CN114833038A - Gluing path planning method and system - Google Patents

Abstract

The invention relates to a gluing path planning method and a system thereof, which comprises a machine vision system and a robot glue dispensing system, wherein the machine vision system acquires images of an object to be glued by using a camera, generates coordinate information of the object to be glued from the processed images, and finally sends the coordinate information to the robot glue dispensing system. According to the system scheme, the machine vision system is added to guide gluing on the basis of the traditional technical scheme, a software platform is developed by combining Vision Pro with C #, a function library and a tool library in Vision Pro are packaged in a software framework, a user can call corresponding functions only by clicking corresponding buttons, inconvenience caused by manual operation is reduced, and working efficiency is improved.

Description

A method and system for planning a gluing path

technical field

The invention relates to the technical field of gluing equipment, in particular to a gluing path planning method and a system thereof.

Background technique

Gluing is a key process in the production and processing of products, the purpose is to closely adhere the various parts of the product through glue. The glue application path planning is to plan a reasonable path according to the size of the object to be glued and the location of the components to assist the glue dispenser to complete the glue dispensing.

Gluing is mainly used in processes that require tight adhesion between product components. For example, there are various components distributed on the PCB board, and it is necessary to apply glue for screws and inductors for secondary tightening. This application is widely used in automobiles, electronics , military and other production fields. Because of the wide variety of products and the use of different paths for different product requirements, there are quite a lot of requirements for glue trajectory planning systems in the market.

The traditional glue application path planning requires specific implementation steps: ① Place the product on the carrier; ② The operator determines the position of each object to be glued on the product, and plans a reasonable path in advance; ③ The operator places each point on the path. The coordinates are input into the dispenser according to the previously planned order. ④ After the input is completed, the operator will adjust the coordinates slightly according to the test results. After confirming that it is correct, batch dispensing can be started.

The entire system of the traditional scheme is input point by point by manually operating the handle. Due to the variety of products, and the rapid replacement of products. On-site manual operations are required frequently, the traditional operation method is complex, professional personnel are required, and it takes a lot of time to maintain the new product path. Secondly, for the same type of product, when the position of the carrier changes, it is also necessary to manually reset the positions of the left and right gluing points, which consumes a lot of time and affects production efficiency.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a glue coating path planning method and a system thereof, so as to solve the problems encountered in the above-mentioned background technology.

For achieving the above object, technical scheme of the present invention is as follows:

A glue coating path planning method, comprising the following steps:

S1. Build a machine vision system and a robotic dispensing system;

S2. Use the machine vision system to calibrate the camera to establish the correspondence between the pixel coordinate system and the mechanical coordinate system;

S3. Use a machine vision system to collect images, and process the collected images to obtain the coordinates of the object to be glued;

S4. Import the coordinate information into the robot dispensing system, and the robot dispensing system performs the dispensing action according to the coordinate point information.

Preferably, in the above solution, there is a manual re-inspection process between steps S3 and S4. Manually check whether the coordinates of the object to be glued are correct, modify and improve the incorrect coordinate information, and then use the obtained coordinate information. Import into the robotic dispensing system.

A glue application path planning system includes a machine vision system and a robot glue dispensing system, wherein the machine vision system uses a camera to collect images of the object to be glued, and generates coordinate information of the object to be glued from the processed image, and finally The coordinate information is sent to the robotic dispensing system.

Preferably, in the above solution, manual re-inspection is required in sending the coordinate information to the robotic dispensing system.

Preferably, in the above solution, the machine vision system consists of a hardware part consisting of six cameras and a software platform jointly developed by VisionPro and C#, and uses stitching technology to process images, and the robot dispensing system consists of a robotic arm. And the equipped dispenser system.

Preferably, in the above solution, the machine vision system is equipped with a laser ranging sensor to detect the height of the camera from the surface of the carrier in real time, which is the basis for adjusting the height of the camera from the surface of the carrier.

