Intrinsic Time-scale Decomposition Research Articles

Non-destructive testing of steel wire ropes incorporating magnetic memory information

In order to avoid the influence of the interfering magnetic field, a wire rope magnetic memory detection platform under the excitation of a weak magnetic field is built and then the enhanced magnetic memory signal, infrared signal and visible light signal are fused to increase the recognition rate and reduce the identification error of the quantitative identification of broken wires, realising more effective defect identification and life assessment of wire ropes. The magnetic memory signal is denoised by applying intrinsic time-scale decomposition (ITD) and a wavelet algorithm to effectively remove noise such as the signal baseline and strand waves. The image fusion method based on curvelet transform is applied to realise pixel-level fusion of the defect images. The extracted fused image features are used as the input to the support vector machine optimised by the grey wolf optimiser (GWO-SVM) neural network to quantitatively identify wire rope defects. The results show that the image fusion method is better than the single detection method for broken wire identification.

Composite Fault Feature Enhancement Approach for Rolling Bearings Grounded on ITD and Entropy-based Weight Method

Aiming to precisely identify a compound fault of rolling bearing, the paper has contributed a fault characteristic enhancement method by combing entropy weight method (EWM) and intrinsic time scale decomposition (ITD). Firstly, to effectively segregate frequency components in vibration signals, proper rotation components (PRCs) were obtained by decomposing vibration signals based on ITD. Secondly, in view of the fact that amplitude, variance and correlation coefficient vary greatly in a bearing fault accompanied by impact components, parameter evaluation indexes were brought in to depict the fault characteristics of PRCs, including average, variance, correlation coefficient, margin factor, kurtosis, impulse factor, peak factor and so on. Thirdly, weight coefficient of each parameter index was calculated by entropy weight method and the characteristics of each PRC highlighted based on that. Finally, the signals were reconstructed according to the PRCs whose characteristics had been enhanced. Meanwhile reconstructed signals were denoised with singular differential spectrum (SDS) to reduce the influence of noise components, and then the type of compound fault was distinguished grounded on the frequency spectrum. To further prove the efficiency of proposed method, it is compared with other methods (SDS, ITD + entropy method). The result indicates that the proposed method can further highlight the characteristic information of compound faults of bearing and embody more exact identification and judgment on the type of faults.

Acoustic Vector Sensor Multi-Source Detection Based on Multimodal Fusion.

The direction of arrival (DOA) and number of sound sources is usually estimated by short-time Fourier transform and the conjugate cross-spectrum. However, the ability of a single AVS to distinguish between multiple sources will decrease as the number of sources increases. To solve this problem, this paper presents a multimodal fusion method based on a single acoustic vector sensor (AVS). First, the output of the AVS is decomposed into multiple modes by intrinsic time-scale decomposition (ITD). The number of sources in each mode decreases after decomposition. Then, the DOAs and source number in each mode are estimated by density peak clustering (DPC). Finally, the density-based spatial clustering of applications with the noise (DBSCAN) algorithm is employed to obtain the final source counting results from the DOAs of all modes. Experiments showed that the multimodal fusion method could significantly improve the ability of a single AVS to distinguish multiple sources when compared to methods without multimodal fusion.

Ensemble empirical mode decomposition and stacking model for filtering borehole distributed acoustic sensing records

We have evaluated the ensemble empirical mode decomposition (EEMD) and stacking model for borehole seismic-data denoising. The borehole records collected by distributed acoustic sensing (DAS) technology have multitype noise contamination, and it is difficult to attenuate these noises while recovering the seismic waves well. We first perform EEMD on the seismic data to obtain the signal-to-noise modal components, then extract the time and frequency information of the decomposed modes using six feature factors, and finally introduce an ensemble learning method to classify the acquired modal features effectively. Stacking is the ensemble learning technique we used in our study. This technique integrates several diverse basic ensemble models using the meta-learning strategy and constructs a highly integrated framework with superior performance and good generalization. In addition, the basic ensemble models consist of many decision tree classifiers following two different ideas of parallelization and serialization. The feature extraction process provides sufficient DAS feature data for the training process of the framework. Synthetic and real experimental results demonstrate that the stacking integration framework effectively separates the signal-to-noise modal features of the borehole DAS records. Furthermore, the EEMD-stacking method performs better than wavelet transform, intrinsic time-scale decomposition, robust principal component analysis, k-means singular value decomposition, and median filtering on the denoising task.

