Wavelet Package Research Articles

Cross-frequency and iso-frequency estimation of functional corticomuscular coupling after stroke.

Functional corticomuscular coupling (FCMC) between the brain and muscles has been used for motor function assessment after stroke. Two types, iso-frequency coupling (IFC) and cross-frequency coupling (CFC), are existed in sensory-motor system for healthy people. However, in stroke, only a few studies focused on IFC between electroencephalogram (EEG) and electromyogram (EMG) signals, and no CFC studies have been found. Considering the intrinsic complexity and rhythmicity of the biological system, we first used the wavelet package transformation (WPT)to decompose the EEG and EMG signals into several subsignals with different frequency bands, and then applied transfer entropy (TE)to analyze the IFC and CFC relationship between each pair-wise subsignal. In this study, eight stroke patients and eight healthy people were enrolled. Results showed that both IFC and CFC still existed in stroke patients (EEG → EMG: 1:1, 3:2, 2:1; EMG → EEG: 1:1, 2:1, 2:3, 3:1). Compared with the stroke-unaffected side and healthy controls, the stroke-affected side yielded lower alpha, beta and gamma synchronization (IFC: beta; CFC: alpha, beta and gamma). Further analysis indicated that stroke patients yielded no significant difference of the FCMC between EEG → EMG and EMG → EEG directions. Our study indicated that alpha and beta bands were essential to concentrating and maintaining the motor capacities, and provided a new insight in understanding the propagation and function in the sensory-motor system.

Metode Wavelet-MFCC dan Korelasi dalam Pengenalan Suara Digit

Voice is the sound emitted from living things. With the development of Automatic Speech Recognition (ASR) technology, voice can be used to make it easier for humans to do something. In the ASR extraction process the features have an important role in the recognition process. The feature extraction methods that are commonly applied to ASR are MFCC and Wavelet. Each of them has advantages and disadvantages. Therefore, this study will combine the wavelet feature extraction method and MFCC to maximize the existing advantages. The proposed method is called Wavelet-MFCC. Voice recognition method that does not use recommendations. Determination of system performance using the Word Recoginition Rate (WRR) method which is validated with the K-Fold Cross Validation with the number of folds is 5. The research dataset used is voice recording digits 0-9 in English. The results show that the digit speech recognition system that has been built gives the highest average value of 63% for digit 4 using wavelet daubechies DB3 and wavelet dyadic transform method. As for the comparison results of the wavelet decomposition method used, that the use of dyadic wavelet transformation is better than the wavelet package.

Network Security Situation Detection of Internet of Things for Smart City Based on Fuzzy Neural Network

In order to ensure the safety of internet of things for smart city and ensure normal operation of smart city, the network security situation of internet of things should be monitored correctly for a long time, therefore the fuzzy neutral network with wavelet package and chaos particle swarm algorithm are applied to monitor the network security situation. Firstly, the basic theory of network security situation of internet of things for smart city is analysed, the corresponding mathematical is constructed, and the security situation awareness framework of internet of things is designed. Secondly, the basic theory of fuzzy neutral network is studied, and the structure of the fuzzy neutral network is designed. Thirdly, the processing method of network security situation data based on wavelet package is constructed. And then training procedure of fuzzy neutral network based on chaos particle swarm algorithm is established, the algorithm procedure is designed. Finally, the simulation analysis is carried out using a smart city as example, and the network security situation of internet of things for it is monitored correctly, then the network safety can be ensured.

Comparative study of wavelet based techniques for electromagnetic noise evaluation and removal

Signals acquired from an industrial environment with many sources of electromagnetic interferences may be polluted by white noise. Polluted data segments with many steady consecutive periods can be used (sometimes unsuccessful) for the estimation of a denoised period from the steady acquired data by using the mean signal method. For data segments with at least 4 periods, when only certain segments (shorter than a period) can be considered steady, hybrid algorithms can be used to automatically evaluate the power of noise and afterward to perform the noise removal by using wavelet thrashing trees. This paper deals with 2 additional denoising techniques. The 1-st one is based on the Wavelet Package Transform and allows for the separation of the noise components which pollute a data segment of at least one period. The second approached denoising technique is also addressing one period data segments and estimates firstly the power of noise by using the energies of the vectors of details from the first 2 levels of a tree used by decompositions with the Stationary Wavelet Transform. The estimated power of noise is afterward used to establish the number of levels in the wavelet thrashing trees. In this last stage, two wavelet mothers were used. Simulated and real test signals were used and performance comparisons were performed.

