Data Augmented of Mechanical Fault Sound Signal based on Generative Adversarial Networks

Abstract

In this paper, a global average pooling convolutional neural network based on CNN is proposed for mechanical fault sound detection, which called as GCMD. To solve the data scarcity of mechanical fault sound data, a spectrum frame selection augmented method based on log Mel spectrum feature is proposed to augment the original data, that aim is to train GCMD and generate counter networks. In order to solve the unbalance problem of data set and further improve the generalization ability of GCMD, an augmented neural network model based on CapsuleGAN was proposed, which called MFS-CapsuleGAN. The model was evaluated on the augmented data set by training GCMD neural network. Compared with the original data set, the accurate recognition rate of the model was improved by 23.7%. The performance of this method is improved significantly, which proves the feasibility and effectiveness of MFS-CapsuleGAN data augmented. In addition, the data set with background noise was used to test the generalization ability of GCMD network. The fluctuation range was within 0.117, indicating the good robustness of GCMD network.