A visual-based steel plate shearing judgment method

Abstract

The application discloses a kind of steel plate shearing judgment methods based on vision, comprising the following steps: S1, a high-definition camera is arranged at the outlet side of lower shear blade of shearing machine, a plurality of characteristic points are processed on lower shear blade, and the high-definition camera is connected with the PLC of shearing machine;S2, calibration program, after high-definition camera is in position, the working environment of the outlet side of shearing machine is photographed and calibrated, and the calibration photo is obtained;S3, after steel plate shearing operation is completed, the upper shear blade of shearing machine returns to original position, the working environment after shearing operation is photographed by high-definition camera, and the post-operation photo is obtained, and it is compared with calibration photo, whether steel plate is sheared according to comparison result is judged.The application can not only effectively avoid the equipment and process accidents caused by the fact that steel plate is not sheared, but also facilitate subsequent implementation of unmanned, intelligent and automatic improvement of shearing machine by judging the shearing state of steel plate in real time after shearing is completed.

Description

Technical Field

[0001] This invention relates to shearing technology in the metallurgical industry, and more specifically, to a vision-based method for judging the cutting of steel plates. Background Technology

[0002] Conventional shearing machines apply shearing force to steel plates by using the relative movement of a moving upper blade and a fixed lower blade. However, after the upper blade retracts, the shearing force automatically returns to zero, making it impossible to determine whether the steel plate has been cut. Currently, operators visually assess whether the plate has been cut, requiring at least one operator per machine. If an operator discovers that the steel plate has not been cut, they must stop further operations and address the issue on-site. However, if the operator fails to notice the uncut plate and continues operations, it can lead to equipment and process accidents. Because the current reliance on manual judgment to determine whether the steel plate has been cut makes fully automated, unmanned, and intelligent shearing lines impossible. This issue has become one of the bottlenecks in improving the intelligent automation of shearing lines.

[0003] Currently, no relevant technology for judging the shearing state during steel plate shearing has been found in the field of steel plate shearing. However, some methods for detecting the shearing state exist in other fields. For example, a paper published in the Journal of Xi'an Jiaotong University on January 1, 2015, by Tao Yichun, Jia Shuhai, Duan Yugang, Zhang Xiaohui, Chen Hualing, et al., discusses a rapid detection method for the shearing state of carbon fiber composite filaments. To address the problem of accurately and effectively identifying the shearing state of carbon fiber filaments in confined spaces, this paper proposes a method for detecting the shearing state of carbon fiber filaments based on electrical signals and designs corresponding hardware and software systems for shearing state monitoring. This detection method first uses a simple detection circuit and data acquisition card to achieve real-time acquisition of electrical signals during the shearing process of carbon fiber filaments. Then, the acquired signals are low-pass filtered to obtain the voltage... By comparing the peak value of the signal with a set detection threshold, the cutting status of the carbon fiber tow can be effectively identified. Experimental results show that during the cutting operation, the resistance of the incompletely cut carbon fiber tow is 10-500Ω, while the resistance of the completely cut tow is infinite. Connecting the tow to the detection circuit, the change in resistance reflects the voltage change between the two electrodes. In the experiment, when completely cut, the voltage across the tow jumps sharply from 0V to 4.37703V, which is greater than the set threshold, while when incompletely cut, the voltage jumps slightly from 0V to 0.06797V, which is less than the set threshold of 1V. Both can effectively identify the cutting state, proving that the detection results of this method are relatively accurate. This method can detect in the narrow space inside the fiber laying head and can quickly identify the cutting status of the carbon fiber tow. The above technology uses real-time acquisition of electrical signals to detect resistance to determine whether it has been cut, but this is not possible with steel plates, as the shearing machines for steel plates are made of iron, and the steel plates are also made of iron, making detection impossible.

