Vibration Waveform Research Articles

A machine learning framework for in situ sensing of pile length from seismic cone penetrometer data

Several hundred high mast light towers (HMLTs) throughout the state of Minnesota have foundation systems, typically concrete-filed steel pipe piles or steel H-piles, with no construction documentation, e.g., pile lengths. Reviews of designs within current standards suggest that some of these foundations may have insufficient uplift capacity in the event of peak wind loads. Without knowledge of the in situ pile length, an expensive retrofit or replacement program would need to be conducted. Thus, developing a screening tool to determine in situ pile length – as compared to a bulk retrofit of all towers with unknown foundations – would provide significant cost savings. The goal of the project is to establish a non-destructive evaluation (NDE) technique, including the testing setup and data analysis algorithms, for determining in situ pile lengths by way of seismic waves. This work specifically focuses on (i) the use of ground vibration waveforms captured by a seismic cone penetrometer; (ii) three-dimensional visco-elastodynamic finite element method (FEM) used as a tool to relate the sensory data to in situ pile length; and (iii) the use of machine learning (ML) algorithms, trained with the outputs of FEM simulations, to solve the germane inverse problem. In principle, the scarcity of existing HMLT configurations with known pile depth creates an absence of field data needed to adequately train an ML algorithm. However, we demonstrate that the use of FEM simulations as proxy training data for the ML algorithms leads to a robust data interpretation scheme.

Research on the identification of common faults of agricultural machinery based on vibration characteristics

Abstract In recent years, along with the rapid growth of the number of agricultural machinery and equipment in China, the problems of high failure rate and low operational efficiency of agricultural machinery have gradually emerged. Therefore, how to diagnose and monitor the common faults of agricultural machinery in real time has become a hot spot for research on common faults of agricultural machinery. Based on the current technical requirements of fault diagnosis and monitoring of common faults of agricultural machinery, this paper designs and implements a vibration feature model based on the GDBT algorithm with the common faults of agricultural machinery as the monitoring object, and shows that the corresponding values of the fault size at 0.1 mm are equal to 8.1m/s2, and the corresponding effective values at the size of 2 mm are 34, 19 m/s2. And the vibration waveform is particularly similar to the trend of the fault, with the minimum values of 13 and 110 m/s2, respectively, both at the fault size of 0.5 mm.

VMD and self-attention mechanism-based Bi-LSTM model for fault detection of optical fiber composite submarine cables

As the main electrical equipment of offshore power grids, optical fiber composite submarine cables undertake the task of power transmission and data communication. In order to ensure the proper functioning of the submarine cable, it is necessary to analyze the working state of it and identify the fault event. This paper proposes a fault detection method for submarine cables, that is, the VMD and self-attention-based Bi-LSTM model. First, we use ANSYS software to generate the vibration waveforms of three main fault events of optical fiber composite submarine cables. Then, by generating the detection matrix of background noise and the vibration waveforms, it can realize the orientation and detection of fault events in single submarine cable. In addition, the vibration signal can be decomposed into IMF components using variational mode decomposition (VMD) for feature extraction. Moreover, the IMF components are input to the self-attention layer for feature fusion and Bi-LSTM module for further feature extraction. Finally, the result of the fault detection is output through the classification layer. According to the comparative experiment and the ablation experiment, the proposed model has proved to outperform the other benchmark models and is robust and stable under the condition of different signal-to-noise ratios.

Velocity feedback control method of low-frequency electromagnetic vibration exciter based on Kalman filter estimation.

The absence of an appropriate low-frequency vibration velocity detection method to establish feedback control limits the further improvement of the low-frequency vibration performance of electromagnetic vibration exciters. In this article, a low-frequency vibration velocity feedback control method based on the Kalman filter estimation is proposed for the first time to reduce the total harmonic distortion of the vibration waveform. The rationality of establishing velocity feedback control in the velocity characteristic band of the electromagnetic vibration exciter is analyzed. Based on an identification model of the system and measured vibration displacements, the vibration velocity is estimated with high accuracy through the Kalman filter. The velocity feedback control system is established to suppress the impacts of disturbances effectively. Experimental results show that the method proposed in this paper can reduce the harmonic distortion of vibration waveform by 40%, which is 20% higher than the traditional control method, thoroughly verifying its superiority.

