Deep Learning for <i>In Situ</i> and Real-Time Quality Monitoring in Additive Manufacturing Using Acoustic Emission

Shevchik, Sergey; Masinelli, Giulio; Kenel, Christoph; Leinenbach, Christian; Wasmer, Kilian

doi:10.1109/tii.2019.2910524

Cited by 143 publications

(52 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the increase in depth of the keyhole, it becomes unstable, which leads to its partial collapse during the process, trapping the overheated vapor in the melted surrounding. This results in porosity after resolidification of the melt pool [9], [32], [33].…”

Section: Results and Discussion A Dataset Categorization And Labmentioning

confidence: 99%

“…Additional advantage of wavelets is in their close relation with the finite impulse response filters (FIRs) that allow de-noising the inputs and potentially allow adapting the processing to the given signals [37]. The efficiency of wavelets was demonstrated by Shevchik et al [31], [32] for additive manufacturing -a close process to laser welding. Besides, the extraction of the data in the time-frequency domain using wavelets may help in the physical interpretation of the observed phenomena.…”

Section: Features Extraction Using M-band Waveletsmentioning

confidence: 99%

“…In the work of Deyong et al [29], support vector machine (SVM) and feedforward neural network (FNN) were applied to detect defects using OE. Wasmer et al [30] and Shevchik et al [31], [32] successfully applied convolutional neural network (CNN) and spectral convolutional neural network (SCNN), respectively, to differentiate AE features of dissimilar quality in additive manufacturing -a process with many similarities to laser welding. Le-Quang et al [33] used high speed X-ray imaging to show the real challenge to monitor the keyhole dynamic, in particular the transition stable-unstable keyhole but even more important the creation and disappearance of pores during the process.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Laser Welding Quality Monitoring via Graph Support Vector Machine With Data Adaptive Kernel

et al. 2019

Self Cite

View full text Add to dashboard Cite

Laser welding is a rapidly developing technology that is of utmost importance in a number of industrial processes. The physics of the process has been investigated over the past 50 years and is mostly well understood. Nevertheless, online laser-quality monitoring remains an open issue until today due to its dynamic complexity. This paper is a supplement to existing approaches in the field of in situ and real-time laser-quality monitoring that presents a novel combination of state-of-the-art sensors and machine learning for data processing. The investigations were carried out using laser welding of titanium workpieces. The quality was estimated a posteriori by the visual inspection of cross-sections of the welded joints. Four quality categories were defined to cover the two main laser welding regimes: conduction and keyhole. The signals from the laser back reflection and optical and acoustic emissions were recorded during the laser welding process and were decomposed with the M-band wavelets. The relative energies of narrow frequency bands were taken as descriptive features. The correlation of the extracted features with the laser welding quality was carried out using the Laplacian graph support vector machine classifier. Also, an adaptive kernel for the classifier was developed to improve the analysis of the distributions of the complex features and was constructed from Gaussian mixtures. The presented laser welding setup and the developed adaptive kernel algorithm were able to classify the quality for every 2 µm of the welded joint with an accuracy ranged between 85.9% and 99.9%. Finally, the results of the developed adaptive kernel were compared with stateof-the-art machine learning methods.

show abstract

Section: Results and Discussion A Dataset Categorization And Labmentioning

confidence: 99%

Section: Features Extraction Using M-band Waveletsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Laser Welding Quality Monitoring via Graph Support Vector Machine With Data Adaptive Kernel

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…WPT spectrograms, formed as the relative energies of the frequency bands, provide simplified time‐frequency representations of the original signals (ie including a lower number of elements and, at the same time, conserving the features of the signal evolution). In the works of Shevchik et al [15, 17, 18], it was shown that such representation of the input data allows reducing the training sets, still providing a high classification accuracy. In the present contribution, these previously reported results were proved, while feeding the raw signals to both algorithms from the training set and showing lower classification accuracy.…”

Section: Methodsmentioning

confidence: 99%

“…Laser‐induced AE is a well‐known phenomenon [7, 13] and the modulations of AE are strongly dependent from the chemical composition, mechanical, and optical properties of the tissues that are exposed to laser irradiation [7, 13]. The same approach has been well established in industrial applications such as laser welding and additive manufacturing [15–19]. Based on these experiences, we believe that this approach will potentially provide information about the ablated zone in biomedical applications as well.…”

Section: Introductionmentioning

confidence: 96%

Machine learning monitoring for laser osteotomy

Shevchik

Kenhagho

Le-Quang

et al. 2021

Journal of Biophotonics

Self Cite

View full text Add to dashboard Cite

This work proposes a new online monitoring method for an assistance during laser osteotomy. The method allows differentiating the type of ablated tissue and the applied dose of laser energy. The setup analyzes the laser‐induced acoustic emission, detected by an airborne microphone sensor. The analysis of the acoustic signals is carried out using a machine learning algorithm that is pre‐trained in a supervised manner. The efficiency of the method is experimentally evaluated with several types of tissues, which are: skin, fat, muscle, and bone. Several cutting‐edge machine learning frameworks are tested for the comparison with the resulting classification accuracy in the range of 84–99%. It is shown that the datasets for the training of the machine learning algorithms are easy to collect in real‐life conditions. In the future, this method could assist the doctors during laser osteotomy, minimizing the damage of the nearby healthy tissues and provide cleaner pathologic tissue removal.

show abstract

In Situ Real-Time Monitoring Versus Post NDE for Quality Assurance of Additively Manufactured Metal Parts

Maierhofer¹,

Altenburg²,

Scheuschner³

2021

Handbook of Nondestructive Evaluation 4.0

View full text Add to dashboard Cite

Deep Learning for In Situ and Real-Time Quality Monitoring in Additive Manufacturing Using Acoustic Emission

Cited by 143 publications

References 31 publications

Laser Welding Quality Monitoring via Graph Support Vector Machine With Data Adaptive Kernel

Laser Welding Quality Monitoring via Graph Support Vector Machine With Data Adaptive Kernel

Machine learning monitoring for laser osteotomy

In Situ Real-Time Monitoring Versus Post NDE for Quality Assurance of Additively Manufactured Metal Parts

Contact Info

Product

Resources

About