Gear Damage Detection Using Impulse Response Wavelet Transform

2011 ◽  
Vol 204-210 ◽  
pp. 1378-1381
Author(s):  
Hui Li
Keyword(s):  
Wavelet Transform ◽  
Impulse Response ◽  
Vibration Signal ◽  
Experimental Result ◽  
Continuous Wavelet ◽  
Effective Technique ◽  
Time Frequency ◽  
Rotating Machine ◽  
Novel Method ◽  
Joint Representation

A novel method for detection the gear wear fault according to impulse response wavelet transform is presented. The continuous wavelet transform is widely recognized as an effective technique for rotating machine fault detection using vibration signal since it can be used to detect both stationary and transitory signals. This advantage makes it very suitable for the detection of singularity generated by localized damage in gearbox. In this study, the impulse response wavelet time-frequency joint representation is used to diagnose the gear wear fault. The experimental result shows that impulse response wavelet time-frequency joint representation is a sensitive indicator of the existence of damage in the gearbox.

Impulse Response Wavelet Transform Based Bearing Fault Diagnosis

2011 ◽  
Vol 204-210 ◽  
pp. 1018-1021
Author(s):  
Hui Li
Keyword(s):  
Wavelet Transform ◽  
Impulse Response ◽  
Outer Race ◽  
Time Frequency ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Frequency Representation ◽  
Localized Defects ◽  
Inner Race ◽  
Joint Representation

The continuous wavelet transform enables one to look at the evolution in the time frequency joint representation plane. This advantage makes it very suitable for the detection of singularity generated by localized defects in mechanical system. This gives a desirable ability to detect the singularity characteristic of a signal precisely. In this study, the impulse response wavelet time frequency joint representation is used in conjunction to detect and diagnose the bearing fault. The impulse response wavelet time frequency joint representation is found to show distinctive signatures in the presence of bearing inner race or outer race damage. The experimental results show that the impulse response wavelet time frequency representation can extract the transients from strong noise signals and can effectively diagnose bearing fault.

scholarly journals Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

Entropy ◽  
2021 ◽  
Vol 23 (1) ◽  
pp. 119
Author(s):  
Tao Wang ◽  
Changhua Lu ◽  
Yining Sun ◽  
Mei Yang ◽  
Chun Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Convolutional Neural Network ◽  
Continuous Wavelet Transform ◽  
Continuous Wavelet ◽  
Time Frequency ◽  
Ecg Signals ◽  
Rr Interval ◽  
Frequency Components ◽  
Fully Connected

Early detection of arrhythmia and effective treatment can prevent deaths caused by cardiovascular disease (CVD). In clinical practice, the diagnosis is made by checking the electrocardiogram (ECG) beat-by-beat, but this is usually time-consuming and laborious. In the paper, we propose an automatic ECG classification method based on Continuous Wavelet Transform (CWT) and Convolutional Neural Network (CNN). CWT is used to decompose ECG signals to obtain different time-frequency components, and CNN is used to extract features from the 2D-scalogram composed of the above time-frequency components. Considering the surrounding R peak interval (also called RR interval) is also useful for the diagnosis of arrhythmia, four RR interval features are extracted and combined with the CNN features to input into a fully connected layer for ECG classification. By testing in the MIT-BIH arrhythmia database, our method achieves an overall performance of 70.75%, 67.47%, 68.76%, and 98.74% for positive predictive value, sensitivity, F1-score, and accuracy, respectively. Compared with existing methods, the overall F1-score of our method is increased by 4.75~16.85%. Because our method is simple and highly accurate, it can potentially be used as a clinical auxiliary diagnostic tool.