Nonlinear Vibration Control Experimental System Design of a Flexible Arm Using Interactive Actuations from Shape Memory Alloy.

The flexible arm easily vibrates due to its thin structural characteristics, which affect the operation accuracy, so reducing the vibration of the flexible arm is a significant issue. Smart materials are very widely used in the research topic of vibration suppression. Considering the hysteresis characteristic of the smart materials, based on previous simulation research, this paper proposes an experimental system design of nonlinear vibration control by using the interactive actuation from shape memory alloy (SMA) for a flexible arm. The experiment system was an interactive actuator-sensor-controller combination. The vibration suppression strategy was integrated with an operator-based vibration controller, a designed integral compensator and the designed n-times feedback loop. In detail, a nonlinear vibration controller based on operator theory was designed to guarantee the robust stability of the flexible arm. An integral compensator based on an estimation mechanism was designed to optimally reduce the displacement of the flexible arm. Obtaining the desired tracking performance of the flexible arm was a further step, by increasing the n-times feedback loop. From the three experimental cases, when the vibration controller was integrated with the designed integral compensator, the vibration displacement of the flexible arm was much reduced compared to that without the integral compensator. Increasing the number of n-times feedback loops improves the tracking performance. The desired vibration control performance can be satisfied when n tends to infinity. The conventional PD controller stabilizes the vibration displacement after the 7th vibration waveform, while the vibration displacement approaches zero after the 4th vibration waveform using the proposed vibration control method, which is proved to be faster and more effective in controlling the flexible arm's vibration. The experimental cases verify the effectiveness of the proposed interactive actuation vibration control approach. It is observed from the experimental results that the vibration displacement of the flexible arm becomes almost zero within less time and with lower input power, compared with a traditional controller.

Remaining Useful Life Prediction for Circuit Breaker Based on SM-CFE and SA-BiLSTM

Targeting at the uncertainty of the degradation of conventional circuit breakers (CCBs) and the perfect mechanical degradation characterization by vibration signals, a remaining useful life (RUL) prediction method based on similarity measure (SM), comprehensive features extraction (CFE) and self-attention bidirectional long short-term memory network (SA-BiLSTM) is proposed in this paper. Firstly, the degradation-sensitive intrinsic mode functions (IMFs) of the vibration signals are separated by the SM method, and the reconstructed signals are divided into intervals based on the working process of CCBs to obtain the vibration signals for life prediction. Secondly, the explicit parametric features (EPFs) are obtained based on the vibration events and waveform features, and the implicit parametric features (IPFs) are extracted using the multi-scale convolutional auto-encoder (MSCAE). Next, the comprehensive features are obtained by combination of the EPFs and IPFs. On this basis, the degradation mode judgment method is formed by using the least square method (LSM) linear fitting of the EPFs. Finally, a quantitative life prediction model based on SA-BiLSTM is constructed, and greater weights are assigned to the important time steps. The proposed method is proved to show high prediction accuracy and good stability, which is more advantageous compared with other hybrid prediction models.

Research on filtering method of rolling bearing vibration signal based on improved Morlet wavelet

<abstract><p>In response to the challenge of noise filtering for the impulsive vibration signals of rolling bearings, this paper presented a novel filtering method based on the improved Morlet wavelet, which has clear physical meaning and is more conducive to parameter optimization through employing Gaussian waveform width to replace the traditional Morlet wavelet shape factor. Simultaneously, the marine predation algorithm was employed and the minimum Shannon entropy was used as the parameter optimization index while optimizing the shape width and center frequency of the improved Morlet wavelet. The vibration waveform of the rolling bearing was matched perfectly by using the optimized Morlet wave. Shannon entropy was used as the evaluation index of noise filtering, and the quantitative analysis of noise filtering was realized. Through experimental validation, this method was proved to be effective in noise elimination for rolling bearing. It is significance to preprocessing of vibration signal, feature extraction and fault recognition of rolling bearing.</p></abstract>