Real-time Subsynchronous Control Interaction Monitoring Using Improved Intrinsic Time-scale Decomposition

In recent years, subsynchronous control interaction (SSCI) has frequently taken place in renewable-connected power systems. To counter this issue, utilities have been seeking tools for fast and accurate identification of SSCI events. The main challenges of SSCI monitoring are the time-varying nature and uncertain modes of SSCI events. Accordingly, this paper presents a simple but effective method that takes advantage of intrinsic time-scale decomposition (ITD). The main purpose is to improve the accuracy and robustness of ITD by incorporating the least-squares method. Results show that the proposed method strikes a good balance between dynamic performance and estimation accuracy. More importantly, the method does not require any prior information, and its performance is therefore not affected by the frequency constitution of the SSCI. Comprehensive comparative studies are conducted to demonstrate the usefulness of the method through synthetic signals, electromagnetic temporary program (EMTP) simulations, and field-recorded SSCI data. Finally, real-time simulation tests are conducted to show the feasibility of the method for real-time monitoring.

Automatic feature learning model combining functional connectivity network and graph regularization for depression detection

Depression has become a major health and economic burden worldwide. Electroencephalography (EEG) data has been used by a growing number of researchers to study depression. EEG-based functional connectivity (FC) features have emerged since they can account for the relationships between different brain regions. In this paper, the time–frequency analysis technique is introduced into the construction of the FC matrix. Specifically, instead of directly building the FC matrix from the EEG signals, the intrinsic time-scale decomposition (ITD) method is employed to mine the time–frequency information, and then the Pearson correlation is used to measure the FC between channels. The results show the significant differences in the FC networks between different groups. Furthermore, the graph-based adaptive least absolute shrinkage and selection operator model (GA-LASSO) is proposed in this paper to learn the discriminative features from the FC matrix, which is mainly achieved by adding both the adaptive L1 and graph regularized terms to the original least absolute shrinkage and selection operator (LASSO) model. The advantages of GA-LASSO come from the processing of discriminative weights of different features, and the connections between features by graph topology. In addition, the effectiveness of the proposed strategy of depression detection is validated on the open dataset MODMA, as well as the self-collected dataset called EDRA. The experimental results show that the current study sheds new light on the pathological mechanism of subclinical depression and suggests that EEG resting-state FC analysis may identify potentially effective biomarkers for its clinical diagnosis.

Attention deficit hyperactivity disorder recognition based on intrinsic time-scale decomposition of EEG signals

Attention deficit hyperactivity disorder (ADHD), a neuro-developmental condition, is characterized by various degrees of impulsivity, hyperactivity, and inattention. Treatment of this condition and minimizing its negative impact on learning, working, forming relationships, and quality of life depends heavily on the early identification. The Electroencephalography (EEG) is a useful neuroimaging technique for understanding ADHD. This study examines the brain activity of children with ADHD by analyzing the EEG signals using the intrinsic time-scale decomposition (ITD). Different combinations of the modes, known as Proper Rotation Components (PRCs), produced by ITD, are used to extract a variety of connectivity-based features (magnitude square coherence, cross power spectral density, correlation coefficient, covariance, cohentropy coefficient, correntropy coefficient). EEG signals of 15 ADHD children and 18 age-matched health children are recorded while resting with the eyes closed. Mentioned features are calculated using different channel pairs chosen from longitudinal and transversal planes. Through various machine learning approaches and a 10-fold cross-validation method, the proposed approach is evaluated to distinguish between ADHD patients and healthy controls. Classification accuracies are obtained for the longitudinal and transverse planes, between 92.90% to 99.90% and 91.70% to 100.00%, respectively. Our results support the remarkable performance of the proposed approach, and represent a substantial advance over similar studies in terms of recognizing and classifying ADHD.

