Control method and system for welding seam adaptive positioning device

Abstract

A control method for a welding seam adaptive positioning device, comprising: step S1), constructing a visual sensor apparatus on the basis of a point laser sensor, a line laser sensor and a depth camera; step S2), installing the visual sensor apparatus at the tail end of a robot, and forming a fixed position relation between the visual sensor apparatus and a welding gun; step S3), acquiring data of the visual sensor apparatus, performing three-dimensional coordinate conversion on the data to acquire an actual welding seam position, and calculating an absolute deviation between the actual welding seam position and a designed welding seam position to obtain a data compensation value; step S4), performing positioning compensation control according to the data compensation value; and step S5), in the welding seam positioning process, performing adaptive deviation compensation in real time. According to the method, by constructing the welding seam adaptive positioning device that integrates multiple sensors such as the point laser sensor, the line laser sensor and the depth camera, adaptive positioning and compensation control of simple and complex welding seams are realized. Also provided is a control system for a welding seam adaptive positioning device.

Description

A control method and system for welding seam adaptive positioning equipment Technical Field

[0001] The present invention relates to the technical field of shipbuilding, and in particular to a control method and system for weld seam adaptive positioning equipment based on a visual sensor. Background Art

[0002] Weld types can be simply divided into straight welds and arc welds. Straight welds are the more common weld type in welding production in major shipyards, while arc welds are the more complex weld type, which is manifested in the diverse forms of processes and connecting plates and the more complex types. At present, with the increase in labor costs, production and manufacturing are developing towards automated and intelligent methods, and the use of robots is becoming more and more common. At the same time, the execution of welding work is more inclined to do more verification in the design to achieve efficient execution of on-site work. In this case, the error between design and reality is particularly important. At this time, how to eliminate or reduce this error affects the efficiency and quality of the entire welding operation. Therefore, the adaptive positioning compensation technology of the on-site robot welding process can significantly reduce this error.

[0003] At present, the starting point positioning function of welding operations has high requirements for the characteristics of the weld. Generally, the connecting plates that constitute the weld are required to have a simple structure and a single form. Both plates are required to be large flat surfaces with no ribs or large cut angles. This makes the positioning function of arc welds incapable of meeting the requirements. In addition, there are also high requirements for the placement accuracy of the workpiece on site, which reduces the efficiency of the welding operation and affects the beat. Some positioning technologies rely heavily on point laser positioning, which will result in the point laser being unable to detect the plate when the spliced ​​plate is narrow, making the positioning function impossible. Therefore, in the existing technology, there is an urgent need for an adaptive positioning equipment control method and system based on the fusion of multiple sensors.

[0004] Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for controlling weld seam adaptive positioning equipment based on a visual sensor, so as to solve the technical problem that the current welding process lacks adaptive positioning compensation, resulting in large welding errors.

[0006] In order to achieve the above object, the technical solution of the present invention is:

[0007] A method for controlling a weld seam adaptive positioning device comprises the following steps:

[0008] Step S1) constructing a visual sensor device based on a point laser sensor, a line laser sensor and a depth camera;

[0009] Step S2) installing the visual sensor device on the end of the robot to form a fixed position relationship with the welding gun;

[0010] Step S3) collecting data from the visual sensor device and performing three-dimensional coordinate conversion on the data to obtain the actual weld position, and calculating the absolute deviation between the actual weld position and the designed weld position to obtain a data compensation value;

[0011] Step S4) performing positioning compensation control according to the data compensation value;

[0012] Step S5) During the weld seam positioning process, adaptive deviation compensation is performed in real time.

[0013] Furthermore, in the visual sensor device constructed in step S1, the point laser sensor is responsible for collecting the distance from the two plates forming the weld to the point laser; the line laser sensor is responsible for collecting point cloud data of the two plates of the workpiece; and the depth camera is responsible for collecting RGB image data and depth information of the workpiece, which are used to identify the type of the workpiece and determine the weld structure and position.