Microvibration transfer and suppression of satellite under multi-source coupling disturbances based on energy flow analysis

The accuracy of satellites is extremely dependent on the control of the micro-vibration while the transmission paths among multiple vibration sources are complex. To reduce the impact of micro-vibration on the payloads of satellites effectively, the transmission characteristics of micro-vibrations under multi-source disturbances were analyzed, and a specific vibration suppression scheme was proposed. Based on the theoretical derivation and energy flow analysis method, the coupling transmission characteristics of micro-vibrations in the satellite under single- and multi-source disturbances were compared. The transmission characteristics of the vibration in the satellite under multi-source disturbance were obtained to determine the main transfer path. The contributions of different waveforms for elastic waves generated by vibration, namely bending wave, longitudinal wave and shear wave, to the target point were obtained by calculating the net transfer ratio to find out the dominant transfer waveform of the vibration. The vibration along the main transmission path was blocked by means of stiffened plates and an optimal vibration isolation scheme was determined by comparing the fluctuations in the vibrational energy of the payload under various stiffened ways. The results showed that the vibration energy under multi-source disturbances could not be obtained by the superposition of that under the single source. The longitudinal wave was the dominant transfer waveform of vibration with the energy to the payload accounting for 92.26%. The optimal vibration isolation treatment on the main transmission path can reduce the vibration by 79.25% on average, up to one order of magnitude.

Improving purity of blasting vibration signals using advanced Empirical Mode Decomposition and Wavelet packet technique

The study proposes a denoising method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Wavelet packet threshold denoising (WPTD) to reduce the noise of blasting vibration signals. CEEMDAN is first employed to decompose noisy blasting vibration signals into different intrinsic mode functions (IMFs), i.e., different frequencies of subcomponents. By using correlation coefficients, all of IMFs are automatically categorized as the dominant IMFs with higher portions of vibration components and the secondary IMFs with less vibration contents. Then, with further decomposing two groups of IMFs into different scales of Wavelet packet coefficient series, WPTD based on the fixed-threshold technique and the soft threshold function method is applied to minimize the level of noise in two groups of IMFs. Two groups of denoised IMFs are finally reconstructed as the pure blasting vibration waveform. Numerical waveforms with different types and intensities of noise and measured blasting vibration signals with different main frequency bands are used to verify the accuracy and capability of the proposed method. The numerical and field results show that the proposed method can not only effectively reduce noise components, but also well remain components of blasting vibrations.

Suppression of Wind Generator Speed Vibration Based on the Internal Model Control with Three Degrees of Freedom

When the wind power system is working in the maximum wind energy tracking area, or when its mechanical drivetrain system vibrates and the vibration frequency is relatively high, the system cannot suppress the speed vibration of the generator in the drivetrain system by adjusting the pitch angle. In this paper, a generator speed control system based on the three degrees of freedom internal model control (3-DOF-IMC) is established to control the generator speed. Thus, a scheme of using the feedback filter in the 3-DOF-IMC to suppress generator speed vibration caused by drivetrain shaft elasticity and gear clearance in the drivetrain system is proposed. Firstly, the vibration problem and waveform of the two-mass wind power drivetrain systems are discussed, and the generator’s vector control and speed control systems are analyzed. Secondly, the principle of the 3-DOF-IMC is described, and the influence of the three controllers on the speed tracking performance and anti-interference performance of the generator is discussed. The suppression ability of the feedback filter for different forms of disturbance signals is emphasized. Finally, the feedback filter controls the generator speed and eliminates the influence of drivetrain vibration on the generator speed. To verify the superiority of the proposed method, the vibration suppression effect, tracking performance and anti-interference performance of the proposed method are compared with the engineering design method (EDM) and conventional IMC (1-DOF-IMC) method. When the parameter α/β = 0.66, the generator speed amplitude overshoot of the proposed method is the same as the EDM. When α/β = 1, it is only 4% of the amplitude overshoot of the EDM. In addition, the tracking performance and anti-interference performance of the proposed method can be adjusted independently, and it is better than the EDM and the 1-DOF-IMC method.

