Time Domain Vibration Signals Research Articles

ASG-HOMGAT: a high-order multi-head graph attention network with adaptive small graph structure for rolling bearing fault diagnosis

Traditional Euclidean spatial data processing is difficult to capture the inherent relationships of unstructured data such as bearing vibration signals. Representing vibration signals in graphical form helps to preserve their topological structure and temporal information. Secondly, most existing graph convolutional network methods are based on large graph structured data, which incurs certain memory overhead when aggregating high-order neighborhood node information and ignores important information between samples in the global graph structure. To address these issues, this paper proposes a high-order multi-head graph attention network based on an adaptive small graph structure (ASG-HOMGAT) for fault diagnosis of rolling bearings. Firstly, the adaptive preprocessing layer is used to adaptively denoise and compress the one-dimensional time-domain vibration signal, generating small rule graph data with topological structure. Then, these small graph structured data samples are input into a higher-order graph neural network, which aggregates features from multiple higher-order neighborhoods to achieve richer feature representations and fully explore the intrinsic correlation between samples. Finally, these features are aggregated into a reinforced representation of graph nodes through a multi head attention mechanism, and a SoftMax classifier is used for fault classification. The experimental results show that the ASG-HOMGAT method has better performance compared to mainstream graph neural network diagnostic models. The code and model will be released at: https://github.com/ding-ss/ASG-HOMGAT.

Nonlinear dynamics of full-ceramic bearing-rotor system considering structural defects in cage pockets

Full ceramic bearings provide exceptional characteristics, including elevated accuracy and substantial load-bearing capability, rendering them indispensable in high-end rotating machinery. Still, the long-term use of the bearing will lead to the gradual wear and defects of the cage pocket, which may affect the unstable operation of the rotor system. This study examines the vibration characteristics of cage failure through simulation and experiments. To study the dynamic characteristics of the bearing-rotor system, a dimensionless model is established by using the lumped mass method, and a cage failure model is added to the model, which can study the influence of cage failure on the system stability. Phase trajectories, Poincaré plots, and bifurcation diagrams are employed to analyze the impact of individual parameters on the nonlinear vibration of the system. Ultimately, to gather cage vibration data from two different types of faulty, the experimental approaches are used. The findings indicate that in the event of cage failure, the system’s amplitude amplifies and the time-domain vibration signal exhibits distinct periodicity. Then, the vibration energy gradually focuses on low-frequency vibrations. Additionally, the spectrograms allow for easier identification of frequency components associated with the cage frequency, such as nfc and mfs ± nfc, the largest error is 3.32% when comparing the two models’ simulated results with the experimental data. The model accurately depicts the frequency characteristics of failures resulting from wear and defects in full ceramic bearing cages. It offers crucial information for detecting failures and monitoring the health of full ceramic bearings.

A 2D-CNN-Based Two-Stage Structural Damage Localization and Quantification Technique Using Time Domain Vibration Data

The conventional approaches for detecting structural degradation are time-consuming, labor-intensive, and costly. The physical monitoring of the structure also poses risks to the health and safety of supervisors. Therefore, damage estimation of any structure using artificial intelligence (AI), more specifically deep learning (DL), is becoming more significant in civil infrastructure. In the presented research article, an efficient two-stage damage detection method is proposed for structural damage detection (SDD) from time domain vibration signals. The proposed method utilizes two-dimensional convolutional neural network (2D-CNN) architecture as a DL algorithm for damage detection. Here, a computer-aided damage detection method for steel beam and frame-type structures is developed using 2D-CNN algorithm in the Google Colab platform. The effectiveness of the proposed method is first verified, and it provides more than 90% accuracy for identifying the damage location and severity of a cantilever beam for single- and multi-damage scenarios from numerically simulated noisy displacement data. The algorithm is also experimentally validated through the raw acceleration data of damaged steel frame joints collected from the Qatar University Grandstand simulator (QUGS). The proposed 2D-CNN algorithm performs better than other DL algorithms by achieving 100% accuracy within 10 epochs for damage detection of steel frames using QUGS data. It demonstrates significant potential for detecting damage location and quantifying damages for single- and multi-damage scenarios using noise-free and noisy datasets. The primary contribution of this study resides in the implementation of two-stage damage detection algorithm utilizing 2D-CNN with time domain vibration response for multiclass damage identification and quantification.

