CN111331247A

CN111331247A - AI intelligent feeding device for laser cutting machine

Info

Publication number: CN111331247A
Application number: CN202010287310.1A
Authority: CN
Inventors: 李荣辉; 谭春晖; 康志国; 申仁军
Original assignee: Shenzhen Make Laser Equipment Co ltd
Current assignee: Shenzhen Make Laser Equipment Co ltd
Priority date: 2020-04-13
Filing date: 2020-04-13
Publication date: 2020-06-26
Anticipated expiration: 2040-04-13
Also published as: CN111331247B

Abstract

The embodiment of the application provides an AI intelligence material feeding unit for laser cutting machine, AI intelligence material feeding unit's upper portion is provided with camera equipment, camera equipment includes: the transmission device drives the camera to move synchronously with a conveyor belt of the AI intelligent feeding device; AI intelligence material feeding unit still includes: an AI device; the technical scheme of this application has the advantage that the yields is high.

Description

AI intelligent feeding device for laser cutting machine

Technical Field

The application relates to the technical field of electronics and laser, especially, relate to an AI intelligence material feeding unit for laser cutting machine.

Background

The laser cutting machine focuses laser emitted from a laser into a laser beam with high power density through an optical path system. The laser beam irradiates the surface of the workpiece to make the workpiece reach a melting point or a boiling point, and simultaneously, the high-pressure gas coaxial with the laser beam blows away the molten or gasified metal. And finally, the material is cut along with the movement of the relative position of the light beam and the workpiece, so that the cutting purpose is achieved.

The laser cutting processing is to replace the traditional mechanical knife by invisible light beams, has the characteristics of high precision, quick cutting, no limitation on cutting patterns, automatic typesetting, material saving, smooth cut, low processing cost and the like, and can gradually improve or replace the traditional metal cutting process equipment. The mechanical part of the laser tool bit is not in contact with the workpiece, so that the surface of the workpiece cannot be scratched in the working process; the laser cutting speed is high, the cut is smooth and flat, and subsequent processing is generally not needed; the cutting heat affected zone is small, the deformation of the plate is small, and the cutting seam is narrow; the notch has no mechanical stress and no shearing burr; the processing precision is high, the repeatability is good, and the surface of the material is not damaged; the numerical control programming can be used for processing any plan, the whole board with large breadth can be cut, a die does not need to be opened, and the method is economical and time-saving.

The AI intelligent feeding device of laser cutting processing can realize autoloading, and the displacement of non-direction of motion can take place for the material during its autoloading, and this kind of condition can lead to the improper aversion of material, and this kind of improper aversion can lead to scrapping of material processing, has reduced the yields.

Disclosure of Invention

The embodiment of the application discloses an AI intelligent feeding method for a laser cutting machine, which can identify abnormal displacement of materials of the AI laser cutting machine, withdraw the materials with abnormal identification and improve the yield of material processing.

The embodiment of the application discloses first aspect discloses an AI intelligence material feeding unit for laser cutting machine, AI intelligence material feeding unit's upper portion is provided with camera equipment, camera equipment includes: the transmission device drives the camera to move synchronously with a conveyor belt of the AI intelligent feeding device; AI intelligence material feeding unit still includes: an AI device for performing an AI operation,

the AI intelligent feeding device is used for controlling the camera to collect n pieces of image information when the material moves;

the AI device is used for cutting a set area from the n pieces of image information along the direction vertical to the moving direction to obtain a plurality of images to be processed;

the AI device is also used for identifying each image to be processed to determine a movement result, and if the movement result is determined to move along the vertical direction, the conveyor belt is controlled to rotate reversely to send the material back;

the AI device is further used for collecting x pictures when the conveyor belt stops, identifying and determining an outer edge line of the first picture for the first picture of the x pictures, identifying and determining an x-th outer edge line of the x-th picture for the x-th picture of the x pictures, determining a difference value between the x-th outer edge line and the first outer edge line, controlling the camera to shoot an x + 1-th picture after moving the difference value, identifying a boundary of the x + 1-th picture to determine a material position, and sending the material position to the laser cutting device for laser cutting.

