Wavelet Packet Entropy Research Articles

A novel chatter detection method in micro-milling process using wavelet packet entropy

A novel chatter detection method in micro-milling process using wavelet packet entropy

Fault diagnosis of analogue circuits based on artificial intelligence algorithms

Abstract The fault diagnosis problem of analog circuits has been paid more and more attention, and the realization of circuit fault feature extraction and pattern classification are two of the key problems. This paper first combines wavelet packet and energy entropy to design a fault feature extraction method based on wavelet packet entropy to solve the problem of analog circuit fault feature extraction. Secondly, the principle of SVM and particle swarm optimization algorithm are combined to design the fault diagnosis process of analog circuits based on an artificial intelligence algorithm. Finally, take the sallen-key circuit as an example to analyze the effectiveness of the wavelet packet entropy algorithm for fault feature extraction and analyze the effectiveness of this paper’s method based on the analog circuit of Wen’s bridge oscillation circuit. The results show that after wavelet packet entropy extraction of the feature vector values is less than 0.001, and the accuracy of the extraction is more than 0.98, the best parameters of the optimization is (182.4, 0.05), the false alarm rate of the fault diagnostic method is 0, the misdiagnosis rate is 0.08, the omission rate is 0, and the correctness rate of the diagnosis of the fault is 0.92. Based on this research is able to carry out the fault diagnosis of the analog circuit.

Voiceprint Recognition under Cross-Scenario Conditions Using Perceptual Wavelet Packet Entropy-Guided Efficient-Channel-Attention–Res2Net–Time-Delay-Neural-Network Model

(1) Background: Voiceprint recognition technology uses individual vocal characteristics for identity authentication and faces many challenges in cross-scenario applications. The sound environment, device characteristics, and recording conditions in different scenarios cause changes in sound features, which, in turn, affect the accuracy of voiceprint recognition. (2) Methods: Based on the latest trends in deep learning, this paper uses the perceptual wavelet packet entropy (PWPE) method to extract the basic voiceprint features of the speaker before using the efficient channel attention (ECA) block and the Res2Net block to extract deep features. The PWPE block removes the effect of environmental noise on voiceprint features, so the perceptual wavelet packet entropy-guided ECA–Res2Net–Time-Delay-Neural-Network (PWPE-ECA-Res2Net-TDNN) model shows an excellent robustness. The ECA-Res2Net-TDNN block uses temporal statistical pooling with a multi-head attention mechanism to weight frame-level audio features, resulting in a weighted average of the final representation of the speech-level feature vectors. The sub-center ArcFace loss function is used to enhance intra-class compactness and inter-class differences, avoiding classification via output value alone like the softmax loss function. Based on the aforementioned elements, the PWPE-ECA-Res2Net-TDNN model for speaker recognition is designed to extract speaker feature embeddings more efficiently in cross-scenario applications. (3) Conclusions: The experimental results demonstrate that, compared to the ECAPA-TDNN model using MFCC features, the PWPE-based ECAPA-TDNN model performs better in terms of cross-scene recognition accuracy, exhibiting a stronger robustness and better noise resistance. Furthermore, the model maintains a relatively short recognition time even under the highest recognition rate conditions. Finally, a set of ablation experiments targeting each module of the proposed model is conducted. The results indicate that each module contributes to an improvement in the recognition performance.

Electroencephalogram-based objective assessment of cognitive function level associated with age-related hearing loss.

Age-Related Hearing Loss (ARHL) is a common problem in aging. Numerous longitudinal cohort studies have revealed that ARHL is closely related to cognitive function, leading to a significant risk of cognitive decline and dementia. This risk gradually increases with the severity of hearing loss. We designed dual auditory Oddball and cognitive task paradigms for the ARHL subjects, then obtained the Montreal Cognitive Assessment (MoCA) scale evaluation results for all the subjects. Multi-dimensional EEG characteristics helped explore potential biomarkers to evaluate the cognitive level of the ARHL group, having a significantly lower P300 peak amplitude coupled with a prolonged latency. Moreover, visual memory, auditory memory, and logical calculation were investigated during the cognitive task paradigm. In the ARHL groups, the alpha-to-beta rhythm energy ratio in the visual and auditory memory retention period and the wavelet packet entropy value within the logical calculation period were significantly reduced. Correlation analysis between the above specificity indicators and the subjective scale results of the ARHL group revealed that the auditory P300 component characteristics could assess attention resources and information processing speed. The alpha and beta rhythm energy ratio and wavelet packet entropy can become potential indicators to determine working memory and logical cognitive computation-related cognitive ability.

