Vibration Acceleration Signals Research Articles

The performance evaluation of hybrid roller bearings under lubricant contamination conditions

Purpose This paper aims to evaluate the dynamic performance of hybrid roller bearings under lubricant contamination. Design/methodology/approach Some steel rollers in traditional cylindrical thrust roller bearings were replaced with ceramic rollers to assemble hybrid roller bearings. Friction experiments were conducted under lubricant contamination using alumina as the contaminant, and simultaneous vibration acceleration signals from the bearings were collected to evaluate their tribological and dynamic performance. Findings Under lubricant contamination, hybrid roller bearings with a sufficient number of ceramic rollers exhibit greater wear resistance compared to traditional all-steel bearings. There is a noticeable suppression of energy in both tangential and normal frequency bands of the bearings, with more pronounced suppression observed in higher frequency bands. Originality/value This study provides valuable insights for the development of hybrid ceramic bearings. Peer review The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-08-2024-0291/

Method for Detecting Roadbed Compaction Degree Based on Machine Learning and Vibration Acceleration

Roadbed construction occupies a core position in highway construction, but its quality is easily constrained by multiple factors such as changing environmental factors, the performance of construction equipment, and the professional abilities of construction personnel, leading to potential quality risks. Traditional quality inspection methods are mostly carried out after construction is completed, making it difficult to achieve continuous and real-time monitoring of roadbed compaction quality, which to some extent limits the real-time feedback and adjustment of construction quality. Vibration compaction technology has been widely used in the field of highway engineering due to its high efficiency and speed. The compaction degree is directly related to the durability and service life of the highway; therefore, accurate and efficient detection of compaction degree is crucial. This article proposes a method for detecting roadbed compaction degree by integrating machine learning (ML) and vibration acceleration signals. This method aims to achieve accurate evaluation of roadbed compaction by real-time monitoring and analysis of vibration acceleration data, combined with the powerful prediction and classification capabilities of ML algorithms. The experimental results show that this method not only improves the detection efficiency, but also significantly enhances the accuracy of compaction degree detection.

Application of Machine Learning Methods to Analyze the Dependence of Vibration Acceleration Signals on the Tightening Forces of Bolted Connections

The article is devoted to the application of machine learning methods for the analysis of vibration acceleration signals in bolted joints that occur under impact. The relevance of the work is due to the need to ensure the reliability and operability of bolted joints under loads. One of the promising areas of non-destructive testing is the analysis of the characteristics of vibration acceleration signals that change with changes in the state of structures, for example, with an increase in the tightening torque. This allows for the timely detection of possible defects and the prevention of emergency situations, ensuring the safety and durability of structures. The vibration acceleration signals under impact action on a bolted joint were analyzed. After calculating the signal characteristics, data sets were formed, including the values of tightening torques and the corresponding calculated signal characteristics, a search for a correlation between the tightening torque of bolted joints and the obtained set of vibration signal parameters was carried out. The frequency spectrum of signals, the Higuchi fractal dimension, detrended fluctuations, spectral power density and position of signal peaks were calculated. Machine learning models such as decision trees, the nearest neighbor method, the k-means method and neural networks were used for the analysis. For these methods, an optimal set of parameters correlating with the tightening torque was searched for. The main results show that machine learning methods are effective in classifying signals and finding correlations with stress state parameters. They allow us to detect the relationship between a set of signal characteristics and tightening torque, which opens up opportunities for more accurate and reliable monitoring of the condition of bolted connections. This should help to increase their operational reliability and durability, as well as reduce the likelihood of failures and accidents. The use of such methods can improve the quality of monitoring and diagnostics of bolted connections.