In a second aspect, an AI intelligent feeding method for a laser cutting machine is applied to an AI intelligent feeding device, wherein a camera device is arranged on the upper portion of the AI intelligent feeding device, and the camera device includes: the transmission device drives the camera to move synchronously with a conveyor belt of the AI intelligent feeding device; AI intelligence material feeding unit still includes: an AI device, characterized in that,

the AI intelligent feeding device controls the camera to collect n pieces of image information when the material moves;

the AI device cuts a set area from n pieces of image information along the vertical direction of the moving direction to obtain a plurality of images to be processed; identifying each image to be processed to determine a movement result, and if the movement result is determined to move along the vertical direction, controlling the conveyor belt to reversely rotate to send the materials back;

the AI device collects x pictures when the conveyor belt stops, identifies and determines an outer edge line of the first picture of the x pictures, identifies and determines an x-th outer edge line of the x-th picture of the x pictures, determines a difference value between the x-th outer edge line and the first outer edge line, controls the camera to shoot an x +1 picture after moving the difference value, identifies a boundary of the x +1 picture to determine a material position, and sends the material position to the laser cutting device for laser cutting.

By implementing the embodiment of the application, the technical scheme provided by the application acquires information of a plurality of images after the AI device stops; cutting a set area from the plurality of pieces of image information along the moving direction to obtain a plurality of images to be processed; the method comprises the steps of identifying each image to be processed to determine a movement result, inquiring an x-th unmoved image to be processed from the plurality of images to be processed, determining image information corresponding to the x-th image to be processed as input image information of an AI device, identifying a boundary of the input image information by the AI device to determine a material position, and sending the material position to a laser cutting device for laser cutting.

Drawings

The drawings used in the embodiments of the present application are described below.

Fig. 1 is a schematic structural diagram of an AI intelligent feeding system for a laser cutting machine according to an embodiment of the present application;

fig. 2 is a schematic flow chart of an AI intelligent feeding method for a laser cutting machine according to an embodiment of the present application;

fig. 2a is a schematic diagram of input data of m × n × 3 provided in an embodiment of the present application (for convenience of description, m is 10, n is 5, and in practical application, the minimum value of m and n needs to be greater than 50);

FIG. 2b is a diagram illustrating the result of convolution of (m-2) (n-2) according to an embodiment of the present application;

fig. 2c is a numerical diagram of a 3 × 3 convolution kernel according to an embodiment of the present application.

Detailed Description

The embodiments of the present application will be described below with reference to the drawings.

The term "and/or" in this application is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in this document indicates that the former and latter related objects are in an "or" relationship.

The "plurality" appearing in the embodiments of the present application means two or more. The descriptions of the first, second, etc. appearing in the embodiments of the present application are only for illustrating and differentiating the objects, and do not represent the order or the particular limitation of the number of the devices in the embodiments of the present application, and do not constitute any limitation to the embodiments of the present application. The term "connect" in the embodiments of the present application refers to various connection manners, such as direct connection or indirect connection, to implement communication between devices, which is not limited in this embodiment of the present application.

The AI device in the embodiments of the present application may refer to various forms of UE, access terminal, subscriber unit, subscriber station, mobile station, MS (mobile station), remote station, remote terminal, mobile device, computer, server, cloud system user terminal, terminal device (terminal equipment), wireless communication device, user agent, or user device. The terminal device may also be a cellular phone, a cordless phone, an SIP (session initiation protocol) phone, a WLL (wireless local loop) station, a PDA (personal digital assistant) with a wireless communication function, a handheld device with a wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a future 5G network or a terminal device in a future evolved PLMN (public land mobile network, chinese), and the like, which are not limited in this embodiment.

Referring to fig. 1, fig. 1 is a schematic block diagram of a structure of an AI intelligent feeding system for a laser cutting machine, as shown in fig. 1, the apparatus includes: AI intelligence material feeding unit, laser cutting device, AI device, wherein the AI device includes: camera, memory, treater (can be general-purpose processor, also can be special AI treater). The technical scheme of this application does not have the improvement to laser cutting device, and this AI intelligence material feeding unit, laser cutting device can adopt current laser cutting device, and this AI intelligence material feeding unit's upper portion is provided with camera equipment, and this camera equipment includes: conveyer and camera, this transmission take camera and AI intelligent feeding device's conveyer belt synchronous motion, this AI intelligent feeding device is still integrated with the AI device.

For an AI intelligent feeding device, a stepping motor is generally adopted for control, after the AI intelligent feeding device moves a material to a preset position, image information is collected by a camera, the image information is identified to determine the position of the material, and then the position of the material is sent to a laser cutting device to realize the cutting of the material.

