Bearing fault diagnosis from raw vibration signals using multi-layer extreme learning machine

Information security plays critical roles in modern society. However, traditional security measures like passwords, tokens and personal ID numbers only provide limited protection. Inspired by the fast training speed of extreme learning machine (ELM) and the promising feature extraction capability of extreme learning machine auto-encoder (ELM-AE), this paper proposes a keystroke dynamics identification method for intelligent keyboard (IKB) based on multi-layer extreme learning machine (ML-ELM). The IKB, as first demonstrated by Wang's group, is a self-powered, non-mechanical perforated keyboard that converts mechanical stimuli applied to the keyboard into electrical signals without the needing an external power source. ML-ELM is a multilayer neural network stacking on top of ELM-AE. Our major contribution is to develop an accurate and efficient keystroke dynamics identification method based on ML-ELM. One significant advantage of the proposed method is that it does not rely on manual feature extraction and selection. In other words, the raw current signals obtained by IKB are directly the input to the network. The network structure is determined by grid search, which minimizes the human involvement. The other one is that the whole training process of the model does not require fine tuning, which makes the training process significantly faster than that of existing deep networks. Experimental results demonstrate that the proposed method has excellent timeliness whereas obtaining high identification accuracy. The proposed method has great potential in applications to computer or network access control, online payment, and cyber security.

According to the rolling bearing local fault vibration mechanism, a monopulse feature extraction and fault diagnosis method of rolling bearing under low‐speed and heavy‐load conditions based on phase scan and CNN is proposed. The synchronous collected speed signal is used to calculate bearing phase function and divide fault monopulse periods. The monopulse waveforms of multiple fault periods are scanned and ensemble averaged to suppress noise interference and detail feature loss at the same time of feature extraction. By iteratively calibrating phase function, the feature matrix containing bearing fault information can be obtained. Finally, CNN is used to recognize and classify different bearing states. The experimental and analysis results show that bearing fault diagnosis can be achieved. The total recognition rates of constant and variable speed samples are 99.67% and 99.89%, respectively. The trained network has fast convergence speed and good generalization ability for different fault sizes and working conditions. Further experiments show that the method can also accurately identify different bearing degradation states. The total recognition rates of constant and variable speed samples are 96.67% and 95.56%, respectively. The limited errors are concentrated between the degradation states with the same type weak fault. The experimental results using Case Western Reserve University bearing data show that feature extraction and network training are better, and the recognition rates of 5 bearing states are all 100%. Therefore, the proposed method is an effective rolling bearing feature extraction and fault diagnosis technology.

Human activity recognition (HAR) is a main research field of context-aware computing; the performance of HAR mainly depends on the feature extraction method and classification algorithm. Extreme learning machine (ELM) is a single hidden layer neural network, which has better classification and generalization ability. However, ELM is not suitable for feature extraction. Deep learning is a hot research field as it can automatically extract significant features from raw data. In this paper, we propose an approach: an ELM-based deep model, which combined convolutional neural network (CNN), multilayer ELM (ML-ELM) as feature extractor, and used kernel ELM (KELM) as classifier. We used CNN and ML-ELM to extract significant features, and used KELM to achieve stable performance. The performance of proposed approach is validated on two public HAR datasets, and the experimental results show that the proposed approach is effective.

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.

Deep neural networks have made significant achievements in representation learning of traditionally man-made features, especially in terms of complex objects. Over the decades, this learning process has attracted thousands of researchers and has been widely used in the speech, visual, and text recognition fields. One deep network multi-layer extreme learning machine (ML-ELM) achieves a good performance in representation learning while inheriting the advantages of faster learning and the approximating capability of the extreme learning machine (ELM). However, as with most deep networks, the ML-ELM’s algorithmic performance largely depends on the probability distribution of the training data. In this paper, we propose an improved ML-ELM made via using the local significant regions at the input end to enhance the contributions of these regions according to the idea of the selective attention mechanism. To avoid involving and exploring the complex principle of the attention system and to focus on the clarification of our local regional enhancement idea, the paper only selects two typical attention regions. One is the geometric central region, which is normally the important region to attract human attention due to the focal attention mechanism. The other is the task-driven interest region, with facial recognition as an example. The comprehensive experiments are done on the three public datasets of MNIST, NORB, and ORL. The comparison experiment results demonstrate that our proposed region-enhanced ML-ELM (RE-ML-ELM) achieves performance increases in important feature learning by utilizing the apriori knowledge of attention and has a higher recognition rate than that of the normal ML-ELM and the basic ELM. Moreover, it benefits from the non-iterative parameter training method of other ELMs, and our proposed algorithm outperforms most state-of-the-art deep networks such as deep belief network(DBN), in the aspects of training efficiency. Furthermore, because of the deep structure with fewer hidden nodes at each layer, our proposed RE-ML-ELM achieves a comparable training efficiency to that of the ML-ELM but has a higher training speed with the basic ELM, which is normally the width single network that has more hidden nodes to obtain the similar recognition accuracy with the deep networks. Based on our idea of combining the apriori knowledge of the human selective attention system with the data learning, our proposed region-enhanced ML-ELM increases the image classification performance. We believe that the idea of intentionally combining psychological knowledge with the most algorithms based on data-driven learning has the potential to improve their cognitive computing ability.

