Fault Diagnosis Method for Imbalanced Data Based on Multi-Signal Fusion and Improved Deep Convolution Generative Adversarial Network

Abstract

The realization of accurate fault diagnosis is crucial to ensure the normal operation of machines. At present, an intelligent fault diagnosis method based on deep learning has been widely applied in mechanical areas due to its strong ability of feature extraction and accurate identification. However, it often depends on enough training samples. Generally, the model performance depends on sufficient training samples. However, the fault data are always insufficient in practical engineering as the mechanical equipment often works under normal conditions, resulting in imbalanced data. Deep learning-based models trained directly with the imbalanced data will greatly reduce the diagnosis accuracy. In this paper, a diagnosis method is proposed to address the imbalanced data problem and enhance the diagnosis accuracy. Firstly, signals from multiple sensors are processed by the wavelet transform to enhance data features, which are then squeezed and fused through pooling and splicing operations. Subsequently, improved adversarial networks are constructed to generate new samples for data augmentation. Finally, an improved residual network is constructed by introducing the convolutional block attention module for enhancing the diagnosis performance. The experiments containing two different types of bearing datasets are adopted to validate the effectiveness and superiority of the proposed method in single-class and multi-class data imbalance cases. The results show that the proposed method can generate high-quality synthetic samples and improve the diagnosis accuracy presenting great potential in imbalanced fault diagnosis.

A novel data augmentation method for steering mechanism fault diagnosis based on variational autoencoding generative adversarial networks with self-attention

“…Deng et al fused vibration signals from different sensors using wavelet transform, then applied DCGAN for data augmentation on the fused features. The experimental results on two sets of public datasets fully validated the effectiveness of this method [23]. Xiong et al employed WGAN-GP to generate fault signals with a small number of samples from rolling bearings and applied SAE for classification on the balanced samples [24].…”

Intelligent fault diagnosis method of rolling bearing based on multi-source domain fast adversarial network

“…In order to obtain the sufficient marking samples, Deng et al [17] and Peng et al [18] used the idea of generative adversarial network (GAN) and made the discriminator more useful. Ye et al [19] adopted the small sample migration method.…”

Fault Diagnosis of the Rolling Bearing by a Multi-Task Deep Learning Method Based on a Classifier Generative Adversarial Network

“…The distinct advantages of deep learning over other machine learning methods include its great learning capacity, more powerful feature extracting ability and faster data processing ability [ 8 ]. With these advantages, deep learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), have achieved excellent performance in the fields of image processing, natural language processing, etc.…”