An intelligent position positioning device based on visual detection

Abstract

The present invention provides an intelligent position positioning device based on visual detection, which belongs to the field of industrial processing technology. It includes an overall control system and a truss. At least two groups of positioning components are arranged on one side of the truss. The positioning component includes a servo-driven translation module installed on the truss. A three-dimensional intelligent camera and an electromagnetic magnetic suction cup are installed at the power output end of the servo-driven translation module. The three-dimensional intelligent camera and the electromagnetic magnetic suction cup are communicatively connected to the overall control system. The beneficial effect of the present invention is that it can accurately position the workpiece transported on the roller conveyor system to ensure that the magnetic suction cup in the loading truss system can still accurately complete the loading operation of the workpiece under complex and changeable working conditions, thereby ensuring production safety.

Description

Technical Field

[0001] The invention belongs to the technical field of industrial processing, and in particular relates to an intelligent position positioning device based on visual detection. Background Art

[0002] One of the significant challenges in the batch automated welding of side panels used on mining machinery and equipment is the wide variety of workpiece types and sizes. These workpieces, ranging from lightweight small components to bulky large plates, each have their own unique geometry and specification requirements, making the positioning structure of the entire production equipment particularly complex. In addition, since pre-welded workpieces inevitably have manufacturing errors of the workpieces themselves and thermal deformation that may occur during welding, these accumulated errors will further increase the difficulty of accurately positioning the workpieces on the roller conveyor system.

[0003] Therefore, in the actual production process of the side plates used in mining machinery and equipment, it is easy to cause different degrees of deviation between the actual position of the workpiece and the theoretical design position due to the above-mentioned workpiece differences and deformation errors, thereby affecting the workpiece transfer and loading actions implemented by the loading device. In particular, the loading truss system that relies on magnetic suction cups for contactless loading, the magnetic suction cups set up must be accurately aligned with the preset lifting points on the surface of the workpiece. Once the position is offset, not only can the workpiece be effectively adsorbed and the predetermined loading action be completed, but it may also cause safety accidents such as workpiece slippage and collision due to uneven magnetic distribution or improper adsorption position, which seriously threatens the operation safety and equipment integrity of the production site.

[0004] Based on this, there is an urgent need for a device that can accurately position the workpiece transported on the roller conveyor system to ensure that the magnetic suction cup in the loading truss system can still accurately complete the loading operation of the workpiece under complex and changeable working conditions, thereby ensuring production safety. Summary of the invention

[0005] The technical problem solved by the present invention is to provide an intelligent positioning device based on visual detection, and enable it to accurately position the workpiece transported on the roller conveyor system, so as to ensure that the magnetic suction cup in the loading truss system can still accurately complete the loading operation of the workpiece under complex and changeable working conditions, thereby ensuring production safety.

[0006] In order to solve the above technical problems, the technical solution provided by the present invention is: an intelligent position positioning device based on visual detection, which includes an overall control system and a truss, at least two groups of positioning components are arranged on one side of the truss, and the positioning component includes a servo-driven translation module installed on the truss, and a three-dimensional intelligent camera and an electromagnetic magnetic suction cup are installed at the power output end of the servo-driven translation module, and the three-dimensional intelligent camera and the electromagnetic magnetic suction cup are communicatively connected to the overall control system; and when the electromagnetic magnetic suction cup adsorbs the workpiece, the overall control system first controls the three-dimensional intelligent camera and the electromagnetic magnetic suction cup in the positioning component to move to the set position, and then controls the three-dimensional intelligent camera in the positioning component to take pictures and identify the corresponding area on the workpiece, and According to the captured image, the three-dimensional point cloud data of the workpiece in the shooting area is obtained; then, according to the acquired three-dimensional point cloud data, it is judged whether there is an excitable area in the shooting area this time; if there is an excitable area, firstly, the distance between the electromagnetic magnetic suction cup and the excitable area in the positioning component is obtained according to the acquired three-dimensional point cloud data, and then the servo drive translation module is controlled to move the electromagnetic magnetic suction cup to the excitable area, and the electromagnetic magnetic suction cup is controlled to excite and adsorb the workpiece; if there is no excitable area, firstly, the three-dimensional intelligent camera and the electromagnetic magnetic suction cup in the positioning component are controlled to move according to the set bias value, and then the three-dimensional intelligent camera is controlled to take pictures and identify the corresponding area on the workpiece, and it is judged whether there is an excitable area in the shooting area according to the captured image. In this way, since the present invention uses a three-dimensional intelligent camera for auxiliary identification, it can accurately identify and locate the adsorption part on the workpiece, thereby ensuring that the upper electromagnetic magnetic suction cup can accurately complete the loading operation of the workpiece under complex and changeable working conditions, thereby ensuring production safety.

