Path Planning of Planar Kinked Line Seam by Visual Servoing for Robotic Welding

Welding path planning can substitute for the manual teaching process of the robot and can promote the autonomous level of the robotic welding. A path planning method by visual servoing was presented, in which the optimal angle of charge-coupled device (CCD) camera was also planned. Aiming at planning two forms of kinked line seams, obtuse angle seam and right angle seam, a practicable solution was put forward. In this solution, the intersection of two adjacent straight segments is detected in each local seam image, and if intersection is found, the seam errors are calculated using the next straight segment. The experimental results show that kinked line seam can be well planned using this solution.

A high-precision control system for robotic welding positioner

Aiming at the robotic welding positioner with characteristic of parameter change, load change, nonlinearity, and an intelligent control system was researched and developed. This control system used a two-mode controller that based on Fuzzy and PID control method. The results of simulation show that the dynamic and steady performances of the intelligent controller are better than that of single PID or Fuzzy controller. This paper has made a detail theoretical analysis of the constitution design and real-time controlled software and brought up the design and fulfillment method of multi-task real-time control software of high precisely and numerically controlled welding positioner, which has a good result in practice.

FUZZY REGRESSION MODEL TO PREDICT THE BEAD GEOMETRY IN THE ROBOTIC WELDING PROCESS

Recently, there has been a rapid development in computer technology, which has in turn led to develop the fully robotic welding system using artificial intelligence （AI） technology. However, the robotic welding system has not been achieved due to difficulties of the mathematical model and sensor technologies. The possibilities of the fuzzy regression method to predict the bead geometry, such as bead width, bead height, bead penetration and bead area in the robotic GMA （gas metal arc） welding process is presented. The approach, a well-known method to deal with the problems with a high degree of fuzziness, is used to build the relationship between four process variables and the four quality characteristics, respectively. Using these models, the proper prediction of the process variables for obtaining the optimal bead geometry can be determined.

Adaptive pass planning and optimization for robotic welding of complex joints

Current industrial robotic welding systems can- not achieve automated solutions for multi-layer multi-pass welding of complex joints due to the presence of non- uniform and irregular welding groove geometries. This paper presents an adaptive pass planning approach for robotic welding of such complex joints. The welding groove is first segmented considering both the variation in groove dimension and the reachability of the robot welding torch. For each welding segment, the welding passes are planned to be in accordance with welding practices, viz., keeping the same number of welding passes in each layer while maintaining consistent welding parameters. An adaptive pass adjustment scheme is developed to address the discrepancies between the simulated results and the actual welding deposition after finishing a few layers of welding. Corresponding robot paths are generated and optimized to ensure minimum joint movement subject to three constraints, viz., reachability, collision-free and singularity avoidance. The proposed approach has been sim- ulated with the arc welding of a Y-type joint found typically in offshore structures.

An approach of artificial neural network to robotic welding process modelling

Artificial neural networks(ANNs)have been investigated for application to robotic welding process.Two types of the ANN models are described.The first is a static modeling approach for the pre-setting of robotic welding parameters, and the other is a dynamic modelling for real time feedback control of robotic welding.These models map the relationship between the weld bead geometry and welding process parameters.Some basic concepts relating to neural networks are discussed. The performance of neural networks for modelling is discussed and evaluated by using actual robotic welding data.It is concluded that neural network is capable of modeling readily and quickly a multivariable welding process and the accuracy of neural networks modelling is comparable with the accuracy achieved by the statistical scheme. The choice between ANN and statistical models will depend on the application and control strategy used.

Seam Tracking and Visual Control for Robotic Arc Welding Based on Structured Light Stereovision

A real-time arc welding robot visual control system based on a local network with a multi-level hierarchy is developed in this paper. It consists of an intelligence and human-machine interface level, a motion planning level, a motion control level and a servo control level. The last three levels form a local real-time open robot controller, which realizes motion planning and motion control of a robot. A camera calibration method based on the relative movement of the end-effector connected to a robot is proposed and a method for tracking weld seam based on the structured light stereovision is provided. Combining the parameters of the cameras and laser plane, three groups of position values in Cartesian space are obtained for each feature point in a stripe projected on the weld seam. The accurate three-dimensional position of the edge points in the weld seam can be calculated from the obtained parameters with an information fusion algorithm. By calculating the weld seam parameter from position and image data, the movement parameters of the robot used for tracking can be determined. A swing welding experiment of type V groove weld is successfully conducted, the results of which show that the system has high resolution seam tracking in real-time, and works stably and efficiently.

3D reconstruction of worn parts for flexible remanufacture based on robotic arc welding

3D reconstruction of worn parts is the foundation for remanufacturing system based on robotic arc welding, because it can provide 3D geometric information for robot task plan. In this investigation, a novel 3D reconstruction system based on linear structured light vision sensing is developed. This system hardware consists of a MTC368-CB CCD camera, a MLH-645 laser projector and a DH-CG300 image grabbing card. This system software is developed to control the image data capture. In order to reconstruct the 3D geometric information from the captured image, a two steps rapid calibration algorithm is proposed. The 3D reconstruction experiment shows a satisfactory result.

