Data Augmentation for Vibration Signals using System Identification Techniques
- 24 November 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 281-285
Abstract
Fault diagnosis of rotating machines by neural networks can be compromised in cases of imbalanced datasets, a common situation in the industry, where it might be necessary to create new data artificially. This subject, called data augmentation, is very recent and, for vibration signals, two approaches are found in the literature: the utilization of signal processing techniques in the time domain, and the creation of signal models by General Adversarial Network (GAN) from the existing signals. However, for this last one, many signal samples are necessary, which may prevent its use for this end. As an alternative, it is proposed a new vibration signal modelling method by using System Identification techniques at the frequency domain, where the trigger signal is used as model input and the vibration signal as output. By how it was structured, this method is only applicable in situations where only harmonic signal components are relevant to the diagnostics, case of many practical situations. For a first attempt of vibration signal modelling by System Identification, the results were very satisfactory, since the model responded with similarity to the collected signals in the frequency band of interest to the application. This work opens a new data augmentation research possibility for vibration signals of rotating machinery, a very relevant area and still little explored in the literature.Keywords
Funding Information
- Universidade de São Paulo
This publication has 11 references indexed in Scilit:
- A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learningMechanical Systems and Signal Processing, 2021
- Exploring predictive maintenance applications in industryJournal of Quality in Maintenance Engineering, 2020
- A Novel Deep Learning System with Data Augmentation for Machine Fault Diagnosis from Vibration SignalsApplied Sciences, 2020
- Machinery fault diagnosis with imbalanced data using deep generative adversarial networksMeasurement, 2020
- Data Simulation by Resampling—A Practical Data Augmentation Algorithm for Periodical Signal Analysis-Based Fault DiagnosisIEEE Access, 2019
- Data Segmentation and Augmentation Methods Based on Raw Data Using Deep Neural Networks Approach for Rotating Machinery Fault DiagnosisIEEE Access, 2019
- Generative adversarial networks for data augmentation in machine fault diagnosisComputers in Industry, 2019
- Intelligent rotating machinery fault diagnosis based on deep learning using data augmentationJournal of Intelligent Manufacturing, 2018
- A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration SignalsSensors, 2017
- Nonlinear System Identification2013