1. A machine vision-based punching process sheet metal offset visual measurement system is characterized by comprising the following components:

the shooting unit is used for shooting images of the edges of the sheet materials in the stamping production line;

the control unit is connected with the shooting unit and used for controlling the light source switch, the shooting angle and the lens focusing in the image shooting of the shooting unit;

the data processing unit is connected with the control unit and the shooting unit and used for storing the images collected by the shooting unit, processing the images, controlling the on and off of the light source and sending the image detection result to the PLC controller or transmitting information;

and the algorithm identification unit is connected with the data processing unit and is used for detecting and calibrating the image processed by the data processing unit to obtain the actual offset of the sheet material in the stamping process.

2. The machine vision based stamping process sheet deviation vision measurement system of claim 1, wherein the camera unit comprises: the high-precision matrix camera comprises a shooting module consisting of a high-precision matrix camera and a lens, and a high-brightness light-gathering light source module;

the high-precision matrix camera adopts a large-size camera target surface and a high-frame-rate camera with high pixels;

the lens group adopts a 25mm FA lens;

the high-brightness light-gathering light source module adopts a 100W light-gathering LED industrial long-throw light source;

the visual field range of the shooting module which is 3m away from the plate to be detected is 1m multiplied by 1 m.

3. The machine vision based punching process sheet deviation vision measurement system according to claim 1, wherein said control unit comprises a light source control mechanism, a shooting angle control mechanism, a lens focusing control mechanism;

the light source control mechanism is used for controlling the on and off of the light source outside the production line;

the shooting angle control mechanism is used for controlling the direction and the angle movement of the shooting unit outside the production line so as to align the edge part of the target plate;

the lens focusing mechanism is used for realizing the focusing of the camera lens outside the production line.

4. The machine vision based punching process sheet deviation vision measurement system according to claim 1, wherein said data processing unit comprises an industrial personal computer, a switch;

the industrial personal computer and the switch are used for being connected with the high-precision matrix camera, the control unit and the PLC of the shooting module respectively.

5. A method for realizing the machine vision based punching process sheet shift vision measurement system according to any one of claims 1-4, characterized in that the machine vision based punching process sheet shift vision measurement method comprises:

shooting a picture at the shooting position of the calibration scale in the stamping die, and calculating the actual single-pixel precision of shooting according to the size of the calibration scale in the picture;

counting the state of the sheet at the accurate position of the model die during stamping as a comparison reference, calculating and recording the position of the sheet edge in the picture, and setting the position as a reference position; taking a first mode of equipment operation as a calibration image, extracting a reference edge of a region to be detected by adopting an edge extraction algorithm, and storing a row value and a column value of a reference line starting point;

after a high-precision matrix camera of the shooting module receives a trigger signal of die opening and closing of a machine tool, shooting a sheet picture in a production process according to the trigger signal, recording the position of the edge of the sheet in the picture at the moment, comparing the position with a reference position, calculating the offset of the sheet relative to the reference position at the moment, multiplying the offset by the single-pixel precision obtained by calculation, and determining the actual offset of the sheet after the punching process.

6. The machine vision based stamping process sheet displacement visual measurement method according to claim 5, wherein the calculation method of single pixel precision comprises:

single pixel accuracy (mm/pix) is unidirectional field size (mm)/camera unidirectional resolution (pix);

the actual offset calculation method includes:

the actual offset (mm) is a single-pixel precision (mm/pix) × sheet offset (pix) from the reference offset.

7. A program storage medium for receiving user input, the stored computer program causing an electronic device to perform the machine vision based stamping process sheet deviation vision measurement method of any one of claims 5 to 6.

8. A computer device, characterized in that the computer device comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the steps of:

shooting a picture at the shooting position of the calibration scale in the stamping die, and calculating the actual single-pixel precision of shooting according to the size of the calibration scale in the picture;

counting the state of the sheet at the accurate position of the model die during stamping as a comparison reference, calculating and recording the position of the sheet edge in the picture, and setting the position as a reference position; taking a first mode of equipment operation as a calibration image, extracting a reference edge of a region to be detected by adopting an edge extraction algorithm, and storing a row value and a column value of a reference line starting point;

after a high-precision matrix camera of the shooting module receives a trigger signal of die opening and closing of a machine tool, shooting a sheet picture in a production process according to the trigger signal, recording the position of the edge of the sheet in the picture at the moment, comparing the position with a reference position, calculating the offset of the sheet relative to the reference position at the moment, multiplying the offset by the single-pixel precision obtained by calculation, and determining the actual offset of the sheet after the punching process.