A Robust Framework for Automated Screening of Diabetic Patient Using ECG Signals

Diabetes mellitus (DM) or diabetes is an incurable, chronic, and genetic link health problem that occurs due to the higher glucose level in the blood. Continuous monitoring and automatic screening of diabetic patients will significantly improve the quality of the medical management system. DM induces cardiovascular autonomic neuropathy, which alters the morphology of electrocardiogram (ECG) signals. Hence, in this experiment, a new single-lead ECG signal database of 86 subjects (35 diabetic and 51 normal) is recorded. For the automatic screening of DM, an intrinsic time-scale decomposition (ITD) and machine learning-based framework is developed. In the first stage, denoised recorded signals are segmented into fragments of 5-s and decomposed into rotational components using the ITD algorithm. In the second stage, four features, namely, Hjorth complexity, Shannon entropy, log energy entropy, and log energy, are extracted from the ITD components. In the third stage, the Kruskal–Wallis (K–W) test is applied to select the most distinguishable features and fed to a decision tree classifier (DTC) with three different kernel functions for the automatic detection of diabetic patients. The fine tree (FT) kernel function provides the highest classification accuracy (ACC) of 86.9%. The proposed framework is developed using a 10-fold validation strategy. The developed framework is patient-centered suitable for screening in resource-limited environments and ready to be tested with more databases.

Myocardial infarction detection using ITD, DWT and deterministic learning based on ECG signals.

Nowadays, cardiovascular diseases (CVD) is one of the prime causes of human mortality, which has received tremendous and elaborative research interests regarding the prevention issue. Myocardial ischemia is a kind of CVD which will lead to myocardial infarction (MI). The diagnostic criterion of MI is supplemented with clinical judgement and several electrocardiographic (ECG) or vectorcardiographic (VCG) programs. However the visual inspection of ECG or VCG signals by cardiologists is tedious, laborious and subjective. To overcome such disadvantages, numerous MI detection techniques including signal processing and artificial intelligence tools have been developed. In this study, we propose a novel technique for automatic detection of MI based on disparity of cardiac system dynamics and synthesis of the standard 12-lead and Frank XYZ leads. First, 12-lead ECG signals are synthesized with Frank XYZ leads to build a hybrid 4-dimensional cardiac vector, which is decomposed into a series of proper rotation components (PRCs) by using the intrinsic time-scale decomposition (ITD) method. The novel cardiac vector may fully reflect the pathological alterations provoked by MI and may be correlated to the disparity of cardiac system dynamics between healthy and MI subjects. ITD is employed to measure the variability of cardiac vector and the first PRCs are extracted as predominant PRCs which contain most of the cardiac vector's energy. Second, four levels discrete wavelet transform with third-order Daubechies (db3) wavelet function is employed to decompose the predominant PRCs into different frequency bands, which combines with three-dimensional phase space reconstruction to derive features. The properties associated with the cardiac system dynamics are preserved. Since the frequency components above 40 Hz are lack of use in ECG analysis, in order to reduce the feature dimension, the advisable sub-band (D4) is selected for feature acquisition. Third, neural networks are then used to model, identify and classify cardiac system dynamics between normal (healthy) and MI cardiac vector signals. The difference of cardiac system dynamics between healthy control and MI cardiac vector is computed and used for the detection of MI based on a bank of estimators. Finally, experiments are carried out on the PhysioNet PTB database to assess the effectiveness of the proposed method, in which conventional 12-lead and Frank XYZ leads ECG signal fragments from 148 patients with MI and 52 healthy controls were extracted. By using the tenfold cross-validation style, the achieved average classification accuracy is reported to be 98.20%. Results verify the effectiveness of the proposed method which can serve as a potential candidate for the automatic detection of MI in the clinical application.

Specific Emitter Identification Based on Multichannel Depth Feature Fusion

Specific emitter identification involves extracting the fingerprint features that represent the individual differences of the emitter. This is achieved by processing the radio-frequency signals. Feature extraction and classifier selection are key factors that affect SEI performance. This paper proposes a deep convolutional neural network model based on multisignal feature fusion to identify the emitters. As part of the implementation model, the methods of singular spectrum analysis (SSA), variational mode decomposition (VMD), and intrinsic time-scale decomposition (ITD) are used to extract various signal features of emitter signals. Finally, a multichannel deep learning model is adopted to fuse each signal feature automatically and identify different signal emitters. Experimental results show that the proposed method completely considers the complementarity and independence of varying signal features and excavates hidden deep feature information. Hence, the process is considered reliable and effective.

