Wyniki wyszukiwania - Biblioteka Nauki

1

Selection of viscous damping coefficients using the continuous wavelet transform method for a gear system

100%

Yousfi N. , Zghal B. , Akrout A. , Walha L. , Haddar M.

Journal of Theoretical and Applied Mechanics

|

2020

|

tom Vol. 58 nr 3

585--598

EN

Viscous damping is frequently used in the equation of motion to present the dissipation mechanism of a mechanical system. The orders of frequencies can be easily selected to determine viscous damping coefficients (VDCs) when the degree of freedom of the structure is low. For complex structures, difficulties in selecting the orders of reference frequencies to obtain reasonable VSCs are encountered. This paper mainly discusses the capability of the CWT method to select optimum frequencies of viscous damping formulation. The proposed procedure considers both the classical Rayleigh, modal and the proposed full model modal damping. The method is validated using a numerical time domain response of a two-stage gear system.

2

Deep Classifiers and Wavelet Transformation for Fake Image Detection

100%

Osowski S. , Golgowski M.

Journal of Telecommunications and Information Technology

|

2023

|

tom nr 4

1--8

EN

The paper presents a computer system for detecting deep fake images in videos. The system is based on continuous wavelet transformation combined with a set of classifiers composed of a few convolutional neural networks of diversified architectures. Three different forms of forged images taken from the FaceForensics++ database are considered in numerical experiments. The results of experiments involving the proposed system have shown good performance in comparison to other current approaches to this particular problem.

3

Experimental damage assessment of support condition for plate structures using wavelet transform

100%

Abdulkareem M. , Bakhary N. , Vafaei M. , Md Noor N. , Abd Samat R.

Journal of Theoretical and Applied Mechanics

|

2019

|

tom Vol. 57 nr 2

501--518

EN

Wavelet transforms (WTs) have gained popularity due to their ability to identify singularities by decomposing mode shapes of structures. In VBDD, the support condition of a structure influences structural responses and modal properties. In fact, the structural responses and modal properties are a lot more sensitive to changing boundary conditions than to crack and fatigue damage, resulting in inaccurate damage detection results. Therefore, in this study, sensitivity tests to estimate a suitable distance range which allows damage detection by imposing single support damage are carried out. The estimated appropriate distance is then applied to detect damage at multiple supports. This involved the applicability of response acceleration of plate structures to support assessment by applying continuous wavelet transform (CWT) and discrete wavelet transform (DWT). The damage cases have been introduced by releasing bolts at specified fixed supports of the plate to simulate the damage. The response accelerations of the rectangular plate at points close to the supports were measured and decomposed using CWT and DWT to assess the structural integrity of each support. The results showed that an appropriate distance range was necessary for accurate damage detection, and both, CWT and DWT could provide reliable outputs. However, the first- and fourth-level detail coefficients of DWT failed to indicate damage in some cases. A more detailed investigation of the effect of different wavelet scale ranges on damage detection using CWT demonstrated that the accuracy of damage detection increased as the scale decreased.

4

Continuous Wavelet and Hilbert-Huang Transforms Applied for Analysis of Active and Reactive Power Consumption

88%

Avdakovic S. , Bosovic A.

|

5

Intelligent fault diagnosis of rolling bearings based on continuous wavelet transform-multiscale feature fusion and improved channel attention mechanism

88%

Zhang J. , Kong X. , Cheng L. , Qi H. , Yu M.

Eksploatacja i Niezawodność

|

2023

|

tom Vol. 25, no. 1

art. no. 16

EN

Accurate fault diagnosis is critical to operating rotating machinery safely and efficiently. Traditional fault information description methods rely on experts to extract statistical features, which inevitably leads to the problem of information loss. As a result, this paper proposes an intelligent fault diagnosis of rolling bearings based on a continuous wavelet transform(CWT)-multiscale feature fusion and an improved channel attention mechanism. Different from traditional CNNs, CWT can convert the 1-D signals into 2-D images, and extract the wavelet power spectrum, which is conducive to model recognition. In this case, the multiscale feature fusion was implemented by the parallel 2-D convolutional neural networks to accomplish deeper feature fusion. Meanwhile, the channel attention mechanism is improved by converting from compressed to extended ways in the excitation block to better obtain the evaluation score of the channel. The proposed model has been validated using two bearing datasets, and the results show that it has excellent accuracy compared to existing methods.

6

Are Stock Prices Hedge Against Inflation? A Revisit over Time and Frequencies in India

75%

Bhanja N. , Dar A. B. , Tiwari A. K. , Olayeni O. R.

Central European Journal of Economic Modelling and Econometrics

|

2012

|

nr 3

7

Radial internal clearance analysis in ball bearings

75%

Ambrożkiewicz B. , Syta A. , Meier N. , Litak G. , Georgiadis A.

