CN117300464A - Intersecting line weld detection and track optimization system and method based on structured light camera - Google Patents
Intersecting line weld detection and track optimization system and method based on structured light camera Download PDFInfo
- Publication number
- CN117300464A CN117300464A CN202311273384.XA CN202311273384A CN117300464A CN 117300464 A CN117300464 A CN 117300464A CN 202311273384 A CN202311273384 A CN 202311273384A CN 117300464 A CN117300464 A CN 117300464A
- Authority
- CN
- China
- Prior art keywords
- welding
- point cloud
- module
- structured light
- light camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005457 optimization Methods 0.000 title claims abstract description 29
- 238000003466 welding Methods 0.000 claims abstract description 206
- 238000012545 processing Methods 0.000 claims abstract description 25
- 230000033001 locomotion Effects 0.000 claims abstract description 20
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 230000003993 interaction Effects 0.000 claims abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 40
- 238000001914 filtration Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 239000011324 bead Substances 0.000 claims 2
- 238000005070 sampling Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
- B23K37/02—Carriages for supporting the welding or cutting element
- B23K37/0211—Carriages for supporting the welding or cutting element travelling on a guide member, e.g. rail, track
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1692—Calibration of manipulator
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Manipulator (AREA)
Abstract
The invention discloses an intersecting line weld detection and track optimization system and method based on a structured light camera, comprising an industrial personal computer, a welding robot, a welding machine and the structured light camera, wherein the industrial personal computer comprises a visual processing module, a motion control module and a user interface module; the visual processing module is used for executing welding seam detection and welding flow control according to the point cloud information of the welding workpiece acquired by the structured light camera; the motion control module is used for optimizing the weld track and controlling the motion of the welding robot; the user interface module provides a man-machine interaction mode and realizes parameter setting, result display and report generation. The welding robot is used for driving the welding gun to carry out welding operation; the welding machine is used for controlling the welding robot to execute a welding task, and the structured light camera is used for collecting images and point cloud information of a welding workpiece. The detection method is provided according to the self characteristics of the intersecting line weld, so that the method has universality and accuracy, and the welding quality is improved by optimizing and fusing the welding gun pose by the weld track.
Description
Technical Field
The invention belongs to the technical field of welding robots, and particularly relates to an intersecting line weld detection and track optimization system and method based on a structured light camera.
Background
The intersecting line welding seam is a common multi-layer plate welding mode, has the advantages of high strength, good shock resistance, high reliability and the like of a welding joint, and is widely applied to the fields of aviation, aerospace, automobiles, robots and the like. However, the detection and trajectory planning of the intersecting line weld of the pipe truss structure weldment based on the ideal mathematical model still is a challenging problem due to the influence of sensor noise and welding workpieces, and certain deviation occurs when the actual welding task is performed.
The traditional welding seam detection and tracking method mainly relies on manual visual detection and measurement, and has the problems of low efficiency, large error and the like. In recent years, with the development of 3D point cloud technology, a weld seam detection and tracking method based on 3D point cloud is receiving more and more attention. The 3D point cloud data of the welding line area is obtained by using equipment such as a structured light camera, and the like, and the steps of preprocessing, feature extraction, curve fitting and the like are carried out on the point cloud data, so that automatic detection and tracking of the welding line are realized. Compared with the traditional method, the method based on the 3D point cloud has the advantages of high detection precision, high detection efficiency, simplicity and convenience in operation and the like, and can greatly improve the welding production efficiency and quality.
However, 3D point cloud based intersecting line weld detection and trajectory optimization of pipe truss structure workpieces still present some challenges. For example, noise and interference of the point cloud data may lead to errors and instability of the recognition and tracking results; complex weld shapes and defects may require processing using complex algorithms and models; deformations and changes in the welding process can also have an impact on identification and tracking. Therefore, the development of the intersecting line welding detection and track optimization method based on the 3D point cloud has important research significance and application value.