Study on general inverse kinematics of rotating/tilting positioner for robotic arc welding off-line programming

Off line programming provides an essential link between CAD and CAM, whose development will result in greater use of robotic arc welding. An arc welding system with a robot and a rotating/tilting positioner is one of the most typical workcells. The inverse kinematics of robot and positioner is the foundation of the off line programming system. The previous researchers only focused on a special solution of the positioner inverse kinematics, which is the solution at down hand welding position. In this paper, we introduce a method for representing welding position. Then a general algorithm of rotating/tilting positioner inverse kinematics is presented, and an approach to find the unique solution of the inverse kinematics is discussed. The simulation experiment results show that the general algorithm can improve the ability of robotic arc welding off line programming system to program all types of welding positions.

Real-time monitoring of weld penetration quality in robotic arc welding process

It is of great significance to develop an intelligent monitoring system for weld penetration defects such as incomplete penetration and burn-through in real-time during robotic arc welding process. In this paper, robotic gas metal arc welding experiments are carried out on the mild steel test pieces with Vee-type groove. Through-the-arc sensing method is used to capture the transient values of the welding voltage and current. The raw data of the captured welding current and voltage are processed statistically, and the feature vector SIO is extracted to correlate the welding conditions to the weld penetration information. It lays foundation for intelligent monitoring of weld quality in robotic arc welding.

Geometric model of roboticarc welding for automatic programming

Geometric information is important for automatic programming of arc welding robot. Complete geometric models of robotic arc welding are established in this paper. In the geometric model of weld seam, an equation with seam length as its parameter is introduced to represent any weld seam. The method to determine discrete programming points on a weld seam is presented. In the geometric model of weld workpiece, three class primitives and CSG tree are used to describe weld workpiece. Detailed data structure is presented. In pose transformation of torch, world frame, torch frame and active frame are defined, and transformation between frames is presented. Based on these geometric models, an automatic programming software package for robotic arc welding, RAWCAD, is developed. Experiments show that the geometric models are practical and reliable.

CCWELD:A CIM system for robotic arc welding

This paper describes a CIM system for robotic arc welding.The system is specially designed for producing workpieces in small and medium batch sizes.Based on the development of AUTOCAD and a structure-light visual sensor.low cost CIM is implemented. Feature modeling of weld workpiece is discussed.which provides complete geometric information and process information for off-line programming.The system provides powerful tools for programming of torch orientation to meet the requirents of achieving good welding quality,avoiding collision and not violating kinematics constraints.

ON INTELLIGENTIZED TECHNOLOGIES FOR MODERN WELDING MANUFACTURING

A short survey on researching and developing status of intelligenttechnologies in modem welding manufacturing is given. According to the developing trend of advancedmanufacturing technology, a concept on intelligentized welding manufacturing engineering (IWME), ispresented for systematization of researching and developing domains on welding automation,intelligentized welding, robotic and flexible welding and advanced welding manufacturingtechnologies. And key technologies of welding intelligent manufacturing and its developing trend inthe future are investigated.

FLEXIBLE MAGNETIC WHEEL TYPE INTELLIGENT WELDING ROBOT FOR SPHERICAL TANK

An intelligent welding robot for spherical tank's all-position multi-layerwelds is developed. Based on the dynamics analyzing and simulation testing, a flexible magneticwheel mechanism is created as the robot's walking carriage. It makes the robot directly attracted tothe surface of the spherical tank so as to realize the all-position walking and welding withoutrail. At the same time, a CCD real-time tracing system is developed for the robot to repeatedlytrace the all-position and multi-layer seams. The welding tests show that the welding robot can makethe all-position and multi-layer welds with high tracing accuracy, excellent quality and reliablebehavior, and it can be applied for practical production.

Constant Speed Control for Complex Cross-section Welding Using Robot Based on Angle Self-Test

Expandable profile liner（EPL） is a promising new oil well casing cementing technique, and welding is a major EPLs connection technology. Connection of EPL is still in the stage of manual welding so far, automatic welding technology is a hotspot of EPL which is one of the key technologies to be solved. A robot for automatic welding of＂8＂ type EPL is studied. Four quadrants of mathematical equations of the 8-shaped cross-section track of EPL, consisting of multiple arcs, are established. Mechanism program for complex cross-section welding of EPL based on angle detection is proposed according to characteristics of small size, small valleys, and large forming errors, etc. A welding velocity vector control model is established by linkage control of a welding vehicle, a small driven actuator, and a height tracking mechanism. A constant speed control model based on an angle and symmetrical analysis model of rectangular coordinate system for EPL is built. Constraint conditions of constant speed control between each section are analyzed with 4 sections in first quadrant as an example, and cooperation work mechanism of the welding vehicle and the small tracking actuator is established based on pressure detection. The constant speed control model using angle self-test can be used to avoid the need for a precise mathematical model for tracking control and to adapt manufacture and installation deviation of EPL workpiece. The model is able to solve constant speed and trajectory tracking problems of EPL cross-section welding. EPL seams welded by the studied robot are good in appearance, and non-destructive testing（NDT） shows the seams are good in quality with no welding defects. Bulge tests show that the maximum pressure of welded EPL is 35 MPa, which can fulfill expansion performance requirements.

