Welding seam recognition and tracking for a novel mobile welding robot based on multi-layer sensing strategy

Abstract

Mobile welding robot with adaptive seam tracking ability can greatly improve the welding efficiency and quality, which has been extensively studied. To further improve the automation in multiple station welding, a novel intelligent mobile welding robot consists of a four-wheeled mobile platform and a collaborative manipulator is developed. Under the support of simultaneous localization and mapping (SLAM) technology, the robot is capable of automatically navigating to different stations to perform welding operation. To automatically detect the welding seam, a composite sensor system including an RGB-D camera and a laser vision sensor is creatively applied. Based on the sensor system, the multi-layer sensing strategy is performed to ensure the welding seam can be detected and tracked with high precision. By applying hybrid filter to the RGB-D camera measurement, the initial welding seam could be effectively extracted. Then a novel welding start point detection method is proposed. Meanwhile, to guarantee the tracking quality, a robust welding seam tracking algorithm based on laser vision sensor is presented to eliminate the tracking discrepancy caused by the platform parking error, through which the tracking trajectory can be corrected in real-time. The experimental results show that the robot can autonomously detect and track the welding seam effectively in different station. Also, the multiple station welding efficiency can be improved and quality can also be guaranteed.

DSNet: A dynamic squeeze network for real-time weld seam image segmentation

“…where 𝑉 𝑐𝑜𝑛𝑣 𝑑 denotes 3 × 1 vertical convolution with LN, and 𝐻𝑐𝑜𝑛𝑣 𝑟 denotes 1 × 3 horizontal convolution with GELU. Let us recall that the indexes 𝑑 and 𝑟 have been defined in (2).…”

“…Welding is a crucial manufacturing process that connects multiple workpieces into a single unit and has a wide range of applications in various industrial domains such as automobile manufacturing, shipbuilding, and aerospace [1]. With the rapid development of the economy in recent years, higher requirements have been put forward for high-quality and efficient welding [2]. Limited by the technical level, harsh welding environments, and other objective and subjective factors [3], traditional manual welding methods can no longer meet the needs of the modern manufacturing industry.…”

Collaborative detection and on-line monitoring of pipeline stress in oil and gas stations

“…Zhou et al [15] propose to combine the electric field locating model with the ground-penetrating radar (GPR) B-scan image interpretation model, which forms a high-efficiency plastic pipeline detection model that can quickly position the buried plastic pipeline. Liu et al [16] used an RGB-D camera and laser vision sensor to form a composite sensor system to improve the weld seam detection and tracking accuracy of mobile welding robots. Neise et al [17] combines electromagnetic acoustic transducer (EMAT), eddy current (EC) and MFL technologies, using the EMAT excitation signal as a pulsed EC excitation.…”

Resonance Suppression of a Controllable Mechanism Welding Robot End with Central Composite Design Methodology

“…Welding is an essential part of manufacturing industry, and welding robots are widely used to decrease costs, improve quality and increase productivity in which quality is one of the most important considerations in the welding process [1][2][3][4]. In the process of operation, vibration inevitably occurs in the welding robot system due to multi-source excitation such as the motor drive and welding gun impact vibration.…”