Search

Feature extraction and classification is a difficult area in motor imagery electroencephalogram (EEG) signal processing. In order to improve the classification accuracy of EEG signals, both a feature extraction method based on the combination of LMD-CSP and a classification algorithm based on the fusion of PSO-SVM are proposed. Firstly, the extended informax ICA algorithm is used to denoise the signal and reduce the influence of noise on the signal. Then, the pre-processed EEG signals are decomposed into multiple Product Function (PF) components by Local Mean Decomposition (LMD), and the most discriminative PF component is selected. Next, feature extraction is carried out from the selected PF components using the Common Space Pattern (CSP). Finally, the obtained features are input into a Support Vector Machine (SVM) classifier improved by Particle Swarm Optimization (PSO) for classification recognition. The experimental results show that compared with the traditional CSP-SVM method, CapsNet method, WPT-CSP+CNN method, FDCSP-SVM method, and EMD-CNN method, the classification accuracy of the proposed method is increased by 26.94 %, 14.9 %, 13.34 %, 8.34 % and 4.04 %, respectively. This further proves the superiority of the proposed method for EEG signal processing technology.

Feature extraction and classification is a difficult area in motor imagery electroencephalogram (EEG) signal processing. In order to improve the classification accuracy of EEG signals, both a feature extraction method based on the combination of LMD-CSP and a classification algorithm based on the fusion of PSO-SVM are proposed. Firstly, the extended informax ICA algorithm is used to denoise the signal and reduce the influence of noise on the signal. Then, the pre-processed EEG signals are decomposed into multiple Product Function (PF) components by Local Mean Decomposition (LMD), and the most discriminative PF component is selected. Next, feature extraction is carried out from the selected PF components using the Common Space Pattern (CSP). Finally, the obtained features are input into a Support Vector Machine (SVM) classifier improved by Particle Swarm Optimization (PSO) for classification recognition. The experimental results show that compared with the traditional CSP-SVM method, CapsNet method, WPT-CSP+CNN method, FDCSP-SVM method, and EMD-CNN method, the classification accuracy of the proposed method is increased by 26.94 %, 14.9 %, 13.34 %, 8.34 % and 4.04 %, respectively. This further proves the superiority of the proposed method for EEG signal processing technology. [ABSTRACT FROM AUTHOR]

Objective: This paper describes an air compressor fault diagnosis method based on audio signals and applied to one faulty and one healthy condition of rolling bearing considering uni-directional microphone along with a single NI 9234 Data Acquisition (DAQ) hardware unit having multiple ports, a NI 9172 USB interface, and a Lab-VIEW based Data acquisition interface. Methodology: Acquired non-stationary and non-linear bearing fault signals are processed using most recent non-traditional Local Mean Decomposition (LMD) signal processing technique. Further, six statistical indicators (Mean, Variance, RMS, RMA, AMA, and Kurtosis) have been evaluated for feature extraction. Further, four classifying techniques namely: SVM, Naïve Bayes, KNN, and Discriminant have been used for the exploration and classification of the fault features in rolling bearing of an air compressor set-up. Findings: It has been observed that LMD along with Kurtosis and SVM machine learning approach is quite accurate for processing and monitoring in situ rolling bearing fault features in air compressor set-up. [ABSTRACT FROM AUTHOR]

To solve the problem of large interference of shearer rocker arm vibration signal and difficulty in feature selection, and recognize accurately the cutting status of shearer, a novel pattern identification method based on Symmetrized Dot Pattern (SDP), Local Mean Decomposition (LMD) and Multi-Scale Convolution Kernel Deep Convolutional Neural Network (MCK-DCNN) is presented. Firstly, the vibration signal of shearer rocker arm is decomposed by LMD to get multiple product functions (PFs). The previous three PFs are transformed into SDP images with different features by SDP method, which are input into MCK-DCNN model to automatically extract features and identify shearer cutting status. The method can achieve the classification rate of 97.9%, which is superior to 1D_CNN and LeNet. The comparison result indicates that the method can provide technical support for improving the automatic coal cutting performance of the shearer. [ABSTRACT FROM AUTHOR]

For the sake of deriving the signature frequencies of the composite malfunctions of broken and worn teeth of gearbox, the essay raised a method on account of local mean decomposition and Hilbert demodulation to diagnose gearbox composite fault. The local mean decomposition translates a complicated multi-component AM-FM signal into several PF elements with certain physical significance. Every PF component can be approximately regarded as a simplex component AM-FM signal. Using correlation coefficient method, the Hilbert envelope demodulation spectrum is analyzed by selecting the PF component which is strongly relevant to the incipient composite malfunction signal, and the malfunction signature frequency is identified from the demodulation spectrum. Through analyzing the emulation signal and the vibration signal of the actual gear box broken-wear complex fault, and compared with EMD, it is shown that the means can effectually discern the malfunction characteristic frequency in the composite fault signal. [ABSTRACT FROM AUTHOR]

