Radar emitter signal recognition based on multi-scale wavelet entropy and feature weighting

In modern electromagnetic environment, radar emitter signal recognition is an important research topic. On the basis of multi-resolution wavelet analysis, an adaptive radar emitter signal recognition method based on multi-scale wavelet entropy feature extraction and feature weighting was proposed. With the only priori knowledge of signal to noise ratio(SNR), the method of extracting multi-scale wavelet entropy features of wavelet coefficients from different received signals were combined with calculating uneven weight factor and stability weight factor of the extracted multi-dimensional characteristics. Radar emitter signals of different modulation types and different parameters modulated were recognized through feature weighting and feature fusion. Theoretical analysis and simulation results show that the presented algorithm has a high recognition rate. Additionally, when the SNR is greater than-4 d B, the correct recognition rate is higher than 93%. Hence, the proposed algorithm has great application value.

A STUDY OF WAVELET ENTROPY MEASURE DEFINITION AND ITS APPLICATION FOR FAULT FEATURE PICK-UP AND CLASSIFICATION

Shannon entropy in time domain is a measure of signal or system uncertainty.When based on spectrum entropy,Shannon entropy can be taken as a measure of signal or system complexity. Therefore,wavelet analysis based on wavelet entropy measure can signify the complexity of non-steady signal or system in both time and frequency domain.In this paper,in order to meet the requirements of post-analysis on abundant wavelet transform result data and the need of information mergence,the basic definition of wavelet entropy measure is proposed,corresponding algorithms of several wavelet entropies,such as wavelet average entropy,wavelet time-frequency entropy,wavelet distance entropy, etc.are put forward,and the physical meanings of these entropies are analyzed as well.The application principle of wavelet entropy measure in ElectroEncephaloGraphy (EEG) signal analysis,mechanical fault diagnosis,fault detection and classification in power system are analyzed.Finally,take the transmission line fault detection in power system for example,simulations in two different systems,a 10kV automatic blocking and continuous power transmission line and a 500kV Extra High Voltage (EHV) transmission line,are carried out,and the two methods,wavelet entropy and wavelet modulus maxima,are compared,the results show feasibility and application prospect of the six wavelet entro- pies.

An Algorithm of Voice Activity Detection Based on EMD and Wavelet Entropy Ratio

A new method was proposed to identify speech-segment endpoints based on the empirical mode decomposition（EMD） and a new wavelet entropy ratio with improving the accuracy of voice activity detection.With the EMD, the noise signals can be decomposed into several intrinsic mode functions（IMFs）. Then the proposed wavelet energy entropy ratio can be used to extract the desired feature for each IMFs component. In view of the question that the method of voice endpoint detection based on the original wavelet entropy ratio cannot adapt to the low signal-to-noise ratio（SNR）condition, an appropriate positive constant was introduced to the basic wavelet energy entropy ratio with effectively improved discriminability between the speech and noise. After comparing the traditional wavelet energy entropy ratio with the proposed wavelet energy entropy ratio, the experiment results show that the proposed method is simple and fast. The speech endpoints can be accurately detected in low SNR environments.

Research on the detecting methods of singularity in deformation signal based on two kinds of wavelet entropy

There are various influencing factors that affect the deformation observation, and deformation signals show differ- ent characteristics under different scales. Wavelet analysis possesses multi-scale property, and the information entropy has great representational capability to the complexity of information. By hamming window to the wavelet coefficients and windowed wavelet energy obtained by multi-resolution analysis （MRA）, it can be achieved to measure the wavelet time entropy （WTE） and wavelet energy entropy （WEE）. The paper established deformation signals, selected the parameters, and compared the sin- gularity detection ability and anti-noise ability of two kinds of wavelet entropy and applied them to the singularity detection at the GPS continuously operating reference stations. It is shown that the WTE performs well in weak singularity information de- tection in finite frequency components signals and the WEE is more suitable for detecting the singularity in the signals with complex, strong background noise.

Alcoholism Detection by Wavelet Energy Entropy and Linear Regression Classifier

Alcoholism is an unhealthy lifestyle associated with alcohol dependence.Not only does drinking for a long time leads to poor mental health and loss of self-control,but alcohol seeps into the bloodstream and shortens the lifespan of the body’s internal organs.Alcoholics often think of alcohol as an everyday drink and see it as a way to reduce stress in their lives because they cannot see the damage in their bodies and they believe it does not affect their physical health.As their drinking increases,they become dependent on alcohol and it affects their daily lives.Therefore,it is important to recognize the dangers of alcohol abuse and to stop drinking as soon as possible.To assist physicians in the diagnosis of patients with alcoholism,we provide a novel alcohol detection system by extracting image features of wavelet energy entropy from magnetic resonance imaging(MRI)combined with a linear regression classifier.Compared with the latest method,the 10-fold cross-validation experiment showed excellent results,including sensitivity 91.54±1.47%,specificity 93.66±1.34%,Precision 93.45±1.27%,accuracy 92.61±0.81%,F1 score 92.48±0.83%and MCC 85.26±1.62%.

