Please use this identifier to cite or link to this item:
Title: Minimizing false-rejection rates in gas leak testing using an ensemble multiclass classifier for unbalanced data
Author: Costa, Diogo
Rocha, Eugénio M.
Ramalho, Pedro
Keywords: Leak Testing
Machine Learning
Multiclass Classification
Ensemble classifier
Unbalanced data
Issue Date: 2022
Publisher: Springer
Abstract: Leak testing is a fundamental stage in the manufacturing process of leak-tight products providing a non-destructive quality measurement. However, leak tests are often influenced by environmental and external factors that increase the risk of test inaccuracy. These phenomena are difficult to properly account for through mathematical models, as they are particular to each individual testing setup, nonetheless, they signify great expense to manufacturers due to substantial bottlenecking. In this paper, we introduce a real-world use-case at Bosch Thermotechnology facilities where over 23.98% of testing instances result in false-rejections. We then propose a data-driven, equipment agnostic, procedure for leak testing fault classification. We first identify seven relevant classes for fault diagnosis, and, due to the highly unbalanced nature of these classes (minority class represents only 0.27% of all data), we apply a novel unbalanced multiclass classification pipeline based on an ensemble of heterogeneous classifiers. Through this method, we are able to obtain F1-macro of 90%, representing a performance improvement of over 120% in comparison with conventional Auto-ML approaches.
Peer review: yes
DOI: 10.1007/978-3-031-20319-0_32
ISBN: 978-3-031-20318-3
Appears in Collections:CIDMA - Capítulo de livro
FAAG - Capítulo de livro

Files in This Item:
File Description SizeFormat 
ARTIIS_2022___Conf__Paper-2.pdf2.31 MBAdobe PDFembargoedAccess

Formato BibTex MendeleyEndnote Degois 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.