This paper proposed a hybrid feature extraction algorithm based on local mean decomposition (LMD), which has better solved the existing problems of low classification performance and adaptability limitation. LMD is employed to decompose the electroencephalogram (EEG) signal into multiple components, and then, the hybrid features based on instantaneous energy, fuzzy entropy, and mathematical morphological features are extracted on specific components, and the optimal feature combination is selected by analysis of variance (ANOVA). Finally, the classification result is output by the linear discriminant analysis (LDA) classifier. The results show that the maximum accuracy of the subjects in Data Set III of BCI‐II by the method in this paper is 92.14%, and the maximum mutual information value is 0.8. The number of novel features used in this paper is small, and the complexity of the algorithm is reduced. It can adaptively select effective features according to individual differences and has good robustness. [ABSTRACT FROM AUTHOR]

The characteristics of non-smoothness and uncertainty of gearbox fault vibration signal lead to the low accuracy of gearbox fault diagnosis. To address this problem, a gearbox fault diagnosis method based on local mean decomposition (LMD) cloud model feature extraction combined with particle swarm optimization (PSO) kernel extreme learning machine (KELM) is proposed. Firstly, the fault vibration signal is decomposed by LMD to obtain several PF components, and the PF components with higher correlation are screened out using the correlation coefficient principle. Secondly, the screened PF components are input into the cloud model, and the feature vectors are extracted using the inverse cloud generator and input into PSO-KELM for fault diagnosis. Finally, the performance of the method is analyzed using the measured data of the QPZZ-Ⅱ test-bed gearbox. The results show that the recognition accuracy of the method is 97.65%, and compared with various methods this method has the best recognition performance.

Streamflow estimation is important in hydrology, especially in drought and flood-prone areas. Accurate estimation of streamflow values is crucial for the sustainable management of water resources, the development of early warning systems for disasters, and for various applications such as irrigation, hydropower production, dam sizing, and siltation management. This study developed the ANN algorithm by optimizing with an artificial bee colony (ABC). Then, the ABC-ANN hybrid model, which was established, was combined with different signal decomposition techniques to evaluate its performance in streamflow estimation in the East Black Sea Region, Türkiye. For this purpose, the lagged streamflow values were divided into subcomponents using the local mean decomposition (LMD) with the empirical envelope and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) signal decomposition techniques presented to the ABC-ANN algorithm. Thus, the success of the novel hybrid LMD-ABC-ANN and CEEMDAN-ABC-ANN approaches in streamflow prediction was evaluated. The outputs are reliable strategies and resources for water resource planners and policymakers. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The accuracy and stability of the envelope estimation function are enduring issues throughout the research process of LMD. This paper presents double interpolation and mutation interval reconstruction local mean decomposition (DIMIRLMD) to improve the stability of the demodulation process and the accuracy of PF components. DIMIRLMD first proposes a mutation interval reconstruction envelope algorithm using extreme symmetry points to suppress the demodulation mutation phenomenon, which disturbs the stability of the demodulation process, and then selects the optimal PF component from a double interpolation PF component library based on the index of orthogonality (IO) for a better hierarchical property. DIMIRLMD was employed to analyze the simulation signal and vibration signal of a reciprocating compressor in an oversized bearing clearance state, and the results illustrate its performances are more excellent than those of three other LMD methods. Furthermore, the envelope frequency spectrum obtained from the proposed LMD presents a clear double rotation fault frequency and lower noise disturbance. [ABSTRACT FROM AUTHOR]

The nonlinear, non-stationary, and random characteristics of series arc current in low-voltage AC systems bring great difficulties to fault feature extraction and detection. Meanwhile, mode decomposition methods based on envelope analysis show a good effect in non-stationary signal analysis. Considering the excellent effect of the mode decomposition methods and the practical difficulties of series arc fault detection, six mature mode decomposition methods, such as empirical mode decomposition (EMD), were systematically combed, and the applicability and effectiveness of these methods in arc fault signal analysis and feature extraction were thoroughly analyzed. Then, through the decomposition experiments and feature calculation experiments of measured arc currents, the advantages and disadvantages of mode decomposition methods in arc current feature extraction and fault detection were discussed from different perspectives. Finally, future research direction of mode decomposition were prospected. [ABSTRACT FROM AUTHOR]

In view of the problems of poor discrimination of fault feature vectors extracted in the process of fault diagnosis of planetary gearboxes and insufficient diagnosis success rate, a method based on Local Mean Decomposition（LMD） permutation entropy and BP neural network is proposed. Through the LMD decomposition of the original signal, the PF components containing the main information are obtained, and the permutation entropy values are calculated to construct the feature vector. The extracted feature vectors are used to train the BP neural network and complete the failure pattern recognition test. Taking the EMD permutation entropy method and the non-dimensional analysis method as the comparison groups, the experiment proves that the feature vectors extracted from different working conditions with this method are more distinguishable, and the fault diagnosis effect is better. Moreover, this method shows better comprehensive performance when the number of training groups changes.