According to the search, the invention of the related patent can not effectively solve the problems. For example:
the patent number with publication number of CN115741724A discloses a weld joint recognition and weld joint tracking system and method based on a 2D/3D camera, comprising an industrial personal computer, a welding robot, a welding machine, a 2D vision sensor, a 3D camera, an off-line programming system, a weld joint recognition and weld joint tracking software system, wherein the industrial personal computer is used for installing the weld joint recognition and weld joint tracking software system; the welding robot drives the welding gun to carry out welding operation; the welding machine controls the welding robot to execute a welding task; the off-line programming system is used for planning the welding seam and controlling the movement of the welding robot; the weld joint recognition and weld joint tracking software system is installed on the industrial personal computer and is responsible for flow control of the whole system. However, the invention only provides a system design for detecting the whole welding seam, does not describe a specific welding seam identification method, does not specifically identify an intersecting line welding seam, and does not generate a welding track for the generated welding seam characteristic points to optimize the welding track.
Disclosure of Invention
The invention provides a weld joint detection and track optimization system and method based on a structured light camera. The detection method and the track optimization method for complex welding seams and intersecting line welding seams are provided, the problems of low manual visual detection and measurement efficiency are solved, and the detection method provided according to the characteristics of the intersecting line welding seams is more universal and accurate. And the welding quality is improved by optimizing and fusing the welding seam track and the welding gun pose.
The aim of the invention is realized by the following technical scheme: in a first aspect, the present invention provides an intersecting line weld detection and trajectory optimization system based on a structured light camera, the system comprising: industrial computer, welding robot, welding machine and structured light camera, wherein:
the industrial personal computer is provided with a visual processing module, a motion control module and a user interface module; the visual processing module is used for executing welding seam detection and welding flow control according to the point cloud information of the welding workpiece acquired by the structured light camera; the motion control module is used for optimizing the weld track and controlling the motion of the welding robot; the user interface module provides a man-machine interaction mode to realize parameter setting, result display and report generation;
the welding robot is used for driving the welding gun to perform welding operation;
the welding machine is used for controlling the welding robot to execute a welding task and supplying power;
the structured light camera is divided into a structured light projection module and a camera acquisition module and is used for acquiring images and point cloud information of a welding workpiece.
Further, the structured light camera is mounted on one side of the welding gun through a clamp.
Further, the welding gun adopts an automatic welding gun, the structured light camera is fixed in the orthogonal direction of the clamp through the clamp, interference is prevented, and an anti-collision sensor is fixedly arranged at the bottom of the welding gun clamping gun.
Further, the vision processing module in the industrial personal computer comprises: a 3D point cloud registration module and a 3D point cloud weld detection module;
the 3D point cloud registration module is used for carrying out point cloud filtering, point cloud downsampling and point cloud registration processing on the point cloud information of the welding workpiece acquired by the structured light camera, and sending a processing result to the 3D point cloud welding seam detection module;
the 3D point cloud welding line detection module is used for detecting all welding lines according to the cross section characteristics and the contour characteristics of the welding lines after the 3D point cloud registration module reconstructs a complete three-dimensional model of the weldment, and sending the welding lines to the motion control module;
further, the motion control module in the industrial personal computer comprises: the welding seam track optimizing module and the control instruction module;
the welding seam track optimization module interpolates the welding seam according to the welding seam data detected by the 3D point cloud welding seam detection module by using a four-element algorithm in consideration of the change of the posture of the welding gun and transmits the interpolation to the control instruction module;
the control instruction module generates corresponding control instructions according to detection and track optimization results, and realizes automatic control in the welding process, including real-time adjustment and control of welding gun positions and welding parameters.
Further, the point cloud filtering algorithm adopted by the 3D point cloud registration module includes: a straight-through filtering algorithm and a statistical filtering algorithm; the point cloud downsampling method adopted in the 3D point cloud registration module comprises the following steps: voxel method and curvature downsampling method; the algorithm adopted by the point cloud registration processing of the 3D point cloud registration module is an ICP algorithm.