Petri net based modeling and analysis for weldingflexible manufacturing cell

Due to the development of advanced manufacturing technology and the introduction of Smart Manufacturing notion in the field of modern industrial production, welding flexible manufacturing using robot technology has become the inevitable developing direction on welding automation. Based on a new intelligent arc welding flexible manufacturing cell (WFMC), its system structure and control policies are studied in this paper. Aiming at the different information flows among every subsystem and central monitoring computer in this WFMC, Petri net theory is introduced into the process of welding manufacturing. A discrete control model of WFMC has been constructed, in which the system's status is regarded as place and the control process is regarded as transition. Moreover, grounded on automation Petri net principle, the judging and utilizing of information obtained from welding sensors are imported into Petri net structure, which extends the traditional Petri net concepts. The control model and policies researched in this paper have established foundation for further intelligent real time control on welding flexible manufacturing cell and system.

Seam tracking control for mobile welding robot based on vision sensor

To solve the seam tracking problem of mobile welding robot,a new controller based on the dynamics of mobile welding robot was designed using the method of backstepping kinematics into dynamics.A self-turning fuzzy controller and a fuzzy-Gaussian neural network(FGNN) controller were designed to complete coordinately controlling of cross-slider and wheels.The fuzzy-neural control algorithm was described by applying the Gaussian function and back propagation(BP) learning rule was used to tune the membership function in real time by applying the FGNN controller.To make the tracking more quickly and smoothly,the neural network controller based on dynamic model was designed,which utilized self-learning and self-adaptive ability of the neural network to deal with the partial uncertainty and the disturbances of the parameters of the robot dynamic model and real-time compensate the dynamics coupling.The results show that the selected control input torques make the system globally and asymptotically stable based on the Lyapunov function selected out;the accuracy of the proposed controller tracing is within ±0.4 mm and can satisfy the requirements of practical welding project.

Control algorithm based on trajectory and orientation of oblique intersection line welding-cutting robot

Working principle for a four-axis oblique intersection line welding robot is analyzed. A mathematical model for welding torch orientation angle is established, and an interpolation algorithm based on time division is proposed. The algorithm makes all interpolation points fall on a required curve in theory with no accumulated errors and a direct interpolation control on the saddle-shaped curve trajectory and space orientation angle can be achieved. It is shown by MATLAB simulation that the algorithm is real-time and fully meets the precision requirement. The algorithm has been applied to real robots.

ALGORITHM AND IMPLEMENTATION OF AUTO-SEARCHING WELD LINE FOR WELDING MOBILE ROBOT

An algorithm of auto-searching weld line for welding mobile robot is presented. Auto-searching weld line is that the robot can automatically recognize a weld groove according to the characteristics of the weld groove before welding, and then adjust itself posture to the desired status preparing for welding, namely, it is a process that the robot autonomously aligns itself to the center of welding seam. Firstly, the configuration of welding mobile robot with the function of auto-searching weld line is introduced, then the algorithm and implementation of auto-searching weld line are presented on the basis of kinematics model of the robot, at last trajectory planning among auto-searching weld line is investigated in detail. The experiment result shows that the developed welding mobile robot can successfully implement the task of auto-searching weld line before welding, tracking error precision can be controlled to approximate ±1.5 mm, and satisfy the requirement of practical welding project.

Guiding the welding robot to the initial welding position with visual method

Using step pattern match technology with variational resolution can recognize the position and orientation of the weld seam in the image. According to using the image segmentation method based on pattern match, not only advanced the speed and anti-jamming capability, but also captured the edge information of the weld seam and the edge of the workpiece, and the image coordinate of the initial welding position can be obtained. The matrix for hand-eye relationship of the robot can be calculated by adopting the rapid calculation method. According to the depth calculating principle with the special point matching using binocular stereovision, the initial welding position can be confirmed by calculating the middle point of the perpendicular line of two radials in the space, and the function to guide the welding robot to the initial welding position can be realized.

Dynamic modeling and simulation for nonholonomic welding mobile robot

Based on the Newton-Euler method, the dynamic behaviors of the left and right driving wheels and the robot body for the welding mobile robot were derived. In order to realize the combination control of body turning and slider adjustment, the dynamic behaviors of sliders were also investigated. As a result, a systematic and complete dynamic model for the welding mobile robot was constructed. In order to verify the effectiveness of the above model, a sliding mode tracking control method was proposed and simulated, the lateral error stabilizes between -0.2 mm and ＋0.2 mm, and the total distance of travel for the slider is consistently within 4-2 ram. The simulation results verify the effectiveness of the established dynamic model and also show that the seam tracking controller based on the dynamic model has excellent performance in terms of stability and robustness. Furthermore, the model is found to be very suitable for practical applications of the welding mobile robot.