[0004] In view of the above, there is an urgent need to develop a method to determine whether the steel plate has been cut during the steel plate shearing process, so as to avoid equipment and process accidents caused by the steel plate not being cut in time, and facilitate subsequent unmanned, intelligent and automated improvements to the shearing machine. Summary of the Invention

[0005] In view of the above-mentioned defects in the existing technology, the purpose of this invention is to provide a vision-based steel plate shearing judgment method. By judging the shearing state of the steel plate after shearing in real time, it can not only effectively avoid equipment and process accidents caused by the steel plate not being sheared, but also facilitate subsequent unmanned, intelligent and automated improvements to the shearing machine.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A vision-based method for determining steel plate cutting edge includes the following steps:

[0008] S1, A high-definition camera is installed on the exit side of the lower shear blade of the shearing machine, multiple feature points are processed on the lower shear blade, and a communication connection is established between the high-definition camera and the PLC of the shearing machine;

[0009] S2, Calibration procedure: The working environment at the outlet side of the shearing machine is photographed and calibrated using the high-definition camera to obtain calibration photos;

[0010] S3, after the steel plate shearing operation is completed, the upper shear blade of the shearing machine returns to its original position, the high-definition camera takes a picture of the working environment after the shearing operation to obtain a post-operation photo, and compares it with the calibration photo to determine whether the steel plate has been cut based on the comparison result.

[0011] Preferably, in step S1, the plurality of feature points cover the entire working area of ​​the lower shear blade exit side.

[0012] Preferably, in step S1, the feature point is a pit or a through hole.

[0013] Preferably, in step S2, the calibration photograph obtained by the calibration program is stored as a calibration film in the PLC of the shearing machine.

[0014] Preferably, the calibration procedure in step S2 is started after the shear blade of the shearing machine is replaced or is manually forced to start.

[0015] Preferably, the calibration program in step S2 starts automatically after several steel plates have been cut.

[0016] Preferably, in step S3, the specific process of determining whether the steel plate has been cut is as follows:

[0017] In the comparison results, if one or more feature points in the post-operation photo are obscured, an alarm is issued indicating that the steel plate has not been cut, and the PLC immediately stops subsequent operation instructions, waiting for manual processing and reset; if none of the feature points in the post-operation photo are obscured, a steel plate cutting signal is issued, and the PLC executes subsequent operation instructions normally.

[0018] The present invention provides a vision-based steel plate cutting judgment method, which realizes real-time judgment of whether the steel plate has been cut after cutting, with an accuracy rate of 99.99%. It can not only effectively avoid equipment and process accidents caused by failure to cut, but also eliminate the need for maintenance of faulty equipment, and facilitate the unmanned and intelligent improvement of the shearing machine. Attached Figure Description

[0019] Figure 1 This is a field schematic diagram of the vision-based steel plate shearing judgment method of the present invention;

[0020] Figure 2This is a schematic diagram of an uncut steel plate in the vision-based steel plate cutting judgment method of the present invention;

[0021] Figure 3 This is a flowchart illustrating the vision-based steel plate shearing judgment method of the present invention. Detailed Implementation

[0022] To better understand the above-mentioned technical solutions of the present invention, the technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0023] Combination Figure 3 As shown, the present invention provides a vision-based steel plate cutting judgment method, the purpose of which is to solve the problem of automatically judging whether the steel plate has been cut after the steel plate is cut, thereby effectively avoiding equipment and process accidents caused by human error in not detecting that the steel plate has not been cut.

[0024] Combination Figure 3 As shown, the present invention provides a vision-based method for determining steel plate cutting, comprising the following steps:

[0025] S1, a high-definition camera 14 is installed on the exit side of the lower shear blade 12 of the shearing machine, multiple feature points 13 are processed on the lower shear blade 12, and a communication connection is established between the high-definition camera 14 and the PLC of the shearing machine.

[0026] Combination Figure 1 As shown, a high-definition camera 14 is installed on the exit side of the lower shear blade 12 of the shearing machine. Specifically, the high-definition camera 14 is installed on the exit side of the blade holder of the lower shear blade 12. Then, multiple feature points 13 are processed below the shear blade working area on the exit side of the blade holder of the lower shear blade 12. In a specific embodiment, the multiple feature points 13 cover the entire shear blade working area on the exit side of the lower shear blade 12. The feature points 13 can be processed into pits or through holes. At the same time, a communication connection is established between the high-definition camera 14 and the PLC of the shearing machine.

[0027] S2, Calibration Procedure: After the high-definition camera 14 is in place, it takes pictures of the working environment on the outlet side of the shearing machine for calibration, and obtains calibration photos.

[0028] Combination Figure 3 As shown, once the high-definition camera 14 is in place, it takes pictures of the working environment at the outlet side of the shearing machine to obtain calibration photos. This operation is used as a calibration program, and the calibration photos are saved as negatives in the calibration program of the shearing machine PLC. This facilitates the automatic start of the calibration program later, or the calibration program can be manually forced to run.