Feature extraction of rotor-stator rubbing faults based on harmonic fusion vector bispectrum, ITD and Hjorth parameters

To solve the difficulty in extracting the characteristics of rotor–stator rubbing faults, the paper has proposed the combined method of Complexity parameter, the harmonic fusion vector bispectrum (HFVB), and intrinsic time-scale decomposition (ITD). First, to fully embody the characteristic information of fault, the HFVB is used to blend the information of signals collected from sensors installed in different positions. Second, taking in mind that the ITD algorithm can embody the effective separation of nonstationary and nonlinear signals, the ITD algorithm makes the separation of blended signals. Third, regarding the important influence of signal complexity on fault characteristic extraction, the complexity parameter of Hjorth parameters can provide very great embodiment of signal complexity. Complexity parameter of Hjorth parameters is introduced as a characteristic parameter index to make a option of proper rotation component (PRC) which can show the characteristics of rubbing fault better. Fourth, signals are reconstructed based on chosen signal components. Meanwhile, to reduce the influence of noise, reconstructed signals are denoised accordingly. Finally, implement the characteristic extraction and fault identification of rubbing faults according to the square demodulation spectrum (SDF) of denoised signals. The result indicates that the harmonic fusion vector bispectrum method can embody the effective blending of fault information; the complexity parameter in Hjorth parameter can serve as the index parameter for option of sensitive characteristic components of rubbing faults. Based on the proposed method, in the square demodulation spectrum of reconstructed signals, it can effectively and precisely provide the characteristics of rotor–stator rubbing fault and successfully identify a fault type.8714542030

Feature extraction of mixed faults of intershaft bearing based on homologous information and Hjorth parameters

To make correct judgment on the mixed faults of intershaft bearing of aeroplane engine, the paper has proposed a feature option method. This method works by decomposing cross-correlation function (CCF) of homogeneous information from casing with intrinsic time scale decomposition (ITD) for the separation and blending of signals. Furthermore, option of proper rotation components (PRCs) for fault identification is made by abandoning the PRC related with the least Complexity parameter in Hjorth parameters. Moreover, signal is reconstructed based on the autocorrelation function (AF) of residual PRCs. Finally, according to the frequency spectrum of signal reconstructed, fault features corresponding to intershaft bearing are extracted and fault types estimated. The result indicates that the Complexity parameter in Hjorth parameter can be used as an evaluation index to implement the selecting of sensitive fault components. Furthermore, the mixed fault types which come from intershaft bearing of aeroplane engine could be judged correctly.

A research on rubbing feature extraction based on information fusion and signal decomposition algorithm

To effectively identify the rotor–stator rubbing fault, the paper has brought forward a method combining principal component analysis (PCA), intrinsic time-scale decomposition (ITD), and information entropy (IE). Firstly, in considering that the characteristic information of faults extracted from the information collected by single sensor is not complete or comprehensive, the approach blends the vibration signals collected from 4 different positions at the same moment based on PCA algorithm; secondly, regarding that ITD algorithm can effectively avoid the problems of poor adaptivity and end effect, blended signals are broken down based on ITD algorithm; thirdly, calculate the IE of self-correlation function of each PRC based on the fact that the smaller IE is, the less confusion system has and the easier it is to extract fault characteristics, and treat the self-correlation function of PRC related with the minimum IE as optimal component to represent fault characteristics; fourthly, characteristic extraction of rotor–stator rubbing fault and identification are done on the basis of the frequency spectrum of optimal component. To prove the availability of method, vibration signals are subjected to validation and analysis, which are collected from different rotation speeds, casing thicknesses, rubbing positions, and types. The result indicates that the proposed PCA–ITD–IE can equally and effectively extract the characteristics of rotor–stator rubbing faults of aero-engine involved in various conditions.

