The hottest robot welding intelligent technology 1

  • Detail

Robot welding Intelligent Technology (1)

1 Introduction

with the development of advanced manufacturing technology, it has become an inevitable trend to realize the automation, flexibility and intelligence of welding product manufacturing []. At present, robot welding has become the main symbol of the modernization of welding automation technology

welding robot has attracted more and more attention because of its strong versatility and reliable work. Using robot technology in welding production can improve productivity, improve working conditions, stabilize and ensure welding quality, and realize welding automation of small batch products [9]

from its birth and development in the 1960s to the present, the research of welding robot has experienced three stages, namely teaching and reproduction stage, offline programming stage and autonomous programming stage. With the continuous progress of computer control technology, the welding robot has developed from a single single machine teaching and reproduction type to a multi-sensor, intelligent flexible machining unit (system). Realizing the transition from the second generation to the third generation will become the goal of the welding robot [9,10]

at present, a large number of arc welding robot systems are used at home and abroad. On the whole, they basically belong to the first or quasi second generation of welding. Because the welding path and welding parameters are preset according to the actual operating conditions, they lack external information sensing and real-time adjustment and control functions during welding. This kind of arc welding robot has strict requirements for the stability of welding operating conditions and lacks flexibility during welding, showing obvious shortcomings. In the actual arc welding process, the welding conditions often change. For example, errors in processing and assembly will cause changes in the position and size of the weld, and changes in the heating and heat dissipation conditions of the workpiece during the welding process will cause weld bead deformation and uneven penetration [9,12]. In order to overcome the influence of various uncertain factors on welding quality in the robot welding process and improve the intelligent level and reliability of robot operation, the arc welding robot system is required to not only realize the automatic real-time tracking of space welds, but also realize the adjustment of welding parameters and the real-time control of weld quality

2. The main composition of robot welding intelligent technology

modern welding technology has typical interdisciplinary integration characteristics [5,11], and the adoption of robot welding is the centralized embodiment of the technical achievements of related disciplines. The main technical composition involved in introducing intelligent technology into welding robot is shown in Figure 1. These include:

1) autonomous planning technology of welding robot for welding tasks

2) motion trajectory control technology of welding robot

3) information sensing, modeling and intelligent control technology of welding dynamic process

4) the robot welding department is going to invest in the integration and control of the plant system in Yucheng next year, integrating the software and hardware of the above welding task planning, trajectory tracking control, sensor system, process model, intelligent control and other subsystems, unified optimization scheduling and control, involving the management and control of material flow and information flow of welding flexible manufacturing system, multi robots and sensors Multi intelligent unit of controller and control of complex system

the main technical research and development status of the above related aspects are briefly described below

3. Robot welding task autonomous planning technology []

as mentioned above, arc welding robots at home and abroad are mostly teaching reproduction type, which can not meet the increasingly complex needs of welding production, and there are still many problems to be studied. The research on arc welding robot has gradually transitioned to autonomy, and the offline programming technology of arc welding robot has emerged. A relatively complete offline programming system of arc welding robot should include welding task description (language programming or graphic simulation), manipulator level path planning, kinematics and dynamics algorithms and optimization, joint level planning for welding tasks, animation simulation of planning results, offline modification of planning results It is composed of the communication interface with the robot (downloading), the use of sensors to independently plan the path and correct the path. Its key technologies usually include the design of vision sensor, the acquisition of weld information and the design of planning controller

at the 1987 International Conference on automation and robot welding, experts summarized the development of offline programming, among which the most representative work is wrap system. H et al. Established an adaptive offline programming and control system wrap for welding robot based on expert system on a welding workstation fanuc/westwood, which includes welding database, offline programming, computer simulation and welding expert system. It is also equipped with visual sensors for pre welding joint detection and post welding defect detection, thus forming a complete expert welding robot system

domestic researchers at Harbin Institute of technology have done research on collision free path planning of welding robots, autonomous planning of arc welding robots with redundancy and joint planning of welding process parameters [], and designed and developed the module structure of offline planning and simulation system, as shown in Figure 2

arc welding robot planning system includes CAD input system, welding expert system, autonomous planning system and simulation system. In a broader sense, a more perfect arc welding robot planning system should also include feedback control system, pre welding sensing system and post welding detection system

4. Seam tracking and guidance technology of robot welding

as far as robot welding is concerned, the motion trajectory control of welding robot mainly refers to the initial welding position guidance and seam tracking control technology. In various application fields of arc welding robot, adaptability is the most important factor affecting welding quality and welding efficiency. The adaptability of the arc welding robot can be confirmed, that is, the input signal of the sensor detected from the welding workpiece is used to control and modify the operation of the robot in real time to adapt to the changed welding conditions and environment