Referring to fig. 2, fig. 2 provides an AI intelligent feeding method for a laser cutting machine, which is performed by the AI intelligent feeding device shown in fig. 1, and the method shown in fig. 2 includes the following steps:

s201, collecting n pieces of image information when the AI intelligent feeding device moves materials;

the collection mode in step S201 may be collected by a camera.

S202, cutting a set area from n pieces of image information by an AI device of the AI intelligent feeding device along the vertical direction of the moving direction to obtain n images to be processed;

s203, the AI device identifies each image to be processed to determine a movement result, and if the movement result is determined to move along the vertical direction, the conveying belt of the AI intelligent feeding device is controlled to rotate reversely to feed back the material;

in an optional scheme, the identifying, by the AI device, each to-be-processed image to determine a movement result may specifically include:

extracting 3 x 3 pixel points at the upper side, 3 x 3 pixel points at the middle part and 3 x 3 pixel points at the lower side of an image to be processed, and aligning 3 x 3 pixel points at the upper sideThe middle 3 × 3 pixels and the lower 3 × 3 pixels are respectively identified to determine the moving result, and the identification operation specifically includes: using 3 pixel points at the upper side as the center, searching y 3 pixel points which are the same as the 3 pixel points at the upper side in the 90-degree direction of the moving direction, searching y 3 pixel points which are the same as the 3 pixel points at the upper side in the 270-degree direction of the moving direction, and calculating the total average value AVG of the brightness of the (2y +1) 3 pixel points_{On the upper part}Calculating the average brightness value and AVG of (2y +1) 3 x 3 pixels_{On the upper part}Variance S of² _{On the upper part}And performing identification operation on the 3 x 3 pixel points in the middle to obtain S² _InAnd performing identification operation on the lower 3 x 3 pixel points to obtain S² _{Lower part}Will S² _{Go up,}S² _{Middle part,}S² _{Lower part}The minimum value in the image to be processed is compared with a moving threshold value, if the minimum value is larger than the moving threshold value, the image to be processed is determined not to move, and if the minimum value is larger than or equal to the moving threshold value, the image to be processed is determined to move along the vertical direction.

For example, when y is 1, S² _{On the upper part}＝[(lum1²_AVG² _{On the upper part})+(lum2²_AVG² _{On the upper part})+(lum3²_AVG² _{On the upper part})]A/3; wherein, lum1 is the luminance average value of looking for 1 3 the same pixel with the 3 pixel of upside along the 90 directions of moving direction, lum2 is the luminance average value of the 3 pixel of upside, lum3 is the luminance average value of looking for 1 the 3 the same pixel with the 3 pixel of upside along the 270 directions of moving direction.

For shooting of image information in a moving state, the method has the characteristic that the difference between brightness values of the same pixel points is small, based on the characteristic, 3 x 3 pixel points of an image to be processed serve as an identified basic pixel block, then the variance of the basic pixel block is calculated, the fluctuation size of the brightness of the basic pixel block is determined through the variance, when the fluctuation is large, for example, larger than a moving threshold value, the image to be processed is determined to move in the vertical direction, and otherwise, the image to be processed is determined not to move.

In an optional manner, the searching y 3 × 3 pixels that are the same as the upper 3 × 3 pixels along the moving direction by using the upper 3 × 3 pixels as the center may specifically include:

and 3 × 3 RGB channels in the upper 3 × 3 pixel points are determined, and y 3 × 3 pixel points which are the same as the 3 × 3 RGB channels and are closest to the pixel points are searched along the moving direction.

For example, the upper 3 × 3 pixels (first and last column) are B, G, B, G, R, G, B, G, B; then, y 3 × 3 pixels that are the same as the RGB channel and closest to the RGB channel are searched along the moving direction, that is, y 3 × 3 pixels (listed in front and back) are searched, B, G, B, G, R, G, B, G, B.

Step S204, when the conveyor belt stops, the AI device collects x pictures, identifies and determines an outer edge line of the first picture of the x pictures, identifies and determines an x-th outer edge line of the x-th picture of the x pictures, determines a difference value between the x-th outer edge line and the first outer edge line, controls the camera to move the difference value and then shoots an x + 1-th picture, carries out boundary identification on the x + 1-th picture to determine a material position, and sends the material position to the laser cutting device for laser cutting.

The laser cutting method can adopt the existing method, and the detailed description is omitted here.