A real time digital vibration acceleration fiber sensing system based on a multi-carrier modulation/demodulation technique

A multi-longitudinal mode fiber laser sensor (MLMFLS) system based on digital modulation/demodulation technique for vibration acceleration detection is proposed. To the best of the authors’ knowledge, this is the first digital vibration acceleration demodulation system ever reported by a MLMFLS system. A few beat frequency signals (BFS) generated by the MLMFLS are used as signal carriers of applied vibration signals. Based on multi-channel digital down-conversion technique, the weak vibration signals modulated on the BFS are superposed by utilizing the digital universal software radio peripheral (USRP). The signal-to-noise ratio (SNR) of the output vibration signal is greatly enhanced. A spectral subtraction method is also utilized to improve the SNR of the demodulated vibration signal. The acceleration of the vibration signal is obtained after second order differential of the time domain vibration signal. By simply changing the position of window function of short-time Fourier transform, a real-time vibration frequency and acceleration sensing system is achieved. The measurement results demonstrated a minimum detectable acceleration of 0.03 g at vibration frequency of 1.0 Hz by the designed sensing system. It also has a simple structure, high signal-to-noise ratio and stability.

Time-Frequency Multi-Domain 1D Convolutional Neural Network with Channel-Spatial Attention for Noise-Robust Bearing Fault Diagnosis

This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on vibration sensor signals that can be implemented at industry sites under a high-noise environment. Previous 1D CNN-based bearing diagnosis models are mostly based on either time domain vibration signals or frequency domain spectral signals. In contrast, our model has parallel 1D CNN modules that simultaneously extract features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information on bearing fault signals. Additionally, physics-informed preprocessings are incorporated into the frequency-spectral signals to further improve the classification accuracy. Furthermore, a channel and spatial attention module is added to effectively enhance the noise-robustness by focusing more on the fault characteristic features. Experiments were conducted using public bearing datasets, and the results indicated that the proposed model outperformed similar diagnosis models on a range of noise levels ranging from −6 to 6 dB signal-to-noise ratio (SNR).

A machine-learning approach to setting optimal thresholds and its application in rolling bearing fault diagnosis

Bearings are one of the critical components of any mechanical equipment. They induce most equipment faults, and their health status directly impacts the overall performance of equipment. Therefore, effective bearing fault diagnosis is essential, as it helps maintain the equipment stability, increasing economic benefits through timely maintenance. Currently, most studies focus on extracting fault features, with limited attention to establishing fault thresholds. As a result, these thresholds are challenging to utilize in the automatic monitoring diagnosis of intelligent devices. This study employed the generalized fractal dimensions to effectively extract the feature of time-domain vibration signals of bearings. The optimal fault threshold model was developed using the receiver operating characteristic curve, which served as the baseline of exception judgment. The extracted fault threshold model was verified using two bearing operation experiments. The experimental results revealed different damaged positions and components observed in the two experiments. The same fault threshold model was obtained using the method proposed in this study, and it effectively diagnosed the abnormal states within the signals. This finding confirms the effectiveness of the diagnostic method proposed in this study.

Classification of multi-type bearing fault features based on semi-supervised generative adversarial network (GAN)