On the other hand, the application also provides an intersecting line weld detection and track optimization method based on the structured light camera, which comprises the following steps:
step 1: performing point cloud registration on the point cloud data scanned by the structured light camera to obtain a three-dimensional model;
step 2: detecting all intersecting line weld joints of the workpiece according to the cross-sectional area and contour characteristics of the intersecting lines for the three-dimensional model after registration;
step 3: after all welding seams are detected, the welding seam track is optimized according to the welding process requirement, so that the welding gun posture is changed according to the welding seam track changes of different sections.
Further, the step 1 includes:
step 1.1: shooting a workpiece through each angle of a structured light camera to obtain multi-frame point cloud data of the workpiece;
step 1.2: performing direct filtering and Gaussian filtering operation on multi-frame point cloud data, removing noise points and outliers, and improving the quality of point cloud;
step 1.3: performing voxel method downsampling and curvature downsampling operation on the filtered point cloud data, and simplifying the point cloud data;
step 1.4: performing point cloud rough registration on the down-sampled point cloud data according to an initial matrix provided by the mechanical arm;
step 1.5: performing point cloud fine registration on the point cloud coarse registration result by using an ICP algorithm to obtain a fine registration result for subsequent weld joint detection
Further, the step 2 includes:
step 2.1: fitting a cylinder according to an iterative closest point method based on the finely registered point cloud;
step 2.2: clustering the point cloud data according to the Euclidean clustering algorithm;
step 2.3: analyzing the clustering area, finding out a possible cylinder area, and extracting point clouds of the intersecting part of the cylinders;
step 2.4: and fitting the point cloud of the extracted part by using a least square algorithm according to the characteristics that the cross section area of the intersecting line weld is elliptical and the symmetry is achieved, so as to obtain the complete point cloud at the intersecting line weld.
Further, step 3 includes:
step 3.1: preprocessing the weld track data to obtain weld track downsampling data;
step 3.2: performing data fitting on the sampled weld track by using a cubic B spline;
step 3.3: the fitted data are used as model value points;
step 3.4: and interpolating the position and the posture of the welding seam track by using a cubic B spline algorithm and a square algorithm respectively to obtain an optimized welding seam track.
The invention has the beneficial effects that:
1. compared with the traditional image information obtained by 2D vision, the method for obtaining the point cloud data by adopting the structured light camera is not easy to be influenced by conditions such as illumination and the like, and the obtained position information of the welding seam is more accurate.
2. The invention adopts a non-contact mode to detect the welding area of the welding workpiece, and solves the problems of inefficiency and limitation of the traditional manual visual inspection.
3. The invention solves the problem that the identification rate of the existing complex curved surface weld joint is low due to the influence of external factors from the profile characteristic of the intersecting line.
4. The invention provides a fusion algorithm of cubic spline curve interpolation and square algorithm interpolation, optimizes welding seam tracks, and solves the problem that the welding quality is influenced by the posture of a welding gun when the welding operation is ignored due to the fact that the smoothness of the welding seam tracks is only considered in the welding path planning of most welding robots.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intersecting line weld detection and trajectory optimization method.
FIG. 2 is a flow chart of intersecting line weld detection.
FIG. 3 is a flow chart of weld trajectory optimization.
Fig. 4 is a jig view of a structured light camera and welder.
In the figure, 1 an anti-collision sensor, 2 a gun clamping device, 3 a welding gun head, 4a clamping part, 5 a connecting flange plate, 6 a structured light camera and 7 a camera connecting base.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
The embodiment of the application provides an intersecting line weld detection and track optimization system and method based on a structured light camera, which are mainly used for intersecting line weld detection and mainly comprise the following steps:
industrial personal computers, welding robots, welding machines, structured light cameras, and the like. The industrial personal computer is used for controlling the flow of the whole system, the welding robot is an executing mechanism and is used for driving the welding gun to carry out welding operation, the welding machine is used for executing the movement of the robot and supplying power, and the structured light camera is used for collecting gray level images and point cloud information of welding workpieces.