Classification of Sleep Stages Using Multi-wavelet Time Frequency Entropy and LDA

2010 ◽  
Vol 49 (03) ◽  
pp. 230-237 ◽  
Author(s):  
K. Lweesy ◽  
N. Khasawneh ◽  
M. Fraiwan ◽  
H. Wenz ◽  
H. Dickhaus ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Discriminant Analysis ◽  
Sleep Stage ◽  
Continuous Wavelet ◽  
Eeg Signal ◽  
Linear Discriminant ◽  
Time Frequency ◽  
Mother Wavelets ◽  
Sleep Stage Scoring

Summary Background: The process of automatic sleep stage scoring consists of two major parts: feature extraction and classification. Features are normally extracted from the polysomno-graphic recordings, mainly electroencephalograph (EEG) signals. The EEG is considered a non-stationary signal which increases the complexity of the detection of different waves in it. Objectives: This work presents a new technique for automatic sleep stage scoring based on employing continuous wavelet transform (CWT) and linear discriminant analysis (LDA) using different mother wavelets to detect different waves embedded in the EEG signal. Methods: The use of different mother wave-lets increases the ability to detect waves in the EEG signal. The extracted features were formed based on CWT time frequency entropy using three mother wavelets, and the classification was performed using the linear discriminant analysis. Thirty-two data sets from the MIT-BIH database were used to evaluate the performance of the proposed method. Results: Features of a single EEG signal were extracted successfully based on the time frequency entropy using the continuous wavelet transform with three mother wavelets. The proposed method has shown to outperform the classification based on a CWT using a single mother wavelet. The accuracy was found to be 0.84, while the kappa coefficient was 0.78. Conclusions: This work has shown that wavelet time frequency entropy provides a powerful tool for feature extraction for the non-stationary EEG signal; the accuracy of the classification procedure improved when using multiple wavelets compared to the use of single wavelet time frequency entropy.

scholarly journals Ground Penetrating Radar for Belowground Phenotyping of High-biomass Grasses for Soil Carbon Sequestration

2021 ◽  
Author(s):  
Matthew Wolfe ◽  
Da Huo ◽  
Henry Ruiz-Guzman ◽  
Brody Teare ◽  
Tyler Adams ◽  
...  
Keyword(s):  
Wavelet Transform ◽  
Continuous Wavelet Transform ◽  
Carbon Capture ◽  
Large Scale ◽  
Agricultural Practices ◽  
Signal Amplitude ◽  
Belowground Biomass ◽  
Continuous Wavelet ◽  
Time Frequency ◽  
Non Invasive

Abstract AimsMany governments and companies have committed to moving to net-zero emissions by 2030 or 2050 to tackle climate change, which require the development of new carbon capture and sequestration/storage (CCS) techniques. A proposed method of sequestration is to deposit carbon in soils as plant matter including root mass and root exudates. Adding perennial traits such as rhizomes to crops as part of a sequestration strategy would result in annual crop regrowth from rhizome meristems rather than requiring replanting from seeds which would in turn encourage no-till agricultural practices. Integrating these traits into productive agriculture requires a belowground phenotyping method compatible with high throughput breeding and selection methods (i.e., is rapid, inexpensive, reliable, and non-invasive), however none currently exist. MethodsGround penetrating radar (GPR) is a non-invasive subsurface sensing technology that shows potential as a phenotyping technique. In this study, a prototype GPR antenna array was used to scan roots of the perennial sorghum hybrid, PSH09TX15. A-scan level time-domain analyses and B-scan level time/frequency analyses using the continuous wavelet transform were utilized to extract features of interest from the acquired radargrams. ResultsOf six A-scan diagnostic indices examined, the standard deviation of signal amplitude correlated most significantly with belowground biomass. Time frequency analysis using the continuous wavelet transform yielded high correlations of B-scan features with belowground biomass. ConclusionThese results demonstrate that continued refinement of GPR data analysis workflows should yield a highly applicable phenotyping tool for breeding efforts in environments where selection is otherwise impractical on a large scale.