Optionally, the identifying and determining the outer edge coordinates of the first picture of the x pictures may specifically include:

converting the first picture into a gray image, identifying the gray value of the pixel points to determine a gray value change area (at least 50 or more than 50 pixel points are extracted in each direction), extracting a sub-picture of the gray value change area from the first picture, forming the sub-picture into input data of m x n x 3 according to the RGB values of the pixel points, and performing convolution operation on the input data and a preset 3 x 3 convolution kernel to obtain a convolution result (m-2) (n-2); finding out a boundary of two interval values from the convolution results (m-2) (n-2), and mapping the boundary on the sub-picture and moving 2 pixel points in the moving direction to obtain an outer edge line of the first picture; the above m and n are integers of 50 or more.

The above-mentioned 3 × 3 convolution kernel may be a convolution kernel with the maximum middle value, the next largest adjacent value and the small edge position, as shown in fig. 2c, the middle value may be 3, the next adjacent value may be 2 and the edge position may be 1. This arrangement enables a better distinction of the dividing lines, since the RGB corresponding to the middle pixel point of the cut input data may be larger, and thus the middle value needs to be set to the maximum.

Referring to fig. 2a, fig. 2a illustrates a schematic diagram of input data of m × n × 3, where m represents a height dimension, n represents a width dimension, and 3 represents a channel number, which may specifically be values of R channel, G channel, and B channel of a pixel, and then for an outer edge line, one side is a material, and the other side is a conveyor belt, and due to different materials, colors and RGB values have large differences, but due to pixel reasons, the colors are not so clear after edge position amplification, and therefore determined by a calculation method, and therefore for different materials, due to large differences in RGB values, a convolution operation is performed by a convolution kernel of 3 × 3 to obtain a (m-2) (n-2) convolution result, and then the (m-2) (n-2) convolution result is divided into two interval values, one interval value (black as shown in fig. 2 b) represents the interval value of the material, and the other interval value is the interval value (white as shown in fig. 2 b) of the conveyor belt, so that a boundary 301 (as shown in fig. 2 b) of the two interval values can be found, when the boundary is found, if a noise point with a longer distance is present, the noise point is removed, in this way, an irregularly shaped boundary line can be identified, and then the boundary line is mapped on the sub-picture, taking a straight line as an example, the boundary line of fig. 2b can be the x-th column of a (m-2) (n-2) matrix, the (x + -2) th column is determined as the edge line of the first picture, the selection of the + -can be determined according to the determined position of the outer edge line on the material, if the outer edge line is the rear edge line of the material (i.e. the edge of the rear-entry conveyor belt), the selection of the '-', otherwise, "+" is selected. Therefore, the technical scheme of the application has the advantages that the calculation of the outer edge line is simple and accurate, and the outer edge line of the irregular material can be determined.

According to the technical scheme provided by the application, a plurality of pieces of image information are collected after the AI device stops; cutting a set area from the plurality of pieces of image information along the moving direction to obtain a plurality of images to be processed; the method comprises the steps of identifying each image to be processed to determine a movement result, inquiring an x-th unmoved image to be processed from the plurality of images to be processed, determining image information corresponding to the x-th image to be processed as input image information of an AI device, identifying a boundary of the input image information by the AI device to determine a material position, and sending the material position to a laser cutting device for laser cutting.

The embodiment of the present application still provides an AI intelligence material feeding unit for laser cutting machine, AI intelligence material feeding unit's upper portion is provided with camera equipment, camera equipment includes: the transmission device drives the camera to move synchronously with a conveyor belt of the AI intelligent feeding device; AI intelligence material feeding unit still includes: an AI device for performing an AI operation,

Optionally, the AI device is specifically configured to convert the first picture into a grayscale image, identify a grayscale value of a pixel point to determine a grayscale value change region, extract a sub-picture of the grayscale value change region from the first picture, compose the sub-picture into input data of m × n × 3 according to RGB values of the pixel point, and perform convolution operation on the input data and a preset 3 × 3 convolution kernel to obtain a convolution result (m-2) (n-2); finding out a boundary of two interval values from the convolution results (m-2) (n-2), and mapping the boundary on the sub-picture and moving 2 pixel points in the moving direction to obtain an outer edge line of the first picture;

the above m and n are integers of 50 or more.