The industrial personal computer is provided with a visual processing module, a motion control module and a user interface module; the visual processing module is used for executing welding seam detection and welding flow control according to the point cloud information of the welding workpiece acquired by the structured light camera; the motion control module is used for optimizing the weld track and controlling the motion of the welding robot; the user interface module provides a man-machine interaction mode to realize parameter setting, result display and report generation;
the structured light camera acquires workpiece information, is installed on one side of the welding gun through the clamp and performs TCP communication with the industrial personal computer to transmit data. And the industrial personal computer acquires the welding seam data and performs TCP communication with the welding robot to transmit the data.
The structural light camera is installed in the orthogonal direction of the welding gun through the clamp, interference is avoided, the structural light camera can have an optimal shooting visual angle, the welding gun is an automatic welding gun, the upper space is enough, the clamp is connected with the tail end of the mechanical arm through the flange connector, the anti-collision sensor is installed at the bottom, and the safety of the welding process is improved.
The vision processing module in the industrial personal computer comprises: a 3D point cloud registration module and a 3D point cloud weld detection module;
the 3D point cloud registration module is used for carrying out point cloud filtering, point cloud downsampling and point cloud registration processing on the point cloud information of the welding workpiece acquired by the structured light camera, and sending a processing result to the 3D point cloud welding seam detection module;
the 3D point cloud welding line detection module is used for detecting all welding lines according to the cross section characteristics and the contour characteristics of the welding lines after the 3D point cloud registration module reconstructs a complete three-dimensional model of the weldment, and sending the welding lines to the motion control module;
the 3D point cloud registration module in this embodiment mainly includes: the system comprises a coarse registration module, a fine registration module, a point cloud processing module, a data transmission module and the like. The point cloud processing module mainly comprises: point cloud filtering, point cloud downsampling, point cloud registration, and the like. The point cloud filtering algorithm comprises a straight-through filtering algorithm and a Gaussian filtering algorithm; the direct filtering is a simple and effective filtering method, and noise and outliers in the point cloud data are removed by setting a threshold value. The method can rapidly filter out some obvious abnormal values in the point cloud data, but for complex point cloud data, the filtering effect of the method is possibly less ideal, and Gaussian filtering is a smooth filtering method based on a Gaussian function, and noise and outliers are removed by carrying out smooth processing on the point cloud data. The method can better retain the characteristics and the structure of the point cloud data, and has better filtering effect on the complex point cloud data. In the invention, two types of filtering are combined, firstly, the through filtering is used for removing obvious outliers and noise, and then the Gaussian filtering is used for smoothing, so that cleaner and smoother point cloud data are obtained. Therefore, the quality of the point cloud data can be effectively improved, and errors and uncertainties of subsequent processing are reduced. The point cloud downsampling should reduce the point cloud density on the premise of not losing the point cloud characteristics; the voxel method and the curvature downsampling fusion method are used, the voxel method downsampling is used firstly to reduce the quantity and the density of point cloud data to a proper degree, and then the curvature downsampling is used for further sampling and filtering the point cloud data to obtain more proper point cloud data. Therefore, the efficiency of point cloud data processing and analysis can be effectively improved, the calculation time and the storage space are reduced, and the main characteristics and the shape of the point cloud data are reserved. The point cloud registration algorithm is an auxiliary registration algorithm under the premise of combining with the assistance of the mechanical arm, coarse registration is carried out according to an initial transformation matrix provided by the mechanical arm and the hand-eye matrix after hand-eye calibration, and fine registration is carried out on the point cloud subjected to coarse registration by using an ICP algorithm, so that a fine registration result is obtained.
