Search

In order to ensure the production quality of high-speed laser welding, it is necessary to simultaneously monitor multiple state properties. Monitoring methods combining vision sensing and deep learning models are popular but most models used can only make predictions on single welding state property. In this contribution, we propose a multi-output model based on a lightweight convolutional neural network (CNN) architecture and introduce the particle swarm optimization (PSO) technique to optimize the loss function of the model, to simultaneously monitor multiple state properties of high-speed laser welding of AISI 304 austenitic stainless steel. High-speed imaging is performed to capture images of the melt pool and the dataset is built. Test results of different models show that the proposed model can achieve monitoring of multiple welding state properties accurately and efficiently. In addition, we make an interpretation and discussion on the prediction of the model through a visualization method, which can help to deepen our understanding of the relationship between the melt pool appearance and welding state. The proposed method can not only be applied to the monitoring of high-speed laser welding but also has the potential to be used in other procedures of welding state monitoring. [ABSTRACT FROM AUTHOR]

Web-core sandwich panels are a typical lightweight structure utilized in a variety of fields, such as naval, aviation, aerospace, etc. Welding is considered as an effective process to join the face panel to the core panel from the face panel side. However, it is difficult to locate the joint position (i.e., the position of core panel) due to the shielding of the face panel. This paper studies a weld position detection method based on X-ray from the face panel side for aluminum web-core sandwich panels used in aviation and naval structures. First, an experimental system was designed for weld position detection, able to quickly acquire the X-ray intensity signal backscattered by the specimen. An effective signal processing method was developed to accurately extract the characteristic value of X-ray intensity signals representing the center of the joint. Secondly, an analytical model was established to calculate and optimize the detection parameters required for detection of the weld position of a given specimen by analyzing the relationship between the backscattered X-ray intensity signal detected by the detector and the parameters of the detection system and specimen during the detection process. Finally, several experiments were carried out on a 6061 aluminum alloy specimen with a thickness of 3 mm. The experimental results demonstrate that the maximum absolute error of the detection was 0.340 mm, which is sufficiently accurate for locating the position of the joint. This paper aims to provide the technical basis for the automatic tracking of weld joints from the face panel side, required for the high-reliability manufacturing of curved sandwich structures. [ABSTRACT FROM AUTHOR]

Automatic joint detection is of vital importance for the teaching of robots before welding and the seam tracking during welding. For narrow butt joints, the traditional structured light method may be ineffective, and many existing detection methods designed for narrow butt joints can only detect their 2D position. However, for butt joints with narrow gaps and 3D trajectories, their 3D position and orientation of the workpiece surface are required. In this paper, a vision based detection method for narrow butt joints is proposed. A crosshair laser is projected onto the workpiece surface and an auxiliary light source is used to illuminate the workpiece surface continuously. Then, images with an appropriate grayscale distribution are grabbed with the auto exposure function of the camera. The 3D position of the joint and the normal vector of the workpiece surface are calculated by the combination of the 2D and 3D information in the images. In addition, the detection method is applied in a robotic seam tracking system for GTAW (gas tungsten arc welding). Different filtering methods are used to smooth the detection results, and compared with the moving average method, the Kalman filter can reduce the dithering of the robot and improve the tracking accuracy significantly. [ABSTRACT FROM AUTHOR]

Lack of fusion can often occur during ultra-thin sheets edge welding process, severely destroying joint quality and leading to seal failure. This paper presents a vision-based weld pool monitoring method for detecting a lack of fusion during micro plasma arc welding (MPAW) of ultra-thin sheets edge welds. A passive micro-vision sensor is developed to acquire clear images of the mesoscale weld pool under MPAW conditions, continuously and stably. Then, an image processing algorithm has been proposed to extract the characteristics of weld pool geometry from the acquired images in real time. The relations between the presence of a lack of fusion in edge weld and dynamic changes in weld pool characteristic parameters are investigated. The experimental results indicate that the abrupt changes of extracted weld pool centroid position along the weld length are highly correlated with the occurrences of lack of fusion. By using such weld pool characteristic information, the lack of fusion in MPAW of ultra-thin sheets edge welds can be detected in real time. The proposed in-process monitoring method makes the early warning possible. It also can provide feedback for real-time control and can serve as a basis for intelligent defect identification. [ABSTRACT FROM AUTHOR]