[0007] Furthermore, the electromagnetic magnetic suction cup is communicated with an alarm component, which is communicated with the overall control system. When the positioning component still fails to identify the excitation area after a set number of offset adjustments, the alarm component sends an alarm prompt to the overall control system, and the overall control system controls the alarm to send an alarm signal to remind the staff to perform manual intervention operations.

[0008] Furthermore, when determining whether there is an excitable area in the shooting area by judging the captured image, the three-dimensional intelligent camera first obtains the three-dimensional model data of the electromagnetic magnetic suction cup, and then calibrates the size of the electromagnetic magnetic suction cup mapped to the obstacle-free plane according to the three-dimensional model data of the electromagnetic magnetic suction cup, and sets the mapped size as a reference value; then, it is determined whether there is a continuous flat plane with a size equal to or greater than the reference value in the shooting area of ​​the workpiece. If there is a continuous flat plane with a size equal to or greater than the reference value, there is an excitable area; if there is no continuous flat plane with a size equal to or greater than the reference value, there is no excitable area.

[0009] Furthermore, when there is no excitable area in the area photographed by the 3D smart camera, the 3D smart camera first compares the acquired 3D point cloud data with the reference value, obtains the comparison result of the 3D point cloud data of the workpiece in the photographing area and the reference value, and then transmits the comparison result to the overall control system. The overall control system controls the display screen to display the received comparison result according to the comparison result, so as to inform the staff why there is no excitable area.

[0010] Furthermore, when the 3D smart camera photographs a workpiece, the 3D smart camera first projects light onto the surface of the workpiece, then photographs the distortion of the reflected light, and calculates the 3D shape of the workpiece based on the distortion angle of the reflected light.

[0011] Furthermore, when the 3D smart camera photographs a workpiece, the 3D smart camera first emits light to the surface of the workpiece, then measures the round-trip time of the light, and calculates the distance between the workpiece and the 3D smart camera and the depth of the workpiece based on the round-trip time of the light.

[0012] Furthermore, when the 3D smart camera photographs a workpiece, the 3D smart camera first projects a speckle pattern onto the workpiece surface, then photographs changes in the speckle pattern, and calculates the 3D deformation of the workpiece based on the changes in the speckle pattern.

[0013] Furthermore, the servo-driven translation module includes a driving screw, both ends of which are rotatably mounted on the lower end of the truss through bearing seats, one end of the driving screw is transmission-connected to a servo motor, the middle part of the driving screw is threadedly connected to a slide, the upper part of the slide is horizontally slidably mounted on the truss, the lower part of the slide is equipped with a corresponding three-dimensional smart camera and an electromagnetic magnetic suction cup, and can slide along the axial direction of the driving screw under the action of the driving screw to achieve the purpose of flexibly adjusting its own position.

[0014] Furthermore, two groups of positioning components are arranged on the lower side of the truss, and the two groups of positioning components are arranged symmetrically to make the structure of the entire device compact.

[0015] Furthermore, the electromagnetic magnetic suction cup is arranged on the bottom surface of the slide, and the three-dimensional smart camera is arranged on a side of the slide away from another group of positioning components. In this way, through the above layout, it is possible to avoid the electromagnetic magnetic suction cup from affecting the shooting range of the three-dimensional smart camera.

[0016] It can be seen from the above technical scheme that the present invention has the following advantages: the present invention can accurately identify and locate the adsorption position on the workpiece, thereby ensuring that the upper electromagnetic magnetic suction cup can accurately complete the loading operation of the workpiece under complex and changeable working conditions, thereby ensuring production safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 It is a structural schematic diagram of a specific embodiment of the present invention;

[0019] Figure 2 is a side view of the positioning assembly in the present invention;

[0020] Figure 3 It is the front view of the positioning component in the present invention.

[0021] In the figure: 1. Truss; 2. Driving screw; 3. Servo motor; 4. Slide; 5. 3D smart camera; 6. Electromagnetic magnetic suction cup. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] like Figure 1 As shown, the present invention provides an intelligent position positioning device based on visual detection, which includes an overall control system and a truss 1. Among them, two or more groups of positioning components are symmetrically arranged on one side of the truss 1, and the positioning component includes a servo-driven translation module installed on the truss 1, and the servo-driven translation module includes a driving screw 2, and the two ends of the driving screw 2 are rotatably installed on the lower end of the truss 1 through a bearing seat, and one end of the driving screw 2 is connected to a servo motor 3 in a transmission manner, and the middle part of the driving screw 2 is threadedly connected to a slide 4, and the upper part of the slide 4 is horizontally slidably installed on the truss 1, and the lower part of the slide 4 is installed with a corresponding three-dimensional smart camera 5 and an electromagnetic magnetic suction cup 6, and the three-dimensional smart camera 5 and the electromagnetic magnetic suction cup 6 are communicatively connected to the overall control system, and the electromagnetic magnetic suction cup 6 is preferably arranged on the bottom surface of the slide 4, and the three-dimensional smart camera 5 is preferably arranged on the side of the slide 4 away from another group of positioning components, so that through the above-mentioned layout, it can avoid the electromagnetic magnetic suction cup 6 from affecting the shooting range of the three-dimensional smart camera 5.