FIG. 1 is a schematic flow diagram of an intersecting line weld detection and trajectory optimization based on a structured light camera according to an embodiment of the present invention. As shown in fig. 1, the internal reference calibration is performed on the structured light camera, and after the calibration is completed, the structured light camera is installed on one side of the welding machine through the fixture, is carried on the tail end of the welding robot, and is calibrated relative to the robot. After the vision calibration is completed, the mobile robot acquires multi-frame point clouds to a proper angle, point cloud preprocessing is carried out on each frame of point clouds, the point cloud preprocessing comprises point cloud filtering and point cloud downsampling, point cloud data which are simplified and retain main characteristics and shapes are finally obtained, coarse registration of the hand-eye matrix obtained according to the hand-eye calibration and the initial pose point clouds provided by the robot is carried out, and fine registration of the point clouds is completed according to an ICP algorithm. If the point cloud registration is successful, european clustering is needed to be carried out on the registered point cloud to obtain differently clustered areas.
The motion control module in the industrial personal computer comprises: the device comprises an intersecting line welding seam detection module, a welding seam track optimization module and a control instruction module;
the intersecting line weld detection module firstly segments the cylinders for the clustering area, then extracts point clouds of the welding area according to the cross-sectional area and profile characteristics of the intersecting line weld, finally fits the intersecting line weld and sends the intersecting line weld to the weld track planning module.
The welding seam track optimizing module interpolates the welding seam according to the welding seam data detected by the intersecting line welding seam detecting module by using a four-element algorithm in consideration of the change of the posture of the welding gun and transmits the interpolation to the control instruction module;
the control instruction module generates corresponding control instructions according to detection and track optimization results, and realizes automatic control in the welding process, including real-time adjustment and control of welding gun positions and welding parameters.
The welding seam track planning module receives welding seam data, optimizes the welding seam track firstly, interpolates the position and the posture of the welding seam track by utilizing a cubic B spline algorithm and a square algorithm in consideration of the influence of the welding posture of a welding gun in the welding process, fuses the posture of the welding gun and the welding seam track data, optimizes the fused data, finally sends the plan of the optimized welding path to an industrial personal computer, and executes the final welding operation.
Fig. 2 is a schematic diagram of an intersecting line weld detection flow provided in an embodiment of the invention. As shown in fig. 2, considering that the curvature of the welding area of the intersecting line weld has large change, the main characteristics of the welding area are maintained by using a curvature downsampling method, and meanwhile, some redundant point clouds are removed. Performing cluster analysis on the down-sampled point cloud, fitting a plurality of cylinders to the clustering area by using a RANSAC algorithm, and extracting a point cloud set Q= { Q of the intersection line part of the cylinders 1 ,q 2 ,…q n It is considered that in the ICP registration process, the coordinate system of the point cloud has been converted to the world coordinate system, and the tube truss structure is placed in a plane parallel to the XYO plane of the world coordinate system. The extracted point cloud is projected onto a XYO plane, and an elliptic equation is fitted by a least square method in consideration of the fact that the intersecting line has an elliptic or circular cross section and has inflection points. The ellipse equation for the detected n point fits is as follows:
where A, B, C, D, E is the coefficient of the ellipse fitted by the least squares method.
Leveling deviceThe set of elliptical points fitted by the surface is P= { P 1 ,p 2 ,…p n Traversing the distance from the point set P to the point set Q, and taking the minimum distance d i Put into array D. d, d i The calculation formula is as follows:
wherein p is i (x i ,y i )，q j (x j ,y j ,z j )，p i Is a point in the elliptic point set fitted by a plane, q i Is the point of the intersecting point cloud Q.
If there are a plurality of points q j And p is as follows i Distance d of (2) i Less than 0.3mm of the threshold value, and selecting the smallest z min Point q of (2) min Z as a new weld key point min Is a plurality of points q j If there is only one minimum value of the Z coordinate of (2) j And p is as follows i Distance d of (2) i Less than the threshold value of 0.3mm, q is determined j Regarded as a new key point of the welding seam, namely
q min (x min ,y min ,z min )
o n (x n ,y n ,z n )
Inverse solving of the point cloud o of the extraction part according to the fitted elliptic equation n And the key points serving as intersecting line welding seams are placed in a point set Q and sent to a welding seam track optimizing module.
Considering the special intersecting line weld joint, the welding mode adopts a crescent swing welding method, and the calculation formulas of the welding speed and the wire output are as follows:
where V is the welding speed, d is the welding wire radius, I is the current, U is the voltage, beta is the wire output, H is the frequency of oscillation, and L is the oscillation length.