Rolling bearings, as important parts on supporting rotating shafts, frequently suffer from fatigue failures. If these rolling bearing failures are not found in time, it will have a huge impact on the whole mechanical system’s operating safety and operating life. To improve the diagnosis of different faults as well as different degrees of faults, a fault diagnosis method based on the multifractal detrended fluctuation analysis (MFDFA) method-singularity power spectrum (SPS) with extreme learning machine (ELM) is proposed. First, MFDFA and SPS analyses are performed on vibration acceleration signals with different faults and different degrees of damage under the same operating conditions, the spectral parameters of stability and quantitative description of differentiation are selected for feature extraction, and then the selected six feature parameters are put into the extreme learning machine for fault classification. The effectiveness of the MFDFA-SPS feature extraction method is demonstrated by analyzing and testing the measured bearing signals. The fault diagnosis accuracy of the bearing fault signals can reach 99.2% based on the MFDFA-SPS with ELM method by using the Case Western Reserve database. The improvements are 6.79% and 18.42% compared to the fault diagnosis methods based on MFDFA with ELM and SPS with ELM. Compared with the methods based on MFDFA-SPS with LSSVM classifier and SVM classifier, the accuracy improvements are 3.54% and 4.25%, respectively. The results show that the method proposed in this paper can achieve the diagnosis of bearing faults and the method based on MFDFA-SPS with ELM is more efficient than the methods based on MFDFA-SPS with LSSVM and SVM classifiers, which is suitable for practical engineering problem-solving.

A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing

Rotating machinery is a crucial component of industrial equipment, and the fault diagnosis of bearings and gears, as vital elements of rotating machinery, is essential since they often fail under harsh working conditions, leading to significant property losses and serious personal safety problems. However, fault data for gears and bearings are often sparse in actual condition, and it is a challenge to ensure the reliability and stability of fault diagnosis results by extracting the features of a single data. To solve the above problems, this paper proposes a fault diagnosis method that combines Transfer Learning and data fusion techniques. Firstly, in this method, two kinds of fault signals are transformed into Gramian Angular Difference Fields and Recurrence Plot. Next, a U-shaped feature fusion dual discriminator generative adversarial network is used to fuse two-dimensional images from multiple sensor data. Its feature fusion module deeply integrates the features of the two images, thereby solving the impact of single data on the reliability and stability of fault diagnosis. Moreover, open-source datasets are used for Transfer Learning training to tackle the small sample problem. Finally, a decision-level information fusion classifier, the Dual-Branch Dempster-Shafer Classifier (DB-DSC), classifies the fused images. This classifier incorporates an improved soft threshold function and D-S evidence theory to achieve adaptive gradient changes and improve the robustness and accuracy of classification results. The experimental results show the effectiveness and stability of the proposed method, and the generated images get high score in several metrics. The average classification accuracy of the classification network reaches 93% and 92.5% on the two datasets, Therefore, the proposed method exhibits strong fault diagnosis capabilities under the small sample conditions of bearings and gears.

The condition monitoring and fault diagnosis of rolling element bearings play an important role in the safe and reliable operation of rotating machinery. Feature extraction based on vibration signals is an effective means to identify the operating condition of rolling element bearings. Methods based on multi-scale mathematical morphology (MM) have recently been developed to extract features from one-dimensional signals. In this paper, a new double-dot structuring element (SE) is constructed for multi-scale MM. A pattern spectrum, obtained from the multi-scale MM, is used as a feature extraction index. A correlation analysis gives the final identification result by utilizing information over a whole pattern spectrum. Compared with the most commonly used flat SE, the double-dot SE can extract more features of original signals at different scales. Vibration signals, measured from defective bearings with outer race faults, inner race faults and ball faults, are used to evaluate the fault detection ability of the proposed SE and bearing fault diagnosis method. Results show that faults at different levels can be identified, including ball fault; and the location of outer race fault can also be differentiated.

