Robotic GMAW online learning: issues and experiments

Rios‐Cabrera, Reyes; Morales-Díaz, América Berenice; Aviles-Viñas, Jaime F.; López-Juárez, Ismael

doi:10.1007/s00170-016-8618-0

Cited by 14 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For an active vision sensing measurement process, researchers generally use the laser to illuminate the weld bead to create a deformation that is proportional to the bead width and height. Hence, WBGFs are modeled by detecting the bead edges such as Canny edge detection [ 26 , 27 ].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Modeling of Weld Bead Geometry Features in Thick Plate GMAW Based on Machine Vision and Learning

Pan

et al. 2020

Sensors

View full text Add to dashboard Cite

Weld bead geometry features (WBGFs) such as the bead width, height, area, and center of gravity are the common factors for weighing welding quality control. The effective modeling of these WBGFs contributes to implementing timely decision making of welding process parameters to improve welding quality and enhance automatic levels. In this work, a dynamic modeling method of WBGFs is presented based on machine vision and learning in multipass gas metal arc welding (GMAW) with typical joints. A laser vision sensing system is used to detect weld seam profiles (WSPs) during the GMAW process. A novel WSP extraction method is proposed using scale-invariant feature transform and machine learning. The feature points of the extracted WSP, namely the boundary points of the weld beads, are identified with slope mutation detection and number supervision. In order to stabilize the modeling process, a fault detection and diagnosis method is implemented with cubic exponential smoothing, and the diagnostic accuracy is within 1.50 pixels. A linear interpolation method is presented to implement sub pixel discrimination of the weld bead before modeling WBGFs. With the effective feature points and the extracted WSP, a scheme of modeling the area, center of gravity, and all-position width and height of the weld bead is presented. Experimental results show that the proposed method in this work adapts to the variable features of the weld beads in thick plate GMAW with T-joints and butt/lap joints. This work can provide more evidence to control the weld formation in a thick plate GMAW in real time.

show abstract

Section: Introductionmentioning

confidence: 99%

Dynamic Modeling of Weld Bead Geometry Features in Thick Plate GMAW Based on Machine Vision and Learning

Pan

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Current advanced sensor technology provides accurate and comprehensive information about the welding process, and multi-variable parameter control has thus been approached with the use of AI decision-making systems. AI-based control systems have been integrated with various sensors such as laser sensors, thermal sensors, arc imaging, and acoustic sensors to address quality inconsistency in conventional automated welding [10,12,13,[18][19][20][21][22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies have reported the development of ANN systems capable of predicting the weld quality outcome [1,10,19,[26][27][28][29][30][31][32][33]. In these studies, ANNbased prediction has been studied considering bead width, bead height, and achieved depth of penetration of the weld.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network Controlled GMAW System: Penetration and Quality Assurance in a Multi-Pass Butt Weld Application

Penttilä

Kah

Ratava

et al. 2019

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Intelligent welding parameter control is fast becoming a key instrument for attaining quality consistency in automated welding. Recent scientific breakthroughs in intelligent systems have turned the focus of adaptive welding control to artificial intelligencebased welding parameter control. The aim of this study is to combine artificial neural network (ANN) decision-making software and a machine vision system to develop an adaptive artificial intelligence (AI)-based gas metal arc welding (GMAW) parameter control system. The machine vision system uses a laser sensor to scan the upcoming seam and gather seam profile data. Based on further processing of the seam profile data, welding parameters are optimized by the decision-making system. In this work, the developed system is tested in a multivariable welding condition environment and its performance is evaluated. The quality of the welds was consistent and surpassed the required quality level. Additionally, the heat-affected zone (HAZ) was evaluated by microscopy, X-ray, and scanning electron microscope (SEM) imaging. It is concluded that the developed ANN system is suitable for implementation in automated applications, can improve quality consistency and cost efficiency, and reduce required workpiece preparation and handling.

show abstract

“…Ding et al (2015) proposed a multi-bead overlapping fitting model for RWAAM, it provided a better accuracy than the traditional overlapping model. Rios-Cabrera et al (2016) presented an on-line/off-line learning and testing method, showing that industrial robots can acquire a useful knowledge base without human intervention to learn and reproduce bead geometries. Li et al (2018) proposed a layer-overlapping strategy, it suggested a little increase of the first bead and the last bead of the lap layers to solve the materials shortage problem at the edges of the layers.…”

Section: Introductionmentioning

confidence: 99%

Fabrication of curved overhanging thin-walled structure with robotic wire and arc additive manufacturing (RWAAM)

Qin

et al. 2019

View full text Add to dashboard Cite

Purpose Robotic wire and arc additive manufacturing (RWAAM) is becoming more and more popular for its capability of fabricating metallic parts with complicated structure. To unlock the potential of 6-DOF industrial robots and improve the power of additive manufacturing, this paper aims to present a method to fabricate curved overhanging thin-walled parts free from turn table and support structures. Design/methodology/approach Five groups of straight inclined thin-walled parts with different angles were fabricated with the torch aligned with the inclination angle using RWAAM, and the angle precision was verified by recording the growth of each layer in both horizontal and vertical directions; furthermore, the experimental phenomena was explained with the force model of the molten pool and the forming characteristics was investigated. Based on the results above, an algorithm for fabricating curved overhanging thin-walled part was presented and validated. Findings The force model and forming characteristics during the RWAAM process were investigated. Based on the result, the influence of the torch orientation on the weld pool flow was used to control the pool flow, then a practical algorithm for fabricating curved overhanging thin-walled part was proposed and validated. Originality/value Regarding the fabrication of curved overhanging thin-walled parts, given the influences of the torch angles on the deposited morphology, porosity formation rate and weld pool flow, the flexibility of 6-DOF industrial robot was fully used to realize instant adjustment of the torch angle. In this paper, the deposition point and torch orientation of each layer of a robotic fabrication path was determined by the contour equation of the curve surface. By adjusting the torch angle, the pool flow was controlled and better forming quality was acquired.

show abstract

Robotic GMAW online learning: issues and experiments

Cited by 14 publications

References 20 publications

Dynamic Modeling of Weld Bead Geometry Features in Thick Plate GMAW Based on Machine Vision and Learning

Dynamic Modeling of Weld Bead Geometry Features in Thick Plate GMAW Based on Machine Vision and Learning

Artificial Neural Network Controlled GMAW System: Penetration and Quality Assurance in a Multi-Pass Butt Weld Application

Fabrication of curved overhanging thin-walled structure with robotic wire and arc additive manufacturing (RWAAM)

Contact Info

Product

Resources

About