Fleet-based early fault detection of wind turbine gearboxes using physics-informed deep learning based on cyclic spectral coherence

The development of a reliable and automated condition monitoring methodology for the detection of mechanical failures in rotating machinery has garnered much interest in recent years. Thanks to the rise in popularity of machine learning techniques, the number of purely data-driven approaches that try to tackle the issue of vibration-based condition monitoring has also drastically improved. Instead of directly using the vibration measurement data as input to a machine learning model, this work first exploits the cyclostationary characteristics inherent to vibration waveforms originating from rotating machinery. The proposed methodology first estimates the two-dimensional cyclic spectral coherence map of a vibration signal in order to decompose the cyclic modulations on the cyclic and carrier frequency plane. While this provides an effective tool to visualize any potential modulation signatures of faulty gears or bearings, it does not allow for easy inspection over time due to its dimensions. To tackle this issue, this paper proposes an unsupervised deep learning approach to wield this vast amount of data as a tool for detecting persistent changes in the modulation characteristics of the vibration signals. In the first phase, a deep autoencoder learns to reconstruct predictions of the cyclic coherence maps based on unlabeled healthy vibration data and the machine operating conditions. Two post-processing steps improve the predictions by mitigating frequency shifts and outlier or noisy measurements. Lastly, the residual error between the predicted and the actual coherence map is then aggregated and employed for further alarming based on thresholds. The autoencoder model is trained using five years of gearbox vibration data from five different wind turbines. The methodology is then validated on two faulty and eight healthy turbines. The results confirm that the proposed approach can deliver clear indications of failure for the faulty turbine while being completely devoid of any significant alarm trends for the healthy turbines. Thanks to the combination of highly effective cyclostationary signal processing with deep learning while using the operating conditions, the proposed methodology can detect and track incipient mechanical faults from non-stationary vibration data of rotating machinery. Lastly, it is important to emphasize that the proposed method is capable of learning the healthy behavior on one turbine and predicting the expected behavior on another turbine.

A New Strategy for Disc Cutter Wear Status Perception Using Vibration Detection and Machine Learning.

Carrying out status monitoring and fault-diagnosis research on cutter-wear status is of great significance for real-time understanding of the health status of Tunnel Boring Machine (TBM) equipment and reducing downtime losses. In this work, we proposed a new method to diagnose the abnormal wear state of the disc cutter by using brain-like artificial intelligence to process and analyze the vibration signal in the dynamic contact between the disc cutter and the rock. This method is mainly aimed at realizing the diagnosis and identification of the abnormal wear state of the cutter, and is not aimed at the accurate measurement of the wear amount. The author believes that when the TBM is operating at full power, the cutting forces are very high and the rock is successively broken, resulting in a complex circumstance, which is inconvenient to vibration signal acquisition and transmission. If only a small thrust is applied, to make the cutters just contact with the rock (less penetration), then the cutters will run more smoothly and suffer less environmental interference, which would be beneficial to apply the method proposed in this paper to detect the state of the cutters. A specific example was to use the frequency-domain characteristics of the periodic vibration waveform during the contact between the cutter and the granite to identify the wear status (including normal wear state, wear failure state, angled wear failure state) of the disc cutter through the artificial neural network, and the diagnosis accuracy rate is 90%.

Development of Vibration Measurement System using a Microcontroller

It is important to interpret resonance in the design to reduce the vibration of mechanical structures, and to verify this resonance phenomenon by experiments and theoretical approach. When the vibration of a continuous system is observed using a vibration system, the experience and skill of the observer affect the measurement accuracy of the natural frequency and vibration modes. Therefore, in this study, a vibration measurement system is developed to stably and quantitatively verify the natural vibration of the beams using a microcontroller and an ultrasonic sensor. The vibration measurement system consists of a microcontroller, a vibration motor and an ultrasonic sensor. The accuracy and validity of the natural frequencies of the beams measured by the system are discussed, and the performance of present system is evaluated on the basis of the measurement results of the natural frequencies and the natural vibration waveforms.