9. The vehicle plate offset detection production line is characterized by implementing the machine vision-based stamping process plate offset vision measurement method according to any one of claims 5 to 6.

10. An information data processing terminal characterized by implementing the steps of:

shooting a picture at the shooting position of the calibration scale in the stamping die, and calculating the actual single-pixel precision of shooting according to the size of the calibration scale in the picture;

counting the state of the sheet at the accurate position of the model die during stamping as a comparison reference, calculating and recording the position of the sheet edge in the picture, and setting the position as a reference position; taking a first mode of equipment operation as a calibration image, extracting a reference edge of a region to be detected by adopting an edge extraction algorithm, and storing a row value and a column value of a reference line starting point;

after a high-precision matrix camera of the shooting module receives a trigger signal of die opening and closing of a machine tool, shooting a sheet picture in a production process according to the trigger signal, recording the position of the edge of the sheet in the picture at the moment, comparing the position with a reference position, calculating the offset of the sheet relative to the reference position at the moment, multiplying the offset by the single-pixel precision obtained by calculation, and determining the actual offset of the sheet after the punching process.

Background

At present, the stamping process is a metal processing method, which is based on metal plastic deformation, and utilizes a die and stamping equipment to apply pressure to a plate material so as to enable the plate material to generate plastic deformation or separation, thereby obtaining a part with certain shape, size and performance. The press forming process plays an important role in the manufacturing process of automobile bodies, and particularly, large-sized covering parts of automobile bodies are very efficient to manufacture by the press processing method because most of the covering parts have complicated shapes and large structural sizes, some of the covering parts are also spatial curved surfaces, and the requirements on surface quality are high.

The stamping process can be divided into four basic processes:

1) blanking: and the stamping process (including punching, blanking, trimming, cutting, etc.) for separating the plate materials is realized.

2) Bending: and a stamping process of bending the sheet material into a certain angle and shape along the bending line.

3) Drawing: and (3) a stamping process for changing the plane plate into various open hollow parts or further changing the shape and the size of the hollow parts.

4) Fine blanking: and (3) punching products with higher precision, and achieving the process required by the drawing through a fine punching die for the products with high requirements on size and surface light quantity.

The bending process can cause large deformation of the stamped sheet, which requires a high degree of matching between the stamping die and the sheet. In the die repairing and production processes, the deviation condition of the plate material during each stamping is detected at any time, and the analysis of the working state of the bending process is facilitated, so that the machining error and the potential hidden danger can be found in time.

Through the above analysis, the problems and defects of the prior art are as follows:

(1) in the prior art, a visual detection system cannot effectively acquire picture information required by offset detection of sheet materials before and after stamping, so that processing errors and potential hidden dangers cannot be found in time.

(2) The mechanical movement in the prior art has complex structural design, potential risks and high equipment maintenance cost.

(3) The prior art vision detection system can finish shooting only by continuously stopping the original punching production line, thereby influencing the production efficiency.

(4) The prior art can not detect the offset distance of a remote material sheet, and the detection can not be carried out after a production line is replaced, so that the practicability is limited.

The difficulty in solving the above problems and defects is: due to the influence of field tools, if an image acquisition unit cannot be placed around the working time of a large-scale punching machine, image acquisition can only be carried out at a distance of 3m, and proper cameras and lenses in the image acquisition device are selected with great difficulty. The equipment requires miniaturization treatment, the selection of the light source of the 3m far lighting device is difficult, and the miniaturization of the equipment is difficult because the power required for illuminating the plate part from 3m far exceeds 100w of the light source and the heat dissipation of the light source has great requirements. When the material sheet shifts, a calibration process is needed, and the calibration reference image influences the detection precision of the subsequent sheet shift, so that the selection of a proper reference image is difficult.

The significance of solving the problems and the defects is as follows: the problem of difficulty in remote monitoring of the offset of the sheet material in the stamping industry is solved, the offset is counted, the production process can be guided reversely, and the production process is optimized. The miniature equipment is convenient to erect; the reproducibility is strong, the detection can be still realized after the production line is replaced, and the popularity is higher.