[0024] At this time, when the electromagnetic magnetic suction cup 6 absorbs the workpiece, the overall control system first controls the 3D smart camera 5 and the electromagnetic magnetic suction cup 6 in the positioning component to move to the set position, and then controls the 3D smart camera 5 in the positioning component to take pictures and identify the corresponding area on the workpiece, and obtains the 3D point cloud data of the workpiece in the shooting area according to the photographed image, and in the simulation process of the point cloud data, it can use the least squares principle to calibrate the scanned simulated point cloud, set the real plane as the reference plane, simulate and fit the scanned point cloud, filter the noise points to generate the plane; then judge according to the acquired 3D point cloud data It is determined whether there is an excitable area in the shooting area this time. If there is an excitable area, first obtain the distance between the electromagnetic magnetic suction cup 6 in the positioning component and the excitable area according to the obtained three-dimensional point cloud data, then control the servo drive translation module to move the electromagnetic magnetic suction cup 6 to the excitable area, and control the electromagnetic magnetic suction cup 6 to excite and adsorb the workpiece; if there is no excitable area, first control the three-dimensional smart camera 5 and the electromagnetic magnetic suction cup 6 in the positioning component to move according to the set offset value, then control the three-dimensional smart camera 5 to take pictures and identify the corresponding area on the workpiece, and judge whether there is an excitable area in the shooting area according to the captured image. And as a preferred embodiment, the electromagnetic magnetic suction cup 6 in the present invention is connected to an alarm component in communication, and the alarm component is connected to the overall control system in communication, and when the positioning component still fails to identify the excitation area after the set offset adjustment times, the alarm component can send an alarm prompt to the overall control system, and the overall control system controls the alarm to send an alarm signal to remind the staff to perform manual intervention operations.

[0025] In addition, specifically, when judging whether there is an excitable area in the shooting area by judging whether the image is taken, the three-dimensional smart camera 5 first obtains the three-dimensional model data of the electromagnetic magnetic suction cup 6, and then calibrates the size of the electromagnetic magnetic suction cup 6 mapped to the obstacle-free plane according to the three-dimensional model data of the electromagnetic magnetic suction cup 6, and sets the mapped size as the reference value; then judges whether there is a continuous flat plane with a size equal to or greater than the reference value in the shooting area of ​​the workpiece, if there is a continuous flat plane with a size equal to or greater than the reference value, there is an excitable area; if there is no continuous flat plane with a size equal to or greater than the reference value, there is no excitable area. And as a preferred embodiment, when there is no excitable area in the shooting area of ​​the three-dimensional smart camera 5, the three-dimensional smart camera 5 can first compare the obtained three-dimensional point cloud data with the reference value, obtain the comparison result of the three-dimensional point cloud data of the workpiece at the shooting area and the reference value, and then transmit the comparison result to the overall control system, and then the overall control system controls the display screen to display the received comparison result according to the comparison result, so as to inform the staff of the reason why there is no excitable area, such as the hand is too close to the workpiece, there is a risk of misdetection for collision avoidance, etc.

[0026] When the three-dimensional smart camera 5 photographs the workpiece, on the one hand, the three-dimensional smart camera 5 can first project a specific pattern of light onto the surface of the workpiece, and then photograph the distortion of the reflected light, and calculate the three-dimensional shape of the workpiece based on the triangulation principle and the distortion angle of the reflected light; on the other hand, the three-dimensional smart camera 5 can first emit infrared light or laser to the surface of the workpiece, and then measure the round-trip time of the light, and calculate the distance between the workpiece and the three-dimensional smart camera 5 and the depth of the workpiece based on the round-trip time of the light; at the same time, the three-dimensional smart camera 5 can also first project a speckle pattern onto the surface of the workpiece, and then photograph the change of the speckle, and calculate the three-dimensional deformation of the workpiece based on the change of the speckle; and photograph the workpiece from different angles through two or more three-dimensional smart cameras 5, and then calculate the parallax and depth of the workpiece by matching the feature points between different three-dimensional smart cameras 5; first scan the surface of the workpiece through a laser line, and then photograph the deformation of the laser line through the three-dimensional smart camera 5 to calculate the three-dimensional contour of the workpiece.

