Intelligent Fault Diagnosis Method Based on Neural Network Compression for Rolling Bearings

As one of the key parts of rotary machine, the fault diagnosis and running condition monitoring of rolling bearings are of great importance for normal working and safe production of rotary machine. However, the traditional diagnosis approaches merely count on artificial feature extraction and domain expertise. Meanwhile, the existing convolutional neural networks (CNNs) have the problem of low fault recognition rates. This paper proposes a novel convolutional neural network with one-dimensional structure (ODCNN) for the automatical fault diagnosis of rolling bearings, which adopts six sets of convolutional and max-pooling layers to extract signal features and applies a flattening convolutional layer followed by two fully-connected layers for feature classification. The architectures of one-dimensional LeNet-5, AlexNet, and the proposed ODCNN are illustrated in detail, followed by the obtaining of training and testing samples, which is pre-processed by overlapping the vibration signals of rolling bearings. Finally, the classification experiment is carried out. The experimental results show that the ODCNN has higher fault diagnosis rates and can achieve high accuracy with load variant. Additionally, the extracted features of three CNNs are visualized, which illustrate that the new CNN has a better classification capacity.

Wind turbine rolling bearings are crucial components for ensuring the reliability and stability of wind power systems. Their failure can lead to significant economic losses and equipment downtime. Therefore, the accurate diagnosis of bearing faults is of great importance. Although existing deep learning fault diagnosis methods have achieved certain results, they still face limitations such as inadequate feature extraction capabilities, insufficient generalization to complex working conditions, and ineffective multi-scale feature capture. To address these issues, this paper proposes an advanced fault diagnosis method named the two-stream feature fusion convolutional neural network (TSFFResNet-Net). Firstly, the proposed method combines the advantages of one-dimensional convolutional neural networks (1D-ResNet) and two-dimensional convolutional neural networks (2D-ResNet). It transforms one-dimensional vibration signals into two-dimensional images through the empirical wavelet transform (EWT) method. Then, parallel convolutional kernels in 1D-ResNet and 2D-ResNet are used to extract multi-scale features, respectively. Next, the Convolutional Block Attention Module (CBAM) is introduced to enhance the network’s ability to capture key features by focusing on important features in specific channels or spatial areas. After feature fusion, CBAM is introduced again to further enhance the effect of feature fusion, ensuring that the features extracted by different network branches can be effectively integrated, ultimately providing more accurate input features for the classification task of the fully connected layer. The experimental results demonstrate that the proposed method outperforms other traditional methods and advanced convolutional neural network models on different datasets. Compared with convolutional neural network models such as LeNet-5, AlexNet, and ResNet, the proposed method achieves a significantly higher accuracy on the test set, with a stable accuracy of over 99%. Compared with other models, it shows better generalization and stability, effectively improving the overall performance of rolling bearing vibration signal fault diagnosis. The method provides an effective solution for the intelligent fault diagnosis of wind turbine rolling bearings.

Deep learning (DL) has inaugurated new approaches to implement fault diagnosis of roller bearings, which is essential to deal with the current industrial big data era. Unfortunately, many existing deep learning models, particularly convolutional neural network (CNN) models, have the following drawbacks. Single-channel convolution neural network in pooling layer has the problem of data loss. The feature information extracted by CNN is not integrated due to lack of feature learning ability, which will induce unsatisfactory diagnostic results and poor generalization ability. To deal with the above issues, a dual-flow convolutional neural network (DFCNN) is proposed for intelligent diagnosis the faults of roller bearings. The multi-channel convolutional neural network is used for feature extraction to solve the problem of data loss in the pooling layer. More comprehensive fault features can be extracted by multiple feature fusion after the input of two dimensions. Network parameters are adjusted using model optimization. The proposed method is demonstrated by the bearing experiment and collected vibration data including different types of faults. The results show that the accuracy rate is more superior than other six different neural network, and it is suitable for roller bearing fault diagnosis.

