Neural Architecture Search for Bearing Fault Classification

Edicson Diaz, Edicson Diaz, Enrique Naredo, Nicolas Díaz, Douglas Dias, Maria Diaz, Maria Diaz, Susan Harnett, Conor Ryan

2024

Abstract

In this research, we address bearing fault classification by evaluating three neural network models: 1D Con-volutional Neural Network (1D-CNN), CNN-Visual Geometry Group (CNN-VGG), and Long Short-Term Memory (LSTM). Utilizing vibration data, our approach incorporates data augmentation to address the limited availability of fault class data. A significant aspect of our methodology is the application of neural architecture search (NAS), which automates the evolution of network architectures, including hyperparameter tuning, significantly enhancing model training. Our use of early stopping strategies effectively prevents overfitting, ensuring robust model generalization. The results highlight the potential of integrating advanced machine learning models with NAS in bearing fault classification and suggest possibilities for further improvements, particularly in model differentiation for specific fault classes.

Paper Citation

in Harvard Style

Diaz E., Naredo E., Díaz N., Dias D., Diaz M., Harnett S. and Ryan C. (2024). Neural Architecture Search for Bearing Fault Classification. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 288-300. DOI: 10.5220/0012373100003636

in Bibtex Style

@conference{icaart24,
author={Edicson Diaz and Enrique Naredo and Nicolas Díaz and Douglas Dias and Maria Diaz and Susan Harnett and Conor Ryan},
title={Neural Architecture Search for Bearing Fault Classification},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2024},
pages={288-300},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012373100003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Neural Architecture Search for Bearing Fault Classification
SN - 978-989-758-680-4
AU - Diaz E.
AU - Naredo E.
AU - Díaz N.
AU - Dias D.
AU - Diaz M.
AU - Harnett S.
AU - Ryan C.
PY - 2024
SP - 288
EP - 300
DO - 10.5220/0012373100003636
PB - SciTePress