An Adaptive Anti-Noise Neural Network for Bearing Fault Diagnosis Under Noise and Varying Load Conditions

Abstract

Fault diagnosis in rolling bearings is an indispensable part of maintaining the normal operation of modern machinery, especially under the varying operating conditions. In this paper, an end-to-end adaptive anti-noise neural network framework (AAnNet) is proposed to solve the bearing fault diagnosis problem under heavy noise and varying load conditions, which takes the raw signal as input without requiring manual feature selection or denoising procedures. The proposed AAnNet employs the random sampling strategy and enhanced convolutional neural networks with the exponential linear unit as the activation function to increase the adaptability of the neural network. Moreover, the gated recurrent neural networks with attention mechanism improvement are further adopted to learn and classify the features processed by the convolutional neural networks part. Besides, we try to explain how the network works by visualizing the intrinsic features of the proposed framework. And we explore the effect of the attention mechanism in the proposed framework. Experiments show that the proposed framework achieves state-of-the-art results on two datasets under varying operating conditions.INDEX TERMS Bearing fault diagnosis, convolutional neural network, deep learning, load domain adaptation, noisy conditions, recurrent neural network.

Bearing Fault Diagnosis in the Mixed Domain Based on Crossover‐Mutation Chaotic Particle Swarm

“…e weight factor δ of the WMRMR algorithm is recorded as δ i � 0.1, . Complexity feature set corresponding to different δ i values is calculated using the WMRMR algorithm, and the candidate feature set Z i corresponding to the weight factor δ i is obtained by sequence arrangement in equation (7). e results are summarized in Table 3.…”

“…e third step is the selection of representative features. e weight factor δ is selected by maximum relevance minimum redundancy algorithm, and the step size is 0.1. e low-dimensional representative feature set Z i is obtained by equation (7). e fourth step is to apply the proposed CMCPSO-SVM technique for bearing fault diagnosis.…”

“…In recent years, support vector machine (SVM) and artificial neural networks have been widely concerned in the classification and recognition field. Although neural network has the characteristics of self-learning and nonlinear processing, it has some clear disadvantages, such as the "black box" effect, expensive computing costs, and time-consuming data specimen training [5][6][7]. SVM is a machine learning method suitable for small sample applications.…”

Remaining Useful Life Estimation of BLDC Motor Considering Voltage Degradation and Attention-Based Neural Network

“…In the added attention mechanism, a quantitative weight is added to each important time step to overcome the shallow attention of LSTM. Due to the additional weights, the model can automatically focus on relevant information and pay more attention to the intrinsic characteristics of sequence data [39]. In case of some nonlinear trends in time-series data, attention mechanisms can put importance on the inconsistent changes and improve the performance of the model.…”

Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer

“…Yao et al [28] bearing fault classes in different noise environments. Jin et al [29] designed a hybrid model based on CNN and gated recurrent unit (GRU) neural network to solve the issue of fault diagnosis for bearing under noise interference. To improve the adaptive feature learning ability, the exponential linear unit (ELU) was introduced into CNN as an activation function, while the attention mechanism was added to the GRU.…”