Burn-through prediction and weld depth estimation by deep learning model monitoring the molten pool in gas metal arc welding with gap fluctuation

Nomura, Kazufumi; Fukushima, Kaori; Matsumura, T.; Asai, Satoru

doi:10.1016/j.jmapro.2020.10.019

Cited by 54 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Long short-term memory neural networks (Zhou et al 2020a) are applied for learning abstract representation from the temporal data for predicting quality. Many more works exist that apply DL for quality monitoring or optimisation in other welding processes, such as laser welding (Mikhaylov et al 2019a;Shevchik et al 2020;Zhang et al 2019a), arc welding (Nomura et al 2021;Zhang et al 2019b), resistance wire welding (Guo et al 2017) etc. It can been seen there exist much more works about classic ML than DL for quality monitoring of RSW.…”

Section: Modellingmentioning

confidence: 99%

Machine learning with domain knowledge for predictive quality monitoring in resistance spot welding

et al. 2022

View full text Add to dashboard Cite

Digitalisation trends of Industry 4.0 and Internet of Things led to an unprecedented growth of manufacturing data. This opens new horizons for data-driven methods, such as Machine Learning (ML), in monitoring of manufacturing processes. In this work, we propose ML pipelines for quality monitoring in Resistance Spot Welding. Previous approaches mostly focused on estimating quality of welding based on data collected from laboratory or experimental settings. Then, they mostly treated welding operations as independent events while welding is a continuous process with a systematic dynamics and production cycles caused by maintenance. Besides, model interpretation based on engineering know-how, which is an important and common practice in manufacturing industry, has mostly been ignored. In this work, we address these three issues by developing a novel feature-engineering based ML approach. Our method was developed on top of real production data. It allows to analyse sequences of welding instances collected from running manufacturing lines. By capturing dependencies across sequences of welding instances, our method allows to predict quality of upcoming welding operations before they happen. Furthermore, in our work we strive to combine the view of engineering and data science by discussing characteristics of welding data that have been little discussed in the literature, by designing sophisticated feature engineering strategies with support of domain knowledge, and by interpreting the results of ML analysis intensively to provide insights for engineering. We developed 12 ML pipelines in two dimensions: settings of feature engineering and ML methods, where we considered 4 feature settings and 3 ML methods (linear regression, multi-layer perception and support vector regression). We extensively evaluated our ML pipelines on data from two running industrial production lines of 27 welding machines with promising results.

show abstract

Section: Modellingmentioning

confidence: 99%

Machine learning with domain knowledge for predictive quality monitoring in resistance spot welding

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This correlation is an indirect connection, but it is often inapplicable when the conditions change. For example, our recent study estimated the depth of invisible internal penetration by machine learning from molten pool monitoring [4]; however, it is an indirect approach that is not based on principles of physics. Currently, only radiographic testing (RT) or ultrasonic testing (UT) is applicable for direct measurement of internal information.…”

Section: Introductionmentioning

confidence: 99%

In situ measurement of ultrasonic behavior during lap spot welding with laser ultrasonic method

Nomura

Deno

Matsuida

et al. 2022

NDT & E International

Self Cite

View full text Add to dashboard Cite

“…Moreover, as welding processes are extremely complicated by themselves due to the extensive number of underlying physical phenomena, it has been recently stated the need of sensor combination or fusion to fully address the defects generated during the joining process [7][8][9]. A combination of online monitoring and artificial intelligence is another line of research to overcome described limitations online [2,[9][10][11].…”

Section: Introductionmentioning

confidence: 99%

A calibration tool for weld penetration depth estimation based on dimensional and thermal sensor fusion

Zalakain-Azpiroz

Rodriguez

Yedra

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Weld quality monitoring and assessment in industrial robotic arc welding processes is key to ensure suitability of a component for the intended application. In particular, weld penetration depth is as a major fabrication requirement that has to be addressed. Several alternatives have been proposed based on the use of individual monitoring techniques, but, due to the physical challenges of the welding process and accessibility restrictions to the weld root, multi-sensor approaches have been recently developed. These methods require the adoption of complex setups or calibration strategies. In this work, a multi-sensor approach is proposed to create a calibration tool for weld penetration depth assessment, overcoming physical accessibility restrictions and enabling depth evaluation instantaneously, opening the gate for online usage.

show abstract

Burn-through prediction and weld depth estimation by deep learning model monitoring the molten pool in gas metal arc welding with gap fluctuation

Cited by 54 publications

References 23 publications

Machine learning with domain knowledge for predictive quality monitoring in resistance spot welding

Machine learning with domain knowledge for predictive quality monitoring in resistance spot welding

In situ measurement of ultrasonic behavior during lap spot welding with laser ultrasonic method

A calibration tool for weld penetration depth estimation based on dimensional and thermal sensor fusion

Contact Info

Product

Resources

About