Deep Convolutional and LSTM Recurrent Neural Networks for Rolling Bearing Fault Diagnosis Under Strong Noises and Variable Loads

Abstract

To research the problems of the rolling bearing fault diagnosis under different noises and loads, a dual-input model based on a convolutional neural network (CNN) and long-short term memory (LSTM) neural network is proposed. The model uses both time domain and frequency domain features to achieve endto-end fault diagnosis. One-dimensional convolutional and pooling layers are utilized to extract the spatial features and retain the sequence features of the data. In addition, an LSTM layer is employed to extract the sequence features. Finally, a dense layer is applied for fault classification. To enhance recognition accuracy under different noises and loads, three techniques are applied to the proposed model, including taking timefrequency domain signals as input, using the CNN-LSTM model, and adopting the mini-batch and batch normalization methods. The Case Western Reserve University and Drivetrain Diagnostics Simulator data sets are used to construct experiments under different conditions, including varying loads and different noises. The proposed model can achieve a high fault recognition rate under variable load and noise conditions as well as satisfactory anti-noise and load adaptability.

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

“…In addition, the proposed method is compared with other fault diagnosis methods of rotating machinery under noise interference to verify its effectiveness. e comparison methods are sparse filtering (SF) [24], multiperspective CNN (MP-CNN) [27], CNN + LSTM [30], wide convolution and multiscale convolution (WMSCCN) [35], and deep convolutional neural networks with wide first-layer kernels (WDCNN) [38]. In the case of different noise intensities, fault diagnosis results of the above methods are shown in Figure 8.…”

“…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. After the time-frequency decomposition of the vibration signals, Qiao et al [30] also combined CNN and LSTM to identify the fault classes of bearings under noise interference. Zhang et al [31] introduced the integrated learning mechanism into the deep shrinkage autoencoder and constructed a fault diagnosis model based on the integrated deep shrinkage autoencoder, which possesses a strong antinoise ability.…”

Bearing Fault Diagnosis Based on Natural Adaptive Moment Estimation Algorithm and Improved Octave Convolution

“…Finally, the Dense layer combined with the NAdam algorithm is used for final classification task on the data. The network model structure is shown in Fig 3. Because the network structure is two-dimensional, the input structure is [30,40,3], which is converted from the time series of [1200,1]. The first three layers use a dilated gate convolution layer to deepen the network model and enhance feature extraction.…”

“…Before network training, data enhancement techniques are used to avoid over-fitting due to few samples. Bearing data are time series data, so a sliding window is used for data enhancement [40]. In Fig 5, the sampling window with sequence length, repetition rate wide, and step size S is resampled along the time axis.…”

Rolling Bearing Fault Diagnosis Based on Convolutional Neural Network and Support Vector Machine

“…Deep learning method can handle the complex and high-dimensional problems in the massive data that cannot be solved by shallow learning [20]. Due to its high efficiency, plasticity and universality, scholars have applied many deep learning models to the research of fault diagnosis, such as Long Short-Term Memory (LSTM) [21], Deep Belief Network (DBN) [22], Deep Auto-encoder (DAE) [23], Gated Recurrent Unit Network (GRUN) [24], and Convolutional Neural Network (CNN). Among them, CNN has more sophisticated applications in image processing, including image classification [25], target positioning [26], and face recognition [27].…”