Wavelet Packet Decomposition Coefficients Research Articles

Identifying microseismic events using a dual-channel CNN with wavelet packets decomposition coefficients

Microseismic monitoring is a widely used technique in coal mine safe production. Microseismic events classification is one of the most important steps in microseismic monitoring. CNN has been proven to be the potential tool to identify microseismic events automatically. When the noise is serious and the signal is weak, the recognition ability of CNN is limited. Some scholars use denoising methods, such as wavelet transform, to enhance the signal-to-noise ratio (SNR) of the input data. However, the effective signal will be broken if the incorrect threshold parameters are set in this wavelet transform-based denoising method. In this paper, we intend to make the data volume of the time-frequency graph obtained by WPT as the input of CNN. But it may lead to a dimensional disaster if taking the time-frequency domain signals as input directly. To utilize the effective information extraction and reduce the data dimension, we propose a dual-channel CNN model by combining time domain information and wavelet packet decomposition coefficients (T-WPD CNN). The wavelet packet decomposition coefficients highlight the characteristics of the signal and suppress the characteristics of noise. In addition, the coefficients have the same dimension as the original signal. These advantages are useful for enhancing the performance of CNN. Two field datasets are used to test the network. One from Australia and another from Jiayang coal mine, Sichuan, China. The feature map of the convolutional layer with different inputs are shown to illustrate the influence effect of raw time domain signal and WPD coefficient on the classification performance. The final results show that the T-WPD CNN is superior to the traditional CNN method in accuracy and robustness.

GEARBOX FAULT CLASSIFICATION BY USING FREQUENCY BASED FEATURE EXTRACTION

Gearboxes are the fundamental elements of rotational systems to provide speed adjustment ratios from a rotating power source to another. In industrial applications, the existence of any kind of faults in rotational systems may be hazardous unless the early detection and maintenance procedures are applied. Incipient types of faults such as a few chipped or worn teeth at the gearbox mechanism may deteriorate and cause the maladjustment of the rotation and even the mechanism may stop to rotate which may cause loss of the production. Preventive maintenance strategies such as monitoring of the vibration signals and comparison of the frequency domain irregularities with normal operation case with healthy gearbox elements is essential to ensure safe and accurate rotational speed transmission in industrial systems. In this work, frequency domain characteristics of three different pinion conditions; healthy, a chipped tooth, and three consequent worn teeth are analyzed, and frequency domain features are proposed for classification of the pinion state. Proposed features obtained from the statistical properties of the coefficients of third level Wavelet packet decomposition. After feature extraction process, classification of the gear condition is made with different Support Vector Machine based classifiers and significant classification success observed with the proposed technique.

Wavelet feature selection of audio and imagined/vocalized EEG signals for ANN based multimodal ASR system

Human-Machine Interaction (HMI) systems demand the use of multiple modalities for correct interaction. Research on these systems started with audio signals for speech recognition and now progressing towards co-operation of other biosignals. Thus, the paper presents an Automatic Speech Recognition (ASR) system based on a single and multiple modalities that include audio and Electroencephalogram (EEG) signals to explore speech recognition. It extracts speech information concealed in audio and ten channels of imagined EEG (EEG-i) & vocalized EEG (EEG-v) signals. Three Wavelet Transform (WT) methods - Discrete Wavelet Transform (DWT), Wavelet Packet Decomposition (WPD) & hybrid of DWT & WPD (DWPD) with four-level decomposition is used to transform the signals into WT coefficients. Then, six statistical parameters are computed from WT coefficients to generate 63 (26-1) feature vectors for each method. An exhaustive search from 63 feature vectors is conducted to determine the best parameter combination that attains good accuracy with ANN classifier. Then, accuracy is improved with 5 level decomposition on WPD coefficients along with the best parameter combination. Results include the accuracy of unimodal ASR & multimodal ASR. WPD method achieved best accuracy as 74.48%, 56.29%, 42.02%, 77.97% & 78.90% for multiclass classification of prompts+words based on audio, EEG-i, EEG-v, audio + EEG-i & audio + EEG-v respectively. It indicates that speech recognition is possible from EEG signals & the fusion of audio with EEG enhances the recognition rate of audio & EEG. The results also show that the proposed method outperforms other methods in the area.

A Fault Diagnosis Approach for Rolling Bearing Based on Wavelet Packet Decomposition and GMM-HMM

Considering frequency domain energy distribution differences of bearing vibration signal in the different failure modes, a rolling bearing fault pattern recognition method is proposed based on orthogonal wavelet packet decomposition and Gaussian Mixture Model-Hidden Markov Model (GMM-HMM). The orthogonal three-layer wavelet packet decomposition is used to obtain wavelet packet decomposition coefficients from low frequency to high frequency. Rolling bearing raw vibration signals are firstly decomposed into the wavelet signals of different frequency bands, then different frequency band signals are reconstructed respectively to extract energy features, which form feature vectors as the model input of GMM-HMM. A large number of samples are trained to get model parameters for different bearing faults, then several groups of test data are adopted to verify GMM-HMMs so different fault types of rolling bearings are recognized. By calculating the current state appearance probability of monitoring data in GMM-HMMs, different failure patterns are recognized and evaluated from the maximum probability. Similarly, we establish GMM-HMMs for different grade fault samples and evaluated the performance degradation state. Test results show that the proposed fault diagnosis approach can identify accurately the fault pattern of rolling bearings and evaluate performance degradation of bearings.

Image watermarking based on inter-tree coefficients differencing in paired wavelet-packets tree constructions

Recently, image watermarking has been used as a tremendous mean for copyright protection of images and multimedia as well. This work presents an image watermarking technique for copyright protection of grayscale images, and is based on the exploitation of the properties of the wavelet packet decomposition (WPD). Here, the input image is applied to WPD, then, modified trees are constructed in such a manner to gather WPD coefficients sharing the same spatial locations at different frequency subbands. The obtained new trees are reorganized in pairs and a differencing step, between the inter-tree coefficients, is performed. The result is compared to a bi-level threshold. At the embedding stage, few locations are modified while most of the locations are left unchanged. To improve the technique security, a content-dependent watermark is implemented and the threshold is made adaptive to the host under consideration. Simulation results have shown superior output watermarking quality with a PSNR > 48 dB as well as high robustness against a wide variety of attacks including moderate-to-severe image compression, filtering, noise addition and enhancement manipulations. Moreover, the technique has demonstrated a low computational cost due to the used approach in selecting the reorganized WPD coefficients.

WPD for Detecting Disturbances in Presence of Noise in Smart Grid for PQ Monitoring

Power quality (PQ) monitoring has been an important issue in smart grid (SG). PQ study involves the detection of the disturbances/events in different power system signals of the SG communication. Detecting disturbances in power system signals itself is a very difficult task and it becomes even more difficult when there are noises in the signal. The detection efficiency of the disturbances is highly downgraded by the noise, which corrupts the detection capability of the system, and hinders the localization and classification of the disturbances. In this work, a PQ monitoring system based on wavelet packet decomposition (WPD) is proposed to detect five different types of disturbances in the presence of noise. The proposed system utilizes the interscale and intrascale relationship of the WPD coefficients for the detection of the PQ disturbances upon noise removal. The correlation among the WPD coefficients exits both within its own scale and across its adjoining scales. For the evaluation, the presented method is applied both on the simulated and real SG disturbance signals obtained from frequency disturbance recorder (FDR), phasor measurement unit (PMU), and power system load. Comparative results are presented with wavelet decomposition.

Pulse Wave Cycle Features Analysis of Different Blood Pressure Grades in the Elderly.

Background and Objective The same range of blood pressure values may reflect different vascular functions, especially in the elderly. Therefore, a single blood pressure value may not comprehensively reveal cardiovascular function. This study focused on identifying pulse wave features in the elderly that can be used to show functional differences when blood pressure values are in the same range. Methods First, pulse data were preprocessed and pulse cycles were segmented. Second, time domain, higher-order statistics, and energy features of wavelet packet decomposition coefficients were extracted. Finally, useful pulse wave features were evaluated using a feature selection and classifier design. Results A total of 6,075 pulse wave cycles were grouped into 3 types according to different blood pressure levels and each group was divided into 2 categories according to a history of hypertension. The classification accuracy of feature selection in the 3 groups was 97.91%, 95.24%, and 92.28%, respectively. Conclusion Selected features could be appropriately used to analyze cardiovascular function in the elderly and can serve as the basis for research on a cardiovascular risk assessment model based on Traditional Chinese Medicine pulse diagnosis.

Research on Seismic Signals Denoising Method based on Multi-Threshold Wavelet Packet

For the distortion problem of traditional denoising threshold function exists, a seismic signal denoising method based on wavelet packet multi-threshold function was present. Seismic wave signals were done wavelet packet decomposition and wavelet packet decomposition coefficients were arranged in the order of magnitude of the frequency, the appropriate threshold criteria was selected on different frequency bands and threshold processing was done on different frequency bands. Synthetic seismic signals and real seismic data were done multi-threshold wavelet packet decomposition, which better remove high frequency random noise and retain useful signals. Experimental results showed that multi-threshold wavelet packet decomposition method can effectively remove noises and improve the resolution of seismic data, with better denoising effect.

Quantitative diagnosis of fault severity trend of rolling element bearings

The condition monitoring and fault diagnosis of rolling element bearings are particularly crucial in rotating mechanical applications in industry. A bearing fault signal contains information not only about fault condition and fault type but also the severity of the fault. This means fault severity quantitative analysis is one of most active and valid ways to realize proper maintenance decision. Aiming at the deficiency of the research in bearing single point pitting fault quantitative diagnosis, a new back-propagation neural network method based on wavelet packet decomposition coefficient entropy is proposed. The three levels of wavelet packet coefficient entropy(WPCE) is introduced as a characteristic input vector to the BPNN. Compared with the wavelet packet decomposition energy ratio input vector, WPCE shows more sensitive in distinguishing from the different fault severity degree of the measured signal. The engineering application results show that the quantitative trend fault diagnosis is realized in the different fault degree of the single point bearing pitting fault. The breakthrough attempt from quantitative to qualitative on the pattern recognition of rolling element bearings fault diagnosis is realized.

Identification and Disease Index Inversion of Wheat Stripe Rust and Wheat Leaf Rust Based on Hyperspectral Data at Canopy Level

Stripe rust and leaf rust with similar symptoms are two important wheat diseases. In this study, to investigate a method to identify and assess the two diseases, the canopy hyperspectral data of healthy wheat, wheat in incubation period, and wheat in diseased period of the diseases were collected, respectively. After data preprocessing, three support vector machine (SVM) models for disease identification and six support vector regression (SVR) models for disease index (DI) inversion were built. The results showed that the SVM model based on wavelet packet decomposition coefficients with the overall identification accuracy of the training set equal to 99.67% and that of the testing set equal to 82.00% was better than the other two models. To improve the identification accuracy, it was suggested that a combination model could be constructed with one SVM model and two models built usingK-nearest neighbors (KNN) method. Using the DI inversion SVR models, the satisfactory results were obtained for the two diseases. The results demonstrated that identification and DI inversion of stripe rust and leaf rust can be implemented based on hyperspectral data at the canopy level.

基于暂态特征突变量的配电网故障选线方法研究

本文对于配电网络常见的单相接地故障，提出了一种基于暂态特征突变量的综合选线方法。首先，对故障后各线路的暂态零序电流进行小波分解；然后，由小波分解系数求得低频能量占总能量的百分比来区分为强故障或弱故障；最后，在强故障情况下采用小波包系数极性法，在弱故障情况下采用暂态零序能量法来选择故障线路。通过MATLAB进行了大量的仿真验证，结果表明该方法具有很好的选线能力，即使发生母线故障、相电压过零故障，高阻接地故障时也能正确选线。 For the single-phase grounding fault in the power distribution, a method to select fault line was proposed in the paper. Firstly, wavelet decomposition was used to transient zero-sequence current of each line after fault; then, the percentage of the low frequency energy to the total energy, which were calculated by the wavelet coefficients, was used to distinguish strong or weak fault; finally, the fault line was selected by comparing the polarities of the wavelet packet decomposition coefficient in the strong fault situation, but comparing the transient zero-sequence energy in the weak fault situation. The MATLAB simulation results show that the method is proposed has good ability to carry out the fault line. The criterion can keep the high reliability when the circuit is bus-bar, high resistance or voltage zero grounding.

Signal Denoising Based on Slip Threshold Value of Wavelet Packets

The signal obtained through measurement is inevitably with noise and interference. Traditional signal denoising method often takes the threshold way to process the wavelets or wavelet packets of noise signal for the purpose of denoising. Denoising by making use of slip threshold value of wavelet packets is proposed by this paper, to quantize the slip threshold value of wavelet packet decomposition coefficient, so as to obtain the reconstructed signal denoising. It is shown by the computer simulation results that the slip threshold value is with good practical value.

A Single Channel Voice Activity Detection for Noisy Environments Using Wavelet Packet Decomposition and Teager Energy

본 논문에서는 WPD (Wavelet Packet Decomposition) 계수에 Teager 에너지를 적용한 특징 계수를 임계값 알고리듬에 적용하여 잡음에 강인한 VAD 알고리듬을 제안하였다. 임계값은 비음성 구간의 평균과 표준편차를 추산하여 설정하였다. TIMIT 음성과 NOISEX 잡음 데이터베이스를 사용한 실험 결과, 제안된 알고리듬이 기존의 대표적인 비교 대상 알고리듬보다 우수함을 보였다. 정확도는 SNR 10 dB부터 -10 dB까지 ROC (Receiver Operating Characteristics) 곡선을 사용하여 비교하였다. In this paper, a feature parameter is obtained by applying the Teager energy to the WPD(Wavelet Packet Decomposition) coefficients. The threshold value is obtained based on means and standard deviations of nonspeech frames. Experimental results by using TIMIT speech and NOISEX-92 noise databases show that the proposed algorithm is superior to the typical VAD algorithm. The ROC(Receiver Operating Characteristics) curves are used to compare performance of VAD's for SNR values of ranging from 10 to -10 dB.

Decentralized modal identification of structures using parallel factor decomposition and sparse blind source separation

In this paper, a novel decentralized modal identification method is proposed utilizing the concepts of sparse blind source separation (BSS) and parallel factor decomposition. Unlike popular ambient modal identification methods which require large arrays of simultaneous vibration measurements, the decentralized algorithm presented here operates on partial measurements, utilizing a sub-set of sensors at-a-time. Mathematically, this leads to an underdetermined source separation problem, which is addressed using sparsifying wavelet transforms. The proposed method builds on a previously presented concept by the authors, which utilizes the stationary wavelet packet transform (SWPT) to generate an over-complete dictionary of sparse bases. However, the redundant SWPT can be computationally intensive depending on the bandwidth of the signals and the sampling frequency of the vibration measurements. This issue of computational burden is alleviated through a new method proposed here, which is based on a multi-linear algebra tool called PARAllel FACtor (PARAFAC) decomposition. At the core of this method, the wavelet packet decomposition coefficients are used to form a covariance tensor, followed by PARAFAC tensor decomposition to separate the modal responses. The underdetermined source identifiability of PARAFAC enables source separation in wavelet packet coefficients with considerable mode mixing, thereby relaxing the conditions to generate over-complete bases, thus reducing the computational burden. The proposed method is validated using a series of numerical simulations followed by an implementation on recorded ambient vibration measurements obtained from the UCLA factor building.

A Data-Driven Failure Prognostics Method Based on Mixture of Gaussians Hidden Markov Models

This paper addresses a data-driven prognostics method for the estimation of the Remaining Useful Life (RUL) and the associated confidence value of bearings. The proposed method is based on the utilization of the Wavelet Packet Decomposition (WPD) technique, and the Mixture of Gaussians Hidden Markov Models (MoG-HMM). The method relies on two phases: an off-line phase, and an on-line phase. During the first phase, the raw data provided by the sensors are first processed to extract features in the form of WPD coefficients. The extracted features are then fed to dedicated learning algorithms to estimate the parameters of a corresponding MoG-HMM, which best fits the degradation phenomenon. The generated model is exploited during the second phase to continuously assess the current health state of the physical component, and to estimate its RUL value with the associated confidence. The developed method is tested on benchmark data taken from the “NASA prognostics data repository” related to several experiments of failures on bearings done under different operating conditions. Furthermore, the method is compared to traditional time-feature prognostics and simulation results are given at the end of the paper. The results of the developed prognostics method, particularly the estimation of the RUL, can help improving the availability, reliability, and security while reducing the maintenance costs. Indeed, the RUL and associated confidence value are relevant information which can be used to take appropriate maintenance and exploitation decisions. In practice, this information may help the maintainers to prepare the necessary material and human resources before the occurrence of a failure. Thus, the traditional maintenance policies involving corrective and preventive maintenance can be replaced by condition based maintenance.