Fault diagnosis is a crucial technology for ensuring the reliable and efficient operation of industrial systems. With the advancement of industrial informatization and intelligence, fault diagnosis methods have the trend shifting from traditional signal processing to deep learning. However, traditional deep learning models are not suitable for industrial scenarios with limited labeled data, imbalanced categories. To address these challenges, this paper proposes a novel approach based on semi-supervised generative adversarial networks (SGANs) to systematically study the fault diagnosis of rolling bearings in the case of unlabeled samples and sparsely labeled samples. In this work, the vibration time-domain vibration signal of the bearing is firstly transformed into a spectrum signal through the fast Fourier transform. This transformed signal is then fed into the GAN model to extract multi-layer sensitive features, providing a deeper understanding of the underlying fault characteristics. Subsequently, the SGAN method utilizes unsupervised learning via spectral clustering algorithms to automatically classify fault patterns in industrial equipment. Furthermore, it enhances semi-supervised learning by incorporating limited label information through softmax functions, effectively discerning the authenticity of unlabeled data. For the effectiveness of SGAN for bearing fault diagnosis, two diverse datasets are utilized including the widely-used Case Western Reserve University dataset and data acquired from South Ural State University. Compared to alternative models, the results underscore SGAN’s robustness, achieving high recognition accuracy and clustering performance. The proposed methodology contributes to the advancement of fault diagnosis technologies by combining unsupervised and semi-supervised learning techniques.

An Improved MSCNN and GRU Model for Rolling Bearing Fault Diagnosis

In this paper, a novel fault diagnosis method based on the fusion of squeeze and excitation-multiscale convolutional neural networks (SENet-MSCNN) and gate recurrent unit (GRU) is proposed to address the problem of low diagnosis rate caused by the fact that normal samples are much larger than fault samples in the vibration big data. The method takes the time-domain vibration signal as input and fuses the spatial features extracted by SENet-MSCNN. The temporal features extracted by GRU in order to bring them into the fully connected layer for identification so as to realize the intelligent diagnosis of rolling bearing adaptive feature extraction. Finally, the method is applied to the simulated signal and experimental data for testing and analysis. The results reveal that the model can reach 98.98 % and 76.44 % migration diagnostic accuracy in bearing and gearbox datasets. At the same time, it has strong noise immunity, adaptivity, and robustness, providing an effective way for intelligent diagnosis of rolling bearing vibration big data.

Multi-Mode Data Generation and Fault Diagnosis of Bearings Based on STFT-SACGAN

To achieve multi-mode fault sample generation and fault diagnosis of bearings in a complex operating environment with scarce labeled data. Combining a semi-supervised generative adversarial network (SGAN) and an auxiliary classifier generative adversarial network (ACGAN), a semi-supervised auxiliary classifier generative adversarial network (SACGAN) is constructed in this paper. The network structure and the loss function are improved. A fault diagnosis method based on STFT-SACGAN is also proposed. The method uses a short-time Fourier transform (STFT) to convert one-dimensional time-domain vibration signals of bearings into two-dimensional time-frequency images, which are used as the input of SACGAN. Two multi-mode fault data generation and intelligent diagnosis cases for bearings are studied. The experimental results show that the proposed method generates high-quality multi-mode fault samples with high fault diagnosis accuracy, generalization, and stability.

Pavement surface defect recognition method based on vehicle system vibration data and feedforward neural network

ABSTRACT The pavement surface will inevitably develop cracks, subsidence, pits, ruts, and other defects due to the effects of traffic and the environment. In road engineering, vibration-based pavement condition monitoring has been widely adopted. Due to differences in vehicle dynamics, acquisition equipment, and road quality, the application of these techniques to the identification of minor pavement damage is limited. With the widespread adoption of the inertial navigation system (INS) in autonomous vehicles, INS-based pavement evaluation has emerged as a promising new technique. In this paper, the acceleration sensor, gyroscope, GPS, and other INS-integrated devices were used to collect data on vehicle attitude changes. For the detection of pavement apparent millimetre disease, a new method utilising INS data and machine learning was proposed. The method analyses the original vibration signal in time domain, determines the degree of sensing parameter influence, and extracts the index that can characterise the signal change. Multiple machine learning recognition models have been built to effectively classify road conditions, with the best-performing model achieving an F1 score of 99.61% and precision of 99.33%. The recall rate, accuracy rate, and F1 score of disease height classification were all above 0.7 on a macro and micro scale.