Eksploatacja i Niezawodność

|

2021

|

tom Vol. 23, no. 1

42--54

EN

Radial internal clearance (RIC) is one of the most important parameters influencing on rolling bearing exploitation in mechanical systems. Lifetime of rotary machines strongly depends on a condition of applied rolling elements, thus a study on applied clearance is very important in terms of maintenance and reliability. This paper proposes, a novel approach of studying RIC, based on a nonlinear dynamics method called recurrences. The results are confronted with standard analyses, i.e. statistical condition indicators, Fast Fourier Transform and Continuous Wavelet Transform. The application of the mentioned methods allowed us to find the optimal radial clearance for operating bearings. To ensure precise measurements of the clearance, an automated setup for RIC measurements is applied and next mounted in a plummer block and tested to finally measure vibration acceleration. The proposed methods are useful for a condition monitoring and lifetime prediction of bearings or bearing-based systems in which a proper value of radial clearance is crucial.

8

Selected aspects in the analysis of the combustion process using wavelet transform

63%

Grądz Ż.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2020

|

tom T. 10, nr 3

52--55

EN

The complexity of changes occurring in the flame during the combustion process has a direct influence on the quantity and qualityof the combustion products. The presented measurement data pertaining to the changes in flame luminosity were recorded using a specialized monitoring system. These signals from the combustion ofsuch fuels as pulverized coal and mazoutwere recorded with high sampling rate. The paper presented the analysis of changes in flame luminosity for different fuels using continuous and discrete wavelet transform. The main aim of the studies was to determine the scale values, which enable differentiating between the type of combusted fuel. The results of studies were presented in the form of scalograms.

PL

Złożoność zmian zachodzących w płomieniu w trakcie procesu spalania różnych paliw ma bezpośredni wpływ na ilość i jakość powstałych produktów spalania. Przedstawione w pracy dane pomiarowe zmian intensywności świecenia płomienia zostały zarejestrowaneprzy użyciu specjalistycznego systemu monitorującego. Sygnały te,dla procesu spalania,zostały zarejestrowane z wysoką częstotliwością próbkowania. W artykule przedstawiono analizę zmian intensywności świecenia płomienia dla różnych paliw przy zastosowaniu ciągłego i dyskretnego przekształcenia falkowego. Podstawowym celem badań było określenie wartości skali, na podstawie których możliwe będzie rozróżnienie rodzaju spalanego paliwa. Wyniki badań zostały zaprezentowane w postaci skalogramów.

9

Time invariant property of weighted circular convolution and its application to continuous wavelet transform

63%

Yi H. , Ru Y.-L. , Dai Y.-Y.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

tom Vol. 69, nr 4

art. no. e137726

EN

Time invariant linear operators are the building blocks of signal processing. Weighted circular convolution and signal processing framework in a generalized Fourier domain are introduced by Jorge Martinez. In this paper, we prove that under this new signal processing framework, weighted circular convolution also has a generalized time invariant property. We also give an application of this property to algorithm of continuous wavelet transform (CWT). Specifically, we have previously studied the algorithm of CWT based on generalized Fourier transform with parameter 1. In this paper, we prove that the parameter can take any complex number. Numerical experiments are presented to further demonstrate our analyses.

10

Diagnosis of amyotrophic lateral sclerosis (ALS) disorders based on electromyogram (EMG) signal analysis and feature selection

63%

Mokdad A. , Debbal S. M. E. A. , Meziani F.

Polish Journal of Medical Physics and Engineering

|

2020

|

tom Vol. 26, Iss. 3

155--160

EN

Electromyogram signal (EMG) provides an important source of information for the diagnosis of neuromuscular disorders. In this study, we proposed two methods of analysis which concern the bispectrum and continuous wavelet transform (CWT) of the EMG signal then a comparison is made to select which one is the most suitable to identify an abnormality in biceps brachii muscle in the main purpose is to assess the pathological severity in bifrequency and time-frequency analysis applying respectively bispectrum and CWT. Then four time and frequency features are extracted and three popular machine learning algorithms are implemented to differentiate neuropathy and healthy conditions of the selected muscle. The performance of these time and frequency features are compared using support vector machine (SVM), linear discriminate analysis (LDA) and K-Nearest Neighbor (KNN) classifier performance. The results obtained showed that the SVM classifier yielded the best performance with an accuracy of 95.8%, precision of 92.59% and specificity of 92%. followed by respectively KNN and LDA classifier that achieved respectively an accuracy of 92% and 91.5%, precision of 92% and 85.4%, and specificity of 92% and 83%.