A High-Speed Train Axle Box Bearing Fault Diagnosis Method Based on Dimension Reduction Fusion and the Optimal Bandpass Filtering Demodulation Spectrum of Multi-Dimensional Signals

The operating state of axle box bearings is crucial to the safety of high-speed trains, and the vibration acceleration signal is a commonly used bearing-health-state monitoring signal. In order to extract hidden characteristic frequency information from the vibration acceleration signal of axle box bearings for fault diagnosis, a method for extracting the fault characteristic frequency based on principal component analysis (PCA) fusion and the optimal bandpass filtered denoising signal analytic energy operator (AEO) demodulation spectrum is proposed in this paper. PCA is used to measure the dimension reduction and fusion of three-direction vibration acceleration, reducing the interference of irrelevant noise components. A new type of multi-channel bandpass filter bank is constructed to obtain filtering signals in different frequency intervals. A new, improved average kurtosis index is used to select the optimal filtering signals for different channel filters in a bandpass filter bank. A dimensionless characteristic index characteristic frequency energy concentration coefficient (CFECC) is proposed for the first time to describe the energy prominence ability of characteristic frequency in the spectrum and can be used to determine the bearing fault type. The effectiveness and applicability of the proposed method are verified using the simulation signals and experimental signals of four fault bearing test cases. The results demonstrate the effectiveness of the proposed method for fault diagnosis and its advantages over other methods.

Wear characteristics evolution of helical gear with initial defects of bearing inner ring

This study investigated the wear characteristics and operational condition of gears with initial defects of the bearing inner ring. The working states of gears were evaluated through a combination of vibration signal analysis, wear debris concentration analysis, qualitative analysis of the wear debris, and tooth surface analysis. Based on the Hertz contact theory, a dynamic model for the gear drive system was constructed, enabling the simulation and comparison of vibration acceleration signals under normal and fault conditions. The research results revealed that bearing defects induced irregularities in vibration frequency and amplitude, adversely affecting the performance and stability of the gear system. Furthermore, these defects trigger the creation of substantial wear debris, which exacerbates gear wear and reduces the gear lifespan by about 15%. Additionally, bearing defects induced intermittent load spikes and uneven stress distribution across tooth contacts, resulting in localized high shear stresses, material flaking, and surface spalling. Consequently, initial defects of the bearing will accelerate gear wear progression and lead to abnormal wear patterns, potentially resulting in the premature failure of the gear train system. The study investigates the underlying mechanisms of gear wear evolution influenced by these defects and offers practical guidelines for the engineering, manufacturing, and maintenance of gear systems.

Cutting state recognition of spiral bevel gear face hobbing

Abstract To investigate the issue of chatter vibration during the face hobbing process of spiral bevel gears, this study conducted experiments on the YKA2260 gear hobbing machine, collecting 142 sets of vibration acceleration signals. The optimal combination for wavelet threshold denoising was determined based on the signal-to-noise ratio (SNR), and preprocessing of the raw signals was performed. Utilizing wavelet packet decomposition, the energy entropy of wavelet packet coefficients was extracted as feature values. A recognition model for the cutting state during the face hobbing process of spiral bevel gears was established using a Support Vector Machine, achieving a recognition accuracy of up to 98.0769%. Furthermore, the model’s high recognition accuracy for small training samples in engineering applications was validated.

Digital twin-assisted intelligent fault diagnosis for bearings

Abstract Data-driven intelligent fault diagnosis methods generally require a large amount of labeled data and considerable time to train network models. However, obtaining sufficient labeled data in practical industrial scenarios has always been a challenge, which hinders the practical application of data-driven methods. A digital twin (DT) model of rolling bearings can generate labeled training dataset for various bearing faults, supplementing the limited measured data. This paper proposes a novel DT-assisted approach to address the issue of limited measured data for bearing fault diagnosis. First, a dynamic model of bearing with damages is introduced to generate simulated bearing acceleration vibration signals. A DT model is constructed in Simulink, where the model parameters are updated based on the actual system behavior. Second, the structural parameters of the DT model are adaptively updated using least squares method with the measured data. Third, a Vision Transformer (ViT) -based network, integrated with short-time Fourier transform, is developed to achieve accurate fault diagnosis. By applying short-time Fourier transform at the input end of the ViT network, the model effectively extracts additional information from the vibration signals. Pre-training the network with an extensive dataset from miscellaneous tasks enables the acquisition of pre-trained weights, which are subsequently transferred to the bearing fault diagnosis task. Experiments results verify that the proposed approach can achieve higher diagnostic accuracy and better stability.