High-Voltage Circuit Breaker Fault Diagnosis Using a Hybrid Feature Transformation Approach Based on Random Forest and Stacked Autoencoder

In recent years, machine learning techniques have been applied to test the fault type in high-voltage circuit breakers (HVCBs). Most related research involves in improving the classification method for higher precision. Nevertheless, as an important part of the diagnosis, the feature information description of the vibration signal of an HVCB has been neglected; in particular, its diversity and significance are rarely considered in many real-world fault-diagnosis applications. Therefore, in this paper, a hybrid feature transformation is proposed to optimize the diagnosis performance for HVCB faults. First, we introduce a nonlinear feature mapping in the wavelet package time–frequency energy rate feature space based on random forest binary coding to extend the feature width. Then, a stacked autoencoder neural network is used for compressing the feature depth. Finally, five typical classifiers are applied in the hybrid feature space based on the experimental dataset. The superiority of the proposed feature optimal approach is verified by comparing the results in the three abovementioned feature spaces.

Monitoring tool wear using wavelet package decomposition and a novel gravitational search algorithm–least square support vector machine model

Monitoring tool wear has drawn much attention recently since tool failure will make it hard to guarantee the surface integrity of workpieces and the stability of manufacturing process. In this paper, the integrated approach that combines wavelet package decomposition, least square support vector machine, and the gravitational search algorithm is proposed for monitoring the tool wear in turning process. Firstly, the wavelet package decomposition is utilized to decompose the original cutting force signals into multiple sub-bands. Root mean square of the wavelet packet coefficients in each sub-band are extracted as the monitoring features. Then, the gravitational search algorithm–least square support vector machine model is constructed by using the extracted wavelet–domain features so as to identify the tool wear states. Eight sets of cutting experiments are conducted to prove the superiority of the proposed integrated approach. The experimental results show that the wavelet–domain features can help to ameliorate the performance of the gravitational search algorithm–least square support vector machine model. Besides, gravitational search algorithm–least square support vector machine performs better than gravitational search algorithm–support vector machine in prediction accuracy of tool wear states even in the case of small-sized training data set and the time consumption of parameters optimization in gravitational search algorithm–least square support vector machine is less than that of gravitational search algorithm–support vector machine under large-sized training data set. What's more, the gravitational search algorithm–least square support vector machine model outperforms some other related methods for tool wear estimation, such as k-NN, feedforward neural network, classification and regression tree, and linear discriminant analysis.

A threshold research for de-noising operation to the vibration signals based on wavelet package

Vibration signals are often interfered by salt and pepper noise, impulse noise, Gaussian noise, and other high-frequency noise, affecting the effect of vibration control research. Therefore, de-noising operation is significant for vibration signal in the practical engineering. In order to resolve this problem, wavelet package is used to remove noises from vibration signal. We provide the principle of de-noising method based on wavelet package at first. And then, the threshold selection of the method is analyzed by a vibration signal with noises. As the result shown, the noise can be effectively eliminated. This reflects that the de-noising method based on wavelet package with the hard threshold is effective.