Motor imagery classification method based on relative wavelet packet entropy brain network and improved lasso.

Motor imagery (MI) electroencephalogram (EEG) signals have a low signal-to-noise ratio, which brings challenges in feature extraction and feature selection with high classification accuracy. In this study, we proposed an approach that combined an improved lasso with relief-f to extract the wavelet packet entropy features and the topological features of the brain function network. For signal denoising and channel filtering, raw MI EEG was filtered based on an R2 map, and then the wavelet soft threshold and one-to-one multi-class score common spatial pattern algorithms were used. Subsequently, the relative wavelet packet entropy and corresponding topological features of the brain network were extracted. After feature fusion, mutcorLasso and the relief-f method were applied for feature selection, followed by three classifiers and an ensemble classifier, respectively. The experiments were conducted on two public EEG datasets (BCI Competition III dataset IIIa and BCI Competition IV dataset IIa) to verify this proposed method. The results showed that the brain network topology features and feature selection methods can retain the information of EEG more effectively and reduce the computational complexity, and the average classification accuracy for both public datasets was above 90%; hence, this algorithms is suitable in MI-BCI and has potential applications in rehabilitation and other fields.

Research on fault diagnosis of a railway point machine based on a multi-entropy feature extraction method and support vector machine

Abstract A new fault diagnosis method is proposed to effectively extract the fault features of the sound signal of typical faults of ZDJ9 railway point machines. A multi-entropy feature extraction method is proposed by combing multi-scale permutation entropy and wavelet packet entropy. Firstly, empirical mode decomposition is performed on sound signals to obtain modal components with different time scales. Then, multi-scale permutation entropy is extracted from these components. Meanwhile, the wavelet packet entropy of the sound signals of these sensitive nodes is obtained by analysing the reconstructed signals of the last layer nodes. Since the multi-scale permutation entropy and the wavelet packet entropy can distinguish the subtle features of the signal, the subtle features of the original signal can be obtained as the feature vector of the ZDJ9 railway point machine in different states. To reduce the redundant information among the high-dimensional features, ReliefF is utilized. Finally, a support vector machine (SVM) is used to judge the fault type of a ZDJ9 railway point machine.

Research on the Recognition of Various Muscle Fatigue States in Resistance Strength Training.

Instantly and accurately identifying the state of dynamic muscle fatigue in resistance training can help fitness trainers to build a more scientific and reasonable training program. By investigating the isokinetic flexion and extension strength training of the knee joint, this paper tried to extract surface electromyogram (sEMG) features and establish recognition models to classify muscle states of the target muscles in the isokinetic strength training of the knee joint. First, an experiment was carried out to collect the sEMG signals of the target muscles. Second, two nonlinear dynamic indexes, wavelet packet entropy (WPE) and power spectrum entropy (PSE), were extracted from the obtained sEMG signals to verify the feasibility of characterizing muscle fatigue. Third, a convolutional neural network (CNN) recognition model was constructed and trained with the obtained sEMG experimental data to enable the extraction and recognition of EMG deep features. Finally, the CNN recognition model was compared with multiple support vector machines (Multi-SVM) and multiple linear discriminant analysis (Multi-LDA). The results showed that the CNN model had a better classification accuracy. The overall recognition accuracy of the CNN model applied to the test data (91.38%) was higher than that of the other two models, which verified that the CNN dynamic fatigue recognition model based on subjective and objective information feedback had better recognition performance. Furthermore, training on a larger dataset could further improve the recognition accuracy of the CNN recognition model.

Exercise Condition Sensing in Smart Leg Extension Machine.

Skeletal muscles require fitness and rehsabilitation exercises to develop. This paper presents a method to observe and evaluate the conditions of muscle extension. Based on theories about the muscles and factors that affect them during leg contraction, an electromyography (EMG) sensor was used to capture EMG signals. The signals were applied by signal processing with the wavelet packet entropy method. Not only did the experiment follow fitness rules to obtain correct EMG signal of leg extension, but the combination of inertial measurement unit (IMU) sensor also verified the muscle state to distinguish the muscle between non-fatigue and fatigue. The results show the EMG changing in the non-fatigue, fatigue, and calf muscle conditions. Additionally, we created algorithms that can successfully sense a user’s muscle conditions during exercise in a leg extension machine, and an evaluation of condition sensing was also conducted. This study provides proof of concept that EMG signals for the sensing of muscle fatigue. Therefore, muscle conditions can be further monitored in exercise or rehabilitation exercise. With these results and experiences, the sensing methods can be extended to other smart exercise machines in the future.