Aiming at the problem that it is difficult to identify the composite fault characteristics of gearboxes in the case of small samples, a local mean decomposition(LMD) gearbox fault diagnosis method based on energy entropy is proposed. The LMD method is used to process the gearbox vibration signal to obtain several PF components；the dispersion value of component energy in the frequency domain is calculated using the uneven distribution of gearbox vibration signals in different states, which is the LMD energy entropy; the gearbox fault classification is carried out through the distribution of LMD energy entropy in different states. The experimental results show that in the case of small samples, the feature extraction and fault diagnosis of gearbox fault types can be accurately carried out based on the LMD energy entropy method, which also shows the superiority of this method in gearbox fault diagnosis.

The strong striping and high-frequency noise existed in Gravity Recovery and Climate Experiment (GRACE) solutions drowned the real geophysical signals, which need other signal extraction methods. Considering the advantages of local mean decomposition (LMD) in extracting geophysical signals from noisy time series, we adopt it to filter the noise and estimate the terrestrial water storage (TWS) changes over 25 global main river basins from the time series of 14-year (2002.04~2016.08) Release 06 (RL06) monthly gravity field models provided by Center for Space Research (CSR), together with the empirical mode decomposition (EMD) as a comparison. To evaluate the efficiency of eliminating noise by LMD and EMD, the ratios of the latitude weighted RMS over the land and ocean signals are adopted. The results show that all RMS ratios of land relative to ocean signals derived by LMD are higher than EMD with the mean values 3.4458 and 3.3302, respectively. Moreover, relative to the Global Land Data Assimilation System (GLDAS) Noah model, the extracted TWS changes by LMD approach have smaller root mean squared errors than EMD over 25 global river basins. Therefore, it is reasonable to conclude that LMD approach outperforms EMD in extracting TWS changes and filtering out the strong noise existed in GRACE monthly gravity field solutions. [ABSTRACT FROM AUTHOR]

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Tool chatter is one of such occurrences that limits MRR in a number of industries. In the current research, a method to boost output while lowering clatter during turning operations on a CNC lathe has been presented. A microphone is used to record the vibration signals generated during turning tests. The denoised signals are analysed using local mean decomposition (LMD). Disruptions and undesirable embedded ambient noise are removed using wavelet denoising (WD). The product functions that expose chatter information are chosen using these decomposed signals. To recreate the real-time chatter, these well-known PFs are used to reconstruct the signal. A consistent range of turning parameters for greater productivity has been created using the Grey relational analysis (GRA) prediction technique. The measured Chatter Index value has been found to denote steady turning, unstable, and moderate chatter circumstances. In order to confirm the validity of the presented methodology, several tests have been conducted. [ABSTRACT FROM AUTHOR]

In order to solve the problem of single-phase ground fault, the characteristics of fault are not obvious when the transition resistance is high, and it is difficult to accurately identify the fault line in the case of noise interference. A fault line selection method based on complementary ensemble empirical mode decomposition (CEEMD), local mean decomposition (LMD) and stochastic configuration network (SCN) was proposed. First, the zero-order currents were decomposed by using CEEMD and LMD, the energy entropy of its corresponding components were computed separately, then the solved energy entropy was combined to form a combined eigenvector, the data was augmented by using the synthetic minority oversampling technique (SMOTE) algorithm, data was divided into a training set and a test set, and the SCN network with strong generalization ability was used to establish the distribution network fault line selection model. The simulation results show that the line selection method can effectively select the proper fault line under different fault distances, different grounding resistance, and different initial fault angles. This method has strong tolerance to high resistance and a relatively good anti-noise capability. [ABSTRACT FROM AUTHOR]

With the rapid development of science and technology, intelligent teaching has been gradually popularized in the campus, and the change of relevant teaching modes has also been carried out. In the new English teaching, it is necessary to analyze the students' psychological behavior. In order to get accurate results, the research captures the students' behavior as a behavior sequence, and uses the improved combined kernel support vector machine to extract features on the basis of approximate entropy and local mean decomposition. At the same time, it is compared with the traditional support vector machine, the traditional least square vector machine and the back-propagation neural network algorithm. The experimental results show that the improved algorithm has higher accuracy, recall and accuracy than the other three algorithms. The overall accuracy of the improved algorithm is 82.53%, the highest accuracy is 90.12%, the overall recall is 58.64% and the overall precision is 86.92%. The experimental results show that the improved algorithm has a significant improvement in performance, and can be applied to the extraction of students' psychological characteristics. Therefore, the algorithm can be used in conventional blended English teaching, which is convenient for teachers to carry out English teaching more efficiently. [ABSTRACT FROM AUTHOR]