Compared with the prior art, the beneficial effects of the present invention are: the system scheme adds a machine vision system to guide gluing on the basis of the traditional technical scheme, and uses VisionPro and C# to develop a software platform, which combines the function library in VisionPro and The tool library is encapsulated in the software framework, and the user only needs to click the corresponding button to call the corresponding function, which reduces the inconvenience caused by manual operation and improves the work efficiency. And this system solution is equipped with a laser ranging sensor on the machine vision system, which can detect the change in the height of the camera from the surface of the vehicle in real time, raise or lower the height of the camera according to the height, and always keep the height of the camera from the surface of the vehicle unchanged. , and always achieve the clearest imaging effect. At the same time, when the horizontal position of the vehicle changes, as long as it does not exceed the field of view of the camera, the camera can still detect the features of the glued object and generate coordinate information.

Description of drawings

The disclosure of the present invention is described with reference to the accompanying drawings. It should be understood that the accompanying drawings are for illustrative purposes only, and are not intended to limit the protection scope of the present invention. In the drawings, the same reference numerals are used to refer to the same parts. in:

FIG. 1 is a schematic diagram of the work flow of the present invention.

Detailed ways

In order to make the technical means, creative features, achieved objects and effects of the present invention easy to understand and understand, the present invention will now be described in further detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, and only illustrate the basic structure of the present invention in a schematic manner, so they only show the related structures of the present invention.

According to the technical solutions of the present invention, without changing the essential spirit of the present invention, those skilled in the art can propose various alternative structures and implementations. Therefore, the following specific embodiments and accompanying drawings are only exemplary descriptions of the technical solutions of the present invention, and should not be regarded as all of the present invention or as limitations or restrictions on the technical solutions of the present invention.

The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

Embodiment 1, as shown in Figure 1, a method for planning a gluing path, comprising the following steps:

S1. Build a machine vision system and a robot dispensing system. Compared with the traditional technical solution, the technical solution of this system is to add a machine vision system on the basis of the robot dispensing system, which can more intuitively present the results of the path planning to the user. before;

S2. Use the machine vision system to calibrate the camera to establish the correspondence between the pixel coordinate system and the mechanical coordinate system: In this machine vision system, the nine-point calibration method is used when calibrating the camera. In the calibration stage, use the robot to place the object in 9 positions under the camera's field of view, take pictures with the camera respectively, obtain the mechanical coordinates and pixel coordinates of the 9 points, and then calculate the difference between the pixel coordinates and the mechanical coordinates through the CogCalibNPointToNPointTool in VisionPro. Best fit 2D linear transformation, and then store the calculated 2D transformation results in the tool, and then the coordinates captured by the camera will automatically obtain the corresponding mechanical coordinates. After converting the pixel coordinates into mechanical coordinates, the robot dispensing system can directly use the coordinates sent from the camera to dispense glue, which greatly improves production efficiency.

S3, using a machine vision system for image acquisition. In this system scheme, the feature points of the objects to be glued, such as screws and inductors, are used to train the feature points using the CogPMAlignTool tool in VisionPro, and the CogPMAlignTool tool is used in image processing to calculate the feature quantities in the image, and get a score Exceeding a certain threshold can be regarded as finding feature points. After the camera is matched to the feature points, it locates the features to be found, and then uses the CogCreateCricleTool and CogCreateSegmentTool to locate the center of the feature point and the center of the line segment, so as to obtain the mechanical coordinates of these points.

S4. Before importing the coordinate information into the robot dispensing system, the machine vision system will sort the coordinates of the found feature points. The system will first sort the objects to be glued according to the category of the objects to be glued, and then sort the objects to be glued of the same type. Divide into groups, and then sort each group according to the X and Y coordinates of the objects to be glued. First, starting from the upper left corner of the image, divide the image into five equal parts with the Y axis, and then use X in each equal part. Sort the coordinates in ascending order, and so on, until all the coordinates in the five equal parts are arranged, and then generate a CSV file for the sorted coordinates and import it into the robot dispensing system, and the robot dispensing system points according to the coordinate point information. glue action. In this way, the sorted coordinates are imported into the robot dispensing system, and the path is planned reasonably, which greatly saves the time required for the robot dispensing and improves the production efficiency.

