Showing papers on "Continuous wavelet transform published in 2018"

Deep-Learning-Based Earth Fault Detection Using Continuous Wavelet Transform and Convolutional Neural Network in Resonant Grounding Distribution Systems

Abstract: Feature extraction for fault signals is critical and difficult in all kinds of fault detection schemes. A novel simple and effective method of faulty feeder detection in resonant grounding distribution systems based on the continuous wavelet transform (CWT) and convolutional neural network (CNN) is presented in this paper. The time-frequency gray scale images are acquired by applying the CWT to the collected transient zero-sequence current signals of the faulty feeder and sound feeders. The features of the gray scale image will be extracted adaptively by the CNN, which is trained by a large number of gray scale images under various kinds of fault conditions and factors. The features extraction and the faulty feeder detection can be implemented by the trained CNN simultaneously. As a comparison, two faulty feeder detection methods based on artificial feature extraction and traditional machine learning are introduced. A practical resonant grounding distribution system is simulated in power systems computer aided design/electromagnetic transients including DC, the effectiveness and performance of the proposed faulty feeder detection method is compared and verified under different fault circumstances.

A Novel Fault Diagnosis Method for Rotating Machinery Based on a Convolutional Neural Network

Abstract: Fault diagnosis is critical to ensure the safety and reliable operation of rotating machinery. Most methods used in fault diagnosis of rotating machinery extract a few feature values from vibration signals for fault diagnosis, which is a dimensionality reduction from the original signal and may omit some important fault messages in the original signal. Thus, a novel diagnosis method is proposed involving the use of a convolutional neural network (CNN) to directly classify the continuous wavelet transform scalogram (CWTS), which is a time-frequency domain transform of the original signal and can contain most of the information of the vibration signals. In this method, CWTS is formed by discomposing vibration signals of rotating machinery in different scales using wavelet transform. Then the CNN is trained to diagnose faults, with CWTS as the input. A series of experiments is conducted on the rotor experiment platform using this method. The results indicate that the proposed method can diagnose the faults accurately. To verify the universality of this method, the trained CNN was also used to perform fault diagnosis for another piece of rotor equipment, and a good result was achieved.

A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network

Abstract: In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time–frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time–frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time–frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset.

Application of stationary wavelet entropy in pathological brain detection

Abstract: Labeling brain images as healthy or pathological cases is an important procedure for medical diagnosis. Therefore, we proposed a novel image feature, stationary wavelet entropy (SWE), to extract brain image features. Meanwhile, we replaced the feature extraction procedure in state-of-the-art approaches with the proposed SWE. We found the classification performance improved after replacing wavelet entropy (WE), wavelet energy (WN), and discrete wavelet transform (DWT) with the proposed SWE. This proposed SWE is superior to WE, WN, and DWT.

A convolution neural networks scheme for classification of motor imagery EEG based on wavelet time-frequecy image

Abstract: Motor imagery classification using electroencephalogram (EEG) is increasingly becoming popular in brain-computer interface (BCI) field. In this paper, we present a novel convolution neural networks (CNN) approach for classifying motor imagery electroencephalogram (EEG). For this, we obtained time-frequency representations of EEGs in cases of left and right motor imageries using continuous wavelet transform (CWT). Through experiments using well known public benchmark dataset, it shows that the proposed method provides the improved accuracy compared to the traditional machine learning based classification methods. It confirms the usefulness of the CNN scheme for BCI research field.

Introduction to redundancy rules: the continuous wavelet transform comes of age

Abstract: Redundancy: it is a word heavy with connotations of lacking usefulness. I often hear that the rationale for not using the continuous wavelet transform (CWT)even when it appears most appropriate for...

An Intelligent Fault Diagnosis Method for Bearings with Variable Rotating Speed Based on Pythagorean Spatial Pyramid Pooling CNN.