[0014] Furthermore, in step S2, the point laser sensor, the line laser sensor and the depth camera are installed in a customized structure at the end of the robot, forming a fixed positional relationship with the welding gun, and the mirrors of the point laser sensor, the line laser sensor and the depth camera are on the same plane, and the positions of the point laser sensor, the line laser sensor and the depth camera are evenly distributed on a circle centered on the axis of the end of the robot.

[0015] Furthermore, step S3 includes:

[0016] Step S31) collecting data from the point laser sensor, line laser sensor and depth sensor in the visual sensor device;

[0017] Step S32) setting a robot posture transformation rule to transform the posture of the visual sensor device at the end of the robot;

[0018] Step S33), converting the collected data of the visual sensor device into coordinates in the world system, and performing data mutation detection on the processed data;

[0019] Step S34) Calculate the absolute deviation between the actual weld position and the designed weld position, and obtain a data compensation value for data compensation.

[0020] Furthermore, in step S31, the initial safety point position and posture of the welding gun are determined according to the preset weld data, so that the robot has sufficient posture transformation space under the posture change with the welding wire as the origin. At this time, data from the point laser sensor, line laser sensor, and depth camera are collected; wherein, the preset weld data includes the three-dimensional coordinates of the starting point and the end point of the straight weld, and the three-dimensional coordinates of the starting point, the midpoint, and the end point of the circular arc weld.

[0021] Furthermore, in step S32, the posture transformation of the welding wire at the end of the robot is controlled by setting the robot posture transformation rule, and data from the point laser sensor, line laser sensor and depth camera are collected in real time; the robot posture transformation rule is defined as the posture transformation of the robot in the tool coordinate system with the welding wire as the end point; the rule is defined as a figure enclosed by the Z-axis XY plane ray of the end point and the XY plane, including a point-shaped posture transformation that rotates around the Z axis at a small angle around the welding wire point, a conical posture transformation that opens at a small angle to the Z axis, a square posture transformation, a rectangular posture transformation, and a straight-line posture transformation.

[0022] Furthermore, in step S33, the collected distance data, image data and depth point cloud data are converted into coordinates in the world system through coordinate conversion; the distance set data with time series characteristics is calculated based on the characteristics and composition of the weld, and the data mutation position is detected using the discrete data smoothness judgment method; the RGB image and depth information are combined to determine whether the mutation position is a weld and the starting point of the weld.

[0023] Furthermore, in step S4, the positioning compensation control according to the data compensation value includes linear fitting and curve fitting of the actual weld, and comparing them with the preset weld data to obtain parameter compensation of the fitting function.

[0024] Furthermore, the step S5 includes collecting data and calculating deviations in real time during the weld positioning process, building a feedback link through the calculated deviations, and adaptively adjusting the robot positioning deviation in real time to perform adaptive deviation compensation.

[0025] The present application also provides a weld adaptive positioning equipment control system, which adopts the weld adaptive positioning equipment control method described above to control the weld adaptive positioning equipment; the weld adaptive positioning equipment includes a robot and a visual sensor device installed at the end of the robot, and the visual sensor device includes a point laser sensor, a line laser sensor and a depth camera.

[0026] The present application provides a control method and system for a weld adaptive positioning device, which realizes adaptive positioning and compensation control of simple and complex welds by constructing a weld adaptive positioning device that fuses multiple sensors such as point laser sensors, line laser sensors and depth cameras. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] FIG1 is a diagram showing an application environment of a control method for a weld seam adaptive positioning device according to an embodiment of the present application;

[0028] FIG2 is a flow chart of a method for controlling a weld seam adaptive positioning device according to an embodiment of the present application;

[0029] FIG3 is a schematic diagram of the installation position of the visual sensor device according to an embodiment of the present application;

[0030] FIG4 is a flow chart of the steps of collecting data from a visual sensor device and performing three-dimensional coordinate conversion on the data, obtaining the actual weld position, and calculating the absolute deviation between the actual weld position and the designed weld position to obtain a data compensation value in an embodiment of the present application;

[0031] FIG5 is a schematic diagram of a sudden change in collected data of a visual sensor device according to an embodiment of the present application;

[0032] FIG6 is a schematic diagram of weld compensation in a weld adaptive positioning device control method according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0034] The present application provides a control method for a weld seam adaptive positioning device, which can be applied in the application environment shown in FIG1 .