Adaptive Multiple Second-order Synchrosqueezing Wavelet Transform and Its Application in Wind Turbine Gearbox Fault Diagnosis

2021 ◽  
Author(s):  
Zhaohong Yu ◽  
Cancan Yi ◽  
Xiangjun Chen ◽  
Tao Huang
Keyword(s):  
Wavelet Transform ◽  
Wind Turbine ◽  
Time Window ◽  
Vibration Signal ◽  
Second Order ◽  
Center Frequency ◽  
Wind Turbine Gearbox ◽  
Adaptive Wavelet ◽  
Time Frequency ◽  
Window Width

Abstract Wind turbines usually operate in harsh environments and in working conditions of variable speed, which easily causes their key components such as gearboxes to fail. The gearbox vibration signal of a wind turbine has nonstationary characteristics, and the existing Time-Frequency (TF) Analysis (TFA) methods have some problems such as insufficient concentration of TF energy. In order to obtain a more apparent and more congregated Time-Frequency Representation (TFR), this paper proposes a new TFA method, namely Adaptive Multiple Second-order Synchrosqueezing Wavelet Transform (AMWSST2). Firstly, a short-time window is innovatively introduced on the foundation of classical Continuous Wavelet Transform (CWT), and the window width is adaptively optimized by using the center frequency and scale factor. After that, a smoothing process is carried out between different segments to eliminate the discontinuity and thus Adaptive Wavelet Transform (AWT) is generated. Then, on the basis of the theoretical framework of Synchrosqueezing Transform (SST) and accurate Instantaneous Frequency (IF) estimation by the utilization of second-order local demodulation operator, Adaptive Second-order Synchrosqueezing Wavelet Transform (AWSST2) is formed. Considering that the quality of actual time-frequency analysis is greatly disturbed by noise components, through performing multiple Synchrosqueezing operations, the congregation of TFR energy is further improved, and finally, the AMWSST2 algorithm studied in this paper is proposed. Since Synchrosqueezing operations are performed only in the frequency direction, this method AMWSST2 allows the signal to be perfectly reconstructed. For the verification of its effectiveness, this paper applies it to the processing of the vibration signal of the gearbox of a 750 kW wind turbine.

Pattern Changes of Time-Shifted Vibration Signals on Wavelet Time-Scale Maps

1995 ◽  
Author(s):  
Da Jun Chen ◽  
Wei Ji Wang
Keyword(s):  
Wavelet Transform ◽  
Time Scale ◽  
Wavelet Transforms ◽  
Vibration Signal ◽  
Continuous Wavelet ◽  
Time Axis ◽  
Orthogonal Wavelet ◽  
Signal Component ◽  
Analysis Technique ◽  
Map Analysis

Abstract As a multi-resolution signal decomposition and analysis technique, the wavelet transforms have been already introduced to vibration signal processing. In this paper, a comparison on the time-scale map analysis is made between the discrete and the continuous wavelet transform. The orthogonal wavelet transform decomposes the vibration signal onto a series of orthogonal wavelet functions and the number of wavelets on one wavelet level is different from those on the other levels. Since the grids are unevenly distributed on the time-scale map, it is shown that a representation pattern of a vibration component on the map may be significantly altered or even be broken down into pieces when the signal has a shift along the time axis. On contrary, there is no such uneven distribution of grids on the continuous wavelet time-scale map, so that the representation pattern of a vibration signal component will not change its shape when the signal component shifts along the time axis. Therefore, the patterns in the continuous wavelet time-scale map are more easily recognised by human visual inspection or computerised automatic diagnosis systems. Using a Gaussian enveloped oscillation wavelet, the wavelet transform is capable of retaining the frequency meaning used in the spectral analysis, while making the interpretation of patterns on the time-scale maps easier.

scholarly journals Fall Detection Using Multiple Bioradars and Convolutional Neural Networks

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5569 ◽  
Author(s):  
Lesya Anishchenko ◽  
Andrey Zhuravlev ◽  
Margarita Chizh
Keyword(s):  
Wavelet Transform ◽  
Input Data ◽  
Detection Method ◽  
Fall Detection ◽  
Modern Medicine ◽  
Radar Signal ◽  
Continuous Wavelet ◽  
Time Frequency ◽  
Frequency Representation ◽  
Life Threatening

A lack of effective non-contact methods for automatic fall detection, which may result in the development of health and life-threatening conditions, is a great problem of modern medicine, and in particular, geriatrics. The purpose of the present work was to investigate the advantages of utilizing a multi-bioradar system in the accuracy of remote fall detection. The proposed concept combined usage of wavelet transform and deep learning to detect fall episodes. The continuous wavelet transform was used to get a time-frequency representation of the bio-radar signal and use it as input data for a pre-trained convolutional neural network AlexNet adapted to solve the problem of detecting falls. Processing of the experimental results showed that the designed multi-bioradar system can be used as a simple and view-independent approach implementing a non-contact fall detection method with an accuracy and F1-score of 99%.

