Abstract
Nondestructive test (NDT) technology is required in the gas metal arc (GMA) welding process to secure weld robustness and to monitor the welding quality in real-time. In this study, a laser vision sensor (LVS) is designed and fabricated, and an image processing algorithm is developed and implemented to extract precise laser lines on tested welds. A camera calibration method based on a gyro sensor is used to cope with the complex motion of the welding robot. Data are obtained based on GMA welding experiments at various welding conditions for the estimation of quality prediction models. Deep neural network (DNN) models are developed based on external bead shapes and welding conditions to predict the internal bead shapes and the tensile strengths of welded joints.
Highlights
The chassis of the car is a component that supports all the other parts, including the car body and the powertrain
The formed steel plates are joined by gas metal arc welding (GMAW) to form the final chassis parts
In the case of weld bead geometry measurements, Huang et al [19,20] developed a laser vision system based on the principle of laser triangulation for nondestructive weld quality inspection, which processed images acquired from the vision sensor and analyzed the acquired 3D profiles of the weld to inspect the positions and sizes of the weld defects
Summary
The chassis of the car is a component that supports all the other parts, including the car body and the powertrain. In the case of weld bead geometry measurements, Huang et al [19,20] developed a laser vision system based on the principle of laser triangulation for nondestructive weld quality inspection, which processed images acquired from the vision sensor and analyzed the acquired 3D profiles of the weld to inspect the positions and sizes of the weld defects. The technology that can measure external bead shapes and estimate the internal bead shapes is required because both bead shape types play important roles in the determination of weld quality It is desirable for the monitoring technology to be able to examine weld bead geometry and predict performance indicators, such as tensile strength and geometrical characteristics in real-time to improve the efficiency of the welding process.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call