Vibration-based Analysis Research Articles

Automated potholes detection using vibration and vision-based techniques

Roads serve as vital parts of our infrastructure, providing as crucial conduits for people's mobility and connectivity. However, the growing number of vehicles on the road has resulted in an increase in pavement strain and degradation, which has a substantial impact on the entire riding experience. To achieve a high-quality surface, roadways must be consistently monitored and maintained. In recent years, transportation infrastructure agencies and governments have shown a rising interest in leveraging new technologies to monitor road pavements. This interest derives from the difficult and time-consuming nature of manual and instrumented techniques. Automated technologies have arisen as a response to these issues, notably in recognizing pavement deterioration, such as the common problem of potholes. The objective of this research is to identify potholes using two low-cost automated techniques: a vibration-based method that uses the G-Sensor Logger application and a vision-based way that uses image processing. On the same roads, both approaches were employed and compared, with manual surveying utilized to validate the results. The results showed that vision-based strategies were more effective than vibration-based methods. Finally, although vibration-based analysis is appropriate for routine monitoring, vision-based analysis provides a more comprehensive and in-depth examination of road conditions. These discoveries will help future efforts to better monitor and maintain road surfaces, ensuring a smooth and safe travel experience for everybody.

Improving the Performance of Convolutional GAN Using History-State Ensemble for Unsupervised Early Fault Detection with Acoustic Emission Signals

Early fault detection (EFD) in run-to-failure processes plays a crucial role in the condition monitoring of modern industrial rotating facilities, which entail increasing demands for safety, energy and ecological savings and efficiency. To enable effective protection measures, the evolving faults have to be recognized and identified as early as possible. The major challenge is to distil discriminative features on the basis of only the ‘health’ signal, which is uniquely available from various possible sensors before damage sets in and before the signatures of incipient damage become obvious and well-understood in the signal. Acoustic emission (AE) signals have been frequently reported to be able to deliver early diagnostic information due to their inherently high sensitivity to the incipient fault activities, highlighting the great potential of the AE technique for EFD, which may outperform the traditional vibration-based analysis in many situations. To date, the ‘feature-based’ multivariate analysis dominates the interpretation of AE waveforms. In this way, the decision-making relies heavily on experts’ knowledge and experience, which is often a weak link in the entire EFD chain. With the advent of artificial intelligence, practitioners seek an intelligent method capable of tackling this challenge. In the present paper, we introduce a versatile approach towards intelligent data analysis adapted to AE signals streaming from the sensors used for the continuous monitoring of rotating machinery. A new architecture with a convolutional generative adversarial network (GAN) is designed to extract the deep information embedded in the AE waveforms. In order to improve the robustness of the proposed EFD framework, a novel ensemble technique referred to as ‘history-state ensemble’ (HSE) is introduced and paired with GAN. The primary merits of HSE are twofold: (1) it does not require extra computing time to obtain the base models, and (2) it does not require a special design of the network architecture and can be applied to different networks. To evaluate the proposed method, a durability rolling contact fatigue test was performed with the use of AE monitoring. The experimental results have demonstrated that the proposed ensemble method largely improves the robustness of GAN.

Postseismic Survey of a Historic Masonry Tower and Monitoring of Its Dynamic Behavior in the Aftermath of Le Teil Earthquake (Ardèche, France)

ABSTRACTOn 11 November 2019, an Mw 4.9 earthquake struck the middle Rhône valley (South-East France) producing moderate to severe damage in the town of Le Teil and its surroundings. This unexpected event stressed the vulnerability of the French cultural built heritage to a moderate seismic hazard. Commonly applied to modern civil engineering structures, passive seismic methods are still lacking on historic constructions to understand properly the different factors driving their dynamic behavior. In this article, the results of a two-month seismic monitoring survey carried out shortly after the Le Teil mainshock in a historic masonry tower are presented and discussed. Located only 5 km south of the epicenter, the Gate Tower of Viviers (eleventh century) was instrumented with four highly sensitive seismic nodes. Ambient vibrations, as well as aftershocks and quarry blasts from the nearby Le Teil quarry, were recorded and used in the analysis. Through vibration-based analysis, the article addresses three relevant aspects of the dynamic response of ancient masonry structures. We discuss first the differences in the building’s response induced by the three reported types of vibrations, focusing on the particular signal characteristics of shallow aftershocks and quarry blasts. Then, we apply the Random Decrement Technique (RDT) to track the dynamic behavior variations over two months and to discuss the role of the environmental conditions in the slight fluctuations of the structural modal parameters (natural frequencies, damping coefficients) of unreinforced masonry structures. We also show evidence of the nonlinear elastic behavior under both weak seismic and atmospheric loadings. The correlation between the presence of heterogeneities in the construction materials and the nonlinear threshold supports the relevance of such types of monitoring surveys as a valuable tool for future modeling works and conservation efforts.

