Intelligent rotating machinery fault diagnosis based on super-resolution enhancement using data augmentation under large speed fluctuation

Abstract

In the real production of industry, in order to solve the problem that it is usually difficult to obtain correctly labeled samples, data augmentation algorithms have received more and more attention. Many efficient deep learning models have been successfully applied to the intelligent fault diagnosis of rotating machinery. However, the premise of the above method is the working conditions of the machinery are constant. It is inevitable that the equipment runs under large speed fluctuation in real industries. To achieve data augmentation under the condition of variable speed, an efficient sub-pixel deep residual neural network (ESPDRN) is proposed. The ESPDRN framework is implemented as follows: utilize low resolution (LR) samples as input to the network, to effectively learn high-level and extract feature maps by constructing a deep residual network. Through sub-pixel convolution layers to arrange the LR features of multi-channels periodically and get a set of ultra high resolution features, and the data points are augmented 16 times compared to raw data. Statistical indicators and experimental results demonstrate that the proposed ESPDRN model can effectively generate data under the condition of variable speed.

Rolling bearing fault diagnosis based on the fusion of sparse filtering and discriminative domain adaptation method under multi-channel data-driven

“…u k can fully reflect the shock characteristics of each channel. Finally, use the Softmax function according to equation (11) to calculate the weights of each channel,…”

“…Jia et al [10] inputted the data after Fourier transforms into the stacked autoencoder to realize efficient fault diagnosis, and demonstrated the feasibility of this method through bearing and gear datasets. Wang et al [11] solved the problem of decreased performance of the fault diagnosis model due to low input signal resolution from the perspective of enhancing signal resolution. Gao et al [12] achieved a good denoising effect on vibration signals by enhancing complementary ensemble empirical mode decomposition and utilized a one-dimensional convolutional neural network (1DCNN) to achieve efficient and accurate diagnosis of bearing faults.…”

A novel convolutional network with a self-adaptation high-pass filter for fault diagnosis of wind turbine gearboxes

“…Han et al [18] developed a novel loss function, called enhanced cross entropy, which can focus more on small samples. Wang et al [19] proposed an efficient sub-pixel deep residual neural network (ResNet) to achieve data enhancement under variable speed conditions. Yu et al [20] proposed a novel asymmetric adversarial domain adaptation (DA) method based on the Wasserstein distance to achieve fault diagnosis in the presence of limited data.…”