Model-Free Adaptive Sliding Mode Control-Based Active Chatter Suppression by Spindle Speed Variation

Abstract This paper presents a novel model-free adaptive sliding mode control (MFA-SMC) algorithm, which is employed to actively adjust the amplitude and frequency of spindle speed variation (SSV) for chatter suppression in turning. The SSV technique is effective for mitigating regenerative chatter, which however is not widely applied due to its poor adaptability to time-varying characteristics of machining dynamics and cutting conditions. The online adjustment of SSV parameters has been reported in previous works, whereas the proportional integral differential (PID)-type controller used cannot compensate for the interactions when abruptly changing the reference input and the parameter tuning procedure consumes much time. The proposed method integrates the model-free adaptive control (MFAC) with the global sliding mode control (GSMC). The method is data-driven and only dependent on the measured input/output data of the cutting process in this paper, which are the normalized wavelet packet entropy and SSV parameters, respectively. The bounded-input bounded-output stability and the tracking error convergence of the proposed control algorithm are guaranteed by theoretical analysis. The effectiveness of the proposed chatter suppression method is investigated with numerical simulations. Finally, experimental results demonstrate that chatter vibration under different cutting conditions can be effectively mitigated by the proposed method.

A Study of Subliminal Emotion Classification Based on Entropy Features

Electroencephalogram (EEG) has been widely utilized in emotion recognition. Psychologists have found that emotions can be divided into conscious emotion and unconscious emotion. In this article, we explore to classify subliminal emotions (happiness and anger) with EEG signals elicited by subliminal face stimulation, that is to select appropriate features to classify subliminal emotions. First, multi-scale sample entropy (MSpEn), wavelet packet energy (Ei), and wavelet packet entropy (WpEn) of EEG signals are extracted. Then, these features are fed into the decision tree and improved random forest, respectively. The classification accuracy with Ei and WpEn is higher than MSpEn, which shows that Ei and WpEn can be used as effective features to classify subliminal emotions. We compared the classification results of different features combined with the decision tree algorithm and the improved random forest algorithm. The experimental results indicate that the improved random forest algorithm attains the best classification accuracy for subliminal emotions. Finally, subliminal emotions and physiological proof of subliminal affective priming effect are discussed.

Fuzzy diagnostics for gearbox failures based on induction motor current and wavelet entropy

In this work, a strategy is proposed for the automatic diagnosis of failures in gearboxes using current signals from an induction motor. The stator currents were represented by the extended Park vector approach technique and decomposed by the wavelet packet transform. The calculation of the wavelet packet entropy promoted the distinction between broken tooth failures and the levels of severity of surface wear. The entropies of two wavelet details were used as inputs for a fuzzy inference for automatic classification of the gearbox condition. The experimental results presented a high rate of correctness in the fuzzy diagnosis, confirming the efficiency of the strategy for high rotation (60 Hz) and low rotation (20 Hz). The strategy presents simplicities related to the practical implementation and reduction of the amount of data analyzed.

Multi-variable classification model for valve internal leakage based on acoustic emission time–frequency domain characteristics and random forest

To use acoustic-emission technology to detect leaks inside valves, the necessary first step is to model the valve-internal-leakage acoustic-emission signal (VILAES) mathematically. A multi-variable classification model that relates the VILAES characteristics and the leakage rate under varying pressure is built by combining time-frequency domain characteristics and the random-forest method. A Butterworth bandpass filter is used to preprocess the VILAES from a liquid medium, and the best frequency band for filtering is determined as being 140 kHz-180 kHz. Then, (i) the standard deviation, (ii) root mean square, (iii) wavelet packet entropy, (iv) peak standard-deviation probability density, and (v) spectrum area are calculated as the VILAES characteristics, and six parameters-the pressure and the five VILAES characteristics-are used as the inputs for the random-forest classification model. Analysis shows that the five VILAES characteristics increase with an increase in the leakage rate. The multi-variable classification model is established by random forest to determine whether the valve leakage is small, medium, or large. The random forest uses many decision trees to predict the final result. For the same experimental data, the accuracy and operating time of the multi-variable classification model are compared with those of a support-vector-machine classification method for the bandpass and wavelet packet filtering preprocessing methods. The results show that the modeling method based on the combination of time-frequency characteristics and random forest has shorter operating time and higher accuracy.

