TY - JOUR
T1 - Generative Adversarial Networks Selection Approach for Extremely Imbalanced Fault Diagnosis of Reciprocating Machinery
AU - Cabrera, Diego
AU - Sancho, Fernando
AU - Long, Jianyu
AU - Sanchez, Rene Vinicio
AU - Zhang, Shaohui
AU - Cerrada, Mariela
AU - Li, Chuan
PY - 2019/1/1
Y1 - 2019/1/1
N2 - At present, countless approaches to fault diagnosis in reciprocating machines have been proposed, all considering that the available machinery dataset is in equal proportions for all conditions. However, when the application is closer to reality, the problem of data imbalance is increasingly evident. In this paper, we propose a method for the creation of diagnoses that consider an extreme imbalance in the available data. Our approach first processes the vibration signals of the machine using a wavelet packet transform-based feature-extraction stage. Then, improved generative models are obtained with a dissimilarity-based model selection to artificially balance the dataset. Finally, a Random Forest classifier is created to address the diagnostic task. This methodology provides a considerable improvement with 99% of data imbalance over other approaches reported in the literature, showing performance similar to that obtained with a balanced set of data.
AB - At present, countless approaches to fault diagnosis in reciprocating machines have been proposed, all considering that the available machinery dataset is in equal proportions for all conditions. However, when the application is closer to reality, the problem of data imbalance is increasingly evident. In this paper, we propose a method for the creation of diagnoses that consider an extreme imbalance in the available data. Our approach first processes the vibration signals of the machine using a wavelet packet transform-based feature-extraction stage. Then, improved generative models are obtained with a dissimilarity-based model selection to artificially balance the dataset. Finally, a Random Forest classifier is created to address the diagnostic task. This methodology provides a considerable improvement with 99% of data imbalance over other approaches reported in the literature, showing performance similar to that obtained with a balanced set of data.
KW - GAN
KW - Imbalanced data
KW - model selection
KW - random Forest
KW - reciprocating machinery
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85067390583&origin=inward
UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85067390583&origin=inward
UR - http://www.mendeley.com/research/generative-adversarial-networks-selection-approach-extremely-imbalanced-fault-diagnosis-reciprocatin
U2 - 10.1109/ACCESS.2019.2917604
DO - 10.1109/ACCESS.2019.2917604
M3 - Article
VL - 7
SP - 70643
EP - 70653
JO - IEEE Access
JF - IEEE Access
M1 - 8718595
ER -