Time domain vibration analysis techniques for condition monitoring of rolling element bearing: A review

Rolling element bearings are very critical components of rotating machines and the presence of defects in the bearing may lead to failure of machines. Rolling Element Bearing (REB) fault detection, diagnosis, prognosis are the key steps of machine failure diagnostics. Under operating condition of the bearing may avoid malfunctioning and breakdown of machines. Although various methods to fault detection and diagnosis of the same have been proposed in the literature, such as the thermograph, visual inspection, ultrasonic test, motor current analysis, acoustic emission analysis, the wear-debris analysis, oil analysis, and the vibration analysis. The vibration-based analysis is proven as a popular among all non-destructive methods due to its merits over the other. Time domain vibration analysis technique is better for the online monitoring, remote area, non human intervention area, and hazard location. This paper reviews time domain vibration analysis techniques for REB fault detection. The collected vibration signals from machinery with the help of appropriate data acquisition system, which incorporates the vibration transducers are in time domain. Various statistical parameters are listed to illustrate them as time domain feature from vibration signals In order to understand various features and terminologies, REB vibration signals (Bearing Data Set) acquired from Bearing Data Center, of Case Western Reserve University (CWRU) are used.

Vibration characteristics of a rotor-bearing system caused due to coupling misalignment – a review

In this paper, the authors presented various insights into theoretical and experimental analysis carried out in past, to understand the vibration characteristics of a misaligned rotor-bearing system. The literature presented by various researchers was reviewed methodically. Firstly, the literature review based on theoretical vibration analysis of misaligned rotor system with emphasis on finite element method has been presented. Secondly, various vibration-based analysis methods and the description of experimental measurement techniques have been discussed in detail. Apart from the above, distinct tools used for the detection of fault analysis of the rotor system is also reviewed systematically, which may be useful for preventive maintenance of the rotating machinery used in several industries.

Envelope Analysis on Vibration Signals for Stator Winding Fault Early Detection in 3-Phase Induction Motors

This paper brings up a novel method for detecting induction motor stator winding faults at an early stage. The contribution of the work comes from the delicate handling of motorvibration by applying envelope analysis, which makes it possible to capture electrical short-circuit signature in mechanical signals, even if the magnitude of the fault is fairly incipient. Conventional induction motor condition-based maintenance methods usually involve current and voltage measurements, which could be expensive to collect, and vibration-based analysis is often only capable of detecting the fault when it is already quite significant. In contrast, the solution presented in this study provides a refreshing perspective by applying time synchronous averaging to remove the discrete frequency component, and amplitude demodulation to further enhance the signal with the help of kurtogram. Experimental results on a three-phase induction motor show that the method is also able to distinguish different fault severity levels.

Fault diagnosis for circuit-breakers using adaptive chirp mode decomposition and attractor’s morphological characteristics

In order to minimize operation and maintenance costs and enhance the reliability of circuit-breaker (CB), faults should be detected simply and diagnosed effectively. To enable this, monitoring or diagnostic-test techniques should provide critical information of the CB and make the decision-making process simple. In recent years, vibration-based analysis has gained attention for the said purpose. However, the diagnostic performance is limited by the highly time-varying and non-stationary vibration signals. Hence, within this paper a new diagnostic framework is proposed for CB fault diagnosis. The recently proposed adaptive chirp mode decomposition (ACMD) is introduced for extracting the fast fluctuating instantaneous frequency in the CB’s vibration signal. A high-resolution adaptive time-frequency spectrum which can clearly represent the time-frequency (TF) characteristics of the vibration signal is obtained by combining the wavelet transform and ACMD. The component with the most significant TF fluctuation is reconstructed into phase space to study the dynamical characteristics of CB. Based on the reconstructed phase space, a new set of dynamical features, namely RST (i.e., ratio of major to minor axis, shape complexity and trajectory compactness), is proposed for achieving a stable and accurate diagnosis of CB faults. The proposed diagnostic framework is evaluated on two experimental scenarios with different types of CB. The reasonable diagnostic performances confirm the ability of the proposed technique in diagnosing CB faults.

