention refers to the period from the start of a certain process to before any change occurs in that process. For example, during the feeding and conveying process, images can be captured from a first-view perspective during feeding, a second-view perspective during conveying, and a third-view perspective when the material is about to be cut below the cutting mechanism. All images captured from these three different perspectives show the die-cutting material during conveying. Combining these different frames from different perspectives makes it easier to determine whether the die-cutting material is moving normally during conveying. Moreover, comparing several frames allows for timely detection of any abnormalities along the conveying path, facilitating prompt identification of the cause. The same principle applies during cutting. However, because the cutting blade cuts quickly, the time interval is set shorter. The timing of image capture by the three cameras at different perspectives can be controlled based on three time points: contact with the die-cutting material, cutting the die-cutting material, and the cutting blade resetting and leaving the die-cutting material. In other words, one camera captures an image at each time point. Furthermore, during image capture, the order of image capture by different perspective cameras is determined by the completeness of the image of the die-cutting material's surface. This can significantly reduce the amount of data collected, transmitted, and processed, thereby improving production efficiency in the die-cutting process.

[0061] S20: Determine whether the die-cutting material target has defects based on the first perspective image, the second perspective image, and the third perspective image;

[0062] S30: When there are no defects, record the defect-free information; the defect-free information here includes at least one of the following: the control parameters of the cutter, the conveying speed of the die-cutting material target, the initial position information when cutting the die-cutting material target, and the relative position information between the die-cutting material target and the support mechanism.

[0063] S40: When a defect exists, generate defect information based on the defect characteristics; the defect information here includes at least one of the following: the defect location information of the die-cutting material target, the defect severity, the defect cause information, and the working parameters of the die-cutting material target involved in the entire process from feeding to waste separation.

[0064] S50: Correct the defect according to the defect information and generate correction information accordingly; the correction information here includes at least one of the following: control correction parameters of the cutter, conveying speed correction parameters of the die-cutting material target, initial position correction parameters when cutting the die-cutting material target, and relative position correction parameters between the die-cutting material target and the support mechanism.

[0065] S60: The defect-free information, defect information, and correction information are sent to the server so that the server can establish a die-cutting model of the die-cutting material target object and distribute the die-cutting model to several slave die-cutting devices. The die-cutting model may include the working parameters of the die-cutting devices, such as transmission speed, offset angle range, and relevant control parameters of the cutter, such as speed, force, and angle, as well as relevant information about the die-cutting material target object, such as shape, size, thickness, and potential problems. It includes data involved in the entire die-cutting process. After being given to the slave die-cutting devices, the slave die-cutting devices can operate according to the data of this die-cutting model. This not only maintains the product yield but also ensures that there are no significant differences between different die-cutting devices when die-cutting the same die-cutting material target object, which is beneficial for industrial production.

[0066] The cloud-based data sharing-based defect detection method, apparatus, and system for die-cutting materials provided in this invention comprehensively considers the defect detection process from material loading to post-die-cutting product defect detection, corrects defects in a timely manner, and establishes a die-cutting model based on the entire process. This model can then be replicated and shared with die-cutting equipment that cuts similar die-cutting materials. In this way, other die-cutting equipment can directly use the verified and compliant die-cutting model to control its operation, greatly improving the yield of die-cutting materials. It also reduces the previous over-reliance on the experience of die-cutting workers, avoids waste of die-cutting materials, and significantly reduces the manufacturing cost of large-scale factory die-cutting. Furthermore, it achieves data sharing and reduces the over-reliance on worker experience in die-cutting inspection and calibration.

[0067] In a preferred embodiment, determining whether the die-cutting material target has defects based on the first perspective image, the second perspective image, and the third perspective image includes:

[0068] The first perspective image includes at least a first pre-cut image of the die-cutting material target object before die-cutting, a first cut-time image of the scene of the die-cutting material target object being cut by the cutter during die-cutting, and a first detection image of the die-cutting material target object for defect detection after die-cutting;

[0069] The second perspective image includes at least: a second pre-cut image of the die-cutting material target object being transferred before die-cutting, a second cut-time image of the scene of the cutter cutting the die-cutting material target object during die-cutting, and a second detection image of the die-cutting material target object for defect detection after die-cutting;

[0070] The third-view image includes at least: a third pre-cut image of the die-cutting material target object being transferred before die-cutting, a third cut-time image of the scene of the cutter cutting the die-cutting material target object during die-cutting, and a third detection image of the die-cutting material target object for defect detection after die-cutting;

[0071] Based on the first pre-cutting image, the second pre-cutting image and the third pre-cutting image, we analyze whether the die-cutting material target object has foreign objects attached during transmission, whether it is arranged at a preset interval, whether the movement trajectory of the carrying mechanism is normal and whether it is located at the designated position on the carrying mechanism.