11

Prediction of drug response in major depressive disorder using ensemble of transfer learning with convolutional neural network based on EEG

63%

Sadat Shahabi M. , Shalbaf A. , Maghsoudi A.

Biocybernetics and Biomedical Engineering

|

2021

|

tom Vol. 41, no. 3

946--959

EN

Major Depressive Disorder (MDD) is one of the leading causes of disability worldwide. Prediction of response to Selective Serotonin Reuptake Inhibitors (SSRIs) antidepressants in patients with MDD is necessary for preventing side effects of mistreatment. In this study, a deep Transfer Learning (TL) strategy based on powerful pre-trained convolutional neural networks (CNNs) in the big data datasets is developed for classification of Responders and Non-Responders (R/NR) to SSRI antidepressants, using 19-channel Electroencephalography (EEG) signal acquired from 30 MDD patients in the resting state. Multiple time-frequency images are obtained from each EEG channel using Continuous Wavelet Transform (CWT) for feeding into pre-trained CNN models that are VGG16, Xception, DenseNet121, MobileNetV2 and InceptionResNetV2. Our plan is to adapt and fine-tune the weights of networks to the target task with the small-sized dataset. Finally, to improve the recognition performance, an ensemble method based on majority voting of outputs of five mentioned deep TL architectures has been developed. Results indicate that the best performance among basic models achieved by DenseNet121 with accuracy, sensitivity and specificity of 95.74%, 95.56% and 95.64%, respectively. An Ensemble of these basic models created to surpass the accuracy obtained by each individual basic model. Our experiments show that ensemble model can gain accuracy, sensitivity and specificity of 96.55%, 96.01% and 96.95%, respectively. Therefore, proposed ensemble of TL strategy of pre-trained CNN models based on WT images obtained from EEG signal can be used for antidepressants treatment outcome prediction with a high accuracy.

12

Automatic sleep stage classification using time–frequency images of CWT and transfer learning using convolution neural network

63%

Jadhav P. , Rajguru G. , Datta D. , Mukhopadhyay S.

Biocybernetics and Biomedical Engineering

|

2020

|

tom Vol. 40, no. 1

494--504

EN

For automatic sleep stage classification, the existing methods mostly rely on hand-crafted features selected from polysomnographic records. In this paper, the goal is to develop a deep learning-based method by using single channel electroencephalogram (EEG) that automatically exploits the time–frequency spectrum of EEG signal, removing the need for manual feature extraction. The time–frequency RGB color images for EEG signal are extracted using continuous wavelet transform (CWT). The transfer learning of a pre-trained convolution neural network, squeezenet is employed to classify these CWT images into its sleep stages. The proposed method is evaluated using a publicly available Physionet sleep EDFx dataset using single-channel EEG Fpz-Cz channel. Evaluation results show that this method can achieve near state of the art accuracy even using single channel EEG signal.

13

An application of continuous wavelet transform and wavelet coherence for residential power consumer load profiles analysis

63%

Kapler P.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

tom Vol. 69, nr 1

art. no. e136216

EN

Load profiles of residential consumers are very diverse. This paper proposes the usage of a continuous wavelet transform and wavelet coherence to perform analysis of residential power consumer load profiles. The importance of load profiles in power engineering and common shapes of profiles along with the factors that cause them are described. The continuous wavelet transform and wavelet coherence has been presented. In contrast with other studies, this research has been conducted using detailed (not averaged) load profiles. Presented load profiles were measured separately on working day and weekend during winter in two urban households. Results of applying the continuous wavelet transform for load profiles analysis are presented as coloured scalograms. Moreover, the wavelet coherence was used to detect potential relationships between two consumers in power usage patterns. Results of coherence analysis are also presented in a colourful plots. The conducted studies show that the Morlet wavelet is slightly better suitable for load profiles analysis than the Meyer’s wavelet. Research of this type may be valuable for a power system operator and companies selling electricity in order to match their offer to customers better or for people managing electricity consumption in buildings.

14

Determination of rail vehicle speed with acoustic signal processed using continuous wavelet transform

63%

Mokrzan D. , Nowakowski T. , Szymański G. M.

Vibrations in Physical Systems

|

2023

|

tom Vol. 34, nr 2

art. no. 2023223

EN

The paper presents the course of research and analysis on the possibility of using time-frequency methods of acoustic signal processing to determine the speed of moving rail vehicles. An experiment was conducted in the form of a trackside pass-by test of the acoustic pressure emitted by passing trams representing the rolling stock of the Municipal Transport Company in Poznan. The recorded signal was then processed using the Continuous Wavelet Transform (CWT), resulting in a scalogram that is a variation of the time-frequency characteristics. This made it possible to identify in the signal the travel time of individual bogies and their wheelsets, as well as the most sensitive value of the scale parameter. The waveform of the scalogram fragment for the selected value of the scale parameter was processed using the RMS envelope, and then the peak values were identified. Juxtaposing the obtained results with the knowledge of the structural dimensions of the tested vehicle, it was possible to determine its moving speed. To validate the results of the experiment, photocells located on both sides of the measurement track were used, which generated voltage when the test vehicle passed between them, allowing the determination of its average moving speed. The result of the study was the formulation of a method that can be used to determine the speed of a vehicle based on the time elapsed between the identification in the signal of the components corresponding to the passage of successive sets of wheels.

