Research on Trajectory Recognition and Control Technology of Real-Time Tracking Welding

Abstract

Real-time tracking welding with the assistance of structured light vision enhances the intelligence of robotic welding, which significantly shortens teaching time and guarantees accuracy for user-customized product welding. However, the robustness of most image processing algorithms is deficient during welding practice, and the security regime for tracking welding is not considered in most trajectory recognition and control algorithms. For these two problems, an adaptive feature extraction algorithm was proposed, which can accurately extract the seam center from the continuous, discontinuous or fluctuating laser stripes identified and located by the CNN model, while the prior model can quickly remove a large amount of noise and interference except the stripes, greatly improving the extraction accuracy and processing speed of the algorithm. Additionally, the embedded Pauta criterion was used to segmentally process the center point data stream and to cyclically eliminate outliers and further ensure the accuracy of the welding reference point. Experimental results showed that under the guarantee of the above-mentioned seam center point extraction and correction algorithms, the tracking average error was 0.1 mm, and even if abnormal trajectory points existed, they did not cause welding torch shaking, system interruption or other accidents.

YOLO-Weld: A Modified YOLOv5-Based Weld Feature Detection Network for Extreme Weld Noise

“…Among various sensors, active optical-vision sensors are more commonly used in welding tracking due to their ability to overcome complex environmental interference using light sources compared to passive vision sensors that use natural light or arc light generated during welding. The line-structured light sensor based on active optical-vision has become increasingly popular in the automatic welding robot industry because of its noncontact nature, high robustness, high accuracy, low cost, and other advantages [ 7 , 8 , 9 ]. It is worth noting that some scholars have also explored other methods to build real-time welding automation quality assessment systems for timely detection of potential defects and problems, such as weld defect detection [ 10 ] and melt pool depth prediction [ 11 ].…”

Development and High-Fidelity Simulation of Trajectory Tracking Control Schemes of a UUV for Fish Net-Pen Visual Inspection in Offshore Aquaculture

“…Among them, PID controllers are one of the highly applicable controllers for automation and robotics in both academia and industries [27]. Due to the simplicity in design & implementation and less computational load for a small UUV, they are often implemented as the baseline comparison with other controllers or modified as required [28]- [31]. For instance, a comparison between PID controller and the soft actor-critic (SAC)-deep reinforcement learning-based controller was reported [32].…”