Publication detail
Why Machine Fault Diagnosis Should Not Be Treated as an "Overfitting Contest"
REKEM, J. PROKOP, A. OTIPKA, V. KOPEČEK, P.
English title
Why Machine Fault Diagnosis Should Not Be Treated as an "Overfitting Contest"
Type
article in a collection out of WoS and Scopus
Language
en
Original abstract
Machine learning and deep learning algorithms are increasingly popular for machine fault diagnosis tasks. Several freely available datasets serve as a benchmark to compare different diagnostic methods. This article explores the CWRU bearing fault dataset and argues that it is essential to understand the machine's operation principles and dataset properties to develop algorithms capable of transferring from laboratory environment to real-world applications.
English abstract
Machine learning and deep learning algorithms are increasingly popular for machine fault diagnosis tasks. Several freely available datasets serve as a benchmark to compare different diagnostic methods. This article explores the CWRU bearing fault dataset and argues that it is essential to understand the machine's operation principles and dataset properties to develop algorithms capable of transferring from laboratory environment to real-world applications.
Keywords in English
bearing fault detection; CWRU dataset
Released
04.09.2025
Publisher
Mendel University in Brno, Faculty of AgriSciences
Location
Brno
ISBN
978-80-7701-051-1
Book
56th INTERNATIONAL SCIENTIFIC CONFERENCE FOCUSED ON RESEARCH AND TEACHING METHODS RELATED TO VEICLES AND DRIVES
Edition number
1
Pages from–to
192–201
Pages count
10
BIBTEX
@inproceedings{BUT198698,
author="Jakub {Rekem} and Aleš {Prokop} and Václav {Otipka} and Pavel {Kopeček},
title="Why Machine Fault Diagnosis Should Not Be Treated as an "Overfitting Contest"",
booktitle="56th INTERNATIONAL SCIENTIFIC CONFERENCE FOCUSED ON RESEARCH AND TEACHING METHODS RELATED TO VEICLES AND DRIVES",
year="2025",
month="September",
pages="192--201",
publisher="Mendel University in Brno, Faculty of AgriSciences",
address="Brno",
isbn="978-80-7701-051-1"
}