Chatter and Surface Waviness Analysis in Oerlikon Face Hobbing of Spiral Bevel Gears

A vectorized analytical model for the cutting dynamics in the spiral bevel gear face hobbing process has been developed, which is based on machine tool kinematics and vibration vectorization. The structural modal parameters of the cutter head spindle system are obtained through experimental modal analysis with hammer impact testing. The analytical model is utilized to simulate the generation of simulated vibration acceleration signals during spiral bevel gear hobbing. A wavelet threshold denoising method is applied to process the simulated vibration signals of the spiral bevel gear face hobbing with added white noise. Signal processing methods, including short-time Fourier transform are employed for time-domain analysis, frequency-domain analysis, and time–frequency-domain analysis of measured signals and simulated signals, thereby extracting the corresponding statistical features. In addition to the results of the experimental modal analysis, the causes of chatter in spiral bevel gear hobbing are discussed in detail, revealing that the main factor is cutter head vibration in the Y direction of the Hunan ZDCY CNC EQUIPMENT YKA2260 machine tool used in this research. The error in the time-domain characteristic parameters between simulated signals and measured vibration acceleration signals is within 15%, with a difference of 3.5% in spectral peak values. The predicted tooth surface morphology from simulation matches the actual morphology on the workpiece, comprehensively validating the reliability of the cutting dynamics model for the spiral bevel gear face hobbing process. Another conclusion drawn from numerical simulation experiments is that the amount of tooth surface waviness of the spiral bevel gears is the ratio of tool chatter frequency to cutting fundamental frequency.

Processing and analysis of friction vibration signal of diamond-like carbon film microtextured dry gas seal rings

PurposeThis paper aims to analyze the characteristics of friction vibration signals and identify the vibration excitation source at the start and stop stage of microtextured end face of dry gas seals.Design/methodology/approachThe friction pair consists of a diamond-like carbon (DLC) film microtextured seal ring and a spiral groove seal ring. Friction vibration signal feature extraction method based on harmonic wavelet packet and spectrum analysis was proposed. Signals were collected using acceleration sensor, acquisition card and LabVIEW software. Vibration acceleration signal was decomposed into 32 frequency bands using MATLAB wavelet packet transformation. The 32nd band coefficient was extracted for reconstruction, time-domain and spectral waveforms were obtained and spectra before/after denoising were compared.FindingsThe end face of the DLC film microtextured seal ring generates a good dynamic pressure effect, and the friction and vibration reduction effects are obvious. The harmonic wavelet packet can decompose the vibration signal conveniently and precisely. In the case of this experiment, the frequency of vibration of the seal ring is 7500 HZ.Originality/valueThe results show that the method is effective for the processing of friction vibration signal and the identification of vibration excitation source. The findings will provide ideas for the frictional vibration signal processing and basis for further research in the field of tribology of dry gas seal ring.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-03-2024-0084/

A Field Test Study on the Instability of a Pump-Turbine under Turbine Mode

Abstract In the context of increasing demand for flexible operation of hydropower plants, this study analyses the factors leading to instability in a prototype pump turbine under turbine mode, based on experimental data collected on-site. Pressure sensors and accelerometers were installed to compare pressure signals and vibration acceleration signals. The test results show that the characteristics of pressure fluctuation are dominated by three specific factors under different output power. Vibration reaches its maximum value at approximately 30% of the rated output and its minimum value at around 70% of the rated output, and the causes of twice increases in vibration is not the same. These characteristics often indicate potential unsteady flow, vortex-induced vibration, and flow separation, subsequently affecting the stability of the pump turbine. Understanding the conditions and severity of the occurrence of instability characteristics in the unit is of great significance for power plant personnel to adjust the unit’s operation strategy and improve operational efficiency.

