2020 International Conference on Omni-Layer Intelligent Systems (COINS) 2020
DOI: 10.1109/coins49042.2020.9191650
|View full text |Cite
|
Sign up to set email alerts
|

Embedded vision system for monitoring arc welding with thermal imaging and deep learning

Abstract: We develop a novel embedded vision system for online monitoring of arc welding with thermal imaging. The thermal images are able to provide clear information of the melt pool and surrounding areas during the welding process. We propose a deep learning processing pipeline with a CNN-LSTM architecture for the detection and classification of defects based on video sequences. The experimental results show that the CNN-LSTM architecture is able to model the complex dynamics of the welding process and detect and cla… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
3
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 13 publications
(4 citation statements)
references
References 17 publications
0
3
0
Order By: Relevance
“…Numerous applications have been successfully developed over the years within the field of infrared thermography research. In this regard, it has been applied in the field of material sciences (deformations and fractures, duct inspection, thermoplastic material inspection, welding process inspection, material deposition analysis, friction analysis of surfaces in contact, materials and structural mechanics heat transfer studies) [16], sports science [17], architecture and evaluation of buildings and constructions [18], historical and artistic heritage [19], inspection of electrical and electronic systems [20], aerial unmanned vehicles inspection [21], inspection and supervision of manufacturing processes [22,23], medical applications [24], security and surveillance [25], fire detection [26], etc.…”
Section: Infrared Thermographymentioning
confidence: 99%
“…Numerous applications have been successfully developed over the years within the field of infrared thermography research. In this regard, it has been applied in the field of material sciences (deformations and fractures, duct inspection, thermoplastic material inspection, welding process inspection, material deposition analysis, friction analysis of surfaces in contact, materials and structural mechanics heat transfer studies) [16], sports science [17], architecture and evaluation of buildings and constructions [18], historical and artistic heritage [19], inspection of electrical and electronic systems [20], aerial unmanned vehicles inspection [21], inspection and supervision of manufacturing processes [22,23], medical applications [24], security and surveillance [25], fire detection [26], etc.…”
Section: Infrared Thermographymentioning
confidence: 99%
“…IR thermography has been used for different kinds of applications, such as to monitor and control the weld geometry [31,32], to detect defects as lack of penetration and estimate of depth of penetration [33], and to perform seam tracking, bead width control, and cooling rate control to ensure acceptable weld quality with artificial neural networks [34]. The thermographic images have largely been studied with DL architectures [35][36][37], since they provide a gold standard for NDT methods. As an example, deep architectures have been employed to detect cracks [38] and characterize defects in a carbon-fiber-reinforced plastic specimen [39,40] by automatically analyzing thermal images and videos.…”
Section: Introductionmentioning
confidence: 99%
“…However, in order to not add more weight to the robot, embedded systems able to acquire the image, preprocess it, and make inferences are required. In the context of Industry 4.0, priority is given to low-power, stand-alone, low-cost, multimodal, digitally robust, intercommunicable, and, above all, compact systems [6]. This paper focuses on the second precept, that is, of vision systems attached to a robotic arm.…”
Section: Introductionmentioning
confidence: 99%