Analysis on Peeping Image Enhancement of Coal Mine Borehole Based on Wavelet Packet Decomposition

According to the characteristics of wavelet packet decomposition and reconstruction, an image enhancement method is put forward by decomposing wavelet packet and adjusting enhancement coefficient of band signal by the energy size. First, borehole peep images were decomposed by wavelet packet, and obtained the signal bandwidth of each layer after wavelet packet decomposition combined with Fourier transform. Secondly, energy of each band signal was calculated, wavelet packet decomposition coefficients according to the size of band energy were enhanced and weakened. Finally, the wavelet packet images were reconstructed. Project case indicates that this method can effectively enhance the images, especially the information of fractured surrounding rock.

Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients

This paper describes feature extraction methods using higher order statistics (HOS) of wavelet packet decomposition (WPD) coefficients for the purpose of automatic heartbeat recognition. The method consists of three stages. First, the wavelet package coefficients (WPC) are calculated for each different type of ECG beat. Then, higher order statistics of WPC are derived. Finally, the obtained feature set is used as input to a classifier, which is based on k-NN algorithm. The MIT-BIH arrhythmia database is used to obtain the ECG records used in this study. All heartbeats in the arrhythmia database are grouped into five main heartbeat classes. The classification accuracy of the proposed system is measured by average sensitivity of 90%, average selectivity of 92% and average specificity of 98%. The results show that HOS of WPC as features are highly discriminative for the classification of different arrhythmic ECG beats.

Condition monitoring of speed controlled induction motors using wavelet packets and discriminant analysis

This work presents an intelligent method for the condition monitoring of induction motors supplied with adjustable speed drives (ASD). Most of the previous work in this area concentrated on the fault detection and classification of induction motors supplied directly from an a.c. line. However, ASD driven induction motors are widely used in industrial processes and therefore obtaining an intelligent tool for the condition monitoring of these motors is necessary in terms of preventive maintenance and reducing down time due to motor faults. Here 3-phase supply side current of the ASD driving an induction motor is used to extract statistical features of wavelet packet decomposition coefficients within a frequency range of interest. This way, the information regarding the output frequency of the ASD and hence the motor speed is not required. Six identical three-phase induction motors were used for the experimental verification of the proposed method. One healthy machine was used as a reference, while other five with various synthetic faults were used for condition detection and classification. Extracted features obtained from decomposition coefficients of different wavelet filter types for all motors were employed in three different and popular classifiers. The proposed method and the performance of the features used for fault detection and classification are examined at various motor loads and speed levels, and it is shown that a successful condition monitoring system for induction motors supplied with ASDs is developed. The effect of selected filter type in wavelet decomposition to the condition monitoring process is analyzed and presented.

Objective research of auscultation signals in Traditional Chinese Medicine based on wavelet packet energy and Support Vector Machine

This study aims at utilising Wavelet Packet Transform (WPT) and Support Vector Machine (SVM) algorithm to make objective analysis and quantitative research for the auscultation in Traditional Chinese Medicine (TCM) diagnosis. First, Wavelet Packet Decomposition (WPD) at level 6 was employed to split more elaborate frequency bands of the auscultation signals. Then statistic analysis was made based on the extracted Wavelet Packet Energy (WPE) features from WPD coefficients. Furthermore, the pattern recognition was used to distinguish mixed subjects' statistical feature values of sample groups through SVM. Finally, the experimental results showed that the classification accuracies were at a high level.

EEG feature extraction based on wavelet packet decomposition for brain computer interface

In the study of brain computer interfaces, a novel method was proposed in this paper for the feature extraction of electroencephalogram (EEG). It was based on wavelet packet decomposition (WPD). The energy of special sub-bands and corresponding coefficients of wavelet packet decomposition were selected as features which have maximal separability according to the Fisher distance criterion. The eigenvector was obtained for classification by combining the effective features from different channels; its performance was evaluated by separability and pattern recognition accuracy using the datasets of BCI 2003 Competition. The classification results have proved the effectiveness of the proposed method. This technology provides another useful way to EEG feature extraction in BCIs.