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 in severe cases, and seriously affects the safe and stable operation of the boiler. In this study, the diffusion combustion surge of gas boiler with a rated power of 350 kW 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.

Beat Effect in Machining Chatter: Analysis and Detection

Abstract In machining processes, regenerative chatter is an unstable vibration which adversely affects surface finish, cutting tools, and spindle bearings. Under some cutting conditions, the beat effect, an interference pattern between two periodical vibrations of slightly different frequencies, has been a common phenomenon where the amplitude of chatter vibration tends to increase and decrease periodically. Until now, few studies have been conducted to analyze the beat effect in machining chatter. On the other hand, researchers have developed various chatter detection methods with the objective to timely avoid detrimental effects induced by chatter. However, none of the existing chatter detection methods in the literature has ever considered the beat effect. The neglect of the beat effect will adversely affect the effectiveness of these methods and even result in false alarms. In this paper, the significance level and the mechanism of the beat effect in turning chatter are analyzed by time domain simulation. Afterward, a multiscale wavelet packet entropy (MWPE) method is proposed to detect machining chatter regardless of the occurrence of the beat effect. The determination strategy of the scale factor in the MWPE is presented based on the beat period, whose relationship with the damping ratio and spindle speed is derived analytically in orthogonal turning scenarios. Finally, machining tests are conducted to verify the feasibility and effectiveness of the proposed chatter detection method with respect to the presence and absence of the beat effect.

Research on motor imagery EEG signal processing algorithm

To address the difficulty of extracting features from motor imagery EEG signals and the low classification accuracy, a method for feature extraction and classification of multiple types of motor imaging EEG signals based on wavelet and support vector machine (SVM) is proposed. This work first calculated the power of motor imagery EEG data and selected the scale of wavelet packet by theoretical analysis. Then, wavelet packet decomposition on power was discussed, wavelet packet entropy (WPE) of power was calculated, and wavelet packet entropy interpolation of leads C3, C4 was extracted, which composed the feature vector. Finally, this work fed the feature vector as the classifier input into a support vector machine to achieve classification. From Graz’s EEG data from the international BCI competition in 2003, the highest accuracy rate of classification was 97.56%. The feature vectors of this algorithm are low in dimension, are small in data size, and have high classification accuracy, which provides a reference method for the task of EEG feature extraction and classification.

Chatter Detection With Beat Effect Based on Beat Frequency Estimation

Machining chatter is an unstable vibration that often results in poor surface quality, low productivity, and degraded machine tool life. Chatter detection is an important approach to timely avoid detrimental effects on the workpiece and machine tools. However, most chatter detection methods will lose effectiveness and even yield false alarms, when chatter is accompanied by the beat effect. The beat effect is a common phenomenon in the machining process, which results in severely modulated amplitude of chatter. In this article, the variable-scale wavelet packet entropy (VSWPE) is proposed to detect chatter with the beat effect based on beat frequency estimation. First, an optimal demodulation technique is presented to extract the chatter vibration component and its modulated instantaneous amplitude (IA) from measured signals contaminated with noise and periodic interference. Afterward, the beat frequency is estimated from the harmonically distorted IA by an interpolated discrete Fourier transform (DFT). Finally, the VSWPE is calculated for chatter detection at a variable scale that is adaptively computed by the beat frequency. Numerical simulations show that the beat frequency can be accurately estimated with computational efficiency. Moreover, machining tests under different cutting conditions demonstrate that the proposed chatter detection method can effectively detect chatter with the beat effect. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Automatic online chatter detection is crucial in order to allow operators to timely interfere with the process and avoid detrimental effects caused by chatter. However, the practical machining process is considerably complex especially for unstable scenarios, where the beat effect is likely to occur simultaneously. Traditional chatter detection methods neglect the presence of the beat effect, and they will give misleading results and even false alarms when the beat effect is present. This article seeks to accurately detect chatter with and without the beat effect in a unified framework. The proposed solution can be integrated into the machine tool system, hence, to enhance the productivity, reliability, and precision of the machining process.