Embodiment 2, as shown in FIG. 1 , a method for planning a gluing path, comprising the following steps:

S1. Build a machine vision system and a robotic dispensing system. The machine vision system belongs to the control system. It consists of a hardware part composed of six cameras and a software platform developed by VisionPro and C#. The six cameras are 2*3 suspended on the module above the machine, and the lens is 600mm below. *500mm aperture surface light source, the camera and light source are installed on the module together to form the hardware part of the machine vision system. The camera is connected to the industrial computer next to the machine through a network cable, and the software platform jointly developed by VisionPro and C# is installed. On the industrial computer, control the camera for image acquisition and processing. And use stitching technology to process the image. The robotic dispensing system belongs to the actuator and consists of a manipulator and a mounted dispensing machine system.

The dispenser is mounted on the manipulator, and the two are regarded as one. When the control system imports the coordinate information obtained after image processing into the dispenser system, the manipulator will carry the dispenser to complete the click action.

S2. Using the machine vision system, the camera is calibrated to establish the correspondence between the pixel coordinate system and the mechanical coordinate system.

In this gluing path planning system, there are three coordinate systems: mechanical coordinate system, platform coordinate system and pixel coordinate system. The pixel coordinate system is a Cartesian coordinate system with the upper left corner of the image as the origin and the unit of pixel as the unit. The x and y axes respectively represent the number of rows and columns of the pixel in the digital image. In order to establish a unified coordinate in the machine vision system and determine the corresponding relationship between a contour point on the image and the actual graphic point, it is necessary to establish the coordinate conversion relationship between the pixel coordinate system and the mechanical coordinate system, the platform coordinate system and the mechanical coordinate system. , and finally unify the platform coordinates and pixel coordinates in the mechanical coordinate system. Therefore, the camera must be calibrated to establish the corresponding relationship between the pixel coordinates and the mechanical coordinates before the system extracts the tape gluing coordinates.

S3. Use a machine vision system to collect images, and process the collected images to obtain the coordinates of the object to be glued.

After receiving the photographing instruction, the camera will start to shoot images, which essentially converts optical signals into electrical signals, and then converts the electrical signals into digital signals after processing by the analog-to-digital conversion chip in the camera, and finally stores them in BMP format. In the computer, a frame of image is collected to the memory by calling the function library that comes with the capture card, and then echoed to the screen.

In image processing, take VisionPro as an example, open the captured image in BMP format in VisionPro, call the image processing tools in VisionPro, including learning and matching of feature points, and select the grayscale threshold to binarize and process the image. Refinement, calculate the feature quantity in the image, realize the output of spatial positioning and feature point coordinates.

S4. Manually check whether the coordinates of the object to be glued are correct, modify and improve the incorrect coordinate information, and then import the obtained coordinate information into the robot dispensing system.

After the image processing is completed, the coordinate information of the object to be glued is output, and the operator rechecks whether the point is correct, and performs additions, deletions and revisions to ensure accuracy. After confirmation, the system will generate a CSV file, and import the coordinate information of the glued object into the dispenser system to assist the dispenser to complete the dispensing.

S5. Import the coordinate information into the robot dispensing system, and the robot dispensing system performs the dispensing action according to the coordinate point information.

Compared with the traditional technical solution, the system is simpler to operate and can be used proficiently without professional training. In operation, only the machine vision system needs to take pictures and wait for the system to complete the calculation to generate a CSV file. However, the traditional technology requires professional training personnel to be skilled in operation, so the system has strong operability.

Embodiment 3, a glue application path planning system, including a machine vision system and a robot glue dispensing system, the machine vision system uses a camera to capture the image of the object to be glued, and generates the coordinates of the object to be glued from the processed image. information, and finally send the coordinate information to the robot dispensing system.

Preferably, in the above solution, manual re-inspection is required when the coordinate information is sent to the robotic dispensing system, and the coordinate information is correct through manual re-inspection.