FIG. 3 is a schematic flow chart of a weld trajectory optimization module according to an embodiment of the present invention. As shown in fig. 3, in the weld track data, the weld contour point cloud data is extracted in an equidistant sampling mode, so that the sparse operation of the weld track is realized. And taking the fitted intersecting line key points as sampling objects, sampling according to the Euclidean space distance of the interval d, and extracting the weld contour point cloud data of the weld scanning feature points. The Euclidean distance d is selected according to the curvature of the welding seam track, so that the sampled welding seam track can better reflect the shape of the welding seam track. In order to reduce sampling errors, data fitting is carried out on the acquired weld joint track by a cubic B spline algorithm. And then taking the fitted data points as model value points, and respectively interpolating the positions and the attitudes of the welding track by using a cubic B spline algorithm and a square algorithm. And finally, a smooth welding track is obtained.
The mounting fixture is schematically shown in FIG. 4: the clamping part 4 is in threaded connection with the gun head 3 of the welding gun, the gun clamping device 2 is used for clamping the welding gun, the gun clamping device 2 is in threaded connection with the camera connecting base 7, the structured light camera 6 is in threaded connection with the camera connecting base 7, the anti-collision sensor 1 is arranged on the gun clamping device 2, and the connecting flange 5 is fixedly connected with the mechanical arm and the gun clamping device 2 through bolts.
Exemplary, the patent provides a method for detecting and optimizing the track of the intersecting line weld and the V-shaped groove weld by adopting the structured light camera, which comprises the following specific steps:
s1: and (3) calibrating a hand and eye of the mechanical arm and calibrating a TCP, shooting a three-dimensional point cloud of a welded workpiece by using a structured light camera, loading a model point cloud of the workpiece by using an industrial personal computer, and performing fine positioning by using a point cloud registration method.
In this embodiment, step S1 includes:
step S11: calibrating a manipulator hand and eye and calibrating a TCP;
step S12: the structured light camera module shoots a workpiece point cloud;
step S13: carrying out point cloud registration on the two point clouds to obtain a rotation translation matrix between the two point clouds;
step S14: obtaining a rotation translation matrix in S13, namely a fine positioning result, through offline programming;
step S15: and carrying out three-dimensional reconstruction on the registered point cloud.
In this embodiment, step S2 includes:
step S21: using the point cloud obtained in the step S1 after the workpiece registration in the step S15;
step S22: selecting a weld type to be detected, and simplifying point cloud by using point cloud preprocessing;
step S23: detecting intersecting line weld joints in the model by using a simplified point cloud through a weld joint recognition algorithm;
step S24: and (4) transmitting the identification result in the S22 to the robot for welding through TCP communication.
In this embodiment, step S3 includes:
step S31: combining the welding seam track in the S23 with the posture of a welding gun to perform data fusion and further optimization;
step S32: determining an initial point based on the optimized weld track;
step S33: the weld is initiated from the initial weld spot.
The above-described embodiments are intended to illustrate the present invention, not to limit it, and any modifications and variations made thereto are within the spirit of the invention and the scope of the appended claims.
Claims (10)
1. An intersecting line weld detection and trajectory optimization system based on a structured light camera, comprising: industrial computer, welding robot, welding machine and structured light camera, wherein:
the industrial personal computer is provided with a visual processing module, a motion control module and a user interface module; the visual processing module is used for executing welding seam detection and welding flow control according to the point cloud information of the welding workpiece acquired by the structured light camera; the motion control module is used for optimizing the weld track and controlling the motion of the welding robot; the user interface module provides a man-machine interaction mode to realize parameter setting, result display and report generation;
the welding robot is used for driving the welding gun to perform welding operation;
the welding machine is used for controlling the welding robot to execute a welding task and supplying power;
the structured light camera is divided into a structured light projection module and a camera acquisition module and is used for acquiring images and point cloud information of a welding workpiece.