Disclosure of Invention

In order to overcome the problems in the related art, the disclosed embodiment of the invention provides a stamping process sheet metal offset vision measurement system and a measurement method based on machine vision. Still relate to image processing technical field such as optical design system, camera integrated design and sheet material edge extraction, technical scheme is as follows:

according to a first aspect of the disclosed embodiments of the present invention, there is provided a machine vision-based stamping process sheet metal offset vision measurement system, comprising:

the shooting unit is used for shooting images of the edges of the sheet materials in the stamping production line;

the control unit is mainly used for controlling the PLC control unit, is connected with the shooting unit and is used for controlling a light source switch (controlling the on and off of a light source), a shooting angle and lens focusing in the image shooting of the shooting unit;

the data processing unit is connected with the control unit and the shooting unit and used for storing the images acquired by the shooting unit, processing the images and sending image detection results or transmitting information;

and the algorithm identification unit is connected with the data processing unit and is used for detecting and calibrating the image processed by the data processing unit to obtain the actual offset of the sheet material in the stamping process.

In an embodiment of the present invention, the photographing unit includes: the high-precision matrix camera comprises a shooting module consisting of a high-precision matrix camera and a lens, and a high-brightness light-gathering light source module;

the high-precision matrix camera adopts a large-size camera target surface and a high-frame-rate camera with high pixels;

the lens group adopts a 25mm FA lens;

the high-brightness light-gathering light source module adopts a 100W light-gathering LED industrial long-throw light source;

the visual field range of the shooting module which is 3m away from the plate to be detected is 1m multiplied by 1 m.

In an embodiment of the present invention, the control unit includes a light source control mechanism, a shooting angle control mechanism, and a lens focusing control mechanism;

the light source control mechanism is used for controlling the on and off of the light source outside the production line;

the shooting angle control mechanism is used for controlling the direction and the angle movement of the shooting unit outside the production line so as to align the edge part of the target plate;

the lens focusing mechanism is used for realizing the focusing of the camera lens outside the production line.

In one embodiment of the invention, the data processing unit comprises an industrial personal computer and a switch;

the industrial personal computer and the switch are used for being connected with the high-precision matrix camera, the control unit and the PLC of the shooting module respectively.

According to a second aspect of the disclosed embodiments of the present invention, there is provided a machine vision-based method for visually measuring offset of a stamping process sheet material, comprising:

shooting a picture at the shooting position of the calibration scale in the stamping die, and calculating the actual single-pixel precision of shooting according to the size of the calibration scale in the picture;

counting the state of the sheet at the accurate position of the model die during stamping as a comparison reference, calculating and recording the position of the sheet edge in the picture, and setting the position as a reference position; taking a first mode of equipment operation as a calibration image, extracting a reference edge of a region to be detected by adopting an edge extraction algorithm, and storing a row value and a column value of a reference line starting point;

after a high-precision matrix camera of the shooting module receives a trigger signal of die opening and closing of a machine tool, shooting a sheet picture in a production process according to the trigger signal, recording the position of the edge of the sheet in the picture at the moment, comparing the position with a reference position, calculating the offset of the sheet relative to the reference position at the moment, multiplying the offset by the single-pixel precision obtained by calculation, and determining the actual offset of the sheet after the punching process.

Actual offset (mm) ═ single pixel precision (mm/pix) × sheet material offset (pix) from the reference;

the known single-pixel precision is 0.1953mm/pix, and the offset of the plate relative to the reference is 200 pix;

the actual offset is 0.1953mm/pix × 200pix 39.06 mm.

In an embodiment of the present invention, the method for calculating the single-pixel precision includes:

single pixel accuracy (mm/pix) is one directional field size (mm)/camera directional resolution (pix).

The field unidirectional view field size is known to be 1m, and the unidirectional resolution of the camera is 5120 pix;

single pixel precision 1000mm/5120pix 0.1953mm/pix

According to a third aspect of the disclosed embodiments of the present invention, there is provided a program storage medium for receiving user input, the stored computer program causing an electronic device to execute the machine vision based stamping process sheet offset visual measurement method.