[0072] Based on the first cutting time image, the second cutting time image, and the third cutting time image, analyze whether there are foreign objects on the cutter when the cutter is cutting the die-cutting material target, the initial position information of the cutter, and whether the die-cutting material target is shifted during cutting;

[0073] Based on the first detection image, the second detection image, and the third detection image, the presence of defect features in the die-cutting material target is analyzed, and the defect information is generated.

[0074] This invention divides the die-cutting process into three stages, which allows for earlier detection of problems with the die-cutting material. Image acquisition and analysis are performed at each stage, which not only reduces waste of die-cutting material but also helps improve the automation level of the product. The detection and analysis at all three stages enable monitoring of the entire die-cutting process and the working parameters obtained from the die-cutting equipment, such as transmission speed, cutting speed, cutting angle, and cutting force, to prevent problems such as misalignment, angular deviation, positional deviation, burrs, or other foreign matter adhesion on the die-cutting material from occurring at an early stage.

[0075] Preferably, the step of analyzing whether the die-cutting material target object has foreign objects attached during transmission, whether it is arranged at a preset interval, whether the movement trajectory of the carrying mechanism is normal, and whether it is located at a designated position on the carrying mechanism based on the first pre-cutting image, the second pre-cutting image, and the third pre-cutting image includes:

[0076] Determine whether the die-cutting material targets are arranged neatly according to the preset spacing;

[0077] After confirming that the material is neatly arranged, determine whether the die-cutting material target has any foreign matter attached to it;

[0078] After confirming that there are no foreign objects, determine whether the movement trajectory of the carrying mechanism when transmitting the die-cut material target object moves along the preset trajectory;

[0079] Before moving along the preset trajectory and reaching the die-cutting position to begin die-cutting, it is determined whether the die-cutting material is located at the designated position of the support mechanism.

[0080] Of course, the preferred order here can promptly detect any anomalies in the die-cutting material target. Furthermore, the difficulty of data processing is also considered; for example, neatly arranged images are easier to process, requiring only comparison with the original images. Next, the focus is on whether there are any foreign objects attached to a particular die-cutting material target. Other visual recognition sequences can also be implemented, such as considering the most likely causes of anomalies and performing visual image acquisition and analysis on frequently occurring problems. A hybrid approach can also be used, combining the chronological order of the die-cutting material target in each process with the most likely causes of anomalies to be determined. For example, motion trajectory detection and foreign object detection can be performed first, followed by foreign object detection once the target is located at a designated position on the support mechanism. This invention does not limit the scope of this approach.

[0081] In one specific embodiment, the step of analyzing whether there are foreign objects on the cutter, the initial position information of the cutter, and whether the die-cutting material target object is shifted during cutting based on the first cutting time image, the second cutting time image, and the third cutting time image includes:

[0082] Determine whether foreign objects adhere to the cutting blade during the cutting process, and as to the size and type of such foreign objects. For example, grease-like foreign objects are sometimes difficult to detect and remove, but for die-cutting equipment, machine oil or lubricating oil on the equipment may contaminate the die-cutting material during operation. It could also be that external foreign objects adhere during the feeding process.

[0083] When it is confirmed that no foreign matter adheres to the die-cutting material, determine whether the cutter starts cutting from the initial position specified on the die-cutting material target during cutting;

[0084] When it is determined that the cutting starts at the specified initial position, monitor whether the cutter causes the die-cutting material target to shift position during the cutting process;

[0085] If it is determined during the cutting process that the target material for die cutting has not shifted in position, then it is determined whether there is any separated waste material when the cutting is completed; waste material includes materials such as backing paper, glue, and base paper that have been cut off.

[0086] The current cutting process ends when the waste material is determined to be separated.

[0087] In one embodiment, the step of analyzing whether the die-cutting material target has defect features based on the first detection image, the second detection image, and the third detection image, and generating the defect information, includes:

[0088] When the analysis based on the first detection image, the second detection image and the third detection image indicates that the die-cutting material target has defect features, the feeding and die-cutting work of the die-cutting material target shall be stopped immediately.

[0089] Record defect information of the die-cut material target.

[0090] Example 2

[0091] like Figure 5 As shown, based on the cloud data sharing-based die-cutting material defect inspection and verification in Embodiment 1, the present invention further provides a cloud data sharing-based die-cutting material defect inspection and verification device, the device comprising:

[0092] Image acquisition module 1 is used to acquire first-view images, second-view images and third-view images of a specified scene from a first-view perspective, a second-view perspective and a third-view perspective respectively. The specified scene includes at least: a cutter, a die-cutting material target and a support mechanism that carries the die-cutting material target. The angles of the first-view perspective, the second-view perspective and the third-view perspective are different when the images are acquired, and the time interval between the acquisition of the first-view perspective, the second-view perspective and the third-view perspective is within a preset range.

