Structured-light vision systems are widely used in robotic welding. The key to improving the robotic visual servo performance and weld quality is the weld seam recognition accuracy. Common detection algorithms are likely to be disturbed by the noise of spatter and arc during the welding process. In this paper, a weld seam recognition algorithm is proposed based on structured light vision to overcome this challenge. The core of this method is fully utilizing information of previous frames to process the current frame, which can make weld seam extraction both more robust and effective. The algorithm can be divided into three steps: initial laser center line recognition, online laser center line detection, and weld feature extraction. A Laplacian of Gaussian filter is used for recognizing the laser center line in the first frame. Afterwards, an algorithm based on the NURBS-snake model detects the laser center line online in a dynamic region of interest (abbreviated ROI). The center line obtained from first step is set as the initial contour of the NURBS-snake model. Using the line obtained from the previous step, feature points are determined by segmentation and straight-line fitting, while the position of the weld seam can be calculated according to the feature points. The accuracy, efficiency and robustness of the recognition algorithm are verified by experiments.

A robust weld seam recognition method under heavy noise based on structured-light vision

Structured light measurement is widely used for weld seam detection owing to its high measurement precision and robust. However, there is nearly no geometrical deformation of the stripe projected onto weld face, whose seam width is less than 0.1 mm and without misalignment. So, it’s very difficult to ensure an exact retrieval of the seam feature. This issue is raised as laser welding for butt joint of thin metal plate is widely applied. Moreover, measurement for the seam width, seam center and the normal vector of the weld face at the same time during welding process is of great importance to the welding quality but rarely reported. Consequently, a seam measurement method based on vision sensor for space weld seam of narrow butt joint is proposed in this article. Three laser stripes with different wave length are project on the weldment, in which two red laser stripes are designed and used to measure the three dimensional profile of the weld face by the principle of optical triangulation, and the third green laser stripe is used as light source to measure the edge and the centerline of the seam by the principle of passive vision sensor. The corresponding image process algorithm is proposed to extract the centerline of the red laser stripes as well as the seam feature. All these three laser stripes are captured and processed in a single image so that the three dimensional position of the space weld seam can be obtained simultaneously. Finally, the result of experiment reveals that the proposed method can meet the precision demand of space narrow butt joint.

A novel weld seam detection method for space weld seam of narrow butt joint in laser welding

3D reconstruction of complex spatial weld seam for autonomous welding by laser structured light scanning

Numerical simulation and experiment analysis of angular distortion and residual stress in hybrid laser-magnetic welding

A review of vision-aided robotic welding

Vision sensor systems with an auxiliary light source such as structured light–based vision sensor have been widely used for weld seam detection. However, the main drawback of this method is the preview distance between the welding position and the sensing position, which can generate unavoidable detecting errors. Laser welding of the small workpiece or narrow butt joint is especially vulnerable to detection error caused by preview distance. Meanwhile, only one point of the weld seam can be measured each time, which makes the corresponding image processing very sensitive to light noise. Consequently, a seam measurement method based on a passive vision sensor for narrow gap butt joint is proposed in this article. The weld pool is observed directly by this vision sensor so that there is no preview distance. An adequately adjusted telecentric lens is used to increase the contrast between the seam feature and the background welding noise. By this manner, a long and noticeable weld seam feature, as well as the weld pool, can be obtained in the captured images. A corresponding image processing algorithm based on particle filter is designed to extract the captured long weld seam. The particle filter is used to track the slope and intercept of the weld seam, which combines the advantage of both particle filter and Hough transform. As the particle filter algorithm could generate the result by evaluating both the previous and the current measurement results, the corresponding image processing can be robust even when a few images are of poor quality. Finally, laser welding experiments were carried out, and the results revealed that the proposed method could achieve detection accuracy of 0.08 mm when welding 0.1 mm width narrow butt joint at 2000 mm/min welding speed.

A robust weld seam detection method based on particle filter for laser welding by using a passive vision sensor

Laser welding technology for skin-stringer joints is widely used in aircraft manufacturing. Double-sided laser beam welding of skin-stringer joints is an approved method for producing defect-free welds. The main drawback for the use of single-sided welding method for T-joints is the occurrence of weld defects. To achieve dual-beam laser-welded T-joint, a dual-beam laser welding platform based on multi-axis CNC machine is set up in this paper. A novel control method of double-sided seam tracking and error compensation based on vision sensor is proposed. The weld seams on both sides of the T-joint are detected simultaneously by two vision sensors. At the same time, the welding deviation on both sides of the T-joint are compensated at real time by an independent error compensation control method based on self-adaptive fuzzy-PID controller. The result shows that the dual-beam laser welding system can achieve high precision dynamic deviation compensation in the double-sided welding process at a high speed.

A novel dual-channel weld seam tracking system for aircraft T-joint welds

Austenitic stainless steel 316L is welded by laser beam with T-joint in this paper. Microstructures of fusion zone consist of a large amount of austenite and a small amount of ferrite; heat-affected zone (HAZ) width is about 10 μm. The fine-equiaxed dendrites existing as network morphology locate at the center of fusion zone, and columnar structures are near HAZ. Microhardness at the top of the cross-section of welded joints is higher than that at the bottom, and the hardness of the second pass is higher than that of the first pass. The numerical result of maximum deformation (2.67 mm) keeps a good line with that of the experiment result (2.52 mm). The maximum value of the longitudinal compressive stress is 306 MPa, while the residual stress of the first pass is slightly released during the second pass welding process. The transverse residual stress along line 1 always presents a compressive state. At the 3.5 mm position far from the bead center, a large fluctuation of angular deformation and longitudinal residual stress are induced by the high-temperature gradient. Maximum values of angular deformation and equivalent residual stress for the whole sample are 1.37 mm and 452.3 MPa, and these both locate at the end-start zone of the welding path.

Laser beam welding of 316L T-joint: microstructure, microhardness, distortion, and residual stress

With excellent mobility and flexibility, mobile manipulators have great potential for loading and unloading tasks of numerical control machine tools (CNC) in manufacturing workshops. However, because of the rough and oily ground, dynamic obstacles and the convex plate of a CNC, harsh manufacturing workshop poses a huge challenge to the localization system of an autonomous mobile manipulator. To address the above problem, this paper presents a hybrid maps enhanced localization system which mainly consists of a global localization method and a pose tracking method. Hybrid maps including hybrid grid map, multi-resolution likelihood fields (MLFs) and hybrid point map are constructed to efficaciously model the harsh environment and to improve localization performance. Our global localization method employs the convex hull sampling to spares dense Lidar data and the MLFs based branch and bound (BnB) search to speed up global search. To achieve real-time localization reliably and accurately, our pose tracking method seamlessly combines the BnB search and the adaptive Monte Carlo localization, and the Iterative Closest Point (ICP) based scan matching using the hybrid point map is adopted for higher accuracy. In addition, a distance filter improved by unscented transform is integrated into the pose tracking process to mitigate the influence of dynamic obstacles. The developed localization system is evaluated through different experiments including two weeks of loading and unloading tasks in a real manufacturing scenario, resulting in superior localization performance.

/pdf/hybrid-maps-enhanced-localization-system-for-mobile-308us4nu09.pdf

Wenjun Shao

Papers

A novel weld seam detection method for space weld seam of narrow butt joint in laser welding

A robust weld seam detection method based on particle filter for laser welding by using a passive vision sensor

A novel dual-channel weld seam tracking system for aircraft T-joint welds

Laser beam welding of 316L T-joint: microstructure, microhardness, distortion, and residual stress

Hybrid Maps Enhanced Localization System for Mobile Manipulator in Harsh Manufacturing Workshop