[0035] As shown in FIG2 , the present application provides a method for controlling a weld seam adaptive positioning device, comprising the following steps:

[0036] Step S1) constructing a visual sensor device based on a point laser sensor, a line laser sensor and a depth camera;

[0037] Step S2) installing the visual sensor device on the end of the robot to form a fixed position relationship with the welding gun;

[0038] Step S3) collecting data from the visual sensor device and performing three-dimensional coordinate conversion on the data to obtain the actual weld position, and calculating the absolute deviation between the actual weld position and the designed weld position to obtain a data compensation value;

[0039] Step S4) performing positioning compensation control according to the data compensation value;

[0040] Step S5) During the weld seam positioning process, adaptive deviation compensation is performed in real time.

[0041] Furthermore, in the visual sensor device constructed in step S1, the point laser sensor is responsible for collecting the distance from the two plates forming the weld to the point laser; the line laser sensor is responsible for collecting point cloud data of the two plates of the workpiece; and the depth camera is responsible for collecting RGB image data and depth information of the workpiece, which are used to identify the type of the workpiece and determine the weld structure and position.

[0042] As shown in Figure 3, in step S2, the point laser sensor, line laser sensor and depth camera are installed in the customized structure at the end of the robot, forming a fixed positional relationship with the welding gun, and the mirrors of the point laser sensor, line laser sensor and depth camera are on the same plane, and the positions of the point laser sensor, line laser sensor and depth camera are evenly distributed on a circle centered on the axis of the end of the robot.

[0043] As shown in Figure 3, the point laser sensor, line laser sensor, and depth camera form a 120-degree angle around the robot module. A simple and quick method exists to convert the relative positions and postures of the sensors.

[0044] As shown in FIG4 , step S3 includes:

[0045] Step S31) collecting data from the point laser sensor, line laser sensor and depth sensor in the visual sensor device;

[0046] Step S32) setting a robot posture transformation rule to transform the posture of the visual sensor device at the end of the robot;

[0047] Step S33), converting the collected data of the visual sensor device into coordinates in the world system, and performing data mutation detection on the processed data;

[0048] Step S34) Calculate the absolute deviation between the actual weld position and the designed weld position, and obtain a data compensation value for data compensation.

[0049] Figure 5 illustrates the data mutation detection performed on the processed data in step S33. The waveform of the distance data collected by the point laser during scanning of the two panels clearly shows that at a certain angle at the robot end, the distance value undergoes a mutation, causing the derivatives of the data on both sides to have different signs. Based on the discrete mathematical derivative formula, delta (height) / delta (angle) in the direction of the angle change, the robot's posture at the time of the mutation can be clearly calculated. Furthermore, based on geometric relationships, the 3D coordinates of that point can be calculated.

[0050] As shown in FIG6 , in step S34 , the absolute deviation between the actual weld position and the designed weld position is calculated and data compensation is performed. According to the spatial geometric linear equation in the three-dimensional coordinate system, it can be known that:

[0051] Where x0, y0, z0 represent the coordinates of a point on the line, a, b, c represent the direction vector of the line in space, then a point x, y, z on the line in space can be expressed as the above equation; where when a=0, b≠0, c≠0, the equation is: x-x0=0 and When a=0, b=0, c≠0, the equation can be understood as the equation system consisting of: x-x0=0 and y-y0=0; the same applies to other cases.

[0052] By solving the straight line equation under the design system and performing straight line fitting based on the scanned weld point data, the actual straight line equation is obtained, and analytical compensation is performed for each weld point by compensating the equation parameters.