[0027] In this way, when the present invention is applied to the actual production operation of the side panels or other components used on mining machinery and equipment, the present invention can accurately identify and locate the adsorption position on the workpiece, thereby ensuring that the upper electromagnetic magnetic suction cup 6 can accurately complete the loading operation of the workpiece under complex and changeable working conditions, thereby ensuring production safety.

[0028] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0029] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent position positioning device based on visual detection, characterized in that: The invention comprises an overall control system and a truss, wherein at least two groups of positioning components are arranged on one side of the truss, wherein the positioning component comprises a servo-driven translation module installed on the truss, wherein a three-dimensional intelligent camera and an electromagnetic magnetic suction cup are installed on the power output end of the servo-driven translation module, wherein the three-dimensional intelligent camera and the electromagnetic magnetic suction cup are communicatively connected to the overall control system; and when the electromagnetic magnetic suction cup adsorbs the workpiece, the overall control system first controls the three-dimensional intelligent camera and the electromagnetic magnetic suction cup in the positioning component to move to the set position, and then controls the three-dimensional intelligent camera in the positioning component to take a picture of the corresponding area on the workpiece for recognition The 3D point cloud data of the workpiece in the shooting area is obtained according to the captured image; then, it is determined whether there is an excitable area in the shooting area according to the acquired 3D point cloud data. If there is an excitable area, the distance between the electromagnetic magnetic suction cup in the positioning component and the excitable area is first obtained according to the acquired 3D point cloud data, and then the servo drive translation module is controlled to move the electromagnetic magnetic suction cup to the excitable area, and the electromagnetic magnetic suction cup is controlled to excite and adsorb the workpiece; if there is no excitable area, the 3D smart camera and the electromagnetic magnetic suction cup in the positioning component are first controlled to move according to the set offset value, and then The three-dimensional intelligent camera is controlled to take photos and identify the corresponding area on the workpiece, and determine whether there is an excitable area in the shooting area according to the captured image; when determining whether there is an excitable area in the shooting area according to the captured image, the three-dimensional intelligent camera first obtains the three-dimensional model data of the electromagnetic magnetic suction cup, and then calibrates the size of the electromagnetic magnetic suction cup mapped to the barrier-free plane according to the three-dimensional model data of the electromagnetic magnetic suction cup, and sets the mapped size as the reference value; then it is determined whether there is a continuous flat plane with a size equal to or greater than the reference value in the shooting area of ​​the workpiece, if there is a continuous flat plane with a size equal to or greater than the reference value, there is an excitable area; if there is no continuous flat plane with a size equal to or greater than the reference value, there is no excitable area; when there is no excitable area in the shooting area of ​​the three-dimensional intelligent camera, the three-dimensional intelligent camera first compares the acquired three-dimensional point cloud data with the reference value, obtains the comparison result of the three-dimensional point cloud data of the workpiece at the shooting area and the reference value, and then transmits the comparison result to the overall control system, and the overall control system controls the display screen to display the received comparison result according to the comparison result, so as to inform the staff of the reason why there is no excitable area; When the 3D smart camera shoots the workpiece, the 3D smart camera first projects light onto the surface of the workpiece, then shoots the distortion of the reflected light, and calculates the 3D shape of the workpiece according to the distortion angle of the reflected light; when the 3D smart camera shoots the workpiece, the 3D smart camera first emits light onto the surface of the workpiece, then measures the round-trip time of the light, and calculates the distance between the workpiece and the 3D smart camera and the depth of the workpiece according to the round-trip time of the light; when the 3D smart camera shoots the workpiece, the 3D smart camera first projects a speckle pattern onto the surface of the workpiece, then shoots the change of the speckle, and calculates the 3D deformation of the workpiece according to the change of the speckle; the servo-driven translation module includes a driving screw, both ends of the driving screw are rotatably mounted on the lower end of the truss through a bearing seat, one end of the driving screw is transmission-connected with a servo motor, the middle part of the driving screw is threadedly connected with a slide, the upper part of the slide is horizontally slidably mounted on the truss, and the lower part of the slide is mounted with a corresponding 3D smart camera and an electromagnetic magnetic suction cup.

2. The intelligent position positioning device based on visual detection according to claim 1 is characterized in that: The electromagnetic magnetic suction cup is communicated with an alarm component, which is communicated with the overall control system. When the positioning component still fails to identify the excitation area after a set number of offset adjustments, the alarm component sends an alarm prompt to the overall control system, and the overall control system controls the alarm to send an alarm signal.

3. The intelligent position positioning device based on visual detection according to claim 1 is characterized in that: Two groups of positioning components are arranged on the lower side of the truss, and the two groups of positioning components are arranged symmetrically.

4. The intelligent position positioning device based on visual detection according to claim 3 is characterized in that: The electromagnetic magnetic suction cup is arranged on the bottom surface of the slide, and the three-dimensional intelligent camera is arranged on a side of the slide away from another group of positioning components.

Images