Abstract: Deep learning methods have been introduced for fault diagnosis of rotating machinery. Most methods have good performance when processing bearing data at a certain rotating speed. However, most rotating machinery in industrial practice has variable working speed. When processing the bearing data with variable rotating speed, the existing methods have low accuracies, or need complex parameter adjustments. To solve this problem, a fault diagnosis method based on continuous wavelet transform scalogram (CWTS) and Pythagorean spatial pyramid pooling convolutional neural network (PSPP-CNN) is proposed in this paper. In this method, continuous wavelet transform is used to decompose vibration signals into CWTSs with different scale ranges according to the rotating speed. By adding a PSPP layer, CNN can process CWTSs in different sizes. Then the fault diagnosis of variable rotating speed bearing can be carried out by a single CNN model without complex parameter adjustment. Compared with a spatial pyramid pooling (SPP) layer that has been used in CNN, a PSPP layer locates as front layer of CNN. Thus, the features obtained by PSPP layer can be delivered to convolutional layers for further feature extraction. According to experiment results, this method has higher diagnosis accuracy for variable rotating speed bearing than other methods. In addition, the PSPP-CNN model trained by data at some rotating speeds can be used to diagnose bearing fault at full working speed.

High-Resolution Seismic Time–Frequency Analysis Using the Synchrosqueezing Generalized S-Transform

Abstract: In this letter, a new method is introduced for a seismic time–frequency (TF) analysis. The proposed method is called synchrosqueezing generalized S-transform (SSGST), which belongs to a postprocessing procedure of the GST. The frequency-dependent Gaussian window used in the standard S-transform may be not suitable for real applications. In order to overcome this limitation, the frequency-dependent Gaussian window is replaced by a parameterized function containing three parameters. These three parameters result in flexibility in the variation of TF resolution. Then, the synchrosqueezing transform is employed to squeeze the TF coefficients of the GST to achieve an energy-concentrated TF representation. Synthetic examples and field data show that the SSGST achieves a high resolution and has the potential in highlighting geological structures with high precision.

Feature extraction of power transformer vibration signals based on empirical wavelet transform and multiscale entropy

Abstract: To achieve an effective feature extraction for power transformer vibration signals, the authors propose a method for signal feature extraction based on empirical wavelet transform (EWT) and multiscale entropy (MSE). First, transformer vibration signals are decomposed into several empirical wavelet functions (EWFs) with the method of EWT. Then, the frequency characteristics of signals are demonstrated in the time-frequency representation by applying a Hilbert transform to each EWF component. Finally, in order to quantify the extracted features, the MSEs of components being highly correlated with the original signals are calculated to construct the eigenvectors of transformer vibration signals. Several experiments are presented showing the effectiveness of this method compared with the classic empirical mode decomposition method.

Analysis of time-varying signals using continuous wavelet and synchrosqueezed transforms

Abstract: The continuous wavelet transform (CWT) has played a key role in the analysis of time-frequency information in many different fields of science and engineering It builds on the classical short-time Fourier transform but allows for variable time-frequency resolution Yet, interpretation of the resulting spectral decomposition is often hindered by smearing and leakage of individual frequency components Computation of instantaneous frequencies, combined by frequency reassignment, may then be applied by highly localized techniques, such as the synchrosqueezing transform and ConceFT, in order to reduce these effects In this paper, we present the synchrosqueezing transform together with the CWT and illustrate their relative performances using four signals from different fields, namely the LIGO signal showing gravitational waves, a 'FanQuake' signal displaying observed vibrations during an American football game, a seismic recording of the Mw 82 Chiapas earthquake, Mexico, of 8 September 2017, followed by the Irma hurricane, and a volcano-seismic signal recorded at the Popocatepetl volcano showing a tremor followed by harmonic resonances These examples illustrate how high-localization techniques improve analysis of the time-frequency information of time-varying signalsThis article is part of the theme issue 'Redundancy rules: the continuous wavelet transform comes of age'