According to a fourth aspect of the disclosed embodiments of the present invention, there is provided a computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:

the stamping process sheet metal offset visual measurement method based on machine vision comprises the following steps:

shooting a picture at the shooting position of the calibration scale in the stamping die, and calculating the actual single-pixel precision of shooting according to the size of the calibration scale in the picture;

counting the state of the sheet at the accurate position of the model die during stamping as a comparison reference, calculating and recording the position of the sheet edge in the picture, and setting the position as a reference position; taking a first mode of equipment operation as a calibration image, extracting a reference edge of a region to be detected by adopting an edge extraction algorithm, and storing a row value and a column value of a reference line starting point;

after a high-precision matrix camera of the shooting module receives a trigger signal of die opening and closing of a machine tool, shooting a sheet picture in a production process according to the trigger signal, recording the position of the edge of the sheet in the picture at the moment, comparing the position with a reference position, calculating the offset of the sheet relative to the reference position at the moment, multiplying the offset by the single-pixel precision obtained by calculation, and determining the actual offset of the sheet after the punching process.

According to a fifth aspect of the disclosed embodiment of the invention, a vehicle plate offset detection production line is provided, wherein the vehicle plate offset detection production line is equipped with the machine vision-based stamping process plate offset visual measurement system and implements the machine vision-based stamping process plate offset visual measurement method.

According to a sixth aspect of the disclosed embodiments of the present invention, there is provided an information data processing terminal that implements the steps of:

shooting a picture at the shooting position of the calibration scale in the stamping die, and calculating the actual single-pixel precision of shooting according to the size of the calibration scale in the picture;

counting the state of the sheet at the accurate position of the model die during stamping as a comparison reference, calculating and recording the position of the sheet edge in the picture, and setting the position as a reference position; taking a first mode of equipment operation as a calibration image, extracting a reference edge of a region to be detected by adopting an edge extraction algorithm, and storing a row value and a column value of a reference line starting point;

after a high-precision matrix camera of the shooting module receives a trigger signal of die opening and closing of a machine tool, shooting a sheet picture in a production process according to the trigger signal, recording the position of the edge of the sheet in the picture at the moment, comparing the position with a reference position, calculating the offset of the sheet relative to the reference position at the moment, multiplying the offset by the single-pixel precision obtained by calculation, and determining the actual offset of the sheet after the punching process.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

the device monitors the extension degree of the material sheets in the factory on the domestic known and famous vehicle enterprise stamping line, can reversely calculate the process problems in the production process of the material sheets according to the test result, saves the labor cost, has guiding and reference values for the production process, and eliminates potential hidden dangers.

The problem of in the punching press production technology personnel can not be close to producing the line, and can't halt and detect the offset is solved, the offset of the tablet of each mould of real time monitoring has been accomplished to this product, has solved the difficult problem that the industry can't real-time detection.

The reasonable type selection of the camera, the lens and the light source solves the problem of high precision of remote monitoring and solves the problem that the existing industry cannot be compatible with both remote and high precision simultaneously.

The detection object of the invention is the offset of the edge of the plate. The stamping process sheet metal offset vision measurement system based on machine vision comprises a shooting unit; a data processing unit; a control unit and an algorithm identification unit. The technical scheme disclosed by the invention saves labor, reduces labor intensity, and maintains cost and potential risk; the shooting precision and the detection speed are improved, enterprises are helped to count the offset of the plate, and the method has guidance and reference values on the production and processing technology; the reverse direction of the production process is convenient to guide, and potential hidden dangers are eliminated.

The effects and advantages obtained by combining experimental or experimental data with the prior art are:

at present, the detection equipment for the irrelevant plate deviation in the industry has the advantages that:

the visual detection system can effectively acquire picture information required by offset detection of the sheet materials before and after stamping;

the solution of the invention uses a structural design with less mechanical movements than the solutions described in the other patents, thus reducing the potential risks and the maintenance costs of the equipment.

When the visual detection system is implemented, the original stamping production line is not required to be interrupted, and only the production line PLC sends out a shooting signal, so that shooting can be automatically completed.

When the visual detection system is implemented, automatic picture acquisition is completed without influencing the production rhythm of the original stamping production line.

The invention realizes the detection of the offset distance of the long-distance (3m far) material sheet, and is convenient to erect; the reproducibility is strong, the detection can be still realized after the production line is replaced, and the popularity is higher.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

FIG. 1 is a drawing of a sheet metal offset vision measurement system for a stamping process based on machine vision according to an embodiment of the present invention.

In the figure: 1. a shooting unit; 2. a control unit; 2-1, a light source control mechanism; 2-2, a shooting angle control mechanism; 2-3, a lens focusing control mechanism; 3. a data processing unit; 4. and an algorithm identification unit.