Landslide disasters cause serious property losses and casualties every year. Landslide displacement prediction is fundamental for mitigating landslide disasters. Several approaches have been used to predict landslide displacement, yet a more accurate and reliable displacement prediction still has a poor understanding of landslide early warning systems for landslide mitigation, due to limited data and mutational displacements. To boost the robustness and accuracy of landslide displacement prediction, this paper assembled a new hybrid model containing the local mean decomposition (LMD), innovations state space models for exponential smoothing (ETS), and the temporal convolutional network (TCN). The proposed model, which is based on over 10 years of long-term time series monitoring GPS data, was tested on the selected case—stepwise Baijiabao landslide in the Three Gorges Reservoir area of China (TGRA) was tested by the proposed model. The results presented that the LMD–ETS–TCN model has the best performance in comparison with other benchmark models. Compared with autoregressive integrated moving average (ARIMA), support vector regression (SVR), and long short-term memory neural network (LSTM), the accuracy was noticeably improved by an average of 40.9%, 46.2%, and 22.1%, respectively. The robustness and effectiveness of the presented approach are attested, and it has discernible improvements for landslide displacement prediction. [ABSTRACT FROM AUTHOR]

Mortar void is a hidden defect in ballastless slab track difficult to be efficiently identified by traditional detection methods. This paper is dedicated to proposing a new detection method to identify the mortar void position and length using the vehicle response combined with the hybrid convolutional neural network-support vector machine (CNN-SVM) classifier. The vertical wheelset accelerations with different mortar void conditions are collected from a vehicle-track coupled dynamics simulation model. The first components decomposed from wheel-set accelerations by local mean decomposition and their envelopes are utilized as the training data due to their sensitivity to mortar void. To improve the identification precision, the scope descent method is proposed to determine the range influenced by mortar void (IMVR) and samples are labeled according to IMVR. Meanwhile, identification results are post processed based on the mortar void characteristics. The results show that over 90 % mortar void conditions with the length of 0.65 m are detected correctly and the identification has a higher precision with the mortar void length greater than 0.95 m. The proposed technology of mortar void detection using the wheelset accelerations with the hybrid CNN-SVM classifier provides reference for engineering application, which is of great significance to relieve the pressure of health monitoring of railway track. [ABSTRACT FROM AUTHOR]

In this paper, the structure and working principle of four-mass vibration MEMS gyroscope (FMVMG) are introduced, and the working modes of FMVMG are simulated and analyzed. On the basis of this, an improved noise reduction method based on interval local mean decomposition (ILMD) and parabolic tracking time-frequency peak filtering (PTTFPF) is proposed. PTTFPF can resample the signal along a parabolic path and select the optimal filtering trajectory, but there is still a contradiction, choosing a short window length may lead to good signal amplitude retention, but the random noise reduction effect is not good, while choosing a long window length may lead to serious amplitude attenuation, but the random noise reduction effect is better. In order to achieve a better balance between effective signal amplitude preservation and random noise reduction, the ILMD method was used to improve PTTFPF. First, the original signal was decomposed into product functions (PFs) by local mean decomposition (LMD) method, and the sample entropy (SE) of each PF was calculated. The PFs are divided into three different components. Then, short window PTTFPF is used for useful PF and long window PTTFPF is used for mixed PF, noise PF is directly removed. Then the final signal is reconstructed. Finally, the denoised useful PF and mixed PF are reconstructed to obtain the final signal. The proposed ILMD-PTTFPF algorithm was verified by temperature experiments. The results show that the denoising performance of the ILMD-PTTFPF algorithm is better than that of traditional wavelet threshold denoising and Kalman filtering. [ABSTRACT FROM AUTHOR]

Existing non-intrusive load identification methods face with the difficulty of being applied to industrial users whose operation and ON/OFF status are hard to be acquired. Focusing on the above challenge, this paper proposes a non-intrusive identification method of harmonic source loads for industrial users. Utilizing Clarke transform, an equation with respect to voltage and current is formulated to calculate the integrated equivalent impedance, which is then decomposed with the improved complex local mean decomposition (CLMD) and complex fast independent component analysis (C-FastICA) achieving non-intrusive separation of the equivalent impedance signals of individual branches. The separated impedance signals will be used as the basis for load type identification. The proposed method is validated by numerical simulations as well as actual three-phase voltage and current monitoring data. The case study shows that it can effectively identify the types of harmonic source loads while being resistant to noise and impacts of sampling accuracy and diverse load capacities, which obviously demonstrates its practical applicability. [ABSTRACT FROM AUTHOR]

In this paper, a magnetic memory detection device under weak magnetic field excitation is designed to better solve the problem of weak magnetic memory detection signals and susceptibility to other factors. In order to reduce the noise in the original signal, a noise reduction method combining local mean decomposition and wavelet transform (LMDW) is proposed. Pseudo-colour transformation is used to enhance the greyscale image after cubic spline interpolation. Finally, a convolutional neural network (CNN) is designed to identify broken wire. Moreover, compared with the support vector machine (SVM) algorithm, the recognition rate of the CNN is 35.8% higher than that of the SVM under the condition that the allowable error is 0. The experimental results show that the system has high detection sensitivity and remains effective for small defects. The filtering algorithm has a better effect on noise removal and improves the signal-to-noise ratio (SNR). The CNN has good recognition ability to identify defects. [ABSTRACT FROM AUTHOR]