Wavelet transform and signal denoising using Wavelet method

Abstract: Over the last decade, a great progress has been made in the signal processing field Especially new signal processing methods such as Wavelet Transform (WT) allowed researchers to solve diverse and complicated signal processing issues The paper provides answers to several questions related to WT technique such as what WT is, how and why WT emerged, what WT types currently available The main advantages like noise reduction and compression of WT are also explained in this study A set of MATLAB experiments were carried out in order to illustrate the use of WT as a signal denoising tool Analysis on different signals contaminated with noise are performed Different types of thresholding and mother wavelets were applied and the outcome of the experiments indicate that Daubechies family along with the soft thresholding technique suited our application the most The study proves that choosing the right thresholding technique and wavelet family is vital for the success of signal denoising applications

Tool wear condition monitoring based on continuous wavelet transform and blind source separation

Abstract: Prognostics and health management (PHM) for condition monitoring systems have been proposed for predicting faults and estimating the remaining useful life (RUL) of components. In fact, in order to produce quickly, economically, with high quality and reduce machine tool downtime, a new intelligent method for tool wear condition monitoring is based on continuous wavelet transform (CWT) and blind source separation (BSS) techniques. CWT is one of the most powerful signal processing methods and has been widely applied in tool wear condition monitoring. The CWT used to transform one set of one-dimensional series into multiple sets of one-dimensional series for preprocessing. After that, BSS was applied to analyze the wavelet coefficients. The signal energy evolution of each independent source obtained by BSS was used for health assessment and RUL estimation, the idea is based on the computation of a nonlinear regression function in a high-dimensional feature space where the input data were mapped via a nonlinear function. Experimental results show that the proposed CWT-BSS method can reflect effectively the performance degradation of cutting tools for the milling process. The proposed method is applied on real-world RUL estimation for a given wear limit based on extracted features.

Fast Amplitude Estimation of Harmonics Using Undecimated Wavelet Packet Transform and Its Hardware Implementation

Abstract: Accurate and fast estimation of time-varying harmonics are essential requirements for online monitoring, analysis, and control of electrical power system. This paper presents a fast algorithm based on the undecimated wavelet packet transform (UWPT) to estimate the amplitude of fundamental and harmonic components of stationary as well as a time-varying power signal. The UWPT uses only one cycle of the fundamental frequency for precise measurement of time-varying harmonics while their amplitude has been determined accurately utilizing the time-invariant property of the UWPT. The robustness and accuracy of the proposed technique have been investigated on synthetic as well as experimental test signals using MATLAB tool. Further, the UWPT algorithm has also been implemented on the Xilinx Virtex-6 FPGA ML-605 board, using XSG/ISE design suite 14.2 and its performance, in terms of hardware accuracy, resource utilization as well as timing requirements have been tested using the experimental test signal.

A Fused Load Curve Clustering Algorithm Based on Wavelet Transform

Abstract: The electricity load data recorded by smart meters contain plenty of knowledge that contributes to obtaining load patterns and consumer categories. Generally, the daily load curves are clustered first in order to obtain load patterns of each consumer. However, due to the volume and high dimensions of load curves, existing clustering algorithms are not appropriate in this situation. Thus, a fused load curve clustering algorithm based on wavelet transform (FCCWT) is proposed to solve this problem. The algorithm includes two main phases. First, FCCWT applies multilevel discrete wavelet transform (DWT) to convert the daily load curves for dimensionality reduction. Second, it detects clusters at two outputs of the first phase, and then fuses two groups of clusters with a subalgorithm named cluster fusion to achieve the optimized clusters. FCCWT is implemented on datasets of both China and United States. Their clustering performances are evaluated by diverse validity indices comparing with four typical clustering methods. The experimental results show that FCCWT outperforms other comparison methods. Additionally, case analysis of two datasets are also provided to discuss the significance of load patterns.