Denoising Vibration Signals of Food Refrigerant Air Compressor Based on Wavelet Transform

2010 ◽  
Vol 439-440 ◽  
pp. 1037-1041 ◽  
Author(s):  
Yan Jue Gong ◽  
Zhao Fu ◽  
Hui Yu Xiang ◽  
Li Zhang ◽  
Chun Ling Meng
Keyword(s):  
Wavelet Transform ◽  
Frequency Characteristic ◽  
Vibration Signal ◽  
Wavelet Denoising ◽  
Signal Denoising ◽  
Denoising Method ◽  
Vibration Signals ◽  
Air Compressor ◽  
Time Frequency ◽  
Soft Threshold

On the basis of wavelet denoising and its better time-frequency characteristic, this paper presents an effective vibration signal denoising method for food refrigerant air compressor. The solution of eliminating strong noise is investigated with the combination of soft threshold and exponential lipschitza. The good denoising results show that the presented method is effective for improving the signal noise ratio and builds the good foundation for further extraction of the vibration signals.

scholarly journals Application of Continuous Wavelet Transform and Convolutional Neural Network in Decoding Motor Imagery Brain-Computer Interface

Entropy ◽  
2019 ◽  
Vol 21 (12) ◽  
pp. 1199 ◽  
Author(s):  
Hyeon Kyu Lee ◽  
Young-Seok Choi
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Convolutional Neural Network ◽  
Motor Imagery ◽  
Continuous Wavelet Transform ◽  
Brain Computer Interface ◽  
Classification Performance ◽  
Computer Interface ◽  
Continuous Wavelet ◽  
Time Frequency

The motor imagery-based brain-computer interface (BCI) using electroencephalography (EEG) has been receiving attention from neural engineering researchers and is being applied to various rehabilitation applications. However, the performance degradation caused by motor imagery EEG with very low single-to-noise ratio faces several application issues with the use of a BCI system. In this paper, we propose a novel motor imagery classification scheme based on the continuous wavelet transform and the convolutional neural network. Continuous wavelet transform with three mother wavelets is used to capture a highly informative EEG image by combining time-frequency and electrode location. A convolutional neural network is then designed to both classify motor imagery tasks and reduce computation complexity. The proposed method was validated using two public BCI datasets, BCI competition IV dataset 2b and BCI competition II dataset III. The proposed methods were found to achieve improved classification performance compared with the existing methods, thus showcasing the feasibility of motor imagery BCI.

Research on Aeroengine Rub-Impact Fault Analysis Based on Wavelet Scalogram Statistical Feature

2011 ◽  
Vol 48-49 ◽  
pp. 942-945 ◽  
Author(s):  
Ya Hui Wu ◽  
Da Zhi Zhang ◽  
Xin Liang Li ◽  
Jing Feng Xue
Keyword(s):  
Wavelet Transform ◽  
Test Data ◽  
Continuous Wavelet Transform ◽  
Dimensional Space ◽  
Vibration Signal ◽  
Fault Analysis ◽  
Continuous Wavelet ◽  
Statistical Features ◽  
Statistical Feature

The characteristics of the continuous wavelet transform scalogram of the aeroengine vibration signal could show the fault symptomatic in the 2-dimensional space and identify the rub-impact fault of the aeroengine. In order to get the precise feature for fault analysis, the statistical features of the scalogram which incorporated the Tamura vision features were proposed to diagnose the aeroengine rub-impact faults quantitatively. The experiments on the aeroengine test data demonstrate these statistic characteristics of the scalogram effectively diagnose the rub-impact faults.

Sign in / Sign up

Export Citation Format

Share Document