Swedish and American companies have successively developed laser scanning and structured light vision sensors for weld tracking systems. Dr. lvweixin and Dr. Zhang Jiong from Harbin Institute of technology developed a vision system based on laser scanning and high-performance linear CCD sensor, as shown in Figure 4, to achieve real-time vision control [13]

in the research of robot vision guidance technology in initial welding position, Dr. lvweixin designed a local search algorithm based on laser scanning vision system, realizing the autonomous guidance of certain workpiece weld characteristics in a certain range [13]. Guo Zhenmin and Li Jinquan discussed the initial welding position guidance, weld recognition and real-time tracking of robot welding using visual servo and image recognition technology respectively

5. Visual sensing, modeling and intelligent control technology for dynamic process of welding pool

the key to high quality robot welding is to realize effective and accurate control of dynamic process of welding. Due to the complexity of the welding process, the practice shows that the effectiveness of the classical control method is greatly limited. Inspired by skilled welders' operating skills, in recent years, intelligent control methods that simulate welders' operations have been introduced into the dynamic welding process, mainly involving visual sensing, modeling and intelligent control of the dynamic visual process of the molten pool

5.1 sensing technology of welding process

sensing of welding process is the key link to realize the quality control of welding process. The trend of welding development in the future is welding automation, roboticization and intellectualization, and sensor technology is the most important part of this development. Welding sensors can be divided into two categories according to their use purposes: measuring and detecting the operating environment, and detecting and monitoring the welding process. In terms of sensing principle, it is mainly divided into acoustics, mechanics, arc, optical sensing, etc

acoustic sensors are mainly used for detecting droplet transfer in GMAW process, plasma perforation welding, etc. Mechanical sensing mainly refers to the molten pool oscillation method developed in recent years. Because the arc sensor directly detects the characteristics of the arc itself (current, arc voltage), it does not need additional sensors and the protection and denoising devices required by the additional sensors, which makes the application simple. At present, the main application fields are weld tracking and deposition control. Compared with other sensing methods, optical sensors do not contact the welding circuit, and the detection of signals does not affect the normal welding process. It is one of the most promising sensing technologies in the future. Using the infrared thermal radiation of the welding area to sense the welding process information is a self-contained method in optical sensing, and there are many research achievements in this regard [16]

5.2 visual sensing of welding pool

for the welding process, direct vision is the best non-contact sensing form. The main advantages of direct vision sensing technology are that it does not touch the workpiece, does not interfere with the normal welding process, and obtains a large amount of information with strong versatility. And because it can get the two-dimensional or three-dimensional information of the dynamic weld pool in the welding process, compared with other welding process information detection methods, the weld pool information detected by this method directly reflects the dynamic behavior of the molten metal in the welding process, and is officially offline in Pudong base, the newly built general assembly and manufacturing center of COMAC, which is suitable for the quality control of the welding process

the application of direct visual sensing in welding includes offline determination of the position of the workpiece to be welded; Compensate the welding path deviation caused by the fixed accuracy, the tolerance of each part of the robot, and the deformation of the weldment during the welding process; Real time sensing of welding joint and weld pool geometry in welding process control; Monitoring of droplet transfer form, etc

in recent years, with the development of computer vision technology, it has become an important research direction to use machine vision to directly observe the welding pool, obtain the geometric information of the weld pool through image processing, and carry out closed-loop control of welding quality []. According to whether the imaging light source in the visual inspection system is an auxiliary light source or a light source generated by the welding area itself, the direct visual inspection system can be divided into two categories: active and passive

(1) active direct vision sensing

in order to reduce the impact of arc light on image quality, active direct vision detection method uses auxiliary light sources such as laser to artificially illuminate the welding area, so as to improve the image quality. Because the laser has the characteristics of single wavelength, good directivity and good coherence, using the laser as an auxiliary light source can obtain a clearer image. Active vision often limits its application and promotion because of its expensive equipment and complex system. There is no detailed introduction here. See references in [14, 15]

(2) passive direct visual sensing

at present, as a practical technology of visual image sensing in the welding process, more research is to use the arc itself to illuminate the welding area without adding an auxiliary light source, that is, the passive direct visual detection method

the more in-depth research on passive direct visual sensing started in the mid-1980s. Researchers at home and abroad have directly used electric arc light to irradiate the workpiece gap in front of the molten pool to obtain the weld information in the welding area, and realized the weld tracking in the welding process according to the flicker of electric arc light intensity at different distances in front of the molten pool; A microcomputer control system with CCD camera was used to observe and control the behavior of pulsed mig/mag welding pool; Ohio University in the United States has developed an integrated visual sensing system that is placed inside the welding torch and coaxial with the electrode to observe the welding pool. Preliminary research has been carried out in the aspects of TIG welding pool observation and MIG welding seam tracking

reference [19] designed the visual image of both sides of the molten pool, and the same sensing system figure 3, obtained the clear image of both sides of the molten pool of pulsed GTAW

Copyright © 2011 JIN SHI