Degradation Trend Prediction of Hydropower Units Based on a Comprehensive Deterioration Index and LSTM

Deterioration trend prediction of hydropower units helps to detect abnormal conditions of hydropower units and can prevent early failures. The reliability and accuracy of the prediction results are crucial to ensure the safe operation of the units and promote the stable operation of the power system. In this paper, the long short-term neural network (LSTM) is introduced, a comprehensive deterioration index (CDI) trend prediction model based on the time–frequency domain is proposed, and the prediction accuracy of the situation trend of hydropower units is improved. Firstly, the time–domain health model (THM) is constructed with back-propagation neural network (BPNN) and condition parameters of active power, guide vane opening and blade opening and the time–domain indicators. Subsequently, a frequency-domain health model (FHM) is established based on ensemble empirical mode decomposition (EEMD), approximate entropy (ApEn), and k-means clustering algorithm. Later, the time–domain degradation index (TDI) is developed according to THM, the frequency-domain degradation index (FDI) is constructed according to FHM, and the CDI is calculated as a weighted sum by TDI and FDI. Finally, the prediction model of LSTM is proposed based on the CDI to achieve degradation trend prediction. In order to validate the effectiveness of the CDI and the accuracy of the prediction model, the vibration waveform dataset of a hydropower plant in China is taken as a case study and compared with four different prediction models. The results demonstrate that the proposed model outperforms other comparison models in terms of predicting accuracy and stability.

Nonlinear characteristic and chip breaking mechanism for an axial low-frequency self-excited vibration drilling robot

Drilling is one of the essential material removal methods in the aerospace field. This study proposes a flexible variable-stiffness axial low-frequency self-excited vibration drilling scheme for automatic manufacturing platforms. Firstly, an elastic zone active conversion mechanism of the drilling actuator is established, which could realize robot stiffness control in different directions and the directional tool vibration excitation. Then, the nonlinear characteristic of self-excited vibration excitation and vibration waveform is analyzed under various inherent characteristics and drilling parameters. An interface separation chip breaking condition of dual-frequency self-excited vibration drilling is proposed based on the dynamic equivalent undamped state. Finally, the self-excited vibration drilling state, tool trajectory, chip breaking performance, chip morphology, and action mechanism of parameters coupling characteristics are investigated based on experiment and simulation results. This drilling system could produce stable self-excited vibration and smooth chip breaking without a vibration excitation device.

Evaluation of human perception thresholds of transient vibrations for the assessment of building vibration

Vibrations in low-rise buildings in the frequency range from a few hertz to tens of hertz are caused by external sources, such as road traffic, and could induce annoyance in occupants if their magnitude is in excess of human perception levels. Although there have been several different standardised metrics to evaluate human responses to such vibrations, no common metric has been accepted worldwide. In the present study, laboratory experiments were conducted to determine human perception thresholds of transient vibrations similar to building vibrations. The thresholds were evaluated by three methods based on running r.m.s. acceleration with different integration methods and frequency weightings and by the fourth power vibration dose method. The metrics based on the Vibration Level used in Japan and the Vibration Dose Value in the international standard were better than the other methods for the evaluation of perception of the input vibrations used in the experiments. The evaluation of threshold of transient vibrations was also investigated with short-time average acceleration by optimising the integration time and time constant for averaging. The optimised integration time and time constant appeared to be dependent on the frequency and waveform of transient vibration.

Experimental investigations of the effect of millisecond-delay time on the blast vibration reduction with electronic detonators

The error of precise initiation time controlled at the microsecond level in the electronic detonator blasting is accurate enough to realize blasting vibration reduction; however, the realization of precise control of blasting vibration using the electronic detonators remains rudimentary, researches on the precise zoning protection of buildings and field experiments are lacked. Therefore, multi-delay time of double-hole and multi-hole blasting experiments were carried out to explore the influence of different delay time on blast-induced PPV (Peak Particle Velocity). Based on the measured blasting vibration waveforms with blasting center distance of 16–200 m the reasonable delay time reducing PPV was investigated when the protective buildings at different blasting center distances and the reasonable delay time suitable for zoning protection was put forward to verify the applicability of the electronic detonators. The results show that as the initiation delay time increases, the PPV of blasting vibration first decreases then increases and finally attenuates to the single-hole PPV, with the increase of the blasting center distance, the reasonable delay time for reducing PPV gradually increases. However, a greater vibration enhancement effect will be produced when the delay time reaches at a certain value in the near area, the generated maximum PPV is about 1.8 times the single-hole PPV and there will be multiple short delay time producing enhancement effect in multi-hole blasting, the short delay time cannot be blindly adopted to reduce vibration. Therefore, the delay time of electronic detonators should be reasonably set to achieve the effect of blasting vibration reduction based on the distance between the protected buildings and the blasting zone.

Full Waveform Prediction of Blasting Vibration Using Deep Learning

Blasting vibration could cause dynamic instability of rock masses within a critical steady state. To control the blasting vibration, it is necessary to understand the complete dynamic response process of the rock masses under the blasting vibration. The Long Short-Term Memory (LSTM) technique uses blast monitoring data to predict the full waveform of the blast vibration. Based on the LSTM, a new full waveform prediction model is proposed in this study. To verify the feasibility of the proposed model, the sample data were constructed using the well-known linear blast wave superposition prediction formula. The full waveform prediction model is trained and the predicted waveform and the actual waveform are then evaluated and compared. The loss function is calculated and discussed, which verifies the feasibility of the prediction method. In addition to the numerical research, the actual blasting vibration data are also used for verification. The parameters, such as sequence size, training algorithm, and some hidden layer nodes, are discussed and optimized. The results show that the proposed full waveform prediction model based on LSTM can predict the full blasting waveform. This study provides a new idea for the prediction and control of blasting vibration.

A new identification method of high voltage circuit breaker mechanical fault based on combined analysis of time‐reference‐distance and shape entropy algorithms

The vibration of high voltage circuit breakers is superimposed by the impact vibration generated by the action of its components. When the operating states of the components change, the vibration waveform will be distorted. To extract the state information contained in the vibration signals, in this paper we propose a new method for the mechanical fault identification of circuit breakers based on the joint analysis of time-frequency domain features. Firstly, a new time-reference-distance algorithm (TRD) which employs feature space to grab information is proposed to get the time-domain features in detail. The feature space is constructed by the kurtosis, crest factor, and peak divergence degree of the time-domain waveform. Further, we propose another new algorithm, the shape entropy algorithm (SE), to extract the frequency-domain features. Through converting the power spectrum of the vibration signals to polar coordinates via the divergence factor, the SE features are then obtained by combining with the information entropy formula. Finally, the TRD and SE features are combined and input into the support vector machine (SVM) model for fault identification. The test results verify the efficiency of the methodology and the identification process takes less time. It has a practical application value.

Impact point localization in three-dimensional structures using wavelet transform

Impact-induced anomalies such as travelling waves can be found in many devices or structures. This article provides an experimental method to localize a point of impact in three-dimensional structures using an array of redundant sensors. Concurrent measurement of vibration waveforms in moving measurement points and stationary reference allows determining the times of arrival of the travelling wave and, more importantly, times of arrival relative to the reference. These relative times of arrival allow for employing more measurement points than channels in the data acquisition system. This work proposes a modified method to estimate the times of arrival by combining continuous wavelet transform with optimal interval partitioning. The work also considers that the path between the impact and the measurement point depends on the properties of the structure, causing apparent wave speeds to differ across the measurement points. Therefore, regular triangulation and multilateration methods, which assume equal wave speeds, offer a reduced accuracy. The localization is solved as a constraint optimization problem considering variable apparent speeds.