Least-Square Support Vector Machine and Wavelet Selection for Hearing Loss Identification

Hearing loss(HL)is a kind of common illness,which can significantly reduce the quality of life.For example,HL often results in mishearing,misunderstanding,and communication problems.Therefore,it is necessary to provide early diagnosis and timely treatment for HL.This study investigated the advantages and disadvantages of three classical machine learning methods:multilayer perceptron(MLP),support vector machine(SVM),and least-square support vector machine(LS-SVM)approach andmade a further optimization of the LS-SVM model via wavelet entropy.The investigation illustrated that themultilayer perceptron is a shallowneural network,while the least square support vector machine uses hinge loss function and least-square optimizationmethod.Besides,a wavelet selection method was proposed,and we found db4 can achieve the best results.The experiments showed that the LS-SVM method can identify the hearing loss disease with an overall accuracy of three classes as 84.89±1.77,which is superior to SVM andMLP.The results show that the least-square support vector machine is effective in hearing loss identification.

WACPN:A Neural Network for Pneumonia Diagnosis

Community-acquired pneumonia(CAP)is considered a sort of pneumonia developed outside hospitals and clinics.To diagnose community-acquired pneumonia(CAP)more efficiently,we proposed a novel neural network model.We introduce the 2-dimensional wavelet entropy(2d-WE)layer and an adaptive chaotic particle swarm optimization(ACP)algorithm to train the feed-forward neural network.The ACP uses adaptive inertia weight factor(AIWF)and Rossler attractor(RA)to improve the performance of standard particle swarm optimization.The final combined model is named WE-layer ACP-based network(WACPN),which attains a sensitivity of 91.87±1.37%,a specificity of 90.70±1.19%,a precision of 91.01±1.12%,an accuracy of 91.29±1.09%,F1 score of 91.43±1.09%,an MCC of 82.59±2.19%,and an FMI of 91.44±1.09%.The AUC of this WACPN model is 0.9577.We find that the maximum deposition level chosen as four can obtain the best result.Experiments demonstrate the effectiveness of both AIWF and RA.Finally,this proposed WACPN is efficient in diagnosing CAP and superior to six state-of-the-art models.Our model will be distributed to the cloud computing environment.

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.

Application of different clustering approaches to hydroclimatological catchment regionalization in mountainous regions, a case study in Utah State

With respect to the different hydrological responses of catchments, even the adjacent ones, in mountainous regions, there are a great number of motivations for classifying them into homogeneous clusters. These motivations include prediction in ungauged basins(PUB), model parameterization, understanding the potential impact of environmental changes, transferring information from gauged catchments to the ungauged ones. The present study investigated the similarity of catchments through the hydro-climatological pure time-series of a 14-year period from 2001 to 2015. Data sets encompass more than 13,000 month-station streamflow, rainfall, and temperature data obtained from 27 catchments in Utah State as one of the eight mountainous states of the USA. The identification, analysis, and interpretation of homogeneous catchments were investigated by applying the four approaches ofclustering, K-means, Ward, and SOM(Self-Organized Map) and a newly proposed Wavelet-Entropy-based(WE-SOM) clustering method. By using two clustering evaluation criteria, 3, 5, and 6 clusters were determined as the best numbers of clusters, depending on the method employed, where each cluster represents different hydro-climatological behaviors. Despite the absence of geographic characteristics in input data matrix, the results indicated a regionalization in agreement with topographic characteristics. Considering the dependency of the hydrological behavior of catchments on the physiographic field aspects and characteristics, WE-SOM method demonstrated a more acceptable performance, compared to the other three conventional clustering methods, by providing more clusters. WE-SOM appears to be a promising approach in catchment clustering. It preserves the topological structure of data which can, as a result, be proofed in a greater number of clusters by dividing data into higher numbers of distinct clusters withsimilar altitudes of catchments in each cluster. The results showed the aptitude of wavelets to quantify the time-based variability of temperature, rainfall and streamflow, in the way contributing to the regionalization of diverse catchments.

