Generative adversarial networks for data augmentation in machine fault diagnosis

By Siyu Shao, Pu Wang, Ruqiang Yan. Computers in industry (Print), 2019

498 citations recorded by the source corpus.

Abstract Generative adversarial networks (GANs) have been proved to be able to produce artificial data that are alike the real data, and have been successfully applied to various image generation tasks as a useful tool for data augmentation. In this paper, we develop an auxiliary classifier GAN(ACGAN)-based framework to learn from mechanical sensor signals and generate realistic one-dimensional raw data. The proposed architecture contains two parts, generator and discriminator, and both of them are built by stacking one-dimensional convolution layers to learn local features from the original input. Such stacked structure is able to learn hierarchical representations through convolution operation and easy to train. Batch normalization is performed within generator to avoid the problem of gradient vanishing during training, and category labels are used as the auxiliary information in this framework to help train the model. The proposed approach is designed to produce realistic synthesized signals with labels and the generated signals can be used as augmented data for further applications in machine fault diagnosis. In order to evaluate the performance of the generative model, we introduce a set of assessment to evaluate the quality of generated samples, including statistical characteristics and experimental verification. Finally, induction motor vibration signal datasets are utilized to investigate the effectiveness of the proposed framework.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/daa357c22e875f1601538b4c7b9ffe36873e6b49

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Ming Zhao
2. Jing Lin
3. Byeng Dong Youn
4. Kaixuan Liang
5. Chao Hu
6. Jinyang Jiao

In Control and Systems Engineering

1. Zhen Hu
2. Ming Zhao
3. Sankaran Mahadevan
4. Jing Lin
5. Byeng Dong Youn
6. Kaixuan Liang
7. Chao Hu
8. Jinyang Jiao

Citations in the corpus

• A comprehensive review on convolutional neural network in machine fault diagnosis (2020, methodology): “diagnosis with small samples. Xie et al. [151] developed a GAN to generate the samples of minority classes for bearing fault diagnosis, which aimed to address the issue of data imbalance. Shao et al. [152] proposed an auxiliary classifier GAN based diagnostic framework to generate synthesized data a”
• A comprehensive review of digital twin — part 1: modeling and twinning enabling technologies (2022, methodology): “After being trained on a real dataset, a GAN can generate synthetic healthy/ faulty data, which share a similar distribution as the real training dataset (Shao et al. 2019).”