scholarly journals 3D Weld Pool Surface Geometry Measurement with Adaptive Passive Vision Images

2019 ◽  
Vol 98 (12) ◽  
pp. 379s-386s
Author(s):  
ZONGYAO CHEN ◽  
◽  
JIAN CHEN ◽  
ZHILI FENG
Keyword(s):  
Real Time ◽  
Weld Pool ◽  
Three Dimensional ◽  
Bead Geometry ◽  
Monitoring And Control ◽  
Surface Geometry ◽  
Weld Bead Geometry ◽  
Pool Surface ◽  
Weld Pool Geometry ◽  
Geometry Measurement

Monitoring weld pool geometry without the appropriate auxiliary light source remains challenging due to the interference from the intense arc light. In this work, a new software framework was developed to measure the key features related to welding pool three-dimensional (3D) geometry based on the two-dimensional (2D) passive vision images. It was found that the interference of the arc light on the weld pool image can be effectively controlled by adjusting the camera exposure time based on the decision made from machine learning classifier. Weld pool width, trailing length, and surface height (SH) were calculated in real time, and the result agreed with the measurement of the weld bead geometry. The method presented here established the foundation for real-time penetration monitoring and control.

Sensing and Control of Weld Pool Geometry for Automated GTA Welding

1995 ◽  
Vol 117 (2) ◽  
pp. 210-222 ◽  
Author(s):  
R. Kovacevic ◽  
Y. M. Zhang ◽  
S. Ruan
Keyword(s):  
Real Time ◽  
Weld Pool ◽  
Gta Welding ◽  
Image Features ◽  
Nitrogen Laser ◽  
Pool Surface ◽  
Weld Pool Geometry ◽  
Difficult Procedure ◽  
Robust Adaptive ◽  
And Control

Weld pool geometry is a crucial factor in determining welding quality, especially in the case of sheet welding. Its feedback control should be a fundamental requirement for automated welding. However, the real-time precise measurement of pool geometry is a difficult procedure. It has been shown that vision sensing is a promising approach for monitoring the weld pool geometry. Quality images that can be processed in real-time to detect the pool geometry are acquired by using a high shutter speed camera assisted with nitrogen laser as an illumination source. However, during practical welding, impurities or oxides existing on the pool surface complicate image processing. The image features are analyzed and utilized for effectively processing the image. It is shown that the proposed algorithm can always detect the pool boundary with sufficient accuracy in less than 100 ms. Based on this measuring technique, a robust adaptive system has been developed to control the pool area. Experiments show that the proposed control system can overcome the influence caused by various disturbances.

ANFIS Modeling of Human Welder's Response to Three-Dimensional Weld Pool Surface in GTAW

2013 ◽  
Vol 135 (2) ◽  
Author(s):  
YuKang Liu ◽  
WeiJie Zhang ◽  
YuMing Zhang
Keyword(s):  
Weld Pool ◽  
Fuzzy Inference ◽  
Vision System ◽  
Three Dimensional ◽  
Welding Current ◽  
Anfis Model ◽  
Inference System ◽  
Pool Surface ◽  
Weld Pool Geometry ◽  
Weld Pool Surface

Understanding and modeling of the human welder's response to three-dimensional (3D) weld pool surface may help develop next generation intelligent welding machines and train welders faster. In this paper, human welder's adjustment on the welding current as a response to the 3D weld pool surface characterized by its width, length, and convexity is studied. An innovative vision system is used to real-time measure the specular 3D weld pool surface under strong arc in gas tungsten arc welding (GTAW). Experiments are designed to produce random changes in the welding speed resulting in fluctuations in the weld pool surface. Adaptive neuro-fuzzy inference system (ANFIS) is proposed to correlate the human welder's response to the 3D weld pool surface using three inputs including the weld pool width, length and convexity. The human welder's behavior is not only related to the 3D weld pool geometry but also relies on the welder's previous adjustment. In this sense, a four input ANFIS model adding the previous human welder's response as a model input is developed and compared with the fitted linear model. It is found that the proposed ANFIS model can derive a more accurate correlation between the human welder's responses and the weld pool geometry and help understand the nonlinear response of the human welder to 3D weld pool surfaces.

Reconstruction of Three-Dimensional Gas Metal Arc Weld Pool Surface From Reflected Laser Pattern

2013 ◽  
Vol 135 (2) ◽  
Author(s):  
XiaoJi Ma ◽  
YuMing Zhang
Keyword(s):  
Weld Pool ◽  
High Speed ◽  
Gas Metal Arc Welding ◽  
Three Dimensional ◽  
Reconstruction Algorithm ◽  
Reconstruction Algorithms ◽  
Surface Geometry ◽  
Pool Surface ◽  
Metal Arc Welding ◽  
Weld Pool Surface

A system has been developed to measure the three-dimensional weld pool surface geometry in the gas metal arc welding (GMAW) process. It utilizes the specular nature of the weld pool surface by projecting a five-line laser pattern onto the surface and imaging its reflection. Specifically, the laser reflection is intercepted by an imaging plane and captured using a high speed camera. The reflected pattern is used to reconstruct the weld pool surface based on the law of reflection. Two reconstruction algorithms, referred to as center-points reconstruction and piece-wise weld pool surface reconstruction algorithm, are applied to sequentially reconstruct the weld pool height and three-dimensional surface geometry. Reconstructions has been conducted using simulated weld pool surface to provide a method to compare the reconstruction result with a known surface and evaluate the reconstruction accuracy. It is found that the proposed method is capable of reconstructing weld pool surface with acceptable accuracy. The height error of reconstructed center-points is less than 0.1 mm and the error of estimated weld pool boundary is less than 10%. Reconstruction results from images captured in welding experiments are also demonstrated.

scholarly journals Analysis and Characterization of the Weld Pool and Bead Geometry of Inconel 625 Super-TIG Welds

Metals ◽  
2020 ◽  
Vol 10 (3) ◽  
pp. 365
Author(s):  
Jung Hyun Park ◽  
Muralimohan Cheepu ◽  
Sang Myung Cho
Keyword(s):  
Production Rate ◽  
Weld Pool ◽  
Tig Welding ◽  
Fusion Welding ◽  
Inconel 625 ◽  
Bead Geometry ◽  
Weld Bead Geometry ◽  
High Production Rate ◽  
The Difference ◽  
Bead Height

The welding market is changing globally, becoming eco-friendly, robotized and automated. The tungsten inert gas welding (TIG) process is indispensable in industries that require high-quality welds with the absence of spatter and fumes. However, the production rate of TIG welding is very low, which limits its many applications. The present study introduces a novel TIG welding method called super-TIG welding. Super-TIG welding is able to produce a high production rate of welds compared to other fusion welding methods. In super-TIG welding, the novel C-type filler is used, which is different from the conventional TIG welding of circular wire. The relations of the heat input ratio in super-TIG welding to weld pool length and weld bead geometry were measured using the Inconel 625 C-filler. Two types of deposition techniques were used for a bead-on-plate welds, such as stringer beads and oscillation beads. The weld pool and bead geometry measurements are found to be different between stringer beads and oscillation bead techniques. The length of the molten pool and bead size were higher for oscillation beads over the stringer beads. These changes were associated with the difference in heat transfer contact area and bead height.

Sign in / Sign up

Export Citation Format

Share Document