Data-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data collected from fault condition states and, without enough and appropriated (balanced) data, no acceptable performance should be expected. Generative adversarial networks (GAN) are receiving a significant interest, especially in the image analysis field due to their outstanding generative capabilities. This paper investigates whether or not GAN can be used as an oversampling tool to compensate for an unbalanced data set in an industrial manipulator fault diagnosis task. A comprehensive empirical analysis is performed taking into account six different scenarios for mitigating the unbalanced data, including classical under and oversampling (SMOTE) methods. In all of these, a wavelet packet transform is used for feature generation while a random forest is used for fault classification. Aspects such as loss functions, learning curves, random input distributions, data shuffling, and initial conditions were also considered. A non-parametric statistical test of hypotheses reveals that all GAN based fault-diagnosis outperforms both under and oversampling classical methods while, within GAN based methods, an average accuracy difference as high as 1.68% can be achieved.
Bibliographical noteFunding Information:
Funding: This work is financed by national funds through FCT—Foundation for Science and Technology, I.P., through IDMEC, under LAETA, project UIDB/50022/2020. This work was supported in part by the National Natural Science Foundation of China under Grant 51775112, the Natural Science Foundation of Chongqing cstc2019jcyj-zdxmX003, the CTBU Project under Grant KFJJ2019060.
Acknowledgments: The authors are thankful for the finance support from FCT—Foundation for Science and Technology, I.P., through IDMEC, under LAETA and in part to the National Natural Science Foundation of China.
c© 2020 by the authors. Licensee MDPI, Basel, Switzerland.
Copyright 2020 Elsevier B.V., All rights reserved.
- Fault diagnosis
- Feature extraction
- Generative adversarial network
- Random forest
- Unbalance data