Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs

Asif, Kaiser; Zhang, Lu; Derrible, Sybil; Indacochea, J. E.; Ozevin, Didem; Ziebart, Brian D.

doi:10.1007/s10845-020-01667-x

Cited by 43 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The nonparametric techniques belong to the general family of ML whose main advantage is the use of algorithms to train often structurally complex models. ML approaches often achieve high accuracy thanks to their ability to capture and model nonlinear behaviors, which have made them very popular in the scientific community; ML has been used to model countless systems. − Nevertheless, because ML models tend to be structurally complex, it is often more difficult to validate trained ML models. A commonly used synonym for ML is “data driven”, as in the models developed only from observed data as opposed to those from theoretically established physical reasoning.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Prediction of TiO₂-Coating Wettability Tuned via UV Exposure

Gukeh

Moitra

Ibrahim

et al. 2021

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

Surfaces with extreme wettability (too low, superhydrophobic; too high, superhydrophilic) have attracted considerable attention over the past two decades. Titanium dioxide (TiO2) has been one of the most popular components for generating superhydrophobic/hydrophilic coatings. Combining TiO2 with ethanol and a commercial fluoroacrylic copolymer dispersion, known as PMC, can produce coatings with water contact angles approaching 170°. Another property of interest for this specific TiO2 formulation is its photocatalytic behavior, which causes the contact angle of water to be gradually reduced with rising timed exposure to UV light. While this formulation has been employed in many studies, there exists no quantitative guidance to determine or tune the contact angle (and thus wettability) with the composition of the coating and UV exposure time. In this article, machine learning models are employed to predict the required UV exposure time for any specified TiO2/PMC coating composition to attain a certain wettability (UV-reduced contact angle). For that purpose, eight different coating compositions were applied to glass slides and exposed to UV light for different time intervals. The collected contact-angle data was supplied to different regression models to designate the best method to predict the required UV exposure time for a prespecified wettability. Two types of machine learning models were used: (1) parametric and (2) nonparametric. The results showed a nonlinear behavior between the coating formulation and its contact angle attained after timed UV exposure. Nonparametric methods showed high accuracy and stability with general regression neural network (GRNN) performing best with an accuracy of 0.971, 0.977, and 0.933 on the test, train, and unseen data set, respectively. The present study not only provides quantitative guidance for producing coatings of specified wettability, but also presents a generalized methodology that could be employed for other functional coatings in technological applications requiring precise fluid/surface interactions.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine Learning Prediction of TiO₂-Coating Wettability Tuned via UV Exposure

Gukeh

Moitra

Ibrahim

et al. 2021

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of neural networks has also been extended to other areas of laser manufacturing, such as laser welding (Asif et al 2020;Günther et al 2014Günther et al , 2016, additive manufacturing (Li et al 2020;Mahato et al 2020;Mycroft et al 2020), and a method to reconstruct laser pulses (Zahavy et al 2018). Here, we extend on both these, and previous (Arnaldo et al 2018), works in the area of laser surface texturing.…”

Section: Introductionmentioning

confidence: 88%

Machine learning for multi-dimensional optimisation and predictive visualisation of laser machining

et al. 2021

View full text Add to dashboard Cite

Interactions between light and matter during short-pulse laser materials processing are highly nonlinear, and hence acutely sensitive to laser parameters such as the pulse energy, repetition rate, and number of pulses used. Due to this complexity, simulation approaches based on calculation of the underlying physical principles can often only provide a qualitative understanding of the inter-relationships between these parameters. An alternative approach such as parameter optimisation, often requires a systematic and hence time-consuming experimental exploration over the available parameter space. Here, we apply neural networks for parameter optimisation and for predictive visualisation of expected outcomes in laser surface texturing with blind vias for tribology control applications. Critically, this method greatly reduces the amount of experimental laser machining data that is needed and associated development time, without negatively impacting accuracy or performance. The techniques presented here could be applied in a wide range of fields and have the potential to significantly reduce the time, and the costs associated with laser process optimisation.

show abstract

“…The existence of a weld introduces a noticeable discontinuity in the material, leading to distinct alterations in the characteristics of AE waves as they interact with the welded area. In comparison to recent studies, like Asif et al 's research, which focuses an innovative machine learning model that leverages air-coupled acoustic emission and weld inputs for predicting welding quality, our study delves into the specific effects of welds on Acoustic Emission (AE) wave characteristics during their propagation through rail sections [10]. We aim to demonstrate how the presence of welds alters AE wave behavior, providing unique insights into health monitoring, particularly for rail sections subjected to welding.…”

Section: Introductionmentioning

confidence: 99%

Acoustic emission-based assessment of weld effects on the health monitoring of the rail section: an experimental study

Pal,

Kundu,

Datta

2024

Eng. Res. Express

View full text Add to dashboard Cite

Railways are a vital lifeline for both passengers and freight, with an extensive network connected by robust welded joints. This study explores the potential of Acoustic Emission (AE) techniques in rail health monitoring, particularly in the context of Indian rail sections and their relationship with welds. While AE-based health monitoring has gained attention, a significant gap exists in understanding welds' influence. This research bridges this gap by examining the interplay between welds and health monitoring. Welds introduce complexities in AE wave propagation, crucial for precise health assessments. Through artificial AE source simulation using the Pencil Lead Break (PLB) method across diverse rail segments, specialized sensors capture AE signals. Rigorous analysis, involving signal processing and statistical methods, reveals how welds impact AE wave behaviour and health assessment accuracy. Importantly, this research underscores how welds alter AE wave propagation, ensuring accurate health evaluations. This study's insights hold far-reaching implications, not only for enhancing current rail system maintenance but also for advancing our understanding of the critical interrelationship between welds and health monitoring, thus contributing to the longevity and reliability of rail systems.

show abstract

Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs

Cited by 43 publications

References 27 publications

Machine Learning Prediction of TiO₂-Coating Wettability Tuned via UV Exposure

Machine Learning Prediction of TiO₂-Coating Wettability Tuned via UV Exposure

Machine learning for multi-dimensional optimisation and predictive visualisation of laser machining

Acoustic emission-based assessment of weld effects on the health monitoring of the rail section: an experimental study

Contact Info

Product

Resources

About

Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs

Cited by 43 publications

References 27 publications

Machine Learning Prediction of TiO2-Coating Wettability Tuned via UV Exposure

Machine Learning Prediction of TiO2-Coating Wettability Tuned via UV Exposure

Machine learning for multi-dimensional optimisation and predictive visualisation of laser machining

Acoustic emission-based assessment of weld effects on the health monitoring of the rail section: an experimental study

Contact Info

Product

Resources

About

Machine Learning Prediction of TiO₂-Coating Wettability Tuned via UV Exposure

Machine Learning Prediction of TiO₂-Coating Wettability Tuned via UV Exposure