Fig. 2 is a flowchart of a sheet metal offset visual measurement method of a stamping process based on machine vision according to an embodiment of the present invention.

Fig. 3 is a diagram of an image effect acquired by each module after the camera receives the trigger signal according to the embodiment of the present invention.

Fig. 4 is a diagram illustrating a result of determining an actual offset of the sheet after the stamping process according to the embodiment of the present invention.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

As shown in fig. 1, a machine vision-based stamping process sheet metal offset visual measurement system provided by the disclosed embodiment of the present invention includes:

the device comprises a shooting unit 1, a control unit 2, a data processing unit 3 and an algorithm identification unit 4.

The photographing unit 1 includes: a shooting module consisting of a high-precision matrix camera and a lens, and a special high-brightness light-gathering light source module.

The control unit 2 comprises a light source control mechanism 2-1, a shooting angle control mechanism 2-2 and a lens focusing control mechanism 2-3;

the light source control mechanism 2-1 is used for controlling the on and off of the light source outside the production line;

the shooting angle control mechanism 2-2 is used for controlling the direction and the angle movement of the shooting unit outside the production line so as to align the edge part of the target plate;

and the lens focusing mechanism 2-3 is used for realizing the focusing of the camera lens outside the production line. The shooting direction can be adjusted, focusing and light source switching operation can be realized without an operator entering a stamping production line. The production line is prevented from pausing, and the potential safety hazard that personnel enter the production line operation is eliminated.

The data processing unit 3 comprises an industrial personal computer, a switch and other equipment.

The industrial personal computer, equipment such as switch are used for linking to each other with the high accuracy matrix camera, the control unit 2 and the PLC controller of shooting the module respectively, store the image that high accuracy matrix camera gathered and handle the image, control the bright and the bright of light source and send the PLC controller or carry out the transmission of information etc. with image detection result.

And the algorithm identification unit 4 is used for implementing calibration and real-time detection.

The technical solution of the present invention is further described with reference to the following specific examples.

Examples

In one embodiment of the present invention, a photographing unit includes: a shooting module consisting of a high-precision matrix camera and a lens, and a special high-brightness light-gathering light source module.

According to the camera imaging principle: determining a visual field range (FOV) and a Working Distance (WD) to be reached, and calculating a focal length (f) of the industrial lens according to the FOV and the Working Distance (WD), wherein the calculation formula is as follows:

focal length f ═ WD × target surface size h/FOV (H or V)

Field range HF ═ WD × target surface size (h)/focal length f

FOV (H or V) of field of view (H or V) is the target surface size (h)/optical magnification

Working distance WD ═ f (focal length) × target surface size (h)/FOV (H or V)

Optical magnification ═ target surface size (h)/fov (h or v).

Determining a working distance WD according to the maximum opening and closing distance of a stamping die and the position of a plate in the die, determining the working distance WD of a camera to be 3m away from the edge of a material sheet, and determining the shooting angle of the camera according to the edge position of the size of the die, wherein the shooting angle can be adjusted by an angle adjusting device; for the visual field range HF, HF is larger than the width d of the plate, and the visual field range HF is set to be 1000mm multiplied by 1000 mm; selecting the focal length f of the lens, wherein f is the working distance WD multiplied by the target surface size (h)/the visual field range HF of the camera, and converting according to a formula to obtain the focal length f of the lens of 25mm through calculation; the control unit realizes remote control focusing; considering that the stamped sheet is usually metal with a smooth surface, the shooting position is far away from a processing production line, and half of industrial light sources cannot meet the requirements, a high-brightness light source with good light condensation is selected to polish the edge and the nearby position of the sheet along the view of a camera; A100W light-gathering far-projecting light source is selected.

According to the industrial field condition, the field environment and the distance requirement, the working distance of a shooting module from the edge of a material sheet is 3m, the requirement of the detection range of the visual field of a mold to be detected is 1m multiplied by 1m, the detection precision is less than 0.7mm/pix, as smooth metal needs to be shot at a far object distance (>2 m), and general industrial diffused light cannot be met, a projection light source with large power light beam collection is determined after an experiment, a large-size camera target surface and a high-frame-rate camera with high pixels are selected according to the precision and the visual field requirement of a client, and the camera is selected to be a 2000 ten thousand USB3.0 black-and-white industrial camera according to the detection requirement; the lens is a 25mmFA lens, the light source is a 100W light-gathering LED industrial long-projection light source, and the 3 m-far visual field range is 1m multiplied by 1 m.