[0053] Furthermore, in step S31, the initial safety point position and posture of the welding gun are determined according to the preset weld data, so that the robot has sufficient posture transformation space under the posture change with the welding wire as the origin. At this time, data from the point laser sensor, line laser sensor, and depth camera are collected; wherein, the preset weld data includes the three-dimensional coordinates of the starting point and the end point of the straight weld, and the three-dimensional coordinates of the starting point, the midpoint, and the end point of the circular arc weld.

[0054] Furthermore, in step S32, the robot's posture transformation rules are set to control the posture transformation of the welding wire at the end of the robot, and data from the point laser sensor, line laser sensor, and depth camera are collected in real time. The robot's posture transformation rules are defined as the robot's posture transformation in the tool coordinate system with the welding wire as the end point. As shown in Figure 6, the rules are defined as the graph formed by the Z-axis ray of the end point and the XY plane, including point-shaped posture transformations (rotating around the Z axis at a small angle around the welding wire point), conical posture transformations (opening at a small angle to the Z axis), square posture transformations, rectangular posture transformations, and linear posture transformations. The data collected under this rule can adapt to all weld types, including straight welds, arc welds, and so on.

[0055] Furthermore, in step S33, the collected distance data, image data and depth point cloud data are converted into coordinates in the world system through coordinate conversion; the distance set data with time series characteristics is calculated based on the characteristics and composition of the weld, and the data mutation position is detected using the discrete data smoothness judgment method; the RGB image and depth information are combined to determine whether the mutation position is a weld and the starting point of the weld.

[0056] Furthermore, in step S4, the positioning compensation control according to the data compensation value includes linear fitting and curve fitting of the actual weld, and comparing them with the preset weld data to obtain parameter compensation of the fitting function.

[0057] Furthermore, step S5 includes real-time data collection and deviation calculation during weld positioning, building a feedback link by calculating the deviation, and adaptively adjusting the robot positioning deviation in real time to perform adaptive deviation compensation, thereby achieving high-precision, fast response and anti-interference positioning.

[0058] The present application also provides a weld adaptive positioning equipment control system, which adopts the weld adaptive positioning equipment control method described above to control the weld adaptive positioning equipment; the weld adaptive positioning equipment includes a robot and a visual sensor device installed at the end of the robot, and the visual sensor device includes a point laser sensor, a line laser sensor and a depth camera.

[0059] The present application provides a control method and system for a weld adaptive positioning device, which realizes adaptive positioning and compensation control of simple and complex welds by constructing a weld adaptive positioning device that fuses multiple sensors such as point laser sensors, line laser sensors and depth cameras.

[0060] The advantages of the present invention are: by constructing a multi-sensor fusion technology architecture based on point laser sensors, line laser sensors and depth vision, and then designing posture transformation rules to convert the collected data into the world coordinate system, and finally calculating the actual position of the weld by calculating the data mutation point, performing position calculation, deviation compensation and tracking, thereby improving the automatic positioning accuracy and recognition of the welding process and improving the efficiency of the welding task; using the weld adaptive positioning equipment control method based on visual sensors, the adaptive positioning process of the equipment welding process is realized.

[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for a weld seam adaptive positioning device, characterized in that: The following steps are involved: Step S1) constructing a visual sensor device based on a point laser sensor, a line laser sensor and a depth camera; Step S2) installing the visual sensor device at the end of the robot to form a fixed position relationship with the welding gun; Step S3) collecting data from the visual sensor device and performing three-dimensional coordinate conversion of the data to obtain the actual weld position, and calculating the absolute deviation between the actual weld position and the designed weld position to obtain a data compensation value; Step S4) performing positioning compensation control according to the data compensation value; Step S5) During the weld seam positioning process, adaptive deviation compensation is performed in real time.

