Porosity Prediction in AM Using PBF-LB Employing Time-Series Classification

Vivek Mahato; Dermot Brabazon; Annalina Caputo

doi:10.4028/p-54j053

Paper Titles

Uncertainty Quantification in the Directed Energy Deposition Process Using Deep Learning-Based Probabilistic Approach
p.323

Thermal Modeling of Laser Powder Bed Fusion during Printing on Temperature-Unstable Materials Considering Local Sintering
p.331

Effect of Finite Element Mesh Size and Time-Increment on Predicting Part-Scale Temperature for Powder Bed Fusion Process
p.341

3D Modeling of Polymer Selective Laser Sintering Process: Laser-Polymer Interaction Modeling
p.349

Porosity Prediction in AM Using PBF-LB Employing Time-Series Classification
p.358

Modelling Thermoplastic Filaments’ Sintering by Level Set Method
p.365

Ultrasonic Monitoring of Part’s Height and Layer Thickness in Powder Bed Fusion
p.373

Metal Forming-Induced Residual Stresses and Rule of Mixtures’ Prediction of Tensile Behavior of Bimetallic Wires
p.381

Process Stability and Reproducibility of the Dieless Drawing Process for AZ31 Magnesium Wires
p.389

HomeKey Engineering MaterialsKey Engineering Materials Vol. 926Porosity Prediction in AM Using PBF-LB Employing...

Porosity Prediction in AM Using PBF-LB Employing Time-Series Classification

Abstract:

Additive Manufacturing (AM) using Powder-Bed Fusion Laser-Beam (PBF-LB) has great potential; however, it has challenges due to its sensitivity to the process parameters [1]. The availability of big data generated in AM facilitates the employment of Machine Learning (ML) tools to understand the process and have a predictive control over the production. An intelligent system like this can thus reduce material wastage and energy cost while increasing a plant’s product quality and throughput. Time-series summary statistics (like mean and variance) can discard valuable discriminatory signatures embedded in raw sensor data. Therefore, special ML time-series classification (TSC) tools that can extract and utilise these signatures from the raw data are much more effective for a task like porosity prediction [1]. However, the data employed in [1] pertains to products with artificially designed pores or gaps. This study focuses on naturally occurring pores, rarer, and evaluates k-Nearest Neighbour (k-NN) with Dynamic Time Warping (DTW) over real-world manufacturing data to classify the porosity of individual raster scans. We believe that natural pores have more diverse signatures than artificial pores, as each pore varies in characteristics (like size and morphology).

By email Full Text Pdf

You might also be interested in these eBooks

Achievements and Trends in Material Forming

View Preview

Info:

Periodical:

Key Engineering Materials (Volume 926)

Pages:

358-364

DOI:

https://doi.org/10.4028/p-54j053

Citation:

Cite this paper

Online since:

July 2022

Authors:

Vivek Mahato*, Dermot Brabazon, Annalina Caputo

Keywords:

Additive Manufacturing, Defect Detection, Machine Learning, Time-Series Classification

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

* - Corresponding Author

References

[1] V. Mahato, M. A. Obeidi, D. Brabazon, and P. Cunningham, Detecting voids in 3d printing using melt pool time series data,, Journal of Intelligent Manufacturing, (2020).

DOI: 10.1007/s10845-020-01694-8

Google Scholar

[2] M. R. Nichols, The pros & cons of powder bed fusion,, Metal Powder Report, vol. 76, no. 2, pp.90-91, (2021).

DOI: 10.1016/j.mprp.2020.04.004

Google Scholar

[3] S. S. Razvi, S. C. Feng, A. Narayanan, Y.-T. T. Lee, and P. Witherell, A review of machine learning applications in additive manufacturing,, Volume 1: 39th Computers and Information in Engineering Conference, (2019).

DOI: 10.1115/detc2019-98415

Google Scholar

[4] X. Qi, G. Chen, Y. Li, X. Cheng, and C. Li, Applying Neural-Network-Based Machine Learning to Additive Manufacturing: Current Applications, Challenges, and Future Perspectives,, Engineering, (2019).

DOI: 10.1016/j.eng.2019.04.012

Google Scholar

[5] Z. Zhang and K. Friedrich, Artificial neural networks applied to polymer composites: a review," Composites Science and Technology, vol. 63, no. 14, pp.2029-2044, 2003. 8https://imbalanced-learn.org/stable/index.html[6] A. Agrawal and A. Choudhary, "Perspective: Materials informatics and big data: Realization of the "fourth paradigm" of science in materials science,, APL Materials, vol. 4, no. 5, p.53208, (2016).

DOI: 10.1063/1.4946894

Google Scholar

[7] Z. Li, Z. Zhang, J. Shi, and D. Wu, Prediction of surface roughness in extrusion-based additive manufacturing with machine learning,, Robotics and Computer-Integrated Manufacturing, vol. 57, pp.488-495, (2019).

DOI: 10.1016/j.rcim.2019.01.004

Google Scholar

[8] G. Pilania, C. Wang, X. Jiang, S. Rajasekaran, and R. Ramprasad, Accelerating materials property predictions using machine learning,, Scientific Reports, vol. 3, no. 1, (2013).

DOI: 10.1038/srep02810

Google Scholar

[9] V. Mahato and P. Cunningham, A case-study on the impact of dynamic time warping in time series regression,, 3nd ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data, vol. abs/2010.05270, (2018).

Google Scholar

[10] V. Mahato, M. A. Obeidi, D. Brabazon, and P. Cunningham, An evaluation of classification methods for 3d printing time-series data,, International Federation of Automatic Control, World Congress, vol. abs/2010.00903, (2020).

DOI: 10.1016/j.ifacol.2020.12.1992

Google Scholar

[11] G. H. Chen and D. Shah, Explaining the success of nearest neighbor methods in prediction,, Foundations and Trends® in Machine Learning, vol. 10, no. 5-6, pp.337-588, (2018).

DOI: 10.1561/2200000064

Google Scholar

[12] H. Sakoe and S. Chiba, Dynamic programming algorithm optimization for spoken word recognition,, IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 26, pp.43-49, February (1978).

DOI: 10.1109/tassp.1978.1163055

Google Scholar