Automatic Fault Detection for Selective Laser Melting using Semi-Supervised Machine Learning

Okaro, Ikenna, Jayasinghe, Sarini, Sutcliffe, Chris, Black, Kate ORCID: 0000-0003-3638-6518, Paoletti, Paolo ORCID: 0000-0001-6131-0377 and Green, Peter (2019) Automatic Fault Detection for Selective Laser Melting using Semi-Supervised Machine Learning. Additive Manufacturing, 27. pp. 42-53.

Access the full-text of this item by clicking on the Open Access link.

	Text Automatic Fault Detection for Selective Laser Melting Using Semi-Supervised Machine Learning.pdf - Submitted version Download (1MB)
	Text Automatic Fault Detection for Laser Powder-Bed Fusionusing Semi-Supervised Machine Learning.pdf - Author Accepted Manuscript Download (2MB)

Abstract

Risk-averse areas such as the medical, aerospace and energy sectors have been somewhat slow towards accepting and applying Additive Manufacturing (AM) in many of their value chains. This is partly because there are still significant uncertainties concerning the quality of AM builds. This paper introduces a machine learning algorithm for the automatic detection of faults in AM products. The approach is semi-supervised in that, during training, it is able to use data from both builds where the resulting components were certified and builds where the quality of the resulting components is unknown. This makes the approach cost efficient, particularly in scenarios where part certification is costly and time consuming. The study specifically analyses Laser Powder-Bed Fusion (L-PBF) builds. Key features are extracted from large sets of photodiode data, obtained during the building of 49 tensile test bars. Ultimate tensile strength (UTS) tests were then used to categorise each bar as ‘faulty’ or ‘acceptable’. Using a variety of approaches (Receiver Operating Characteristic (ROC) curves and 2-fold cross-validation), it is shown that, despite utilising a fraction of the available certification data, the semi-supervised approach can achieve results comparable to a benchmark case where all data points are labelled. The results show that semi-supervised learning is a promising approach for the automatic certification of AM builds that can be implemented at a fraction of the cost currently required.

Item Type:	Article
Uncontrolled Keywords:	Laser powder-bed fusion, Process control, Semi-supervised machine Learning, Randomised singular value decomposition
Depositing User:	Symplectic Admin
Date Deposited:	21 Feb 2019 08:31
Last Modified:	18 Feb 2023 06:16
DOI:	10.1016/j.addma.2019.01.006
Open Access URL:	https://doi.org/10.1016/j.addma.2019.01.006
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3033196

Available Versions of this Item

• Automatic Fault Detection for Selective Laser Melting using Semi-Supervised Machine Learning. (deposited 21 Sep 2018 08:44)
  • Automatic Fault Detection for Selective Laser Melting using Semi-Supervised Machine Learning. (deposited 21 Feb 2019 08:31) [Currently Displayed]