Hybrid Energy Storage System (HESS) optimization enabling very short-term wind power generation scheduling based on output feature extraction

Incorporating Energy Storage System (ESS) with wind farm to establish Wind-Storage Combined Generation System is a promising solution to improve the dependability of integrated wind power. Hybrid Energy Storage System (HESS) is designed based on wind power fluctuation and ESS features. The optimization of system sizing and very short-term generation scheduling are the key points affecting system effectiveness and reliability of wind power. This paper proposes a novel real-time model prediction control (MPC) -multi objective cross entropy (MOCE) based energy management algorithm (MMEMA) to coordinate an HESS based on power output feature extraction. The proposed algorithm includes the SOC regulation strategies considering practical issues including charge/discharge power. Firstly, based on Wavelet Package Decomposition (WPD) and Hilbert Huang Transform (HHT) respectively, the fluctuation feature of real-time wind power output is studied to propose a HESS model aiming to obtain the economic capacity as well as maximum charging/discharging power in every generation scheduling period (10 min). Thus, according to case study, the sizing approach can reduce invest cost by 25.7–47.0%. Then, HESS data is taken as parameters and constraints for the proposed model prediction control (MPC) –multi objective cross entropy (MOCE) algorithm to minimize the deviation between generation scheduling plan and real-time integrated power. The optimization results from case wind farm show that the proposed MMEMA algorithm performs better in smoothing out the fluctuation and managing the SOC of HESS than Non-dominated Sorting Genetic Algorithm II based method (NEMA) by means of evaluating the indexes PD, HSOC and MSE.

A weak fault feature extraction of rolling element bearing based on attenuated cosine dictionaries and sparse feature sign search

The time domain signal of bearing pitting/spalling fault always presents shock and modulation, and it is often submerged by strong noises, especially in the early stage. the conventional fault feature extraction method may have insufficient feature extraction accuracy, and even in some extreme cases, the fault feature frequency cannot be extracted because of the strong noise interference. Aiming at overcoming the noise interference problem encountered in this kind of weak fault feature extraction, a novel weak fault feature extraction algorithm termed as ACFSS of rolling bearing is proposed. The ACFSS is based on an overcomplete dictionary (or overcomplete atomic library) of Attenuated Cosines(AC) basis, which is highly matched to the bearing fault waveforms, and an improved Basis Pursuit algorithm with Feature Sign Search(FSS) is introduced into the ACFSS to improve the calculating speed. In order to select the suitable parameters of the attenuated cosine dictionary, some methods such as peak resonance frequency (PRF), power variation peak (PVK), time shift parameter (TSP), etc. are introduced. These parameters span the sparse overcomplete dictionary. Finally, the bearing fault data of Case-Western University and full life accelerated IMS bearing data are utilized to verify the validation of ACFSS. Compared with the ordinary envelope spectrum analysis(ESA) method /the ordinary Basis Pursuit Denoising(BPDN) method/ Wavelet package transform(WPT) Kurtogram method and Empirical Mode Decomposition(EMD) combining Singular Value Decomposition(SVD) method, The experiment show that the proposed method are more redundant and robust when facing strong noise interference, and it can be used to extract the weak fault feature frequency efficiently and accurately.

Fault Diagnosis of Train Plug Door Based on a Hybrid Criterion for IMFs Selection and Fractional Wavelet Package Energy Entropy

The train plug door is the only way for passengers getting on and off. Its failures will make train operation ineffective. Taking the developed digital signal processing technologies into consideration, a data-driven diagnosis method for train plug doors is proposed based on sound recognition. First, a novel preprocessing method based on empirical mode decomposition and hybrid intrinsic mode functions (IMFs) selection criterion is proposed. The selected significant IMFs are used to reconstruct the signals. Inspired by the idea of fractional calculus, novel entropy named fractional wavelet package decomposition energy entropy (FWPDE) is proposed. Finally, multi-class support vector machine is used for classification and validation. Experimental results indicate that the proposed preprocessing method is of great significance to extract effective FWPDE features. In addition, FWPDE is more powerful in comparison with the classical wavelet package decomposition energy entropy. The identification accuracy using the proposed method reaches 96.28%, which demonstrates its effectiveness and superiority.