Influence of microtextured parameters of dry gas sealing rings on tribological performance

PurposeThis study aims to research the influence mechanism of microtextured geometric parameters of dry gas seal end face on the tribological behavior under dry frictional conditions.Design/methodology/approachThe microtexture was processed using laser processing, while the diamond-like carbon (DLC) film was applied through magnetron sputtering; the experimental platform of friction vibration was established, the frictional and vibrational properties of different geometric parameters were tested; the data signals of vibrational acceleration and frictional torque were collected and processed using data acquisition instrument. The entropy characteristic parameters of 3D vibrational acceleration were extracted based on wavelet packet decomposition method. The end-face topography was measured with ST400 three-dimensional noncontact surface topography instrument.FindingsThe geometry of pits plays a key role in influencing friction performance; the permutation entropy and fuzzy entropy of the vibration acceleration signal changed with variations in microtextured parameters. A textured surface with appropriately size parameters can trap debris, enhance the dynamic pressure effect, reduce impact between the friction interfaces and improve the frictional vibrational performance. In this research, microtextured surface with Φ150 µm-10% and Φ200 µm-5% can effectively reduce friction and vibration between the end faces of a dry gas seal.Originality/valueDLC film improves the hardness of seal ring end face, and microtexture improves the dynamic effect; the tribological behavior monitoring can be realized by analyzing the characteristics of vibration acceleration sensitive parameter with friction state. The findings will provide a basis for further research in the field of tribology and the microtexture optimization of dry gas seal ring end face.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-12-2023-0389/

Techniques for Accelerometer Reading Processing on Railway Transport Using Wavelet Transform

Introduction. Safety issues of railway transport are inevitably connected with the condition of railway tracks and railway wheels. Various defects, such as irregularities of the railway track, may lead to emergencies and incidents. Therefore, it is important to measure and calculate short and impulse irregularities. A joint analysis of vibration acceleration signals is needed in order to study the types and size of railway track irregularities.Aim. Development of an algorithm for irregularity search based on accelerometer readings with the vertical measurement axis.Materials and methods. The research encompassed wavelet transformation and wavelet-based signal processing including discrete-time signal processing and continuous wavelet processing. In addition, time-frequency analysis based on Fourier transform and continuous wavelet scalogram was used. These methods provide for time-frequency localization for irregularity detection and measurement.Results. Algorithms for vibrational signal processing using the continuous and discrete-time wavelet transform are proposed. The results show that the discrete wavelet transform is effective for multiresolution and multiband analysis, and continuous wavelet transform and wavelet scalogram allows extraction of irregularities and determination of their parameters. The relative error for irregularity depth was improved by 18 %, and the absolute error for irregularity length determinations was reduced by 7 times.Conclusion. Application of the discrete Fourier transform and Fourier spectrogram provides for fine resolution in the frequency domain. However, separation of signal components in the time-frequency domain is impeded. The continuous-time wavelet transform ensures sufficient resolution in the low-frequency domain for component localization and visualization of irregularities.

Indirect identification of bridge damage based on coupled vehicle–bridge vibration and 2D-CNN

