An ensemble of convolution-based methods for fault detection using vibration signals

Abstract

This paper focuses on solving a fault detection problem using multivariate time series of vibration signals collected from planetary gearboxes in a test rig. Various traditional machine learning and deep learning methods have been proposed for multivariate time-series classification, including distance-based, functional data-oriented, feature-driven, and convolution kernel-based methods. Recent studies have shown using convolution kernel-based methods like ROCKET, and 1D convolutional neural networks with ResNet and FCN, have robust performance for multivariate time-series data classification. We propose an ensemble of three convolution kernel-based methods and show its efficacy on this fault detection problem by outperforming other approaches and achieving an accuracy of more than 98.8\%.

arXiv comment12 Pages, 9 Figures, 2 Tables. Accepted at ICPHM 2023

References in corpus (5)

• ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels
• MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification
• Non-linear Functional Modeling using Neural Networks
• A tale of two toolkits, report the third: on the usage and performance of HIVE-COTE v1.0
• A Functional approach for Two Way Dimension Reduction in Time Series