Although some methods of feature extraction for photoplethysmography (PPG) biometric recognition have been extensively studied, effectiveness of local features, time cost of feature extraction, and robust identification for small-scale data remain challenging. To address these issues, we proposed a feature-extraction method of PPG biometrics combining singular value decomposition with local mean decomposition and time-domain parameters. First, we used the singular-value-decomposition method to de-noise the original PPG data. Second, we extracted the local-mean-decomposition-based and time-domain features, which are fused into a concatenated feature. Finally, we combined the concatenated feature with four classifiers for classification and decision-making. Extensive experiments on the three datasets have shown that the waveform of the PPG signal de-noised by singular value decomposition was smoother and more regular, the concatenated feature had strong inter-subject distinguishability and intra-subject similarity, and the concatenated feature combined with a random-forest classifier was the best and could achieve 99.40%, 99.88%, and 99.56% recognition rates on the respective datasets. The method is competitive with several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The observation of celestial light variation data is discontinuous and uneven in the time domain due to weather, equipment, and other factors. And the discontinuous observation data introduce a significant error in the study of the varying light periods. This paper combines the newly developed local mean decomposition(LMD) method and the Lomb–Scargle (LS) algorithm, the most widely used period estimation algorithm for non-uniform time series; a method for analizing the optical variable period of quasars based on the LMD and the LS algorithm is proposed. The principle and the application steps of the method were discussed. The observation data for OJ 287 and 3C 345 at 4.8, 8.0, and 14.5 GHz (radio bands) were collected and analyzed from the University of Michigan UMRAO database. For OJ 287, periods of 12 ± 0.3, 5 ± 0.65, and 2.4 ± 0.01 yr are found in all three bands. There also exist periods of 11 ± 0.9, 5 ± 0.31, and 3 ± 0.28 yr in the three bands for 3C 345. These periods agree with the results of the methods commonly used in some literature. At the same time, some other possible periods are also obtained that can provide references for further research. Results show that estimating the power spectrum is feasible based on LMD+Lomb–Scargle, which provides a new idea for the photoperiod analysis of quasars. [ABSTRACT FROM AUTHOR]

As the wind turbine operates in harsh conditions, numerous of its components are critical and present an important downtime for maintenance. In this paper, we propose a fault diagnosis algorithm to detect and locate the defects affecting the generator rotor and the pinion of the gearbox lay shaft in a real 25 kW wind turbine drivetrain. The induction generator was used as a fault sensor for gear teeth damage. Through the use of the wavelet packet transform, and the local mean decomposition combined with the Fast Fourier Transform, the detection of gear meshing frequency in the stator current reflects teeth faults. Hence, the principal component analysis of the stator current gives a suitable classification for the gearbox states under different working stages. The obtained results have been significant, despite the use of a short duration and a low sampling frequency of the experimental data. • Improved theoretical basis of the AM-FM effect of gear failure on stator current. • Gear fault frequency detection is enhanced by using WPT (+10dB) and LMD (+18dB). • Original algorithm for optimal selection of the level and the node of WPT. • The eigenvalues allows the monitoring of the generator shaft and the gear health. • An algorithm collects the fault features from WPT and LMD to build a fault index. [ABSTRACT FROM AUTHOR]

The accuracy and stability of the envelope estimation function are enduring issues throughout the research process of LMD. This paper presents double interpolation and mutation interval reconstruction local mean decomposition (DIMIRLMD) to improve the stability of the demodulation process and the accuracy of PF components. DIMIRLMD first proposes a mutation interval reconstruction envelope algorithm using extreme symmetry points to suppress the demodulation mutation phenomenon, which disturbs the stability of the demodulation process, and then selects the optimal PF component from a double interpolation PF component library based on the index of orthogonality (IO) for a better hierarchical property. DIMIRLMD was employed to analyze the simulation signal and vibration signal of a reciprocating compressor in an oversized bearing clearance state, and the results illustrate its performances are more excellent than those of three other LMD methods. Furthermore, the envelope frequency spectrum obtained from the proposed LMD presents a clear double rotation fault frequency and lower noise disturbance.