SEMG-based Endpoint Stiffness Estimation of Human Arm using Gene Expression Programming

The endpoint stiffness of the human arm has been long recognized as a key factor in the smooth contact between humans and environment. And the endpoint stiffness of the human arm is highly correlated with the surface electromyography (sEMG) produced by the contraction of the muscles. In this paper, the Gene Expression Programming (GEP) Algorithm is proposed to estimate the endpoint stiffness of human arm based on sEMG. This paper improves the traditional decoding method of GEP. Instead of generating an expression tree, it is directly decoded by looking for the effective length of the gene. And experimental results show that nonlinear models such as GEP models in this paper have higher correlation and lower RMSE (root mean square error) than regression stiffness using linear regression models. Selecting different feature of EMG signals, the correlation coefficient and the root mean square error of the model is very different. For the GEP model in this paper, WPTSVD (Wavelet Package Transform Singular Value Decomposion) and WTSVD (Wavelet Transform Singular Value Decomposion) are selected as the feature of sEMG signals have high performances and the correlation can reach 57%±12.1%

Nonlinear Blind Source Separation and Fault Feature Extraction Method for Mining Machine Diagnosis

Mining machines are strongly nonlinear systems, and their transmission vibration signals are nonlinear mixtures of different kinds of vibration sources. In addition, vibration signals measured by the accelerometer are contaminated by noise. As a result, it is inefficient and ineffective for the blind source separation (BSS) algorithm to separate the critical independent sources associated with the transmission fault vibrations. For this reason, a new method based on wavelet de-noising and nonlinear independent component analysis (ICA) is presented in this paper to tackle the nonlinear BSS problem with additive noise. The wavelet de-noising approach was first employed to eliminate the influence of the additive noise in the BSS procedure. Then, the radial basis function (RBF) neural network combined with the linear ICA was applied to the de-noised vibration signals. Vibration sources involved with the machine faults were separated. Subsequently, wavelet package decomposition (WPD) was used to extract distinct fault features from the source signals. Lastly, an RBF classifier was used to recognize the fault patterns. Field data acquired from a mining machine was used to evaluate and validate the proposed diagnostic method. The experimental analysis results show that critical fault vibration source component can be separated by the proposed method, and the fault detection rate is superior to the linear ICA based approaches.

Ultrasonic Detection Method for Grouted Defects in Grouted Splice Sleeve Connector Based on Wavelet Pack Energy.

Grouted splice sleeve (GSS) connectors are mainly used in precast concrete structures. However, errors in manual operation during construction cause grouted defects in the GSS connector, which can lead to a negative effect on the overall mechanical properties of the structures. Owing to the complex structure of precast concrete members with a GSS connector, it is difficult to detect grouted defects effectively using traditional ultrasonic parameters. In this paper, a wavelet packet analysis algorithm was developed to effectively detect grouted defects using the ultrasonic method, and a verified experiment was carried out. Laboratory detection was performed on the concrete specimens with a GSS connector before grouting, in which the grouted defects were mimicked with five sizes in five GSS connectors of each specimen group. A simple and convenient ultrasonic detection system was developed, and the specimens were detected. According to the proposed grouted defect index, the results demonstrated that when the grouted defects reached certain sizes, the proposed method could detect the grouted defects effectively. The proposed method is effective and easy to implement at a construction site with simple instruments, and so provides an innovative method for grouted defects detection of precast concrete members.

Portable brain-computer interface based on novel convolutional neural network

Electroencephalography (EEG) is a powerful, noninvasive tool that provides a high temporal resolution to directly reflect brain activities. Conventional electrodes require skin preparation and the use of conductive gels, while subjects must wear uncomfortable EEG hats. These procedures usually create a challenge for subjects. In the present study, we propose a portable EEG signal acquisition system. This study consists of two main parts: 1) A novel, portable dry-electrode and wireless brain–computer interface is designed. The EEG signal acquisition board is based on 24 bit, analog-to-digital converters chip and wireless microprocessor unit. The wireless portable brain computer interface device acquires an EEG signal comfortably, and the EEG signals are transmitted to a personal computer via Bluetooth. 2) A convolutional neural network (CNN) classification algorithm is implemented to classify the motor imagery (MI) experiment using novel feature 3-dimension input. The time dimension was reshaped to represent the first and second dimension, and the frequency band was used as the third dimension. Specifically, frequency domain representations of EEG signals obtained via wavelet package decomposition (WPD) are obtained to train CNN. The classification performance in terms of the value of kappa is 0.564 for the proposed method. The t-test results show that the performance improvement of CNN over other selected state-of-the-art methods is statistically significant. Our results show that the proposed design is reliable in measuring EEG signals, and the 3D CNN provides better classification performance than other method for MI experiments.

