In Situ Quality Monitoring in AM Using Acoustic Emission: A Reinforcement Learning Approach

Wasmer, Kilian; Le-Quang, Tri; Meylan, Bastian; Shevchik, Sergey

doi:10.1007/s11665-018-3690-2

Cited by 107 publications

(38 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They are the followings: a more efficient noise suppression inside the network, an input data dimensionality reduction, some investigations of conditions, determine the limits for over fit and finally use self-learning of new events. The later has been already conducted by using reinforcement learning [41].…”

Section: Discussionmentioning

confidence: 99%

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

Shevchik

Masinelli

Kenel

et al. 2019

IEEE Trans. Ind. Inf.

Self Cite

143

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

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

Shevchik

Masinelli

Kenel

et al. 2019

IEEE Trans. Ind. Inf.

Self Cite

143

View full text Add to dashboard Cite

“…One-dimensional data can be processed faster but provide less information compared to two- and three-dimensional data. Shevchik et al [ 73 , 74 ] investigated the possibility to use acoustic emission to monitor quality by combining the acoustic emission sensor with the ANN. Figure 9 shows a schematic of the workflow used to monitor the quality during the printing process.…”

Section: Applications Of Ann In 3d Printingmentioning

confidence: 99%

“… Schematic of the workflow used to monitor the quality during the printing process; based on the data from [ 73 , 74 ]. …”

Section: Figurementioning

confidence: 99%

Artificial Neural Network Algorithms for 3D Printing

et al. 2020

View full text Add to dashboard Cite

Additive manufacturing with an emphasis on 3D printing has recently become popular due to its exceptional advantages over conventional manufacturing processes. However, 3D printing process parameters are challenging to optimize, as they influence the properties and usage time of printed parts. Therefore, it is a complex task to develop a correlation between process parameters and printed parts’ properties via traditional optimization methods. A machine-learning technique was recently validated to carry out intricate pattern identification and develop a deterministic relationship, eliminating the need to develop and solve physical models. In machine learning, artificial neural network (ANN) is the most widely utilized model, owing to its capability to solve large datasets and strong computational supremacy. This study compiles the advancement of ANN in several aspects of 3D printing. Challenges while applying ANN in 3D printing and their potential solutions are indicated. Finally, upcoming trends for the application of ANN in 3D printing are projected.

show abstract

“…In a L-PBF process, a simple microphone was used to monitor the process signature in Ye et al (2017) and machine learning methods were employed to find process signals correlating to irregular track formation and porosity formation due to balling and overheating, showing great promise for the method (Ye et al, 2018). Under less severe conditions with smaller porosities, a similar approach was recently found to be successful, though using a more specialized microphone (fiber Bragg grating) (Shevchik et al, 2018;Wasmer et al, 2018;Wasmer et al, 2019). A similar concept is under development and preliminary results reported in (Eschner et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Monitoring of Laser Powder Bed Fusion by Acoustic Emission: Investigation of Single Tracks and Layers

et al. 2021

View full text Add to dashboard Cite

Quality concerns in laser powder bed fusion (L-PBF) include porosity, residual stresses and deformations during processing. Single tracks are the fundamental building blocks in L-PBF and their shape and geometry influence subsequent porosity in 3D L-PBF parts. The morphology of single tracks depends primarily on process parameters. The purpose of this paper is to demonstrate an approach to acoustic emission (AE) online monitoring of the L-PBF process for indirect defect analysis. This is demonstrated through the monitoring of single tracks without powder, with powder and in layers. Gas-borne AE signals in the frequency range of 2–20 kHz were sampled using a microphone placed inside the build chamber of a L-PBF machine. The single track geometry and shape at different powder thickness values and laser powers were studied together with the corresponding acoustic signals. Analysis of the acoustic signals allowed for the identification of characteristic amplitudes and frequencies, with promising results that support its use as a complementary method for in-situ monitoring and real-time defect detection in L-PBF. This work proves the capability to directly detect the balling effect that strongly affects the formation of porosity in L-PBF parts by AE monitoring.

show abstract

In Situ Quality Monitoring in AM Using Acoustic Emission: A Reinforcement Learning Approach

Cited by 107 publications

References 30 publications

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

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

Artificial Neural Network Algorithms for 3D Printing

Monitoring of Laser Powder Bed Fusion by Acoustic Emission: Investigation of Single Tracks and Layers

Contact Info

Product

Resources

About