Semi-Supervised Adversarial Transfer Networks for Cross-Domain Intelligent Fault Diagnosis of Rolling Bearings

In recent advances, deep learning-based methods have been broadly applied in fault diagnosis, while most existing studies assume that source domain and target domain data follow the same distribution. As differences in operating conditions lead to the deterioration of diagnosis performance, domain adaptation technology has been introduced to bridge the distribution gap. However, most existing approaches generally assume that source domain labels are available under all health conditions during training, which is incompatible with the actual industrial situation. To this end, this paper proposes a semi-supervised adversarial transfer networks for cross-domain intelligent fault diagnosis of rolling bearings. Firstly, the Gramian Angular Field method is introduced to convert time domain vibration signals into images. Secondly, a semi-supervised learning-based label generating module is designed to generate artificial labels for unlabeled images. Finally, the dynamic adversarial transfer network is proposed to extract the domain-invariant features of all signal images and provide reliable diagnosis results. Two case studies were conducted on public rolling bearing datasets to evaluate the diagnostic performance. An experiment under variable operating conditions and an experiment with different numbers of source domain labels were carried out to verify the generalization and robustness of the proposed approach, respectively. Experiment results demonstrate that the proposed method can achieve high diagnosis accuracy when dealing with cross-domain tasks with deficient source domain labels, which may be more feasible in engineering applications than conventional methodologies.

Multi-scale deep neural network for fault diagnosis method of rotating machinery

In recent years, deep learning technology has shown great potential in the fault diagnosis of rotating machinery based on vibration signals. However, the feature extraction and noise robustness still need to be improved. To this end, we propose a multi-scale deep neural network fault diagnosis method. Firstly, multi-scale down sampling of time-domain vibration signals. Next, the attention long short-term memory network and the fully convolutional neural network of the multi-scale convolution kernel are used for feature extraction. Then, a fusion module is utilized to fuze the extracted features. The proposed method is evaluated on the public bearing datasets. Experimental results demonstrate that the proposed method can achieve high accuracy and noise robustness.

Deep order-wavelet convolutional variational autoencoder for fault identification of rolling bearing under fluctuating speed conditions

Because of the complex operating environment of high-end industrial machinery, rolling bearing is generally operated at fluctuating working conditions such as variable speeds or loads, thus enables fault feature information is not obvious. That said, bearing fault identification under fluctuating working conditions are recognized as a very challenging problem. Deep learning blazes a valid route to address this issue by right of strong self-learning performance. Nevertheless, the performance of traditional deep learning model will degrade in the face of the fluctuating data with a sharp rising and heavy external interference. Therefore, to overcome this limitation, this study proposes a novel method named deep order-wavelet convolutional variational autoencoder (DOWCVAE) to identify bearing faults under fluctuating speed conditions, which can improve feature learning ability of a plain convolutional variational autoencoder (CVAE). Within this approach, an improved energy-order analysis with frequency-weighted energy operator (FWEO) is firstly presented to convert the raw time-domain vibration signal into the resampled angle-domain signal to relieve the influence of speed fluctuating and acquire the enhanced order spectrum data. Afterwards, wavelet kernel convolutional block (WKCB) with anti-symmetric real Laplace wavelet (ARLW) is constructed to extract the latent feature information closely related to equipment states from the enhanced order spectrum data via the stacked way layer by layer, which is capable of further promoting learning performance of overall network model and improve its generalizability. In addition, a high-efficiency intelligent optimization algorithm termed as multi-objective gray wolf optimizer (MOGWO) is introduced for choosing automatically optimal wavelet parameters of DOWCVAE model and avoiding negative impact posed by artificially adjusting parameter. Ultimately, the learned latent features are loaded to the softmax classifier to achieve automatic identification of different bearing health states and provide comprehensive diagnosis result. The analysis results from two experiment cases testify the effectiveness of our approach. Quantitatively, average identification accuracy of the proposed approach can reach 99% above, which shows its competitive advantages and is more satisfying as compared to some representative deep learning methods.