2. The system of claim 1, wherein the structured light camera is mounted to one side of the welding gun by a fixture.
3. The intersecting line weld detection and trajectory optimization system based on a structured light camera according to claim 1, wherein the welding gun is an automatic welding gun, the structured light camera is fixed in the orthogonal direction of the fixture through the fixture to prevent interference, and an anti-collision sensor is fixedly installed at the bottom of the welding gun clamping gun.
4. The structured light camera-based intersecting line weld detection and trajectory optimization system of claim 1, wherein the vision processing module in the industrial personal computer comprises: a 3D point cloud registration module and a 3D point cloud weld detection module;
the 3D point cloud registration module is used for carrying out point cloud filtering, point cloud downsampling and point cloud registration processing on the point cloud information of the welding workpiece acquired by the structured light camera, and sending a processing result to the 3D point cloud welding seam detection module;
the 3D point cloud welding line detection module is used for detecting all welding lines according to the cross section characteristics and the contour characteristics of the welding lines after the 3D point cloud registration module reconstructs a complete three-dimensional model of the weldment, and sending the welding lines to the motion control module.
5. The system for detecting and optimizing an intersecting line weld based on a structured light camera as defined in claim 4, wherein the motion control module in the industrial personal computer comprises: the welding seam track optimizing module and the control instruction module;
the welding seam track optimization module interpolates the welding seam according to the welding seam data detected by the 3D point cloud welding seam detection module by using a four-element algorithm in consideration of the change of the posture of the welding gun and transmits the interpolation to the control instruction module;
the control instruction module generates corresponding control instructions according to detection and track optimization results, and realizes automatic control in the welding process, including real-time adjustment and control of welding gun positions and welding parameters.
6. The structured light camera-based intersection weld detection and trajectory optimization system of claim 4, wherein the 3D point cloud registration module employs a point cloud filtering algorithm comprising: a straight-through filtering algorithm and a statistical filtering algorithm; the point cloud downsampling method adopted in the 3D point cloud registration module comprises the following steps: voxel method and curvature downsampling method; the algorithm adopted by the point cloud registration processing of the 3D point cloud registration module is an ICP algorithm.
7. A structured light camera-based intersection bead detection and trajectory optimization method based on the structured light camera-based intersection bead detection and trajectory optimization system of any one of claims 1-6, the method comprising:
step 1: performing point cloud registration on the point cloud data scanned by the structured light camera to obtain a three-dimensional model;
step 2: detecting all intersecting line weld joints of the workpiece according to the cross-sectional area and contour characteristics of the intersecting lines for the three-dimensional model after registration;
step 3: after all welding seams are detected, the welding seam track is optimized according to the welding process requirement, so that the welding gun posture is changed according to the welding seam track changes of different sections.
8. The method for detecting and optimizing a trajectory of an intersecting line weld based on a structured light camera as claimed in claim 7, wherein said step 1 comprises:
step 1.1: shooting a workpiece through each angle of a structured light camera to obtain multi-frame point cloud data of the workpiece;
step 1.2: performing direct filtering and Gaussian filtering operation on multi-frame point cloud data, removing noise points and outliers, and improving the quality of point cloud;
step 1.3: performing voxel method downsampling and curvature downsampling operation on the filtered point cloud data, and simplifying the point cloud data;
step 1.4: performing point cloud rough registration on the down-sampled point cloud data according to an initial matrix provided by the mechanical arm;
step 1.5: and performing point cloud fine registration on the point cloud coarse registration result by using an ICP algorithm to obtain a fine registration result for subsequent weld detection.
9. The method for detecting and optimizing trajectories of intersecting line welds based on structured light cameras as claimed in claim 8, wherein said step 2 comprises:
step 2.1: fitting a cylinder according to an iterative closest point method based on the finely registered point cloud;
step 2.2: clustering the point cloud data according to the Euclidean clustering algorithm;
step 2.3: analyzing the clustering area, finding out a possible cylinder area, and extracting point clouds of the intersecting part of the cylinders;
step 2.4: and fitting the point cloud of the extracted part by using a least square algorithm according to the characteristics that the cross section area of the intersecting line weld is elliptical and the symmetry is achieved, so as to obtain the complete point cloud at the intersecting line weld.