Aiming at the problem of low positioning accuracy caused by modal aliasing and noise interference in DC cable fault location analysis of a VSC-HVDC system, a double-ended fault location method for flexible DC cables based on improved local mean decomposition is proposed. Firstly, the local mean decomposition (LMD) is used to decompose the six-mode voltage signal to obtain the product function (PF) component; then, to overcome the problem that the instantaneous frequency function of the LMD is limited by the extreme value, the Hilbert transform is performed on the PF1 to obtain the instantaneous frequency curve, and the arrival time of the voltage traveling wave head is determined from the mutation information. Finally, the fault distance is obtained by using the principle of double-ended traveling wave fault location. Different fault conditions are simulated, analyzed, and compared with wavelet transform and Hilbert–Huang transform. The results show that the proposed method has a positioning error within 1%, and it is less affected by interference noise and transition resistance. [ABSTRACT FROM AUTHOR]

In landslide displacement prediction, random factors that would affect the performance of prediction are usually ignored by using a time series analysis method. In order to solve this problem, in this paper, a landslide displacement prediction model, the local mean decomposition-bidirectional long short-term memory (LMD-BiLSTM), is proposed based on the time-frequency analysis method. The model uses the local mean decomposition (LMD) algorithm to decompose landslide displacement and obtains several subsequences of landslide displacement with different frequencies. This paper analyzes the internal relationship between the landslide displacement and rainfall, reservoir water level, and landslide state. The maximum information coefficient (MIC) algorithm is used to calculate the intrinsic correlation between each subsequence of landslide displacement and rainfall, reservoir water level, and landslide state. Subsequences of influential factors with high correlation are selected as input variables of the bidirectional long short-term memory (BiLSTM) model to predict each subsequence. Finally, the predicted results of each of the subsequences are added to obtain the final predicted displacement. The proposed LMD-BiLSTM model effectiveness is verified based on the Baishuihe landslide. The prediction results and evaluation indexes show that the model can accurately predict landslide displacement. [ABSTRACT FROM AUTHOR]

Summary: Network has become an indispensable part of public life. To improve network utilization, network performance, network quality, and enhance network security, precise prediction of network traffic is an indispensable method and basis for solving the above problems. In order to accurately predict the network traffic, a novel combination prediction model for network traffic is proposed. In this model, local mean decomposition (LMD), bidirectional long short‐term memory (BiLSTM), and Bayesian optimization algorithm are combined. First, the LMD method decomposes the network traffic time series to obtain several product function (PF) components and a residual by LMD. Then, each PF component and residual is predicted with BiLSTM model. Meanwhile, the Bayesian optimization algorithm is introduced to optimize the hyperparameters of BiLSTM. Finally, the predicted value of each PF component and residual is linearly superimposed to obtain the final predicted value. Through the study of two groups of actual network traffic datasets and compared with a variety of state‐of‐the‐art prediction models, the proposed model has a preferable prediction results by comparison of the results. [ABSTRACT FROM AUTHOR]

In the past few decades, the demand for reliable and robust systems capable of monitoring unmanned aerial vehicles (UAVs) increased significantly due to the security threats from its wide applications. During UAVs surveillance, birds are a typical confuser target. Therefore, discriminating UAVs from birds is critical for successful non-cooperative UAVs surveillance. Micro-Doppler signature (m-DS) reflects the scattering characteristics of micro-motion targets and has been utilized for many radar automatic target recognition (RATR) tasks. In this paper, the authors deploy local mean decomposition (LMD) to separate the m-DS of the micro-motion parts from the body returns of the UAVs and birds. After the separation, rotating parts will be obtained without the interference of the body components, and the m-DS features can also be revealed more clearly, which is conducive to feature extraction. What is more, there are some problems in using m-DS only for target classification. Firstly, extracting only m-DS features makes incomplete use of information in the spectrogram. Secondly, m-DS can be observed only for metal rotor UAVs, or large UAVs when they are closer to the radar. Lastly, m-DS cannot be observed when the size of the birds is small, or when it is gliding. The authors thus propose an algorithm for RATR of UAVs and interfering targets under a new system of L band staring radar. In this algorithm, to make full use of the information in the spectrogram and supplement the information in exceptional situations, m-DS, movement, and energy aggregation features of the target are extracted from the spectrogram. On the benchmark dataset, the proposed algorithm demonstrates a better performance than the state-of-the-art algorithms. More specifically, the equal error rate (EER) proposed is 2.56% lower than the existing methods, which demonstrates the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin University of Science & Technology is the property of Journal of Harbin University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Improper selection of cutting parameters leads to regenerative chatter and loss in productivity. In the present work, a methodology has been proposed to select a proper combination of input cutting parameters for stable turning with improved metal removal rate. Chatter signals generated during the turning of Al6061-T6 have been acquired using a microphone. Stability lobes diagram has been plotted to access the stability regime. Further, to study the effect of feed rate on stability, the recorded signals have been processed using local mean decomposition signal processing technique, followed by the selection of dominating product functions using Fourier transform. The decomposed signals have been used to evaluate the new output parameter, that is, chatter index. Prediction models of chatter index and metal removal rate have been developed. Moreover, these prediction models have been optimized using multi-objective genetic algorithm for ascertaining the optimal range of cutting parameters for stable turning with higher metal removal rate. Finally, obtained stable range has been validated by performing more experiments. [ABSTRACT FROM AUTHOR]

