Multi-Seam Tracking With a Portable Robotic Welding System in Unstructured Environments

Most welding manufacturing of the heavy industry, such as shipbuilding and construction, is carried out in an unstructured workspace. The term Unstructured indicates the production environment is irregular, changeable and without model. In this case, the changeable workpiece position, workpiece shape, environmental background, and environmental illumination should be carefully considered. Because of such complicated characteristics, the welding is currently being relied on the manual operation, resulting in high cost, low efficiency and quality. This work proposes a portable robotic welding system and a novel seam tracking method. Compared to existing methods, it can cope with more complex general spatial curve weld. Firstly, the tracking pose of the robot is modeled by a proposed dual-sequence tracking strategy. On this basis, the working parameters can be adjusted to avoid robot-workpiece collision around the workpiece corners during the tracking process. By associating the forward direction of the welding torch with the viewpoint direction of the camera, it solves the problem that the weld feature points are prone to be lost in the tracking process by conventional methods. Point cloud registration is adopted to globally locate the multi-segment welds in the workpiece, since the system deployment location is not fixed. Various experiments on single or multiple welds under different environmental conditions show that even if the robot is deployed in different positions, it can reach the starting point of the weld smoothly and accurately track along the welds.

Overview on the digitized production of welded steel structures

This paper presents a concept and practical topics involved in digitized production. The term “production” denotes the design, fabrication, and service life of a product, which in this case elaborates on welded steel structures. This includes the required information for guiding all the process stages of the chosen material back to its re-melting, following the material flow in a fully digitized form. This concept enables an increase in production quality at a higher level while minimizing the risk of human errors. Automation of the short-run production of steel structures for demanding applications is also a key goal, together with securing a cost-efficient process. Typically, such structures are fabricated from high- or ultra-high-strength steels. Though challenging, reaching these aims seems to be realistic by applying advanced fatigue design methods, using high-quality robotic welding and receiving information about the real loading of the structure.

Project and Software of a Robotic Welding Station Using Virtual Reality Technology

The use of VR technology in various industries, including in the industry is constantly growing. ABB is one of the first companies to introduce programming using virtual reality to its offer. This system greatly facilitates the work of an engineer, allowing the user to interact with 3D models through virtual reality goggles. The article presents the design and software of a robotic station that enables the creation of movement instructions using virtual reality technology. The review of the existing industrial solutions using VR technology in welding simulators and other industries. A project of a welding station in the RobotStudio environment was presented and built. Software was written using virtual reality and a model of the real tool was made using the 3D printing method. The designed welding station was tested.

Mixed Reality-Enhanced Intuitive Teleoperation with Hybrid Virtual Fixtures for Intelligent Robotic Welding

This paper presents an integrated scheme based on a mixed reality (MR) and haptic feedback approach for intuitive and immersive teleoperation of robotic welding systems. By incorporating MR technology, the user is fully immersed in a virtual operating space augmented by real-time visual feedback from the robot working space. The proposed robotic tele-welding system features imitative motion mapping from the user’s hand movements to the welding robot motions, and it enables the spatial velocity-based control of the robot tool center point (TCP). The proposed mixed reality virtual fixture (MRVF) integration approach implements hybrid haptic constraints to guide the operator’s hand movements following the conical guidance to effectively align the welding torch for welding and constrain the welding operation within a collision-free area. Onsite welding and tele-welding experiments identify the operational differences between professional and unskilled welders and demonstrate the effectiveness of the proposed MRVF tele-welding framework for novice welders. The MRVF-integrated visual/haptic tele-welding scheme reduced the torch alignment times by 56% and 60% compared to the MRnoVF and baseline cases, with minimized cognitive workload and optimal usability. The MRVF scheme effectively stabilized welders’ hand movements and eliminated undesirable collisions while generating smooth welds.

A Efficient System based on Model Segmentation for Weld Seam Grinding Robot

Uneven surface quality often occurs when butt welds are manually grinding, so robotic weld grinding automation has become a fast-developing trend. Weld seam extraction and trajectory planning are important for automatic control of grinding process. However, most of the research on weld extraction is focused on before welding. Due to the irregular shape of the weld after welding, and too little work has been devoted to the weld identification after welding. Consequently, in this paper, a novel simple and efficient weld extraction algorithm is proposed, and the robot grinding path is planned. Firstly, a new flexible bracket structure for welding seam extraction is designed. Secondly, the weld seam section profile model is established, and the processing of spatial point cloud problem is transformed into the processing of two-dimensional point cloud problem. The least square method (LSM) based on threshold comparison is used to segment the weld seam, which greatly improved the processing speed and accuracy. Then the grinding path and pose are obtained according to the extracted weld space structure. Finally, a robotic welding seam automatic grinding system is built. Experiments show that the proposed method could well extract the irregular weld contour after welding and the grinding system built is reliable, which greatly improves the grinding efficiency.

Semi-Supervised Training for Positioning of Welding Seams

Robotic welding often uses vision-based measurement to find the correct placement of the welding seam. Traditional machine vision methods work well in many cases but lack robustness when faced with variations in the manufacturing process or in the imaging conditions. While supervised deep neural networks have been successful in increasing accuracy and robustness in many real-world measurement applications, their success relies on labeled data. In this paper, we employ semi-supervised learning to simultaneously increase accuracy and robustness while avoiding expensive and time-consuming labeling efforts by a domain expert. While semi-supervised learning approaches for various image classification tasks exist, we purpose a novel algorithm for semi-supervised key-point detection for seam placement by a welding robot. We demonstrate that our approach can work robustly with as few as fifteen labeled images. In addition, our method utilizes full image resolution to enhance the accuracy of the key-point detection in seam placement.

Road Traffic Safety: High-Quality Welding - Ensuring Cost-Effectiveness and Safety

Welding industry is one of the leaders in the field of investments in the development of technologies and innovations aimed at ensuring functional cost-effectiveness, improving safety and speed of movement in the digital age. Ensuring the reliability and safety of the railway tracks requires the development of new scientific approaches to the use of welding technologies in the construction and operation of a high-speed railway. The main criterion for evaluating efficiency of the new approaches is the quality of the resulting welded joints and the productivity of the welding processes used. Rail connections should be made in such a way from a technical point of view that there are no restrictions during operation, the service life of the rails is not reduced, the percentage of defects does not increase, and the noise level is within the normal limits. The purpose of the study is to substantiate the cost-effectiveness and safety of the introduction of new contact welding technologies in Russia. Technical and economic analysis of welding methods is given, including using the rail welding machines — a new generation of equipment for the contact butt welding of high-strength rails during the construction and reconstruction of a high-speed railway. The Up-to-date technologies are based on the process of contact welding by pulsating reflow, on the one hand ensuring high productivity of the process, and on the other — reducing the influence of the human factor on it. This is achieved through a set of options for controlling the welding process, with online monitoring of the operational characteristics, with the software for storage and the possibility of using robotic welding in the future in the field of digital doubles and processing archived data based on the artificial intelligence as part of the implementation of Smart City projects. Feasibility study is also presented concerning the efficiency of the introduction of contact welding technology by the pulsed reflow on high-speed railway projects of Russia based on reducing the rail joint failures and improving the characteristics of the welding process and safe operation.