A Fault Diagnosis Method Based on Wavelet Singular Entropy and SVM for VSC-HVDC Converter

The converter is the core component of voltage source converter-high voltage direct current(VSC-HVDC),which is related to the stable operation of the system.The converter has a complex structure where the accuracy of feature extraction is low,and the computation speed of traditional fault diagnosis strategies is slow.To solve this problem,a fault diagnosis strategy based on wavelet singular entropy(WSE)and support vector machine(SVM)was proposed.This method includes fault and label setting,converter fault feature extraction based on wavelet singular entropy,and converter fault classification based on support vector machine.The DC-side voltage signal was used as the detection signal,and the wavelet singular entropy was used for feature extraction to avoid noise interference.The classification is based on SVM.The experimental verification in PSCAD simulation proved that the method has better fault diagnosis ability for various faults and meets the needs of converter fault diagnosis.

Wavelet Variance Analysis of EEG Based on Window Function

A new wavelet variance analysis method based on window function is proposed to investigate the dynamical features of electroencephalogram(EEG).The exprienmental results show that the wavelet energy of epileptic EEGs are more discrete than normal EEGs, and the variation of wavelet variance is different between epileptic and normal EEGs with the increase of time-window width. Furthermore, it is found that the wavelet subband entropy (WSE) of the epileptic EEGs are lower than the normal EEGs.

Adaptive TQWT filter based feature extraction method and its application to detection of repetitive transients

The local defect in rotating machine always gives rise to repetitive transients in the collected vibration signal. However, the transient signature is prone to be contaminated by strong background noises, thus it is a challenging task to detect the weak transients for machine fault diagnosis. In this paper, a novel adaptive tunable Q-factor wavelet transform(TQWT) filter based feature extraction method is proposed to detect repetitive transients. The emerging TQWT possesses distinct advantages over the classical constant-Q wavelet transforms, whose Q-factor can be tuned to match the oscillatory behavior of different signals, but the parameter selection for TQWT heavily relies on prior knowledge. Within our adaptive TQWT filter algorithm, the automatic optimization techniques for three TQWT parameters are implemented to achieve an optimal TQWT basis that matches the transient components. Specifically, the decomposition level is selected according to a center frequency ratio based stopping criterion, and the Q-factor and redundancy are optimized based on the minimum energy-weighted normalized wavelet entropy.Then, the adaptive TQWT decomposition can be achieved in a sparse way and result in subband signals at various wavelet scales.Further, the optimum subband signal which carries transient feature information, is identified using a normalized energy to bandwidth ratio index. Finally, the single branch reconstruction signal from the optimum subband is obtained with transient signatures via inverse TQWT, and the frequency of repetitive transients is detected using Hilbert envelope demodulation. It has been verified via numerical simulation that the proposed adaptive TQWT filter based feature extraction method can adaptively select TQWT parameters and the optimum subband for repetitive transient detection without prior knowledge. The proposed method is also applied to faulty bearing vibration signals and its effectiveness is validated.

Fault Feeder Identification in Non-effectively Grounded Distribution Network with Secondary Earth Fault

Secondary earth faults occur frequently in power distribution networks under harsh weather conditions.Owing to its characteristics,a secondary earth fault is typically hidden within the transient of the first fault.Therefore,most researchers tend to focus on a feeder with single fault while disregarding secondary faults.This paper presents a fault feeder identification method that considers secondary earth faults in a non-effectively grounded distribution network.First,the wavelet singular entropy method is used to detect a secondary fault event.This method can identify the moment at which a secondary fault occurs.The zero-sequence current data can be categorized into two fault stages.The first and second fault stages correspond to the first and secondary faults,respectively.Subsequently,a similarity matrix containing the time-frequency transient information of the zero-sequence current at the two fault stages is defined to identify the fault feeders.Finally,to confirm the effectiveness and reliability of the proposed method,we conduct simulation experiments and an adaptability analysis based on an electromagnetic transient program.

Pressure Analysis of the Initial Process of Diffusion Combustion Surge in a 350 kW Gas Boiler

In order to meet the increasingly stringent requirements for nitrogen oxides(NOx)emissions from gas boilers,flue gas recirculation(FGR)technology is commonly used to achieve ultra-low NOx emissions.However,under some ultra-low NOx combustion conditions with FGR,a surge phenomenon occurs in the boiler,which causes a flameout and should be avoided.In this study,the diffusion combustion surge of gas boiler with a rated power of 350 k W and equipped with FGR device was investigated.Pressure characteristic analysis results of the initial process of combustion surge showed that the high-frequency component of pressure is closely related to combustion stability and its change can provide reference for the occurrence of surge.Besides,the initial process of surge was analyzed by wavelet packet entropy method.Results indicated that the wavelet packet entropy of pressure signals could effectively reflect the stability of combustion in the furnace,and it could also be used to study the occurrence of surge.