This study puts forth a methodology to discern structural damage in bridges that employs two-dimensional convolutional neural network (2D-CNN), which is rooted in the principles of continuous wavelet transform (CWT) theory. The method combines the vehicle–bridge coupled vibration response with deep learning models to extend the application of indirect bridge damage identification methods. To test the proposed method, a spatial vehicle and bridge computational model is established for a three-span continuous beam bridge, and bridge damage is simulated by reducing the stiffness of the unit under different damage conditions. Considering the stochastic nature of road roughness, a self-developed vehicle–bridge coupled vibration analysis program is utilized to acquire the vehicle acceleration response signal and construct the dataset. The 2D-CNN model, with its high sensitivity to 2D data features, is used to extract features from the vehicle vertical acceleration vibration signal. The signal undergoes transformation via CWT, resulting in a 2D grayscale time-frequency image. This image is subsequently utilised as input to construct the 2D-CNN model. Results demonstrate that this method performs well in the identification of bridge structural damage, exhibiting high accuracy in identifying the location and severity of such damage. Thus, a novel avenue is provided for the identification and assessment of bridge structural damage.

A vibration-based Machine Learning type Structural Health Monitoring methodology for populations of composite aerostructures under uncertainty

A robust to uncertainty Machine Learning (ML) based Structural Health Monitoring methodology for populations of composite aerostructures is postulated. The methodology is founded upon a number of unsupervised ML algorithms for damage detection and a supervised counterpart for damage characterization. Damage detection is specifically based on two types of Healthy Subspace representations: A Multiple Model (MM) and a varying radii Hyper-Sphere (HS) type. Both are built upon response-only vibration acceleration and/or strain signals at properly selected sensor locations. Based on them, Multiple Input Single Output (MISO) Transmittance Function AutoRegressive with eXogenous (TF-ARX) excitation data driven models representing the partial structural dynamics are obtained. Decision making is then based on the model parameter vector that may be transformed and reduced via Principal Component Analysis (PCA). Damage detection is achieved via multi-level information fusion using acceleration and/or strain sensors. Damage characterization, referring to damage type, location, and level determination, is achieved via a hierarchical cosine similarity based algorithm. The methodology is successfully assessed via hundreds of experiments using a population of small-scale composite coupons for the detection and characterization of Delamination and Impact damage under material/manufacturing, temperature, excitation, and experimental uncertainty.

Effects of Macro-Pitting Fault on Dynamic Characteristics of Planetary Gear Train Considering Surface Roughness

The planetary gearbox plays a vital role in a wide range of mechanical power transmission systems, including high-speed trains, wind turbines, vehicles, and aircraft. At the same time, the planetary gear train inside the gearbox is regarded as the most susceptible to failure in the entire transmission system. To analyze the influence of surface roughness on the dynamic characteristics of the planetary gear train, a dynamic modeling method based on fractal theory is proposed. Firstly, the tooth surface contact model was established based on the W-M fractal function, and the time-varying mesh stiffness (TVMS) of the planetary gear train was calculated under healthy and tooth macro-pitting. Then, the lumped-parameter method is introduced to construct a planetary gear train translation-torsion dynamic model that comprehensively considers TVMS and tooth backlash. The vibration acceleration signals of the planetary gear train under different macro-pitting states and surface roughness are simulated and calculated, allowing a quantificative analysis of the influence of surface roughness on system vibration response. Finally, the correctness of the model for the planetary gear train is verified by experiments. The results show that compared with the planetary gear train modeling method based on Hertz contact theory, the root mean squared error of the vibration signal of this work under a macro-pitting fault state is reduced by 8.7%, further improving the reliability of the model.

Measurements of underwater noise genenrated during wind turbine operation in Korea Southwest Offshore Wind Farm

Offshore wind power generation, a representative eco-friendly energy generation, is known as one of the promising solutions for sustainable development. However, the potential negative impact of underwater noise emitted from wind turbine operation on the marine ecosystem may limit development. Measurements of underwater noise generated from the operation of a 3-MW offshore wind turbine in the Korea Southwest Offshore Wind Farm located off the southwest coast of Korea were made twice in late February to early March and November 2021, and the acoustic characteristics of operational noise with wind speed, rotor speed, and tower vibration were investigated. As a result, the tonal frequencies of the underwater noise and tower vibration acceleration signal coincided, and their changes showed high correlations with the wind speed and rotor speed. Our results may be used as a reference to evaluate the impact of underwater operational noise of offshore wind turbines on the marine environment.

Quantitative assessment for tooth crack of the sun gear in a planetary gearbox

The sun gear in a planetary gearbox is prone to generate tooth crack due to its much more severe load conditions than other gears. The cracked sun gear will evolve into distinct tooth breakages and thus may deteriorate the operation status and even cause catastrophic loss of the whole transmission system. To avoid tooth crack induced malfunction of the planetary gearbox, the tooth crack of sun gear should be accurately identified during the early stage. Therefore, a novelty quantitative assessment methodology for tooth crack damage is proposed, which is a mathematical model for crack propagation of the sun gear in planetary gearboxes based on vibration acceleration signal. Firstly, the quantitative relationship between the crack propagation parameters along the gear thickness and width directions and the time-varying mesh stiffness is analytically formulated. The analytical time-varying mesh stiffness formulation is incorporated into a translational–torsional dynamic model to reveal the effects of crack propagation on the vibration signal of internal and external meshing pairs in the planetary gearbox. Secondly, a quantitative mapping function is established by taking the cracked section area as the variable and the residual of the summed envelope spectrum amplitude of the vibration acceleration signal as the assessment index. Finally, a numerical simulation as well as an experimental test is conducted and compared to verify the correctness of the proposed assessment methodology. We believe that the established model and the corresponding index provide a physically intuitive yet mathematically quantitative reference for diagnosing tooth crack in planetary gearboxes.

Evaluation of theoretical models describing the scratch adhesion test based on experimental results

ABSTRACT The article presents theoretical analyzes and results of research work on the verification of a commonly used method for measuring the adhesion of thin hard and superhard coatings applied to the blades of cutting tools made of various materials. The paper contains descriptions of the scratch adhesion test, taking into account, inter alia, interfacial shear stress model, energy model and friction model. This method of measuring the adhesion of the coating to the substrate has been presented in theoretical analyzes as a means of transmitting the appropriate amount of mechanical force or energy necessary to detach the coating from the substrate. The article discusses three approaches to describe the scratch adhesion test. The presented approaches concern: 1) “delivering” the critical shear stresses in the transition layer between the coating and the substrate according to the Benjamin and Weaver model, 2) “providing” additional elastic energy according to the Lauger model (according to the energy balance equation), 3) taking into account the criterion of deformation and matching of the coating to the substrate in the place of the indentation in the Burnett and Rickerby model by using the interfacial restraint parameter . The above-mentioned theoretical models have been experimentally verified for coatings deposited on substrates (cutting blades) made of high-speed steel, sintered carbides, white (oxide) tool ceramics, black tool ceramics (mixed, oxide-carbide), and cubic boron nitride. The tests of the adhesion force were performed with the use of proprietary equipment. This device is equipped with two channels for acoustic wave measurement by using a sound level meter and vibration measurement by a piezoelectric transducer. The adhesion force at which detaches the coating from the substrate was estimated by measuring the actual value of the amplitude of the vibration acceleration signal, its absolute value and the vibration signal intensity. The obtained values were verified using images from the profilometer and scanning electron microscope (SEM). In the final part of the article, the described models were verified on the basis of own experimental research and conclusions were formulated resulting from the analyzes and comparisons made. So far, mentioned models have not been assessed in terms of which of them allows the most accurate determination of the actual value of the critical load for the selected coating-substrate system. This was done in this article on the basis of own research. This innovative approach is a basic achievement.