2. The weld seam adaptive positioning device control method according to claim 1, characterized in that: In the visual sensor device constructed in step S1, the point laser sensor is responsible for collecting the distance from the two plates forming the weld to the point laser; the line laser sensor is responsible for collecting the point cloud data of the two plates of the workpiece; the depth camera is responsible for collecting the RGB image data and depth information of the workpiece, which are used to identify the type of the workpiece and determine the weld structure and position.

3. The weld seam adaptive positioning device control method according to claim 1, characterized in that: In step S2, the point laser sensor, the line laser sensor and the depth camera are installed in a customized structure at the end of the robot to form a fixed position relationship with the welding gun, and the mirrors of the point laser sensor, the line laser sensor and the depth camera are on the same plane, and the positions of the point laser sensor, the line laser sensor and the depth camera are evenly distributed on a circle centered on the axis of the end of the robot.

4. The control method of weld seam adaptive positioning equipment according to claim 1, characterized in that: The step S3 comprises: Step S31) collecting data of the point laser sensor, line laser sensor and depth sensor in the visual sensor device; Step S32) setting a robot posture transformation rule to transform the posture of the visual sensor device at the end of the robot; Step S33) converting the collected data of the visual sensor device into coordinates in the world system through coordinates, and performing data mutation detection on the processed data; Step S34) Calculate the absolute deviation between the actual weld position and the designed weld position, and obtain the data compensation value for data compensation.

5. The control method of weld seam adaptive positioning equipment according to claim 4, characterized in that: In the step S31, the initial safety point position and posture of the welding gun are determined according to the preset weld data, so that the robot has sufficient posture change space under the posture change with the welding wire as the origin, and the data of the point laser sensor, the line laser sensor and the depth camera are collected at this time; Wherein, the preset weld data include the three-dimensional coordinates of the starting point and the end point of the straight weld, and the three-dimensional coordinates of the starting point, the midpoint and the end point of the arc weld.

6. The control method of weld seam adaptive positioning equipment according to claim 4, characterized in that: In the step S32, the posture transformation of the welding wire at the end of the robot is controlled by setting the robot posture transformation rule, and the data of the point laser sensor, the line laser sensor and the depth camera are collected in real time; the robot posture transformation rule is defined as the posture transformation of the robot in the tool coordinate system with the welding wire as the end point; the rule is defined as a figure enclosed by the Z-axis XY plane ray of the end point and the XY plane, including a point-shaped posture transformation rotating around the Z axis at a small angle around the welding wire point, a conical posture transformation opened at a small angle to the Z axis, a square posture transformation, a rectangular posture transformation, and a straight-line posture transformation.

7. The control method of weld seam adaptive positioning equipment according to claim 4, characterized in that: In the step S33, the collected distance data, image data and depth point cloud data are converted into coordinates in the world system through coordinate conversion; the distance set data with time series characteristics is calculated according to the characteristics and composition of the weld, and the data mutation position is detected by using the discrete data smoothness judgment method; the RGB image and depth information are combined to determine whether the mutation position is the weld and the starting point of the weld.

8. The control method of weld seam adaptive positioning equipment according to claim 1, characterized in that: In the step S4, the positioning compensation control according to the data compensation value includes straight line fitting and curve fitting of the actual weld, and comparing with the preset weld data to obtain parameter compensation of the fitting function.

9. The control method of weld seam adaptive positioning equipment according to claim 1, characterized in that: The step S5 includes collecting data and calculating deviations in real time during the weld positioning process, building a feedback link by calculating the deviations, and adaptively adjusting the robot positioning deviation in real time to perform adaptive deviation compensation.

10. A weld seam adaptive positioning equipment control system, characterized in that: The weld adaptive positioning equipment control system adopts the weld adaptive positioning equipment control method described in any one of claims 1 to 9 to control the weld adaptive positioning equipment; the weld adaptive positioning equipment includes a robot and a visual sensor device installed at the end of the robot, and the visual sensor device includes a point laser sensor, a line laser sensor and a depth camera.

Images