An Improved Scheme for Vibration-Based Rolling Bearing Fault Diagnosis Using Feature Integration and AdaBoost Tree-Based Ensemble Classifier

Bearings are key components in modern power machines. Effective diagnosis of bearing faults is crucial for normal operation. Recently, the deep convolutional neural network (DCNN) with 2D visualization technology has shown great potential in bearing fault diagnosis. Traditional DCNN-based fault diagnosis mostly adopts a single learner with one input and is time-consuming in sample and network construction to obtain a satisfied performance. In this paper, a scheme combining diverse DCNN learners and an AdaBoost tree-based ensemble classifier is proposed to improve the diagnosis performance and reduce the requirement of sample and network construction simultaneously. In this scheme, multiple types of samples can be constructed independently and employed for diagnosis simultaneously; next, the same number of DCNN learners are built for underlying features extraction and the obtained results are integrated and finally fed into the ensemble classifier for fault diagnosis. An illustration based on the Case Western Reserve University datasets is given, which proves the superiority of the proposed scheme in both accuracy and robustness. Herein, we present a universal scheme to improve the diagnosis performance, and give an example for practical application, where the signal preprocessing and image sample construction methods can also be applied in other vibration-based analysis.

Nonconvex Wavelet Thresholding Total Variation Denoising Method for Planetary Gearbox Fault Diagnosis

The vibration-based analysis is an effective technique for planetary gearbox fault diagnosis, but a difficult task is how to accurately identify fault features from noisy vibration signals. In this paper, a nonconvex wavelet thresholding total variation (WATV) denoising method is proposed for planetary gearbox fault diagnosis, which combines wavelet-domain sparsity and total variation (TV) regularization. The TV regularization algorithm is employed to modify the retained wavelet coefficients so that the occurrence of oscillations caused by wavelet thresholding is suppressed. To overcome the underestimation shortcoming of L1-norm regularization, nonconvex penalty function regularization is used to strongly promote the sparsity of estimation while guaranteeing that the global optimal solutions are obtained even though the objective function is nonconvex. Then, the split augmented Lagrangian shrinkage (SALSA) method is developed to solve the nonconvex WATV denoising problem. Two experimental studies are performed to verify the performance and effectiveness of the proposed method. Comparisons with the soft thresholding and basis pursuit denoising (BPD) methods show that the proposed method can accurately estimate the fault features from vibration signals, which means that the proposed method is an effective and promising tool for planetary gearbox fault diagnosis.

Adsorption-induced symmetry reduction of metal-phthalocyanines studied by vibrational spectroscopy

We investigate the vibrational properties of Pt- and Pd-phthalocyanine (PtPc and PdPc) molecules on Ag(111) with high resolution electron energy loss spectroscopy (HREELS). In the monolayer regime, both molecules exhibit long range order. The vibrational spectra prove a flat adsorption geometry. The red shift of vibrational modes and the presence of asymmetric vibrational peaks suggest a moderate interaction of the molecules with the substrate, accompanied by a static charge transfer from the metal to the molecules. The appearance of a particular vibrational mode, which (i) belongs to the $\mathrm{B_{1g}}$ representation of the original fourfold $\mathrm{D_{4h}}$ molecular symmetry group and which (ii) exhibits interfacial dynamical charge transfer (IDCT), proves that a preferential charge transfer from the Ag surface into one of the originally doubly degenerate lowest unoccupied molecular orbitals (LUMOs) of $\mathrm{E_g}$ symmetry takes place, i.e. the electronic degeneracy is lifted and the molecule-surface complex acquires the twofold symmetry group $\mathrm{C_{2v}}$. The vibration-based analysis of orbital degeneracies, as carried out here for PtPc/Ag(111) and PdPc/Ag(111), is not restricted to these cases. It is particularly useful whenever the presence of multiple molecular in-plane orientations at the interface makes the analysis of orbital degeneracies with angle-resolved photoemission spectroscopy difficult.

Vibration-based gearbox fault diagnosis using deep neural networks

Vibration-based analysis is the most commonly used technique to monitor the condition of gearboxes. Accurate classification of these vibration signals collected from gearbox is helpful for the gearbox fault diagnosis. In recent years, deep neural networks are becoming a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. In this paper, a study of deep neural networks for fault diagnosis in gearbox is presented. Four classic deep neural networks (Auto-encoders, Restricted Boltzmann Machines, Deep Boltzmann Machines and Deep Belief Networks) are employed as the classifier to classify and identify the fault conditions of gearbox. To sufficiently validate the deep neural networks diagnosis system is highly effective and reliable, herein three types of data sets based on the health condition of two rotating mechanical systems are prepared and tested. Each signal obtained includes the information of several basic gear or bearing faults. Totally 62 data sets are used to test and train the proposed gearbox diagnosis systems. Corresponding to each vibration signal, 256 features from both time and frequency domain are selected as input parameters for deep neural networks. The accuracy achieved indicates that the presented deep neural networks are highly reliable and effective in fault diagnosis of gearbox.

