Finding One's Bearings in the Hyperparameter Landscape of a Wide-Kernel Convolutional Fault Detector

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hudson, Dan, Hoogen, Jurgen van den, Atzmueller, Martin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912378169327616
author Hudson, Dan
Hoogen, Jurgen van den
Atzmueller, Martin
author_facet Hudson, Dan
Hoogen, Jurgen van den
Atzmueller, Martin
contents State-of-the-art algorithms are reported to be almost perfect at distinguishing the vibrations arising from healthy and damaged machine bearings, according to benchmark datasets at least. However, what about their application to new data? In this paper, we confirm that neural networks for bearing fault detection can be crippled by incorrect hyperparameterisation, and also that the correct hyperparameter settings can change when transitioning to new data. The paper combines multiple methods to explain the behaviour of the hyperparameters of a wide-kernel convolutional neural network and how to set them. Since guidance already exists for generic hyperparameters like minibatch size, we focus on how to set architecture-specific hyperparameters such as the width of the convolutional kernels, a topic which might otherwise be obscure. We reflect different data properties by fusing information from seven different benchmark datasets, and our results show that the kernel size in the first layer in particular is sensitive to changes in the data. Looking deeper, we use manipulated copies of one dataset in an attempt to spot why the kernel size sometimes needs to change. The relevance of sampling rate is studied by using different levels of resampling, and spectral content is studied by increasingly filtering out high frequencies. We find that, contrary to speculation in earlier work, high-frequency noise is not the main reason why a wide kernel is preferable to a narrow kernel. Finally, we conclude by stating clear guidance on how to set the hyperparameters of our neural network architecture to work effectively on new data.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15191
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Finding One's Bearings in the Hyperparameter Landscape of a Wide-Kernel Convolutional Fault Detector
Hudson, Dan
Hoogen, Jurgen van den
Atzmueller, Martin
Machine Learning
Artificial Intelligence
Signal Processing
State-of-the-art algorithms are reported to be almost perfect at distinguishing the vibrations arising from healthy and damaged machine bearings, according to benchmark datasets at least. However, what about their application to new data? In this paper, we confirm that neural networks for bearing fault detection can be crippled by incorrect hyperparameterisation, and also that the correct hyperparameter settings can change when transitioning to new data. The paper combines multiple methods to explain the behaviour of the hyperparameters of a wide-kernel convolutional neural network and how to set them. Since guidance already exists for generic hyperparameters like minibatch size, we focus on how to set architecture-specific hyperparameters such as the width of the convolutional kernels, a topic which might otherwise be obscure. We reflect different data properties by fusing information from seven different benchmark datasets, and our results show that the kernel size in the first layer in particular is sensitive to changes in the data. Looking deeper, we use manipulated copies of one dataset in an attempt to spot why the kernel size sometimes needs to change. The relevance of sampling rate is studied by using different levels of resampling, and spectral content is studied by increasingly filtering out high frequencies. We find that, contrary to speculation in earlier work, high-frequency noise is not the main reason why a wide kernel is preferable to a narrow kernel. Finally, we conclude by stating clear guidance on how to set the hyperparameters of our neural network architecture to work effectively on new data.
title Finding One's Bearings in the Hyperparameter Landscape of a Wide-Kernel Convolutional Fault Detector
topic Machine Learning
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2411.15191