Emotional State Recognition from Peripheral Physiological Signals Using Fused Nonlinear Features and Team-Collaboration Identification Strategy.

Emotion recognition realizing human inner perception has a very important application prospect in human-computer interaction. In order to improve the accuracy of emotion recognition, a novel method combining fused nonlinear features and team-collaboration identification strategy was proposed for emotion recognition using physiological signals. Four nonlinear features, namely approximate entropy (ApEn), sample entropy (SaEn), fuzzy entropy (FuEn) and wavelet packet entropy (WpEn) are employed to reflect emotional states deeply with each type of physiological signal. Then the features of different physiological signals are fused to represent the emotional states from multiple perspectives. Each classifier has its own advantages and disadvantages. In order to make full use of the advantages of other classifiers and avoid the limitation of single classifier, the team-collaboration model is built and the team-collaboration decision-making mechanism is designed according to the proposed team-collaboration identification strategy which is based on the fusion of support vector machine (SVM), decision tree (DT) and extreme learning machine (ELM). Through analysis, SVM is selected as the main classifier with DT and ELM as auxiliary classifiers. According to the designed decision-making mechanism, the proposed team-collaboration identification strategy can effectively employ different classification methods to make decision based on the characteristics of the samples through SVM classification. For samples which are easy to be identified by SVM, SVM directly determines the identification results, whereas SVM-DT-ELM collaboratively determines the identification results, which can effectively utilize the characteristics of each classifier and improve the classification accuracy. The effectiveness and universality of the proposed method are verified by Augsburg database and database for emotion analysis using physiological (DEAP) signals. The experimental results uniformly indicated that the proposed method combining fused nonlinear features and team-collaboration identification strategy presents better performance than the existing methods.

The Fault Diagnosis of Rolling Bearings Based on Wavelet Packet Entropy and Affinity Propagation Clustering

In this paper, a fault diagnosis method based on wavelet packet entropy and affine propagation clustering method is proposed for fault diagnosis of rolling bearings. The features of fault bearings are extracted by wavelet packet entropy method, and affine propagation algorithm is used to cluster the features to realize the fault diagnosis of rolling bearings. The bearing fault data of case Western Reserve University are used to verify the proposed method, and the results show that the diagnosis of rolling bearings can be achieved by this method effectively.

Entropy-Based Local Irregularity Detection for High-Speed Railway Catenaries With Frequent Inspections

The condition-based maintenance of high-speed railway catenary is an important task to ensure the continuous availability of train power supply. To improve the condition monitoring of catenary, this paper presents a novel scheme to detect catenary local irregularities using pantograph head acceleration measurements. First, a series of experimental inspections is carried out in a section of the Beijing-Guangzhou high-speed line in China. The time intervals between the inspections are shortened from the traditional six months to about 40 days, which enables monitoring the short-term degradation of local irregularities. Then, based on the wavelet packet entropy, an approach is proposed to detect local irregularities with different scales in length. Criteria for identifying and verifying the local irregularities are established based on the gradient and repeatability of entropy from multiple measurements. Results from the experimental inspections show that different scales of local irregularities can be detected by the proposed scheme. By using frequent inspections, local irregularities can be effectively verified after about seven inspections. The spatial distribution of local irregularities is found to be closely related to the catenary structure. These findings provide valuable information to deploy the scheme for a railway network.

Comparison of Multilevel Wavelet Packet Entropy using Various Entropy Measurement for Lung Sound Classification

Wavelet Entropy (WE) is one of the entropy measurement methods by means of the discrete wavelet transform (DWT) subband. Some of the developments of WE are wavelet packet entropy (WPE), wavelet time entropy. WPE has several variations such as the Shannon entropy calculation on each subband of WPD that produces 2N entropy or WPE, which yields an entropy value. One of the WPE improvements is multilevel wavelet packet entropy (MWPE), which yields entropy value as much as N decomposition level. In a previous research, MWPE was calculated using Shannon method; hence, in this research MWPE calculation was done using Renyi and Tsallis method. The results showed that MWPE using Shannon calculation could yield the highest accuracy of 97.98% for N = 4 decomposition level. On the other hand, MWPE using Renyi entropy yielded the highest accuracy of 93.94% and the one using Tsallis entropy yielded 57.58% accuracy. Here, the test was performed on five lung sound data classes using multilayer perceptron as the classifier.