[0093] Defect determination module 2 is used to determine whether there are defects in the die-cutting material target based on the first perspective image, the second perspective image, and the third perspective image;

[0094] Recording module 3 is used to record no-defect information when no defects are found;

[0095] Defect information generation module 4 is used to generate defect information based on defect characteristics when a defect exists.

[0096] The correction information generation module 5 is used to correct the defect based on the defect information and generate correction information accordingly.

[0097] The sending module 6 is used to send the defect-free information, defect information, and correction information to the server so that the server can build a die-cutting model of the die-cutting material target object and distribute the die-cutting model to several designated die-cutting devices.

[0098] The cloud-based data sharing-based die-cutting material defect inspection and calibration device provided in this invention, by setting up an image acquisition module, a defect determination module, a defect information generation module, and a correction information generation module, detects and analyzes defects in the die-cutting process from material loading to post-die-cutting product defects, corrects the detected defects in a timely manner, and establishes a die-cutting model based on the entire die-cutting process. This model can then be replicated and shared with die-cutting equipment cutting similar die-cutting materials. In this way, other die-cutting equipment can directly use the verified and compliant die-cutting model to control its operation, greatly improving the yield of die-cutting materials. It also reduces the previous problem of over-reliance on the experience of die-cutting workers, avoids the waste of die-cutting materials, and significantly reduces the manufacturing cost of large-scale die-cutting in factories. Furthermore, it achieves data sharing and reduces the over-reliance on worker experience in die-cutting inspection and calibration.

[0099] Example 3

[0100] Embodiment 3 of the present invention provides a cloud data sharing-based defect inspection system for die-cut materials, based on Embodiments 1 and 2 above. Please refer to further details. Figure 1 The system includes: a server 20, a main die-cutting device 10, and a plurality of slave die-cutting devices 30. The server, the main die-cutting device, and the plurality of slave die-cutting devices are communicatively connected to each other. The main die-cutting device is used for:

[0101] First-view, second-view, and third-view images of a specified scene are acquired from a first-view, second-view, and third-view perspective, respectively. The specified scene includes at least: a cutter, a die-cutting material target, and a support mechanism carrying the die-cutting material target. The angles of the first-view, second-view, and third-view perspectives are different during image acquisition, and the time intervals between the acquisition of the first-view, second-view, and third-view perspectives are within a preset range. Based on the first-view, second-view, and third-view images, it is determined whether the die-cutting material target has defects.

[0102] When no defects are found, record the defect-free information.

[0103] When a defect exists, defect information is generated based on the defect characteristics;

[0104] The defect is corrected based on the defect information, and corresponding correction information is generated;

[0105] Send the defect-free information, defect information, and correction information to the server;

[0106] The server is used to: receive the defect-free information, the defect information, and the correction information, then establish a die-cutting model of the die-cutting material target object, and distribute the die-cutting model to several die-cutting devices;

[0107] The die-cutting equipment adjusts its own die-cutting control parameters according to the die-cutting model.

[0108] Since the system of Embodiment 3 of the present invention is based on Embodiment 1, it also has the advantages of the method in Embodiment 1. In addition, the system can set up a central control console to uniformly manage the operation of each die-cutting device and share the established die-cutting model with each slave die-cutting device. Of course, each slave die-cutting device can also communicate with the master die-cutting device. Each slave die-cutting device does not need to install a camera, or only needs to install one camera to monitor the device. In this way, with minimal changes to the existing die-cutting equipment, the product yield can be greatly improved by making corresponding modifications to the control program, etc., greatly reducing manual intervention, saving labor costs and reducing the consumption of product die-cutting materials.

[0109] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0110] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0111] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0112] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A method of die material defect verification, the method comprising: The method comprises: acquiring a first-view image, a second-view image and a third-view image of a specified scene, wherein the specified scene comprises at least a cutting tool, a die-cutting material target object and a bearing mechanism bearing the die-cutting material target object; the first-view image, the second-view image and the third-view image are acquired at different angles and within a preset time interval; the first-view image comprises at least a first detection image of the die-cutting material target object after die-cutting for defect detection; the second-view image comprises at least a second detection image of the die-cutting material target object after die-cutting for defect detection; the third-view image comprises at least a third detection image of the die-cutting material target object after die-cutting for defect detection; analyzing whether the die-cutting material target object has a defect feature according to the first detection image, the second detection image and the third detection image, and generating defect information; correcting the defect according to the defect information and generating correction information accordingly; sending the defect information and the correction information to a server so that the server establishes a die-cutting model of the die-cutting material target object according to the defect information and the correction information, and distributes the die-cutting model to a plurality of die-cutting devices; the defect information is used to represent the defect of the die-cutting material target object; the correction information is parameter information generated when the defect is corrected according to the defect information; the die-cutting model comprises at least one of the following: working parameters of a die-cutting device, control parameters of the cutting tool, and shape, size and thickness of the die-cutting material target object.