A Novel Approach for Seismic Time-Frequency Analysis Based on High-Order Synchrosqueezing Transform

Abstract: Time-frequency analysis always plays a central role in the field of seismic processing due to the advantage in characterizing nonstationary signals. In this letter, we present a novel technique for seismic time-frequency analysis based on the high-order synchrosqueezing transform, which obtains more accurate instantaneous frequencies by using the higher order approximations for both amplitude and phase in order to achieve a highly energy-concentrated time-frequency representation. A synthetic example is employed to demonstrate the validity of the proposed method in sharpening time-frequency representation. Application on field data example further proves its potential in enhancing time-frequency resolution and delineating stratigraphic characteristics with higher precision and renders that this technique is promising for seismic data analysis.

A Fault Diagnosis Method of Rolling Bearing Based on Complex Morlet CWT and CNN

Abstract: In view of some shortcomings of traditional rolling bearing fault diagnosis, for instance, feature extraction relies heavily on subjective experience of people and the extracted features do not have high recognition rate for rolling element faults, a new fault type intelligent diagnosis method transforming signal recognition into image recognition based on time frequency diagram and Convolution Neural Networks (CNN) is proposed in this paper. Firstly, the Joint Time-Frequency Analysis (JTFA) with continuous wavelet transform (CWT) of complex Morlet wavelet is used to obtain the time frequency diagram features of the vibration signal, and the inputs of CNN is obtained through normalizing them. Then, the CNN is trained by the time frequency diagram with labels. Finally, the trained model is used to diagnose the fault type of the unknown data. The effectiveness of the proposed method is validated by fault simulation experiment.

Chatter detection and stability region acquisition in thin-walled workpiece milling based on CMWT

Abstract: Milling chatter is one of the biggest obstacles to achieve high performance machining operations of thin-walled workpiece in industry field. In the milling process, the time-varying and position-dependent characteristics of thin-walled components are evident. So, effective identification of modal parameters and chatter monitoring are crucial. Although the advantage of chatter monitoring by sound signals is obvious, the milling sound signals are nonstationary signals which contain more stability information both in time domain and frequency domain, and the common analytical transformation methods are no longer applicable. In this paper, short time Fourier transform (STFT) is taken as an example to compare the processing results with cmor continuous wavelet transform (CMWT). This article concerns the chatter detection and stability region acquisition in thin-walled workpiece milling based on CMWT. CMWT combines the advantages of the cmor wavelet and continuous wavelet transform which has good locality and the optimal time-frequency resolution. Therefore, CMWT can be adaptively adjusted signal by the window, which is very suitable for processing nonstationary milling signals. Firstly, the model and characteristics of thin-walled workpiece during the cutting process are presented. Secondly, the CMWT method for chatter detection based on acoustic signals in thin-walled component milling process is presented. And the chatter detection results and stability region acquisitions are analyzed and discussed through a specific thin-walled part milling process. Finally, the accuracy of the method presented is verified through the traditional stability lobe diagram predicted using the exiting numerical method and the machined surface morphologies at different cutting positions obtained through the confocal laser microscope.

A Detail Study of Wavelet Families for EMG Pattern Recognition

Abstract: Wavelet transform (WT) has recently drawn the attention of the researchers due to its potential in electromyography (EMG) recognition system However, the optimal mother wavelet selection remains a challenge to the application of WT in EMG signal processing This paper presents a detail study for different mother wavelet function in discrete wavelet transform (DWT) and continuous wavelet transform (CWT) Additionally, the performance of different mother wavelet in DWT and CWT at different decomposition level and scale are also investigated The mean absolute value (MAV) and wavelength (WL) features are extracted from each CWT and reconstructed DWT wavelet coefficient A popular machine learning method, support vector machine (SVM) is employed to classify the different types of hand movements The results showed that the most suitable mother wavelet in CWT are Mexican hat and Symlet 6 at scale 16 and 32, respectively On the other hand, Symlet 4 and Daubechies 4 at the second decomposition level are found to be the optimal wavelet in DWT From the analysis, we deduced that Symlet 4 at the second decomposition level in DWT is the most suitable mother wavelet for accurate classification of EMG signals of different hand movements