To realize accurate fault diagnosis of rolling bearing under random noise, a novel fault diagnosis method based on ensemble empirical mode decomposition (EEMD) and optimized Elman_AdaBoost is proposed in this paper. First, the EEMD method is used to decompose the original vibration signal into several intrinsic mode functions (IMFs). Then, the correlation coefficient and kurtosis of IMFs are used to remove any excess ingredients, and the signal is reconstructed by using the rest of IMFs. In addition, based on the analysis of the time–frequency characteristics of the reconstructed signal, the root-mean-square value and the power spectrum center are extracted as a 2-D feature vector from each reconstructed signal and regarded as the input characteristic vector of the Elman neural network. Combined with the AdaBoost classification algorithm, the Elman_AdaBoost algorithm is improved and proposed to establish the strong classifier. Finally, based on the vibration data recorded in the bearing center of the Case Western Reserve University, three kinds of bearings with different faults and normal bearings are selected as the sample data and the training samples and test samples are constructed. Experimental results show that the proposed EEMD method and optimized Elman_AdaBoost model can effectively diagnose the rolling bearing under random noise, and has the advantages of fast speed, small error, and stable performance. Comparing with the traditional Elman_AdaBoost and single Elman neural network algorithm, this paper with fewer characteristics can get better accuracy and real-time processing performance, and presents a simple and practical resolution for the fault diagnosis of rolling bearings.

Rolling bearings are essential for ensuring smooth operation of rotating machinery, when it suffer from faults, the extraction of fault features and fault diagnosis of rolling bearings become difficult due to the interference of noise and other vibration components. A fault diagnosis model based on symplectic geometric mode decomposition (SGMD), convolutional neural networks (CNN) and optimized long short-term memory networks (LSTM) is proposed to facilitate feature extraction and improve robustness of fault diagnosis. Firstly, bearing signals from different faults are decomposed using the SGMD, selecting the symplectic seometric components (SGCs) based on their correlation and constructing feature vectors by fuzzy dispersion entropy (FDE). Then, a CNN-LSTM model is built by combining the CNN and the LSTM. Inputting training data into the model to adjust its hyperparameters, and the softmax layer is replaced with a least squares support vector machine (LSSVM). The parameters of the LSSVM are optimized with the electric eel foraging optimization (EEFO) algorithm and the optimized model is used for fault identification and classification. Finally, experiments are conducted on two public datasets, achieving accuracy rates of 98.57% and 97.22% respectively, which validates the feasibility of this method and demonstrates its superiority over traditional CNN models.

Rotating machinery contains numerous rolling bearings, which are critical for ensuring the normal working position and accurate operation of individual shaft systems. However, damage to rolling bearings can change their damping, stiffness, and elastic force. As a result, fault signals appear nonlinear and nonstationary. Vibration signals thus become difficult to diagnose clearly, especially in the incipient fault stage. To solve this problem, this article proposes an intelligent approach based on variational mode decomposition and the self-organizing feature map for rolling bearing fault diagnosis. First, the intrinsic mode function components of rolling bearing vibration signals are effectively separated by variational mode decomposition. Then, permutation entropy is used to extract feature vectors, which are used as training and testing data for the self-organizing feature map network. Finally, the various fault types of states are clustered on an intuitive visualization map. Clustering results of the experimental signal and the measured signal prove that the proposed method can successfully extract and cluster the rolling bearing faults in engineering applications. The proposed method improves the fault recognition rate to some extent over traditional methods.

The rolling bearing is a critical part of rotating machinery and its condition determines the performance of industrial equipment; it is necessary to detect rolling bearing faults as early as possible. The traditional methods of fault diagnosis are not efficient and are time-consuming. With the help of deep learning, the convolution neural network (CNN) plays a huge role in the data-driven methods of bearing fault diagnosis. However, the vibration signal is non-stationary, contains high noise, and is one-dimensional, which is difficult to analyze directly by the CNN model. Considering the multi-domain learning as an advantage of deep learning, this paper proposes a novel rolling bearing fault diagnosis approach using an improved one-dimensional (1D) and two-dimensional (2D) convolution neural network (CNN) of two-domain information learning. The constructed fault diagnosis model combining 1D and 2D CNN extracts the fault features from the two-domain information of bearing fault samples. The padding and dropout technology are utilized to fully extract features from the raw data and reduce over-fitting. To prove the validity of the proposed method, this paper performs two tests with two bearing datasets, the Case Western Reserve University (CWRU) bearing dataset and the Dalian University of Technology (DUT) vibration laboratory dataset. The experimental results show that our proposed method achieves high recognition accuracy of rolling bearing fault states via two-domain learning of monitoring data, and there is no manual experience necessary. Vibration data under strong noise were also used to test the method, and the results show the superiority and robustness of the proposed method.