2. The method of claim 1, wherein, the first-view image further comprises a first pre-cut image of the die-cutting material target object before die-cutting; the second-view image further comprises a second pre-cut image of the die-cutting material target object before die-cutting; the third-view image further comprises a third pre-cut image of the die-cutting material target object before die-cutting; the method further comprises: analyzing whether foreign matter is attached to the die-cutting material target object, whether the die-cutting material target object is arranged at a preset interval, whether the motion trajectory of the bearing mechanism is normal, and whether the die-cutting material target object is located at a specified position on the bearing mechanism according to the first pre-cut image, the second pre-cut image and the third pre-cut image.

3. The method of claim 2, wherein, the first-view image further comprises a first cutting-time image of the die-cutting material target object when the cutting tool cuts the die-cutting material target object; the second-view image further comprises a second cutting-time image of the die-cutting material target object when the cutting tool cuts the die-cutting material target object; the third-view image further comprises a third cutting-time image of the die-cutting material target object when the cutting tool cuts the die-cutting material target object; the method further comprises: analyzing whether foreign matter is attached to the cutting tool when the cutting tool cuts the die-cutting material target object, initial position information of the cutting tool when the cutting tool cuts the die-cutting material target object, and whether the die-cutting material target object is shifted in position when the cutting tool cuts the die-cutting material target object according to the first cutting-time image, the second cutting-time image and the third cutting-time image.

4. The method according to any one of claims 1 to 3, characterized in that, the analysis of whether the die-cutting material target object has a defect feature according to the first detection image, the second detection image and the third detection image, and the generation of the defect information comprise: When it is analyzed that the die-cutting material target object has a defect feature according to the first detection image, the second detection image and the third detection image, the feeding of the die-cutting material target object and the die-cutting work are stopped immediately; The defect information of the die-cutting material target object is recorded.

5. The method according to any one of claims 1 to 3, characterized in that, The defect information at least includes one of the following: defect position information, defect severity, defect cause information of the die-cutting material target object and working parameters related to the die-cutting material target object from the feeding to the separation of the waste.

6. The method of claim 1, wherein, The correction information at least includes one of the following: control correction parameters of the cutter, correction parameters of the conveying speed of the die-cutting material target object, initial position correction parameters when cutting the die-cutting material target object and relative position correction parameters between the die-cutting material target object and the carrier mechanism on the carrier mechanism.

7. The method of claim 1, wherein, The working parameters of the die-cutting model device include: the conveying speed of the die-cutting device and the offset angle range of the die-cutting device.

8. A die material defect inspection system, characterized by, The system includes: a server, a master die-cutting device and a plurality of slave die-cutting devices, and the server, the master die-cutting device and the plurality of slave die-cutting devices are communicatively connected to each other, wherein the master die-cutting device is used to: Obtain a first perspective image, a second perspective image and a third perspective image in a specified scene from a first perspective, a second perspective and a third perspective respectively, wherein the specified scene at least includes: a cutter, a die-cutting material target object and a carrier mechanism for carrying the die-cutting material target object; the first perspective and the second perspective and the third perspective are different in angle when the images are collected, and the time interval between the first perspective and the second perspective and the third perspective is within a preset range when they are collected; The first perspective image at least includes: a first detection image for detecting defects of the die-cutting material target object after die-cutting; The second perspective image at least includes: a second detection image for detecting defects of the die-cutting material target object after die-cutting; The third perspective image at least includes: a third detection image for detecting defects of the die-cutting material target object after die-cutting; According to the first detection image, the second detection image and the third detection image, it is analyzed whether the die-cutting material target object has a defect feature, and defect information is generated; According to the defect information, the defect is corrected, and correction information is generated accordingly; The defect information and the correction information are sent to the server; The server is used to: after receiving the defect information and the correction information, a die-cutting model of the die-cutting material target object is established, and the die-cutting model is distributed to a plurality of slave die-cutting devices; The slave die-cutting device adjusts its die-cutting control parameters according to the die-cutting model; The defect information is used to represent the defect of the die-cutting material target object; The correction information is parameter information generated when the defect is corrected according to the defect information; The die-cutting model at least includes one of the following: working parameters of the die-cutting device, control parameters of the cutter and shape, size and thickness of the die-cutting material target object.

Images