10. The structured light camera-based intersecting line weld detection and trajectory optimization method of claim 7, wherein step 3 comprises:
step 3.1: preprocessing the weld track data to obtain weld track downsampling data;
step 3.2: performing data fitting on the sampled weld track by using a cubic B spline;
step 3.3: the fitted data are used as model value points;
step 3.4: and interpolating the position and the posture of the welding seam track by using a cubic B spline algorithm and a square algorithm respectively to obtain an optimized welding seam track.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311273384.XA CN117300464A (en) | 2023-09-28 | 2023-09-28 | Intersecting line weld detection and track optimization system and method based on structured light camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311273384.XA CN117300464A (en) | 2023-09-28 | 2023-09-28 | Intersecting line weld detection and track optimization system and method based on structured light camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117300464A true CN117300464A (en) | 2023-12-29 |
Family
ID=89254897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311273384.XA Pending CN117300464A (en) | 2023-09-28 | 2023-09-28 | Intersecting line weld detection and track optimization system and method based on structured light camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117300464A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118162756A (en) * | 2024-05-15 | 2024-06-11 | 深圳市高素科技有限公司 | Battery module laser welding system and method based on visual guidance |
-
2023
- 2023-09-28 CN CN202311273384.XA patent/CN117300464A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118162756A (en) * | 2024-05-15 | 2024-06-11 | 深圳市高素科技有限公司 | Battery module laser welding system and method based on visual guidance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112518072B (en) | Spatial intersecting curve weld joint structure modeling method based on line structure light vision | |
| CN110091333B (en) | Device and method for identifying and automatically grinding and polishing weld joint features on surface of complex curved surface | |
| CN112223293B (en) | Online grinding method of welding line grinding and polishing robot | |
| CN110227876A (en) | Robot welding autonomous path planning method based on 3D point cloud data | |
| CN112958959A (en) | Automatic welding and detection method based on three-dimensional vision | |
| Tsai et al. | Machine vision based path planning for a robotic golf club head welding system | |
| Zhou et al. | Autonomous acquisition of seam coordinates for arc welding robot based on visual servoing | |
| CN114515924B (en) | Automatic welding system and method for tower foot workpiece based on weld joint identification | |
| Hou et al. | A teaching-free welding method based on laser visual sensing system in robotic GMAW | |
| CN111496344B (en) | V-shaped groove information processing method based on laser sensor | |
| CN113798634A (en) | Method, system and equipment for teaching spatial circular weld and tracking weld | |
| CN114769988B (en) | Welding control method, system, welding equipment and storage medium | |
| CN211028836U (en) | Automatic assembly system of six-axis industrial robot | |
| Zhou et al. | Intelligent guidance programming of welding robot for 3D curved welding seam | |
| CN114161048A (en) | Iron tower foot parametric welding method and device based on 3D vision | |
| CN111168288A (en) | Double-ring welding seam laser visual tracking system and tracking method | |
| Ma et al. | A fast and robust seam tracking method for spatial circular weld based on laser visual sensor | |
| Chen et al. | The decoupling visual feature extraction of dynamic three-dimensional V-type seam for gantry welding robot | |
| CN109128540B (en) | Method for determining laser welding focal track of T-shaped joint | |
| CN117047237B (en) | Intelligent flexible welding system and method for special-shaped parts | |
| CN117584121A (en) | Welding robot path planning method based on point cloud scene understanding | |
| CN117300464A (en) | Intersecting line weld detection and track optimization system and method based on structured light camera | |
| Lei et al. | The development of tube-to-tubesheet welding from automation to digitization | |
| CN115041887A (en) | Contour measuring and recognizing system for robot welding workpiece | |
| Wu et al. | Research on Welding Guidance System of Intelligent Perception for Steel Weldment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |