Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning-based Machine Condition Diagnosis using Short-time Fourier Transformation Variants

Eduardo Jr Piedad, Zherish Galvin Mayordo, Eduardo Prieto-Araujo, Oriol Gomis-Bellmunt

TL;DR

This study converts time-series motor current signals to time-frequency 2D plots using Short-time Fourier Transform (STFT) methods, and four methods outperformed the previous best ML method with 93.20% accuracy.

Abstract

In motor condition diagnosis, electrical current signature serves as an alternative feature to vibration-based sensor data, which is a more expensive and invasive method. Machine learning (ML) techniques have been emerging in diagnosing motor conditions using only motor phase current signals. This study converts time-series motor current signals to time-frequency 2D plots using Short-time Fourier Transform (STFT) methods. The motor current signal dataset consists of 3,750 sample points with five classes - one healthy and four synthetically-applied motor fault conditions, and with five loading conditions: 0, 25, 50, 75, and 100%. Five transformation methods are used on the dataset: non-overlap and overlap STFTs, non-overlap and overlap realigned STFTs, and synchrosqueezed STFT. Then, deep learning (DL) models based on the previous Convolutional Neural Network (CNN) architecture are trained and validated from generated plots of each method. The DL models of overlap-STFT, overlap R-STFT, non-overlap STFT, non-overlap R-STFT, and synchrosqueezed-STFT performed exceptionally with an average accuracy of 97.65, 96.03, 96.08, 96.32, and 88.27%, respectively. Four methods outperformed the previous best ML method with 93.20% accuracy, while all five outperformed previous 2D-plot-based methods with accuracy of 80.25, 74.80, and 82.80%, respectively, using the same dataset, same DL architecture, and validation steps.

Deep Learning-based Machine Condition Diagnosis using Short-time Fourier Transformation Variants

TL;DR

This study converts time-series motor current signals to time-frequency 2D plots using Short-time Fourier Transform (STFT) methods, and four methods outperformed the previous best ML method with 93.20% accuracy.

Abstract

In motor condition diagnosis, electrical current signature serves as an alternative feature to vibration-based sensor data, which is a more expensive and invasive method. Machine learning (ML) techniques have been emerging in diagnosing motor conditions using only motor phase current signals. This study converts time-series motor current signals to time-frequency 2D plots using Short-time Fourier Transform (STFT) methods. The motor current signal dataset consists of 3,750 sample points with five classes - one healthy and four synthetically-applied motor fault conditions, and with five loading conditions: 0, 25, 50, 75, and 100%. Five transformation methods are used on the dataset: non-overlap and overlap STFTs, non-overlap and overlap realigned STFTs, and synchrosqueezed STFT. Then, deep learning (DL) models based on the previous Convolutional Neural Network (CNN) architecture are trained and validated from generated plots of each method. The DL models of overlap-STFT, overlap R-STFT, non-overlap STFT, non-overlap R-STFT, and synchrosqueezed-STFT performed exceptionally with an average accuracy of 97.65, 96.03, 96.08, 96.32, and 88.27%, respectively. Four methods outperformed the previous best ML method with 93.20% accuracy, while all five outperformed previous 2D-plot-based methods with accuracy of 80.25, 74.80, and 82.80%, respectively, using the same dataset, same DL architecture, and validation steps.
Paper Structure (6 sections, 1 equation, 6 figures, 1 table)

This paper contains 6 sections, 1 equation, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Electric Motor Current Dataset
  3. Short-time Fourier Transform and its variants
  4. Convolutional Neural Network (CNN)
  5. Results and Discussion
  6. Conclusion

Figures (6)

  • Figure 1: Sample plots showing the five STFT transformation variants with 64x64 image resolution of the motor dataset across five condition classes under the full-load condition (load=100%).
  • Figure 2: The Convolutional Neural Network (CNN) architecture of FOPCNN with the following input layer corresponding to the 64x64 RGB images.
  • Figure 3: The training and validation classification accuracy performances of the five STFT models
  • Figure 4: The training and validation loss function graphs of the five STFT models.
  • Figure 5: A box plot of the five STFT models performances under the 10-fold stratified cross validation step
  • ...and 1 more figures