This paper introduces a fault diagnosis method for petroleum electric drill turntable bearings, addressing the challenge of low diagnostic accuracy due to difficulties in feature extraction. The proposed approach utilizes the Adaptive Cauchy Noise Ensemble Empirical Mode Decomposition with Adaptive Noise (CNCEEMDAN) and the Differential Evolution Grey Wolf Optimization Algorithm (DE-GWO) to optimize hyperparameters for the Least Squares Support Vector Machine (LSSVM). In this paper, CNCEEMDAN is an improved signal decomposition method designed for processing vibration signals. This improves the efficiency of extracting both time and frequency-domain features. The feature datasets are then constructed based on the energy entropy criterion. LSSVM serves as the core algorithm of the classification model, while DE-GWO is a hybrid optimization strategy used to search for the optimal combination of LSSVM hyperparameters. The optimized LSSVM is subsequently used for fault diagnosis on the feature data sets. Comparative experiments demonstrate the method’s excellent performance under actual operating conditions, achieving a fault diagnosis accuracy of 97.33%. The method enables early fault detection and enhances equipment reliability in the oil industry, providing a dependable solution for diagnosing faults in electric drill turntable bearings.

The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM) was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.

Fault diagnosis of rotating machinery is vital to identify incipient failures and avoid unexpected downtime in industrial systems. This paper proposes a new rolling bearing fault diagnosis method by integrating the fine-to-coarse multiscale permutation entropy (F2CMPE), Laplacian score (LS) and support vector machine (SVM). A novel entropy measure, named F2CMPE, was proposed by calculating permutation entropy via multiple-scale fine-grained and coarse-grained signals based on the wavelet packet decomposition. The entropy measure estimates the complexity of time series from both low- and high-frequency components. Moreover, the F2CMPE mitigates the drawback of producing time series with sharply reduced data length via the coarse-grained procedure in the conventional composite multiscale permutation entropy (CMPE). The comparative performance of the F2CMPE and CMPE is investigated by analyzing the synthetic and experimental signals for entropy-based feature extraction. In the proposed bearing fault diagnosis method, the F2CMPE is first used to extract the entropy-based features from bearing vibration signals. Then, LS and SVM are used for selection of features and fault classification, respectively. Finally, the effectiveness of the proposed method is verified for rolling bearing fault diagnosis using experimental vibration data sets, and the results have demonstrated the capability of the proposed method to recognize and identify the bearing fault patterns under different fault states and severity levels.

Recently, multilayer extreme learning machine (ELM) algorithms have been extensively studied for hierarchical abstract representation learning in the ELM community. In this paper, we investigate the specific combination of $$L_{21}$$ -norm based loss function and regularization to improve the robustness and the sparsity of multilayer ELM. As we all known, the mean square error (MSE) cost function (or squared $$L_{2}$$ -norm cost function) is commonly used as optimization cost function for ELM, but it is sensitive to outliers and impulsive noises that are pervasive in real-world data. Our $$L_{21}$$ -norm loss function can lessen the harmful influence caused by noises and outliers and enhance robustness and stability of the learned model. Additionally, the row sparse inducing $$L_{21}$$ -norm regularization can learn the most-relevant sparse representation and reduce the intrinsic complexity of the learning model. We propose a specific combination of $$L_{21}$$ -norm loss function and regularization ELM auto-encoder (LR21-ELM-AE), and then stack LR21-ELM-AE hierarchically to construct the hierarchical extreme learning machine (H-LR21-ELM). Experiments conducted on several well-known benchmark datasets are presented, the results show that the proposed H-LR21-ELM can generate a more robust, more discriminative and sparser model compared with the other state-of-the-art multilayer ELM algorithms.

This paper proposes an optimized DenseNet-Transformer model based on FFT-VMD processing for bearing fault diagnosis. First, the original bearing vibration signal is decomposed into frequency-domain and time–frequency-domain components using FFT and VMD methods, extracting key signal features. To enhance the model’s feature extraction capability, the CBAM (Convolutional Block Attention Module) is integrated into the Dense Block, dynamically adjusting channel and spatial attention to focus on crucial features. The alternating stacking strategy of channel and spatial attention further improves the feature extraction ability at different scales. This optimized structure increases the diversity and discriminative power of feature representations, enhancing the model’s performance in fault diagnosis tasks. Furthermore, the Transformer module, replacing the LSTM, is employed to model long-term and short-term dependencies in the time series. Through its Self-Attention mechanism, Transformer efficiently captures the global relationships within the sequence, improving the model’s ability to handle complex temporal dependencies. Experimental results show that the proposed model achieves outstanding performance in bearing fault classification, with a classification accuracy of 99.68%, demonstrating excellent generalization ability. This model provides an effective and reliable solution for the health monitoring of chemical equipment.

Intelligent fault diagnosis of rotating machinery using improved multiscale dispersion entropy and mRMR feature selection