Preferably, in the above solution, the machine vision system belongs to a control system, and consists of a hardware part consisting of six cameras and a software platform jointly developed by VisionPro and C#. Among them, VisionPro is mainly responsible for image processing, which belongs to the background algorithm and is invisible to the user, while C# uses its own encapsulation characteristics to encapsulate the tools in VisionPro into a series of interfaces or methods for calling, and finally interact with the software The form of the interface is presented in front of the user. For the user, who wants to plan the dispensing path, just click the run button on the software interface to get the planned file containing the coordinates of the glued object. The robotic dispensing system belongs to an executive mechanism and is composed of a manipulator and a mounted dispensing machine system.

The machine vision system is equipped with a laser ranging sensor, which is installed on the left side of the camera perpendicular to the plane of the machine, and is on the same horizontal line as the camera lens. It can detect the change in height between the camera and the surface of the carrier in real time, and raise or lower it according to the height. The height of the camera keeps the same height from the camera to the surface of the vehicle, so as to achieve the clearest imaging effect. At the same time, when the horizontal position of the vehicle changes, as long as it does not exceed the field of view of the camera, the camera can still detect the glued object. features and generate coordinate information.

In terms of image acquisition, the system uses the image stitching technology of six cameras to stitch together the images of six 20-megapixel cameras, and the pixels are superimposed together to form a 120-megapixel picture, which greatly improves the field of view and accuracy. Compared with the traditional technology, which relies on the human eye to compare the points, the accuracy is greatly improved, the product consistency is ensured, and the product quality is improved.

In terms of image processing, the coordinates of the glued object are obtained by binarizing the image, and the whole process can be realized in a few seconds. In image processing, this system includes learning and matching of feature points, selecting grayscale thresholds to binarize and refine the image, calculating the feature quantities in the image, and realizing spatial positioning and output of feature point coordinates. It takes a few seconds, a huge time saver.

This system solution adds machine vision system to guide gluing on the basis of the traditional technical solution, and uses VisionPro and C# to develop a software platform, which encapsulates the function library and tool library in VisionPro in the software framework, and the user only needs to click the corresponding button. The corresponding function can be called. This system solution can not only output the coordinates of the glued object as a CSV file, but also send it to the glue dispenser system in various forms, which is compatible with most glue dispensers on the market.

The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention and are not intended to limit the protection scope of the present invention. , any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (6)

1. a glue coating path planning method, is characterized in that, comprises the following steps: S1. Build a machine vision system and a robotic dispensing system; S2. Use the machine vision system to calibrate the camera to establish the correspondence between the pixel coordinate system and the mechanical coordinate system; S3. Use a machine vision system to collect images, and process the collected images to obtain the coordinates of the object to be glued; S4. Import the coordinate information into the robot dispensing system, and the robot dispensing system performs the dispensing action according to the coordinate point information. 2. A gluing path planning method according to claim 1, characterized in that: between steps S3 and S4, a manual re-inspection process is provided to check whether the coordinates of the object to be glued obtained by manual inspection are correct, and whether the coordinates of the object to be glued are correct. The coordinate information is modified and perfected, and then the obtained coordinate information is imported into the robot dispensing system. 3. A gluing path planning system, characterized in that it comprises a machine vision system and a robot dispensing system, and the machine vision system utilizes a camera to collect images of the object to be glued, and generates the object to be glued from the processed image. the coordinate information, and finally send the coordinate information to the robot dispensing system. 4 . The glue application path planning system according to claim 3 , wherein the sending of coordinate information to the robot glue dispensing system requires manual re-inspection. 5 . 5. a kind of gluing path planning system according to claim 3, is characterized in that: described machine vision system is formed by the hardware part of six cameras and the software platform by VisionPro joint C# secondary development, and adopts splicing The technology processes the image, and the robotic dispensing system consists of a manipulator and a mounted dispensing machine system. 6 . The method for planning a gluing path according to claim 3 , wherein a laser ranging sensor is mounted on the machine vision system to detect the height of the camera from the surface of the carrier in real time, so as to adjust the distance between the camera and the surface of the carrier. 7 . height as the basis.

Images