15

Application of continuous wavelet transform and convolutional neural networks in fault diagnosis of PMSM stator windings

63%

Pietrzak P. , Wolkiewicz M.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2024

|

tom Vol. 72, nr 5

art. no. e150202

EN

Efficiency, reliability, and durability play a key role in modern drive systems in line with the Industry 4.0 paradigm and the sustainability trend. To ensure this, highly efficient motors and appropriate systems must be deployed to monitor their condition and diagnose faults during the operation. For these reasons, in recent years, research has been increasingly focused on developing new methods for fault diagnosis of permanent magnet synchronous motors (PMSMs). This paper proposes a novel hybrid method for the automatic detection and classification of PMSM stator winding faults based on combining the continuous wavelet transform (CWT) analysis of the negative sequence component of the stator phase currents with a convolutional neural network (CNN). CWT scalogram images are used as the inputs of the CNN-based interturn short circuits fault classifier model. Experimental tests were conducted to verify the effectiveness of the proposed approach under various motor operating conditions and at an incipient stage of fault propagation. In addition, the effects of the input image format, CNN structure, and training process parameters on model accuracy and classification effectiveness were investigated. The results of the experimental tests confirmed the high effectiveness of fault detection (99.4%) and classification (97.5%), as well as other important advantages of the developed method.

16

The wavelet-aided methods for evaluating the output signal that is designated for uninterruptible power supply systems

63%

Dyga Ł. , Rymarski Z. , Bernacki K.

Przegląd Elektrotechniczny

|

2020

|

tom R. 96, nr 11

50--54

EN

In the article an analysis of the quality of the output voltage for Uninterruptible Power Supply (UPS) was performed. The currently used and commonly known methods for calculating the different quality factors mainly focus on averaging the values of the waveform e.g. Total Harmonic Distortion (THD), Total Distortion Factor (TDF), Weighted Total Harmonic Distortion (WTHD). The main goal of the paper is to propose a complete and supplementary methodology for assessing the quality and parameters that are the complements of the algorithms that are currently used.

PL

W artykule przedstawiono analizę jakości napięcia wyjściowego falowników w systemach bezprzerwowego zasilania UPS. Obecnie znane i stosowane metody wyliczania różnych współczynników skupiają się głównie na wartościach uśrednionych przebiegu wyjściowego. Na przykład są to współczynnik zniekształceń harmonicznych THD, TDF oraz ważony WTHD. Głównym celem artykułu jest przedstawienie kompletnej i dodatkowej procedury pozwalającej na obiektywną ocenę sygnału wyjściowego będącą wsparciem dla stosowanych już metod.

17

The application of time-frequency methods of acoustic signal processing in the diagnostics of tram drive components

51%

Mokrzan D. , Nowakowski T. , Szymański G. M.

Archives of Transport

|

2023

|

tom Vol. 68, iss. 4

55--75

EN

The paper presents the course of investigations and the analysis of the possibility of applying selected methods of time frequency processing of non-stationary acoustic signals in the assessment of the technical condition of tram drive components, as well as a new combined method proposed by the authors. An experiment was performed in the form of a pass-by test of the acoustic pressure generated by a Solaris Tramino S105p tram. A comparative analysis has been carried out for an efficient case and a case with damage to the traction gear of the third bogie in the form of broken gear teeth. The recorded signal was analyzed using short-time Fourier transform (STFT) and continuous wavelet transform (CWT). It was found that the gear failure causes an increase in the sound level generated by a given bogie for frequencies within the range of characteristic frequencies of the tested device. Due to the limitations associated with the fixed window resolution in STFT and the inability to directly translate scales to frequencies in CWT, it was found that these methods can be helpful in determining suspected damage, but are too imprecise and prone to errors when the parameters of both transforms are poorly chosen. A new CWT-Cepstrum method was proposed as a solution, using the wavelet transform as a pre-filter before cepstrum signal processing. With a sampling rate of 8192 Hz, a db6 mother wavelet, and a scale range of 1:200, the new method was found to infer the occurrence of damage in an interpretation-free manner. The results were validated on an independent pair of trams of the same model with identical damage and as a reference on a pair of undamaged trams demonstrating that the method can be successfully replicated for different vehicles.