Simulacija torzijske vibracije signala dvotaktnog brodskog dizelskog motora pri normalnom paljenju i zatajenju paljenja

The article presented the modelling of torsional vibration signal of marine diesel engine, MAN B&W 6S46MC-C7, installed in general cargo ships 34000 DWT, built at Pha Rung Shipyard (Vietnam). The authors imitated the torsional vibration signal, based on the established signal modelling when diesel engine works normal firing and mis-firing state, according to the Class Regulation Rules for new building steel hull ships when calculating and measuring the torsional vibration of marine diesel propulsion shaft-line system. The authors used Matlab software to imitate the torsional vibration signals in the real time domain and then converted them into the frequency order by Fast Fourier Transform (FFT).

A deep capsule neural network with data augmentation generative adversarial networks for single and simultaneous fault diagnosis of wind turbine gearbox

The fault diagnosis (FD) of wind turbine gearbox (WTG) is of special importance for keeping the wind turbine drivetrain working normally and safely. However, owing to the limited training data and the mutual interference of various mechanical parts, it is of great difficulty to realize the simultaneous-fault monitoring task of WTG using existing intelligent FD methods or manual inspection-based approaches. To tackle the issue, a deep capsule neural network with data augmentation generative adversarial networks, named ST-DAGANs-CapNet, is developed for the single and simultaneous FD of WTG by integrating capsule neural network (CapsNet) with Stockwell transform (ST) and data augmentation generative adversarial networks (DAGANs). The proposed ST-DAGANs-CapNet method mainly consists of three steps. First of all, ST is adopted to extract two-dimension (2-d) image features of time–frequency domain from raw time-domain vibration signals of WTG. Then, DAGANs are employed for generating more fake image samples to address the problem of lacking training data. At last, the built CapsNet model is utilized to diagnose the single and compound faults of WTG by the primary 2-d feature images and the made fake 2-d feature images in training set. Two experimental studies are implemented to prove the effectiveness of the proposed method, and the result is compared with some existing intelligent FD of WTG. It indicates that DAGANs are effective in helping to tackle the issue of limited and unbalanced training samples in real FD of WTG, and the diagnosis result of the proposed approach in test sample set is better than that of several commonly used FD methods in literatures.

Bearing Fault Diagnosis for Time-Varying System Using Vibration–Speed Fusion Network Based on Self-Attention and Sparse Feature Extraction

Nowadays, most deep-learning-based bearing fault diagnosis methods are studied under the condition of steady speed, while the performance of these models cannot be fully played under time-varying conditions. Therefore, in order to facilitate the practical application of a deep learning model in bearing fault diagnosis, a vibration–speed fusion network is proposed, which utilizes a transformer with a self-attention module to extract vibration features and utilizes a sparse autoencoder (SAE) network to extract sparse features from speed pulse signal. The vibration–speed fusion network enables the efficient fusion of different signals in a high-dimensional vector space with a high degree of model interpretability, without additional signal processing steps. After tuning the hyperparameters of the network, the key segments of the bearing’s time-domain vibration signals can be optimally extracted, the network performance is much better than traditional deep learning methods, and the classification accuracy can reach 95.18% and 99.85% on the two public bearing datasets from the Xi’an Jiaotong University and the University of Ottawa.

Shock detection of rotating machinery based on activated time-domain images and deep learning: An application to railway wheel flat detection

Failures of rotating mechanical components (e.g., turbine, gear, wheelset) often cause serious shocks to the mechanical system, and real-time detection of these shocks is of importance in maintenance decision-making for the equipment. The service conditions (e.g., rotating speed, load) of rotating machinery are often complex, and therefore the self-adaptability and generalizability of shock detection methods under variable operating conditions is an issue worthy of in-depth study. In this paper, a novel hybrid method combining a threshold-based method for feature extraction and a machine-learning-based method for pattern recognition is developed. This method consists of two steps. First, an adaptive feature called activated time-domain image (ATDI) is proposed, where two adaptive activation functions are proposed to activate the time-domain vibration signals after being preprocessed. The resulting ATDI feature image is highly adaptive and changes adaptively depending on the operating conditions. Then, a hybrid method combining ATDI and deep neural network (ATDI-DNN) is developed, where a circshift-based data augmentation method is introduced for enriching the ATDI feature images. Finally, the proposed ATDI-DNN method is used for wheel flat detection of a railway vehicle under variable operating conditions. Experiments demonstrate that the ATDI-DNN model trained with samples from one speed level can be directly applied to other speed levels, and its superiority is demonstrated by comparative methods. The proposed method can be extended to shock detection of other similar rotating machinery.