The comprehensive model selection is a shooting module consisting of a high-precision 2000-ten-thousand matrix camera and a 25mm FA lens, and a special 100W high-brightness light-gathering light source module.

In an embodiment of the present invention, the algorithm identification unit includes a calibration step and a detection step.

As shown in fig. 2, a method for visually measuring the sheet metal offset in a stamping process based on machine vision is provided, which includes:

s101, shooting a picture at the shooting position of a calibration scale in a stamping die, and calculating the actual single-pixel precision of shooting according to the size of the calibration scale in the picture;

s102, counting the state of the sheet at the accurate position of the model die during stamping as a comparison reference, calculating and recording the position of the sheet edge in the picture, and setting the position as a reference position; taking a first mode of equipment operation as a calibration image, extracting a reference edge of a region to be detected by adopting an edge extraction algorithm, and storing a row value and a column value of a reference line starting point;

s103, after receiving a trigger signal of die opening and closing of the machine tool, a high-precision matrix camera of the shooting module shoots a sheet picture in a production process according to the trigger signal, records the position of the edge of the sheet in the picture at the moment, compares the position with a reference position, calculates the offset of the sheet relative to the reference position at the moment, multiplies the offset by the single-pixel precision obtained by calculation, and determines the actual offset of the sheet after the punching process at the moment.

In a preferred embodiment, step S101, the single-pixel accuracy (mm/pix) is the unidirectional view field size (mm)/camera unidirectional resolution (pix).

In step S102 in a preferred embodiment, after receiving a trigger signal for opening and closing the dies of the machine tool, a high-precision matrix camera of the shooting module shoots a sheet material picture in a production process according to the trigger signal, where fig. 3 is an image effect picture acquired by each die after the camera receives the trigger signal.

In step S103 in a preferred embodiment, the position of the edge of the sheet material in the picture at this time is recorded, the picture selected by the client is used as a reference picture, the edge of the material sheet of the picture to be measured is extracted, the edge feature point is found according to the reference, and the edge offset is calculated by multiplying the edge feature point by the single-pixel precision, so as to determine whether there is a material edge offset phenomenon. The actual offset of the plate after the stamping can be determined. As shown in fig. 4, the result is the detection result. And (3) extracting the edge of the material piece of the picture to be detected by using the picture selected by the client as a reference picture, multiplying the edge by the single-pixel precision to calculate the edge offset, and judging whether the material edge offset phenomenon exists or not. Such as: and calculating the average value of the offset pixels of the picture to be measured according to the first line and the second line as the reference, wherein the average value of the offset pixels is 18.527pix, and the offset is 18.527(pix) multiplied by 0.34(mm/pix) which is 6.12 mm. And checking the picture, and judging that the algorithm works normally corresponding to the actual size calibration.

In a preferred embodiment of the present invention, an area Image1 may be framed in the punch working first die Image as a reference area; and during the subsequent stamping process, a certain die Image2 can be monitored in real time during the working of the stamping machine; moreover, the image of the mark point can be found according to the reference image; performing later data processing by comparing the offset of the reference point in Image1 and Image 2; after the comparison processing, 6.12mm is the offset. And (4) detecting the value of each mould in real time, and alarming if the value exceeds 5mm according to the requirements of customers, so that the real-time detection can be realized.

In a preferred embodiment of the present invention, the algorithm processing flow provided by the present invention is:

(1) if the image is the first-mode image, the ROI area is the ROI area which is manually taken by a field operator in an animation mode, and for the non-first-mode image, the ROI area of the image is extended from the reference of the first-mode image. And subsequently, carrying out algorithm processing on the images, wherein each mode image is consistent in the algorithm processing process.

(2) Screening by using a self-adaptive threshold value, and drawing out the area to be detected at the edge of the material sheet by matching with the expansion corrosion of the area;

(3) extracting Canny edges of the regions, namely extracting positions to be detected of the edges of the material sheets;

(4) dividing the edge line of the material sheet along the line value and column value areas of the image to obtain characteristic points, and comparing the offset of the characteristic points of the first mold and the real-time mold to obtain whether the offset of the material sheet exceeds the standard or not.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure should be limited only by the attached claims.