Retrieval of the Modes of Multicomponent Signals From Downsampled Short-Time Fourier Transform

Abstract: In this paper, we investigate the retrieval of the modes of multicomponent signals from their downsampled short-time Fourier transform. To this end, we first recall signal reconstruction techniques based on shifted downsampled short-time Fourier transform, and then explain how to adapt these to the context of the retrieval of the modes of a multicomponent signal. We then show, on simulated and real data, that downsampling the short-time Fourier transform does not result in a significant performance loss of the mode retrieval procedures. Finally, comparisons with recent mode retrieval techniques based on synchrosqueezing transform are carried out, the focus being put on the amount of information needed to perform the recovery of the modes.

Estimation of crowd density applying wavelet transform and machine learning

Abstract: We conducted a simple experiment in which one pedestrian passed through a crowded area and measured the body-rotational angular velocity with commercial tablets. Then, we developed a new method for predicting crowd density by applying the continuous wavelet transform and machine learning to the data obtained in the experiment. We found that the accuracy of prediction using angular velocity data was as high as that using raw velocity data. Therefore, we concluded that angular velocity has relationship with crowd density and we could estimate crowd density by angular velocity. Our research will contribute to management of safety and comfort of pedestrians by developing an easy way to measure crowd density.

Scale–location specific soil spatial variability: A comparison of continuous wavelet transform and Hilbert–Huang transform

Abstract: Soil spatial variability has become the rule rather than the exception; it is the consequence of spatial dependence, periodicity, nonstationarity, and nonlinearity. The continuous wavelet transform (CWT) has been extremely useful in revealing scale- and location-specific information of nonstationary soil spatial variation. The Hilbert–Huang transform (HHT) has also been used in soil science to reveal scales and locations of variations in soil properties. These variations may be controlled by the underlying soil processes that can also be represented using a linear or nonlinear equation/function. The objective of this manuscript was to compare the inherent strengths and weaknesses of CWT and HHT in quantifying scale- and location-specific soil spatial variation. Examples using four simulated spatial series (stationary–linear, stationary–nonlinear, nonstationary–linear, and nonstationary–nonlinear) and two real world measurements of soil properties (organic carbon and soil water storage) were used to compare the methods. With its algorithmic basis, HHT identified the scale components present in the spatial series more flexibly, while the redundancy in CWT identified a diffuse band of scales as it is based on an underlying mathematical model. Additionally, the CWT identified variations that were biased towards large scales. The HHT used a more flexible basis for interpreting real data and could deal with nonlinear issues, while CWT could not. A similar result was also observed for soil organic carbon and soil water storage. Both methods could produce certain levels of information but the choice should be made based on the type of information that is required while taking into consideration the underlying assumptions. For example, to quantify the scale- and location-specific spatial variability of soil properties as controlled by soil processes which can be represented by a nonlinear equation, one achieves benefits from using HHT rather than CWT. In this case study, HHT showed superior performance in identifying scales and locations of soil spatial variability over CWT. In this study, HHT is compared with CWT only and needs further comparison with other types of wavelet analysis.

A Nano-Watt ECG Feature Extraction Engine in 65-nm Technology

Abstract: This brief presents an ultralow power electrocardiography (ECG) feature extraction engine. ECG signal represents the cardiac cycle and contains key features, such as QRS complex, ${P}$ -wave, and ${T}$ -wave, which provide important diagnostic information about cardiovascular diseases. The ECG feature extraction is based on combined techniques of curve length transform (CLT) and discrete wavelet transform. A novel pipelined architecture for implementing CLT is proposed. The system was fabricated using GF-65-nm technology and consumed 642 nW only when operating at a frequency of 7.5 kHz from a supply voltage of 0.6 V. Ultralow power consumption of the SoC made it suitable for self-powered wearable devices.