An Investigation into the Acoustic Emissions of Internal Combustion Engines with Modelling and Wavelet Package Analysis for Monitoring Lubrication Conditions

Online monitoring of the lubrication and friction conditions in internal combustion engines can provide valuable information and thereby enables optimal maintenance actions to be undertaken to ensure safe and efficient operations. Acoustic emission (AE) has attracted significant attention in condition monitoring due to its high sensitivity to light defects on sliding surfaces. However, limited understanding of the AE mechanisms in fluid-lubricated conjunctions, such as piston rings and cylinder liners, confines the development of AE-based lubrication monitoring techniques. Therefore, this study focuses on developing new AE models and effective AE signal process methods in order to achieve accurate online lubrication monitoring. Based on the existing AE model for asperity–asperity collision (AAC), a new model for fluid–asperity shearing (FAS)-induced AE is proposed that will explain AE responses from the tribological conjunction of the piston ring and cylinder. These two AE models can then jointly demonstrate AE responses from the lubrication conjunction of engine ring–liner. In particular, FAS allows the observable AE responses in the middle of engine strokes to be characterised in association with engine speeds and lubricant viscosity. However, these AE components are relatively weak and noisy compared to others, with movements such as valve taring, fuel injection and combustions. To accurately extract these weaker AE’s for lubricant monitoring, an optimised wavelet packet transform (WPT) analysis is applied to the raw AE data from a running engine. This results in four distinctive narrow band indicators to describe the AE amplitude in the middle of an engine power stroke. Experimental evaluation shows the linear increasing trend of AE indicator with engine speeds allows a full separation of two baseline engine lubricants (CD-10W30 and CD-15W40), previously unused over a wide range of speeds. Moreover, the used oil can also be diagnosed by using the nonlinear and unstable behaviours of the indicator at various speeds. This model has demonstrated the high performance of using AE signals processed with the optimised WPT spectrum in monitoring the lubrication conditions between the ring and liner in IC engines.

A novel data pre-processing method for odour detection and identification system

This paper presents a novel electronic nose (E-nose) data pre-processing method, based on a recently developed non-parametric kernel-based modelling (KBM) approach. The proposed method is tested by an automated odour detection and classification system, named “NOS.E”, developed by the NOS.E team in University of Technology Sydney. Experimental results show that when extracting the derivative-related features from signals collected by the NOS.E, the proposed non-parametric KBM odour data pre-processing method achieves more reliable and stable pre-processing results comparing with other pre-processing methods such as wavelet package correlation filter (WPCF), mean filter (MF), polynomial curve fitting (PCF) and locally weighted regression (LWR). Based on these derivative-related features, the NOS.E can achieve a 96.23% accuracy of classification with the popular Support Vector Machine (SVM) classifier.

Visibility Graph Feature Model of Vibration Signals: A Novel Bearing Fault Diagnosis Approach.

Reliable fault diagnosis of rolling bearings is an important issue for the normal operation of many rotating machines. Information about the structure dynamics is always hidden in the vibration response of the bearings, and it is often very difficult to extract them correctly due to the nonlinear/chaotic nature of the vibration signal. This paper proposes a new feature extraction model of vibration signals for bearing fault diagnosis by employing a recently-developed concept in graph theory, the visibility graph (VG). The VG approach is used to convert the vibration signals into a binary matrix. We extract 15 VG features from the binary matrix by using the network analysis and image processing methods. The three global VG features are proposed based on the complex network theory to describe the global characteristics of the binary matrix. The 12 local VG features are proposed based on the texture analysis method of images, Gaussian Markov random fields, to describe the local characteristics of the binary matrix. The feature selection algorithm is applied to select the VG feature subsets with the best performance. Experimental results are shown for the Case Western Reserve University Bearing Data. The efficiency of the visibility graph feature model is verified by the higher diagnosis accuracy compared to the statistical and wavelet package feature model. The VG features can be used to recognize the fault of rolling bearings under variable working conditions.