Rotor Fault Diagnosis Using Domain-Adversarial Neural Network with Time-Frequency Analysis

Intelligent fault diagnosis of rotors always requires a large amount of labeled samples, but insufficient vibration signals can be obtained in operational rotor systems for detecting the fault modes. To solve this problem, a domain-adaptive transfer learning model based on a small number of samples is proposed. Time-domain vibration signals are collected by overlapping sampling and converted into time-frequency diagrams by using short-time Fourier transform (STFT) and characteristics in the time domain and frequency domain of vibration signals are reserved. The features of source domain and target domain are projected into the same feature space through a domain-adversarial neural network (DANN). This method is verified by a simulated gas generator rotor and experimental rig of rotor. Both the transfer in the identical machine (TIM) and transfer across different machines (TDM) are realized. The results show that this method has high diagnosis accuracy and good robustness for different types of faults. By training a large number of simulation samples and a small number of experimental samples in TDM, high fault diagnosis accuracy is achieved, avoiding collecting a large amount of experimental data as the source domain to train the fault diagnosis model. Then, the problem of insufficient rotor fault samples can be solved.

Influence of the Order of Phase Differentiation and Unwrapping on Retrieval of Temporal Waveforms in Phase-Demodulated φ-OTDR

Generally, phase differentiation and unwrapping are both used to retrieve vibration events in phase-demodulated φ-OTDR. We investigate the influence of the order of these two operations on vibration retrieval, i.e., unwrapping the differential phase (UDP) and differentiating the unwrapped phase (DUP). The results demonstrate the UDP would add an extra DC value on the resulting phase and be unable to exactly restore temporal waveforms of vibration signals. Hence, it is necessary to firstly unwrap the original demodulated phase before performing differentiation to reliably restore the disturbances. Before retrieving temporal waveforms of vibration signals, a sliding rectification average (SRA) is applied to locate multiple events for better noise performance. In our experiment, the temporal waveforms of two different vibration sources at different positions are retrieved by phase changes extracted by the DUP. It is observed that the SNR is considerably improved due to reduction of background noises, and time-domain vibration signals are well recovered by the DUP-acquired phase changes.

Research on degradation prediction of rolling bearing based on adaptive multi-GA-BP

Rolling bearings are widely used in industrial equipment. It is of great significance to study the degradation trend of rolling bearings. In this paper, an Adaptive Multi-population Genetic Algorithm (AMGA) is proposed. Firstly, Kernel Principal Component Analysis (KPCA) method is used to fuse the vibration signal in both time domain and frequency domain, which uses kernel to map the sample space to higher dimensional space and uses the higher dimensional space for linear dimensionality reduction. It can effectively reduce the dimension of nonlinear correlation variables and obtain the trend signal representing the Remaining Useful Life (RUL) characteristics of rolling bearing. Moreover, AMGA is proposed to optimize the number of neurons, initial weight, and initial threshold of the Back Propagation (BP) neural network prediction model. AMGA applies chaos algorithm to Genetic Algorithm (GA) to improve the diversity of the initial population. Meanwhile, the communication frequency between different populations is controlled by judging the similarity of the optimal solution among different populations, so as to effectively jump out of the local optimum and obtain the global optimal solution. Finally, the whole life data of the spin-up process of the rolling bearing from University of Cincinnati is taken as an example to analyze the performance of the algorithm. Compared with the traditional BP, the R2-score performance and the MAPE performance of KPCA-AMGA-BP are improved by 0.297 and 2.46% respectively. Furthermore, compared with the optimized BP, this method obtains the improved R2-score performance and the MAPE performance by 0.218 and 0.46%.