[0029] In a specific embodiment, the calibration program can start automatically after cutting a number of steel plates. For example, after cutting 20 steel plates (the specific number of steel plates can be adjusted arbitrarily according to the actual situation), the calibration program will start automatically and replace the retained film. The calibration program can also be started after the shearing blade of the shearing machine is replaced, or manually forced to start, or for other reasons.

[0030] S3. After the steel plate shearing operation is completed, the upper shear blade 11 of the shearing machine returns to its original position. The high-definition camera 14 takes a picture of the working environment after the shearing operation to obtain a picture of the operation, and compares it with the calibration picture. Based on the comparison result, it is determined whether the steel plate has been cut.

[0031] Combination Figure 3 As shown, if the PLC does not receive a shearing command, the shearing machine enters a waiting state; if the PLC receives a shearing command, it simultaneously sends it to the shearing machine to perform the shearing operation. After the steel plate shearing operation is completed, the upper shear blade 11 of the shearing machine returns to its original position. At this time, the PLC sends a command to the high-definition camera 14, which takes pictures of the working environment after the shearing operation to obtain a post-operation photo. The post-operation photo is then compared with the calibration photo in step S2, with a key comparison of the feature points 13 on the lower shear blade 12. Based on the comparison results, it is determined whether the steel plate has been sheared. Figure 3 As shown, the high-definition camera 14 is in a waiting state when the steel plate shearing operation is not completed.

[0032] Combination Figure 3 As shown, the specific process for determining whether the steel plate has been cut is as follows: In the comparison results, if one or more feature points 13 are obscured in the post-operation photo (see... Figure 2 As shown, if some feature points 13 are obscured by uncut steel plates 21, an alarm for uncut steel plates is issued. Upon receiving the alarm, the PLC immediately stops subsequent operations and waits for manual reset. If, after the operation, feature points 13 are not obscured in the photograph (see...), the PLC will immediately stop subsequent operations and wait for manual reset. Figure 1 As shown, if no feature point 13 is obscured and only the cut steel plate 15 remains on the lower shear blade 13, a steel plate cutting signal is issued, and the PLC executes subsequent operation instructions normally.

[0033] Those skilled in the art should recognize that the above embodiments are merely illustrative of the present invention and are not intended to limit the present invention. Any variations or modifications to the above embodiments that are within the spirit and essence of the present invention will fall within the scope of the claims of the present invention.

Claims

1. A vision-based method for determining steel plate cutting, characterized in that, Includes the following steps: S1, A high-definition camera is installed on the exit side of the lower shear blade of the shearing machine, multiple feature points are processed on the lower shear blade, and a communication connection is established between the high-definition camera and the PLC of the shearing machine; S2, Calibration procedure: The high-definition camera takes pictures of the working environment at the outlet side of the shearing machine for calibration, and obtains calibration photos; S3, after the steel plate shearing operation is completed, the upper shear blade of the shearing machine returns to its original position, the high-definition camera takes a picture of the working environment after the shearing operation to obtain a post-operation photo, and compares it with the calibration photo to determine whether the steel plate has been cut based on the comparison result.

2. The vision-based steel plate shearing judgment method according to claim 1, characterized in that, In step S1, the plurality of feature points cover the entire working area of ​​the lower shear blade exit side.

3. The vision-based steel plate shearing judgment method according to claim 2, characterized in that, In step S1, the feature point is a pit or a through hole.

4. The vision-based steel plate shearing judgment method according to claim 1, characterized in that, In step S2, the calibration photograph obtained by the calibration program is stored as a calibration film in the PLC of the shearing machine.

5. The vision-based steel plate shearing judgment method according to claim 1, characterized in that, The calibration procedure in step S2 is started after the shear blade of the shearing machine is replaced or is manually forced to start.

6. The vision-based steel plate shearing judgment method according to claim 1, characterized in that, The calibration program in step S2 starts automatically after several steel plates have been cut.

7. The vision-based steel plate shearing judgment method according to claim 1, characterized in that, In step S3, the specific process of determining whether the steel plate has been cut is as follows: In the comparison results, if one or more feature points in the post-operation photo are obscured, an alarm is issued indicating that the steel plate has not been cut, and the PLC immediately stops subsequent operation instructions, waiting for manual processing and reset; if none of the feature points in the post-operation photo are obscured, a steel plate cutting signal is issued, and the PLC executes subsequent operation instructions normally.

Images