Classification of inter-ictal and ictal EEGs using multi-basis MODWPT, dimensionality reduction algorithms and LS-SVM: A comparative study

Abstract Wavelet-based feature extraction techniques are very promising for classifying epileptic electroencephalograph (EEG) but the determination of the optimal wavelet basis is intractable. To overcome this strait, maximal overlap discrete wavelet package transform (MODWPT) was introduced to characterize epileptic EEG for the first time and the multi-basis MODWPT-based feature extraction was further proposed in this study. Instead of merely using single wavelet basis, multiple bases were synchronously adopted in one-time implementation of multi-basis MODWPT. Six dimensionality reduction algorithms, namely principal component analysis (PCA), independent component analysis (ICA), kernel principal component analysis (KPCA), isometric feature mapping (ISOMAP), locally linear embedding (LLE) and Laplacian eigenmaps (LE), were then employed to map the extracted features into other domain in feature selection procedure. Finally, the mapped features were fed into a least squares support vector machine (LS-SVM) for classification and multiple kernel learning support vector machine (MKLSVM) was used as comparison. Experimental results show the combination of multi-basis MODWPT, ICA and LS-SVM with linear kernel provides the highest accuracy of 99.67% in classifying inter-ictal and ictal EEGs while MKLSVM in conjunction with multi-basis MODWPT-based PCA also leads to the maximal accuracy of 99.83%. Our presented scheme yields superior performance than the majority of newly-developed methods and is proven useful.

Vibration-Based Intelligent Fault Diagnosis for Roller Bearings in Low-Speed Rotating Machinery

This paper proposes a new signal feature extraction and fault diagnosis method for fault diagnosis of low-speed machinery. Statistic filter (SF) and wavelet package transform (WPT) are combined with moving-peak-hold method (M-PH) to extract features of a fault signal, and special bearing diagnostic symptom parameters (SSPs) in a frequency domain that are sensitive to bearing fault diagnosis are defined to recognize fault types. The SF is first used to adaptively cancel noises, and then fault detection is performed by exploiting the optimum symptom parameters in a time domain to identify a normal or fault state. For precise diagnosis, the SSPs are calculated after the signals are processed by M-PH and WPT. A decision tree is used to structure intelligent diagnosis rules in each step until the states are fully and automatically detected. The efficacy of this method was confirmed by applying it to an experimental low-speed rotation machine.

Novel Particle Swarm Optimization-Based Variational Mode Decomposition Method for the Fault Diagnosis of Complex Rotating Machinery

The vibration signals of faulty rotating machinery are typically nonstationary, nonlinear, and mixed with abundant compounded background noise. To extract the potential excitations from the observed rotating machinery, signal demodulation and time–frequency analysis are indispensable. This work proposes a novel particle swarm optimization-based variational mode decomposition method, which adopts the minimum mean envelope entropy to optimize the parameters ( $\alpha$ and $K$ ) in the existing variational mode decomposition. The proposed fault-detection framework separated the observed vibration signals into a series of intrinsic modes. A certain number of the intrinsic modes are then selected by means of the Hilbert transform-based square envelope spectral kurtosis. Subsequently, in this study, the feature representations were reconstructed via the selected intrinsic modes; then, the envelope spectra of the real faulty conditions were generated in the rotating machinery. To verify the performance of the proposed method, a testbed platform of a gearbox with a combination of different faults was implemented. The experimental results demonstrated that the proposed method represented the patterns of the fault frequency more explicitly than the available empirical mode decomposition, the local mean decomposition, and the wavelet package transform method.