Vibration-Based Damage Identification Method Using Modified Back-Propagation Neural Networks

This paper presents a damage detection method using a combination of global (changes in natural frequencies) and local (displacement mode shapes) vibration-based analysis data as input in neural networks for location and severity prediction of structural damage. The necessary features for damage detection have been selected by performing sensitivity analyses. In order to check the robustness of the input used in the analysis and to simulate the numberical errors, artificial random noise has been generated numerically and added to noise-free data during the training of the neural networks. Furthermore, a modified back-propagation neural networks with the dynamic steepest descent (DSD) algorithm as training algorithm is used to improve the training efficiency. With those as basis, the neural networks can assess damage condition (locaiton and severity) with very good accuracy.

Recovery of vibration signal based on a super-exponential algorithm

Vibration-based analysis is an important technique in machine fault diagnosis. In complex machines, the vibration generated by a component is easily affected by the vibration of other components or is corrupted by noise from other sources. Hence, the fault-related vibration must be recovered from among those sources for accurate diagnosis. In this paper, a super-exponential algorithm (SEA) based on the single-input single-output (SISO) convolution mixing model is investigated to deconvolve the vibration signal of interest. Based on simulated vibration signals generated by a test bench in a laboratory and real signals generated by industrial machines, the characteristics of the SEA with skewness and kurtosis schemes are studied extensively for the recovery of signals with different statistical distributions. It is shown that the SEA with the skewness scheme is more suitable for the isolation of a vibration signal with an asymmetric distribution, whereas the SEA with the kurtosis scheme is more efficient for detecting a vibration with abrupt changes in its distribution. Furthermore, the effect of the equalizer length on the characteristics of the equalized signal is discussed. A performance curve that presents the equalization performance is defined, and a method that uses this curve to select the optimal equalizer length for successfully recovering the defect signal from the mixed signal is then proposed. The study presented in this paper thus shows that the SEA is a promising method for the recovery of vibrations in machine fault diagnosis.

Quantification and localisation of damage in beam-like structures by using artificial neural networks with experimental validation

This paper presents a damage detection algorithm using a combination of global (changes in natural frequencies) and local (curvature mode shapes) vibration-based analysis data as input in artificial neural networks (ANNs) for location and severity prediction of damage in beam-like structures. A finite element analysis tool has been used to obtain the dynamic characteristics of intact and damaged cantilever steel beams for the first three natural modes. Different damage scenarios have been introduced by reducing the local thickness of the selected elements at different locations along finite element model (FEM) of the beam structure. The necessary features for damage detection have been selected by performing sensitivity analyses and different input–output sets have been introduced to various ANNs. In order to check the robustness of the input used in the analysis and to simulate the experimental uncertainties, artificial random noise has been generated numerically and added to noise-free data during the training of the ANNs. In the experimental analysis, two steel beams with eight distributed surface-bonded electrical strain gauges and an accelerometer mounted at the tip have been used to obtain modal parameters such as resonant frequencies and strain mode shapes. Finally, trained feed-forward backpropagation ANNs have been tested using the data obtained from the experimental damage case for quantification and localisation of the damage.

Vibration-based damage identification in beam-like composite laminates by using artificial neural networks

This paper investigates the effectiveness of the combination of global (changes in natural frequencies) and local (curvature mode shapes) vibration-based analysis data as input for artificial neural networks (ANNs) for location and severity prediction of damage in fibre-reinforced plastic laminates. A finite element analysis tool has been used to obtain the dynamic characteristics of intact and damaged cantilever composite beams for the first three natural modes. Different damage scenarios have been introduced by reducing the local stiffness of the selected elements at different locations along the finite element model of the beam structure. After performing the sensitivity analyses aimed at finding the necessary parameters for the damage detection, different input-output sets have been introduced to various ANNs. In order to check the robustness of the input used in the analysis, random noise has been generated numerically and added to noise-free data during the training of the ANNs. Finally, trained feedforward back-propagation ANNs have been tested using new damage cases and checks have been made for severity and location prediction of the damage.