This paper presents a hybrid AC/DC microgrid consisting of multiple distributed energy sources, modeled in MATLAB/Simulink environment that undergoes islanding and non-islanding (symmetrical and unsymmetrical Faults) disturbances. These disturbances result in various changes in circuit parameters (voltage, current, and frequency) and this paper focuses only on disturbed current signals that are extracted from the solar and wind-connected buses. Further to extract rich and useful fault features from the extracted current signals, an adaptive detection technique, local mean decomposition (LMD) is proposed that results in series of product functions (PFs). Various feature extraction indices are used to extract the underlying features of the decomposed PFs that are processed through a deep-stacked random vector functional link network (RVFLN) based auto-encoder (AE) technique for classifying the faults. The effectiveness of the proposed RVFLN based AE technique is evidenced in terms of classification accuracy (CA) and confusion matrix (CM). The performance of the proposed technique has been evaluated through reliability analysis (MAPE, MAE, RMSE, and CM) by comparison with various artificial neural networks under both islanding and non-islanding mode of operation. [ABSTRACT FROM AUTHOR]

To enhance the precision of rolling bearing fault diagnosis, a new rolling bearing fault diagnosis method based on improved local mean decomposition (LMD), compound multi-scale weighted permutation entropy (CMWPE), and support vector machine (SVM) is proposed. Firstly, the improved LMD algorithm is adopted to accomplish the adaptive decomposition of rolling bearing vibration signals. By computing the Pearson correlation coefficients between each component and the initial signal, the components with higher correlation are selected for signal reconstruction to accomplish the mission of noise reduction. Then, a feature extraction approach based on CMWPE is employed to extract corresponding feature parameters from the de-noised signals and construct a multi-scale nonlinear fault feature set with good stability and high recognition. Finally, the high-dimensional fault feature set is input into the SVM to achieve rolling bearing fault diagnosis. The experimental results reveal that the proposed approach can precisely distinguish various fault types of rolling bearings under the same fault degrees. For inner ring failures of different fault degrees, this method also has good identification correctness. Compared with several typical fault diagnosis approaches, the proposed method has a more trustworthy diagnosis result. [ABSTRACT FROM AUTHOR]

The processing and interpretation of microseismic (MS) signals are the basis for obtaining source information of MS events in rock engineering. However, MS signal processing is subjective and time-consuming, in which different strategies have to be empirically adopted to cope with different issues. To facilitate MS signal analysis, this study proposes an entirely data-driven method based on local mean decomposition (LMD), which has been applied in various signal processing fields. Through some numerical experiments, the superiorities (e.g., smaller reconstruction errors and fewer sifting iterations) of the proposed method over other methods are demonstrated, and the proposed method is identified as an effective filtering and frequency analysis tool to process recorded MS signals. Our analysis results show that the proposed method can effectively remove interfering noise existing in MS signals collected from the Lianghekou hydropower station during underground rock excavation. Moreover, the proposed method can be employed to analyze the frequency revolution features of MS signals before and after rock mass failure. In addition, it is found that MS signal frequency migrates to a low-frequency range when approaching rock failure, which can be regarded as an early warning indicator of rock instability. The proposed method is believed to facilitate MS monitoring and offer a new clue to conduct MS signal processing and interpretation. [ABSTRACT FROM AUTHOR]

The echo signal of light detection and ranging (LiDAR) system is easily disturbed by various noises under the influence of intense background light. The signal to noise ratio (SNR) decreases with increasing distance, which seriously affects the retrieval accuracy of the LiDAR system. This paper combines local mean decomposition and an improved thresholding method (LMD-ITM) to process the Lidar signal with a lot of noise, so as to avoid the loss of useful information. In this research, the correlation coefficient and energy entropy are used to distinguish between the relevant and irrelevant components decomposed by the local mean decomposition. Subsequently, the improved thresholding method is applied to process the irrelevant components. It can extract the effective signals which are difficult to be separated from the high-frequency signals. Finally, all components are reconstructed to get the denoising signal. The experimental results demonstrate that this method can effectively avoid the short-range migration, suppress the long-range noise, and adapt to different weather conditions. Compared with the previous denoising method, the proposed method increases the SNR by about 15%.

Aiming at the problem that existing adaptive diagnosis methods of coal mine machinery bearing fault were susceptible to the interference of high frequency noise and intermittent noise, which led to the low accuracy of original signal decomposition and feature extraction, a fault diagnosis method for coal mine machinery bearing was proposed which was based on modified local mean decomposition(MLMD). The method adopts adjuvant noise decomposition method in self-adaptive decomposition part of local mean decomposition(LMD) method, namely adding Gaussian white noise to original signal firstly and then carrying out LMD, so as to restrain influence of high-frequency and intermittent noise on signal decomposition. In feature parameter extraction part, MLMD method does Hilbert transformation for product function components, then extracts feature parameters, so as to realize feature parameter extraction in whole value range. The simulation and test results show that MLMD method has good effect on decomposition and feature parameter extraction of bearing fault signal and high diagnosis accuracy of inner and outer ring fault of bearing.