An efficient lossless robust watermarking scheme by integrating redistributed invariant wavelet and fractional Fourier transforms

Abstract: An ensemble lossless watermarking scheme is proposed in the present study by integrating different concepts like redistributed invariant wavelet transform, discrete fractional Fourier transform, singular value decomposition (SVD) and visual cryptography within the framework of a single algorithm The invariant wavelet transform helps to obtain the transform domain, which is invariant to flipping and rotation of image, this is followed by discrete fractional Fourier transform to obtain the translation invariant domain Finally, embedding positions are selected based on a key and reliable features are extracted by performing SVD on a window centered at these positions Based on these reliable features a binary map is generated through which a master share is created The corresponding ownership share is produced from the master share and the watermark In verification process the same operations of the embedding process are applied to the test image to obtain the master share and the watermark is recovered by stacking it over the ownership share There are two main features of the proposed scheme (1) The quality of the image to be watermarked do not degrade during the process and (2) the extracted watermark can still be identified even from a seriously distorted image These findings are also demonstrated with the help of a comparative study with several related schemes

Inversion-Driven Attenuation Compensation Using Synchrosqueezing Transform

Abstract: Attenuation is a fundamental mechanism as seismic wave propagates through the earth. The loss of high-frequency energy and concomitant phase distortion can be compensated by inverse ${Q}$ filtering to enhance the resolution of seismic data. Since the attenuation process depends on time and frequency, it is routinely performed in the time–frequency domain. The synchrosqueezing transform (SST), which provides highly localized time–frequency representations for the nonstationary signals due to reduced spectral smearing, is applied to implement the inverse ${Q}$ filtering scheme. However, the amplitude compensation process is unstable because energy amplification is involved. To stabilize it, the amplitude compensation is regarded as an inverse problem with an L1-norm regularization term in the SST domain. The iteratively reweighted least-squares algorithm is used to solve the regularized inverse problem. Synthetic and real data examples illustrate the stability and effectiveness of the proposed method.

A Novel Pre-Processing Algorithm Based on the Wavelet Transform for Raman Spectrum.

Abstract: Noise and fluorescent background are two major problems for acquiring Raman spectra from samples, which blur Raman spectra and make Raman detection or imaging difficult. In this paper, a novel algorithm based on wavelet transform that contains denoising and baseline correction is presented to automatically extract Raman signals. For the denoising section, the improved conventional-scale correlation denoising method is proposed. The baseline correction section, which is performed after denoising, basically consists of five aspects: (1) detection of the peak position; (2) approximate second derivative calculation based on continuous wavelet transform is performed using the Haar wavelet function to find peaks and background areas; (3) the threshold is estimated from the peak intensive area for identification of peaks; (4) correction of endpoints, spectral peaks, and peak position; and (5) determine the endpoints of the peak after subtracting the background. We tested this algorithm for simulated and experimental Raman spectra, and a satisfactory denoising effect and a good capability to correct background are observed. It is noteworthy that this algorithm requires few human interventions, which enables automatic denoising and background removal.

Spectro-temporal ecg analysis for atrial fibrillation detection

Abstract: This article is concerned with spectro-temporal (i.e., time varying spectrum) analysis of ECG signals for application in atrial fibrillation (AF) detection. We propose a Bayesian spectro-temporal representation of ECG signal using state-space model and Kalman filter. The 2D spectro-temporal data are then classified by a densely connected convolutional networks (DenseNet) into four different classes: AF, non-AF normal rhythms (Normal), non-AF abnormal rhythms (Others), and noisy segments (Noisy). The performance of the proposed algorithm is evaluated and scored with the PhysioNet/Computing in Cardiology (CinC) 2017 dataset. The experiment results shows that the proposed method achieves the overall F1 score of 80.2%, which is in line with the state-of-the-art algorithms. In addition, the proposed spectro-temporal estimation approach outperforms standard time-frequency analysis methods, that is, short-time Fourier transform, continuous wavelet transform, and autoregressive spectral estimation for AF detection.