To solve the problem of fault diagnosis of rolling bearing caused by large amount of data and difficulties of processing those data on to bearing set, based on Convolution Neural Network, a new method of data processing is proposed in this paper. With this method, one-dimensional time domain signal can be transformed into two-dimensional images, which is more suitable for Convolutional Neural Network processing. Meanwhile, the traditional machine learning method has the disadvantage of low robustness and low recognition rate with noise interference. Therefore, based on the feature extraction of Convolution Neural Network, in this paper we proposed an improved LeNet-5 Convolution Neural Network model, that is, adding a convolution layer and a pooling layer to the classic LeNet-5 model. The hidden layer features are extracted by using the trainable convolution kernel, while the extracted implicit features are reduced by the pooling layer, the Softmax classifier is used for classification and recognition of rolling bearing faults. In this paper we verified the effectiveness of the improved LeNet-5 model for fault diagnosis of rolling bearing by using the rolling bearing data to train the classic LeNet-5 model and the improved model.

The rolling bearing is an important part of the train’s running gear, and its operating state determines the safety during the running of the train. Therefore, it is important to monitor and diagnose the health status of rolling bearings. A convolutional neural network is widely used in the field of fault diagnosis because it does not require feature extraction. Considering that the size of the network model is large and the requirements for monitoring equipment are high. This study proposes a novel bearing fault diagnosis method based on lightweight network ShuffleNet V2 with batch normalization and L2 regularization. In the experiment, the one-dimensional time-domain signal is converted into a two-dimensional Time-Frequency Graph (TFG) using a short-time Fourier transform, though the principle of graphics to enhance the TFG dataset. The model mainly consists of two units, one for extracting features and one for spatial down-sampling. The building units are repeatedly stacked to construct the whole model. By comparing the proposed method with the origin ShuffleNet V2, machine learning model and state-of-the-art fault diagnosis model, the generalization of the proposed method for bearing fault diagnosis is verified.

In the fault diagnosis of rolling bearings, compared to using vibration signals as the diagnostic target, utilising motor stator current signals can effectively reduce diagnostic costs and improve diagnostic efficiency. However, current signals often contain abundant noise that tends to obscure the characteristic signals related to bearing faults. Furthermore, the manifestation in signals of fault features for complex faults in rolling bearings is more intricate than that for single-point faults. Therefore, this paper proposes a signal processing method that can effectively suppress noise in current signals and further enhance the weak bearing composite fault features. The main content of this study leverages the inherent characteristics of motor stator current signals to eliminate a substantial amount of noise interference unrelated to fault characteristic signals, enabling the expression of weak fault characteristic signals to be further emphasised, thus achieving an effective representation of bearing composite fault features in current signals. Finally, the processed fault signals are used for fault classification through convolutional neural networks (CNNs). Experimental results effectively demonstrate that this method also has certain advantages and reliability in detecting and extracting weak compound fault features of bearings.

It is a great challenge to manipulate unbalanced fault data in the field of rolling bearings intelligent fault diagnosis. In this paper, a novel intelligent fault diagnosis method called the Wasserstein gradient-penalty generative adversarial network with deep auto-encoder is proposed for intelligent fault diagnosis of rolling bearings. Firstly, the gradient penalty term is added to the Wasserstein generative adversarial network to enhance the stability and convergence of the network. Secondly, a deep auto-encoder network comprised of multiple auto-encoders is regarded as the discriminator. Finally, the sparse auto-encoder is placed at the end of the proposed method as the classifier to classify synthetic bearing faults. The results show that the proposed method has a better performance than traditional methods and the Wasserstein generative adversarial network.