In the case of strong noise, Ensemble local mean decomposition (ELMD) is proposed for the modal aliasing phenomenon of local mean decomposition（LMD）. However, the white noise added in ELMD cannot be completely neutralized, which will result in the reconstruction error increases due to the Product functions（PF）components to be affected by the added white noise. Therefore, a compound fault feature extraction method for gearbox based on PE-CELMD(Permutation Entropy-Complementary Ensemble local mean decomposition) is proposed. The idea is to optimize ELMD by adding pairwise white noise in combination with Permutation Entropy (PE) method based on ELMD. The method is applied to the simulated signal and the measured signal, and compared with LMD and CELMD, the results show that the PE-CELMD method is an effective compound fault feature extraction method.

In this paper, the structure and working principle of four-mass vibration MEMS gyroscope (FMVMG) are introduced, and the working modes of FMVMG are simulated and analyzed. On the basis of this, an improved noise reduction method based on interval local mean decomposition (ILMD) and parabolic tracking time-frequency peak filtering (PTTFPF) is proposed. PTTFPF can resample the signal along a parabolic path and select the optimal filtering trajectory, but there is still a contradiction, choosing a short window length may lead to good signal amplitude retention, but the random noise reduction effect is not good, while choosing a long window length may lead to serious amplitude attenuation, but the random noise reduction effect is better. In order to achieve a better balance between effective signal amplitude preservation and random noise reduction, the ILMD method was used to improve PTTFPF. First, the original signal was decomposed into product functions (PFs) by local mean decomposition (LMD) method, and the sample entropy (SE) of each PF was calculated. The PFs are divided into three different components. Then, short window PTTFPF is used for useful PF and long window PTTFPF is used for mixed PF, noise PF is directly removed. Then the final signal is reconstructed. Finally, the denoised useful PF and mixed PF are reconstructed to obtain the final signal. The proposed ILMD-PTTFPF algorithm was verified by temperature experiments. The results show that the denoising performance of the ILMD-PTTFPF algorithm is better than that of traditional wavelet threshold denoising and Kalman filtering.

The classification of electroencephalography (EEG) induced by the same joint is one of the major challenges for brain-computer interface (BCI) systems. In this paper, we propose a new framework, which includes two parts, feature extraction and classification. Based on local mean decomposition (LMD), cloud model, and common spatial pattern (CSP), a feature extraction method called LMD-CSP is proposed to extract distinguishable features. In order to improve the classification results multi-objective grey wolf optimization twin support vector machine (MOGWO-TWSVM) is applied to discriminate the extracted features. We evaluated the performance of the proposed framework on our laboratory data sets with three motor imagery (MI) tasks of the same joint (shoulder abduction, extension, and flexion), and the average classification accuracy was 91.27%. Further comparison with several widely used methods showed that the proposed method had better performance in feature extraction and pattern classification. Overall, this study can be used for developing high-performance BCI systems, enabling individuals to control external devices intuitively and naturally.

Al 6061 because of its high strength, lightweight and good corrosion resistance is being widely used in aerospace industry. Regenerative chatter is an unavoidable phenomenon often encountered during machining of this aluminum alloy. In the present work, a methodology has been proposed in order to extract tool chatter features during turning operation. Chatter signals generated during the turning of Al 6061 have been acquired using a microphone. The recorded signals have been processed using local mean decomposition. The decomposed signals have been analyzed using different statistical indicators considering Nakagami distribution approach for ascertaining the thresholds of chatter severity. Prediction models of most effective statistical indicator have been developed using artificial neural network to ascertain safe range of cutting parameters. From the analysis and validation experiments, it has been inferred that the obtained safe cutting zone is significant and capable of limiting the chatter. [ABSTRACT FROM AUTHOR]

Objective of the present study is to determine an optimum range of turning parameters using merged wavelet denoising and local mean decomposition (WDLMD) technique in order to establish stable turning settings in computer numerical control (CNC) lathe. In this method, the embedded ambient noise and other disturbances in experimentally acquired chatter signals are removed using wavelet denoising (WD). Further, local mean decomposition (LMD) technique is applied on denoised signals to extract a series of product functions (PFs). Thereafter, fast Fourier transformation (FFT) of these PFs is done and then considering these FFTs, prominent PFs containing the chatter information are selected. These prominent PFs are combined to reconstruct the signal containing rich information of chatter. Finally, reconstructed signal has been explored by evaluating statistical indexes in order to extract tool chatter features and stability regimes in CNC turning. More experiments have been performed to corroborate the ascertained stability zone. [ABSTRACT FROM AUTHOR]