CONFIGURATIONS OF ULTRASONIC EMITTER RESONANCE MODES FOR UNILATERAL ACCESS TO AN OBJECT

Link for citation: Azin A.V., Bogdanov E.P., Vasilyev A.V., Ponomarev S.A., Ponomarev S.V., Rikkonen S.V. Configurations of ultrasonic emitter resonance modes for unilateral access to an object. Bulletin of the Tomsk Polytechnic University. Geo Аssets Engineering, 2023, vol. 334, no. 10, рр. 199-209. In Rus. Relevance. To prepare high-viscosity oil for transport, a number of methods are used in practice: thermal, chemical and the method of physical influences. Ultrasonic exposure of hydrocarbon raw materials is one of the physical methods. It is necessary to develop an effective method for tuning an ultrasonic emitter for maximum energy transfer into a multilayer technological medium. Aim: to study resonant operating modes of an ultrasonic emitter in a multilayer system with unilateral access to the object with simplified design of a resonance type ultrasonic emitter. Objects: oscillating system of an ultrasonic resonant type emitter, multilayer system, physical model of a system «ultrasonic emitter – multilayer system». Methods: mathematical modeling of linear oscillating system to determine the properties of oscillating system influence and technological factors on the form of vibration oscillations and on the amplitude-frequency characteristics of the system; experimental research on the basis of the physical model «ultrasonic emitter – multilayer system». Results. The authors have revealed a physical feature of the oscillatory system operation, which consists in the fact that at resonance the form of oscillations of the force signals of a multilayer piezoactor and vibration acceleration signals are purely harmonic in nature. This effect extends to operation of a resonant-type ultrasonic emitter in a short-circuit mode on a multilayer system. It was found that force and vibration acceleration amplitude-frequency characteristics of a multilayer piezoactor are similar to each other. Based on the analysis of theoretical and experimental data, the authors developed the method for adjusting the resonant operating modes of an ultrasonic emitter with unilateral access to an object. This allows simplification and reduction in the emitter design cost. The method for setting up oscillatory systems is applicable for laboratory and industrial installations. Conclusion. The research results show that in practice, harmonic shape of acceleration and force signals, as well as force amplitude of a multilayer piezoactor can be used as criteria for determining and adjusting the resonance of an oscillatory system. The oscillatory system of a resonant-type ultrasonic emitter can be tuned to resonance according to the shape and amplitude of the signal from the force sensor of the multilayer piezoactor. The force sensor is located in series with the multilayer piezoactor and does not require additional structural elements for its fastening. The ultrasonic emitter design is greatly simplified due to the absence of a vibration acceleration sensor. The method of adjusting the resonance of an oscillatory system using only a force sensor is also applied when operating a resonant-type ultrasonic emitter to a multilayer mechanical system. The developed design and technique for tuning the oscillatory system of a resonant-type ultrasonic emitter can be conveniently used when influencing process fluids through the walls of tanks and storage tanks.

Speech extraction from vibration signals based on deep learning.

Extracting speech information from vibration response signals is a typical system identification problem, and the traditional method is too sensitive to deviations such as model parameters, noise, boundary conditions, and position. A method was proposed to obtain speech signals by collecting vibration signals of vibroacoustic systems for deep learning training in the work. The vibroacoustic coupling finite element model was first established with the voice signal as the excitation source. The vibration acceleration signals of the vibration response point were used as the training set to extract its spectral characteristics. Training was performed by two types of networks: fully connected, and convolutional. And it is found that the Fully Connected network prediction model has faster Rate of convergence and better quality of extracted speech. The amplitude spectra of the output speech signals (network output) and the phase of the vibration signals were used to convert extracted speech signals back to the time domain during the test set. The simulation results showed that the positions of the vibration response points had little effect on the quality of speech recognition, and good speech extraction quality can be obtained. The noises of the speech signals posed a greater influence on the speech extraction quality than the noises of the vibration signals. Extracted speech quality was poor when both had large noises. This method was robust to the position deviation of vibration responses during training and testing. The smaller the structural flexibility, the better the speech extraction quality. The quality of speech extraction was reduced in a trained system as the mass of node increased in the test set, but with negligible differences. Changes in boundary conditions did not significantly affect extracted speech quality. The speech extraction model proposed in the work has good robustness to position deviations, quality deviations, and boundary conditions.