Optionally, the AI device is specifically configured to extract 3 × 3 pixels on the upper side, 3 × 3 pixels in the middle, and 3 × 3 pixels on the lower side of one to-be-processed image, and to identify and determine the movement result of the upper side, 3 × 3 pixels in the middle, and 3 × 3 pixels on the lower side, respectively, and the identification operation specifically may include: using 3 pixel points at the upper side as the center, searching y 3 pixel points which are the same as the 3 pixel points at the upper side in the 90-degree direction of the moving direction, searching y 3 pixel points which are the same as the 3 pixel points at the upper side in the 270-degree direction of the moving direction, and calculating the total average value AVG of the brightness of the (2y +1) 3 pixel points_{On the upper part}Calculating the average brightness value and AVG of (2y +1) 3 x 3 pixels_{On the upper part}Variance S of² _{On the upper part}And performing identification operation on the 3 x 3 pixel points in the middle to obtain S² _InAnd performing identification operation on the lower 3 x 3 pixel points to obtain S² _{Lower part}Will S² _{Go up,}S² _{Middle part,}S² _{Lower part}The minimum value in the image to be processed is compared with a moving threshold value, if the minimum value is larger than the moving threshold value, the image to be processed is determined not to move, and if the minimum value is larger than or equal to the moving threshold value, the image to be processed is determined to move along the vertical direction.

Optionally, the AI device may also implement a refinement of the method shown in fig. 2.

In the embodiment of the present application, the electronic device may be divided into the functional units according to the method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

Embodiments of the present application also provide a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, the computer program enabling a computer to execute part or all of the steps of any one of the methods described in the above method embodiments, and the computer includes an electronic device.

Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods as described in the above method embodiments. The computer program product may be a software installation package, the computer comprising an electronic device.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units is only one type of division of logical functions, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-mentioned method of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. An AI intelligence material feeding unit for laser cutting machine, AI intelligence material feeding unit's upper portion is provided with camera equipment, camera equipment includes: the transmission device drives the camera to move synchronously with a conveyor belt of the AI intelligent feeding device; AI intelligence material feeding unit still includes: an AI device, characterized in that,

2. The AI smart feeding device for a laser cutting machine according to claim 1,

the AI device is specifically used for converting the first picture into a gray image, identifying the gray value of a pixel point to determine a gray value change area, extracting a sub-picture of the gray value change area from the first picture, forming the sub-picture into input data of m × n × 3 according to the RGB values of the pixel point, and performing convolution operation on the input data and a preset 3 × 3 convolution kernel to obtain a convolution result (m-2) (n-2); finding out a boundary of two interval values from the convolution results (m-2) (n-2), and mapping the boundary on the sub-picture and moving 2 pixel points in the moving direction to obtain an outer edge line of the first picture;

the above m and n are integers of 50 or more.

3. The AI smart feeding device for a laser cutting machine according to claim 1,

the AI device is specifically used for extracting 3 × 3 pixels on the upper side, 3 × 3 pixels in the middle and 3 × 3 pixels on the lower side of an image to be processed, and identifies and determines a movement result of the image to the 3 × 3 pixels on the upper side, 3 × 3 pixels in the middle and 3 × 3 pixels on the lower side respectively, and the identification operation specifically can include: using 3 pixel points at the upper side as the center, searching y 3 pixel points which are the same as the 3 pixel points at the upper side in the 90-degree direction of the moving direction, searching y 3 pixel points which are the same as the 3 pixel points at the upper side in the 270-degree direction of the moving direction, and calculating the total average value AVG of the brightness of the (2y +1) 3 pixel points_{On the upper part}Calculating the average brightness value and AVG of (2y +1) 3 x 3 pixels_{On the upper part}Variance S of² _{On the upper part}And performing identification operation on the 3 x 3 pixel points in the middle to obtain S² _InAnd performing identification operation on the lower 3 x 3 pixel points to obtain S² _{Lower part}Will S² _{On the upper part}、S² _In、S² _{Lower part}Is compared with a movement threshold value,and if the minimum value is larger than or equal to the moving threshold value, determining that the image to be processed moves along the vertical direction.

4. An AI intelligent feeding method for a laser cutting machine is applied to an AI intelligent feeding device, the upper part of the AI intelligent feeding device is provided with a camera shooting device, and the camera shooting device comprises: the transmission device drives the camera to move synchronously with a conveyor belt of the AI intelligent feeding device; AI intelligence material feeding unit still includes: an AI device, characterized in that,