Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings

By David Verstraete, Andres Ferrada, Enrique López Droguett, Viviana Meruane, Mohammad Modarres. 2017

402 citations recorded by the source corpus.

Traditional feature extraction and selection is a labor-intensive process requiring expert knowledge of the relevant features pertinent to the system. This knowledge is sometimes a luxury and could introduce added uncertainty and bias to the results. To address this problem a deep learning enabled featureless methodology is proposed to automatically learn the features of the data. Time-frequency representations of the raw data are used to generate image representations of the raw signal, which are then fed into a deep convolutional neural network (CNN) architecture for classification and fault diagnosis. This methodology was applied to two public data sets of rolling element bearing vibration signals. Three time-frequency analysis methods (short-time Fourier transform, wavelet transform, and Hilbert-Huang transform) were explored for their representation effectiveness. The proposed CNN architecture achieves better results with less learnable parameters than similar architectures used for fault detection, including cases with experimental noise.

Subfields: Control and Systems Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/51edff944461dc7e5da7fd8dfb6437505a196235

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Dhiraj Neupane
2. Dongxiang Jiang
3. Yihao Xue
4. Chao Liu
5. Ming Zhao
6. Jing Lin
7. Mengjie Huang
8. Jong-Hoon Seok

In Mechanical Engineering

1. Dhiraj Neupane
2. Dongxiang Jiang
3. Chao Liu
4. Ming Zhao
5. Jing Lin
6. Jong-Hoon Seok
7. Kaixuan Liang
8. Te Han

Citations in the corpus

• A comprehensive review on convolutional neural network in machine fault diagnosis (2020, methodology): “Analogously to wavelet transform, Short Time Fourier Transform (STFT), as another common time-frequency analysis approach, has also been used for data preprocessing in CNFD. Verstraete et al. [88] utilized In this subsection, the applications of 2-”
• Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application (2018, background): “In fault diagnosis applications, CNN has also gained increasing interests.”
• Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review (2020, methodology): “The research which use this dataset for rolling bearing fault detection are [58]–[61].”
• Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016 (2023, background): “Time domain analysis [22, 67], frequency domain analysis [68–71] and time-frequency domain analysis [72–77] are widely used in fault diagnosis.”