The intelligent fault diagnosis method based on transformer and convolutional neural network (CNN) has achieved good global and local feature extraction results. However, the multi-head self-attention mechanism adopted by the transformer and the cross-channel convolution operation in CNN increases the complexity of the model, thereby increasing the demand for hardware resources, which to some extent, limits its broad applicability in industrial applications. Therefore, this paper proposes a lightweight fault diagnosis framework based on compact multi-scale feature extraction and pruned-restructured vision transformer (ViT) to address the above challenges. Firstly, a compact multi-scale feature extraction module is designed to efficiently capture complex features in rolling bearing vibration signals through parallel multi-scale convolution kernels, combined with channel reduction strategies to significantly reduce computational complexity while maintaining feature richness. Next, short-time Fourier transform and pseudo-color processing techniques are used to obtain time–frequency images. Then, a dual optimization of matrix sparsity and structural reorganization is implemented for Self-attention in ViT to ensure model performance and significantly reduce computational overhead. Finally, the time–frequency images are segmented and rearranged before being fed into the improved lightweight ViT for global feature extraction and fault recognition of rolling bearings. The experimental results show that the proposed fault diagnosis method has the advantages of lightweight (Params:4.27 K, floating point operations per seconds:0.1 M, multiplication and accumulation operations per seconds:51.07 K) and robustness compared to mainstream algorithms.

With the emergence of Internet-of-Things (IoT) and big data technologies, data-driven fault diagnosis approaches, notably deep learning (DL)-based methods, have shown promising capabilities in achieving high accuracy through end-to-end learning. However, these deterministic neural networks cannot incorporate the prediction uncertainty, which is critical in practical applications with possible out-of-distribution (OOD) data. This present article develops a reliable and intelligent fault diagnosis (IFD) framework based on evidence theory and improved visual geometry group (VGG) neural networks, which can achieve accurate and reliable diagnosis results by incorporating additional estimation of the prediction uncertainty. Specifically, this article treats the predictions of the VGG as subjective opinions by placing a Dirichlet distribution on the category probabilities and collecting the evidence from data during the training process. A specific loss function assisted by evidence theory is adopted for the VGG to obtain improved uncertainty estimations. The proposed method, which incorporates evidential VGG (EVGG) neural networks, as termed here, is verified by a case study of the fault diagnosis of rolling bearings, in the presence of sensing noise and sensor failure. The experimental results illustrate that the proposed method can estimate the prediction uncertainty and avoid overconfidence in fault diagnosis with OOD data. Also, the developed approach is shown to perform robustly under various levels of noise, which indicates a high potential for use in practical applications.

Rolling element bearings are a vital component of all machines; thus, identifying their issues is critical. Rolling bearing fault diagnosis is essential for ensuring operational efficiency and safety in complex mechanical systems. Data collection, signal conditioning, and fault categorization are the three main components of the fault assessment approach. With the increasing volume of monitoring data and the confrontation with associated with long-established fault diagnosis approaches, deep learning has come into view as a powerful modus operandi to finding out insightful bearing faults. This paper offers a comprehensive review of the literature on deep learning techniques for diagnosing bearing faults, a topic that has attracted scholarly interest recently. It explores widely used deep learning algorithms namely Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Autoencoders (AE), Generative Adversarial Networks (GAN), as well as Deep Belief Networks (DBN).

Rolling bearing failures can lead to machinery breakdowns and loss of control, posing significant operational and safety risks. Traditional algorithms based on the empirical wavelet transform (EWT) face challenges in accurately extracting valid components under variable conditions. Additionally, conventional max-pooling methods often overlook critical features, while fully connected layers tend to overfit due to excessive parameterization. To address these challenges, an enhanced algorithm is proposed, defined as the improved EWT-improved residual network (IEWT-IResNet) method. First, the vibration signals are preprocessed to enhance resilience under variable conditions. Second, an improved EWT (IEWT) is proposed with an optimal ridge-curve extraction strategy. It incorporates an efficient weighted energy entropy (EWEE) as a sensitive indicator for signal reconstruction. Additionally, the 1-D angular-serial signals are transformed into 2-D image matrices using the generalized S-transform. Finally, an optimized residual network (ResNet) model is presented, incorporating singular value decomposition (SVD) pooling and global SVD pooling (GSP) strategies in the pooling and full connection layers. These enhancements benefit the optimal feature extraction while mitigating overfitting. The experimental results demonstrate the superior feature extraction capabilities of the proposed method when processing noisy and nonstationary signals. Furthermore, the effectiveness of the approach is investigated and validated using real-world data from rolling bearings.