Roll eccentricity extraction and compensation based on MPSO-WTD and ITD.

To meet the high thickness accuracy requirements in cold-rolling processes, a roll eccentricity signal extraction method based on modified particle swarm optimization and wavelet threshold denoising (MPSO-WTD) with intrinsic time-scale decomposition (ITD) is proposed. The strong denoising ability of the wavelet is combined with the decomposition and recognition attributes of ITD for non-stationary signals. Periodic disturbances in strip thickness caused by roll eccentricity are actively compensated. First, the wavelet is used to denoise the signal and the MPSO algorithm is applied to determine a rational threshold and improve the calculation efficiency. Then, the denoised signal is decomposed into proper rotational components (PRCs) using the ITD method, and an appropriate PRC component representing the eccentricity signal is extracted. Finally, the eccentricity compensation signal is applied in the automatic gauge control (AGC) system of the cold rolling mill. During the rolling process, the rolling speed is not constant and will directly affect the frequency of the roll eccentricity signal. To solve this problem, an encoder is installed at the end of the roll and the compensation frequency of the roller eccentricity signal is determined in the roller eccentricity compensation system according to the pulse number output. The results of simulations and experiments show that roll eccentricity signals extracted using the proposed method can effectively remove the influence of interference signals. An average improvement of 62.3% in the roll eccentricity compensation effect was achieved under the stable rolling condition in the finishing rolling stage.

Identifying rotor-stator rubbing positions based on intrinsic time scale decomposition-hjorth-cepstrum

To accurately locate rotor–stator rubbing faults in aero-engine, a method combining intrinsic time scale decomposition (ITD), Hjorth parameter and cepstrum analysis has been proposed. First, the method works by decomposing vibration signals from casing into proper rotation components (PRCs) based on ITD; second, calculates the autocorrelation function of each rotation component and the complexity parameters of autocorrelation functions; third, chooses PRCs for signal reconstruction according to complexity from Hjorth parameters and reconstructs the signals based on chosen PRCs; at last, considering that with different positions of rubbing, transfer paths of signals collected by the sensors from the same position are different, cepstrum analysis has been made according to reconstructed signals, and the transfer paths characteristics from cepstrum are taken as feature vectors and inputted into support vector machine for identifying the positions of rotor-stator rubbing faults. The results indicate proposed ITD-Hjorth-Cepstrum method can work well in the identification rate of training and test samples as for the identification rate for an unknown sample.

Denoising Chaotic Signals Using Ensemble Intrinsic Time-Scale Decomposition

Processing chaotic signals is a complicated task due to their nonlinear and non-periodical properties. Conventional linear filters do not allow to properly denoise signals generated by chaotic systems, distorting the carrier while removing the noise, which is critical for such applications as coherent chaotic communications. In this paper, we propose a novel denoising algorithm, called Ensemble Intrinsic Time-Scale Decomposition (EITD) using specific chaotic noise generators. We may use specific chaotic noise generators in the known Ensemble Empirical Mode Decomposition (EEMD), as we also show. Considering the examples of Rössler and Lorenz systems as chaotic waveforms generators, we compare the developed algorithm modifications with other filtration algorithms using ITD and EMD. We use the root-mean-square error (RMSE) as a metric to estimate the denoising quality. Signal-to-noise ratio (SNR) range -10...20 dB is examined, and white, pink and chaotic noise generators are utilized to disturb signals under study. As a result, we explicitly show that the developed approach provides the error 2-10 times less in the case of white and pink noise, and is capable of denoising chaotic signals in case of all the considered types of noises, in contrast to Conventional and Iterative ITD and EMD algorithms.

Research on compound fault diagnosis of rolling bearing based on intrinsic time scale decomposition and information fusion

In view of the difficulty to effectively extract compound faults of rolling bearing from aero-engine and precisely identify their types, the paper has proposed a method integrating signal separation algorithm and information fusion. Firstly, the method decomposes the vibration acceleration signals collected by sensors from different positions at the same moment based on intrinsic time scale decomposition algorithm. Secondly, cross correlation analysis is given to the proper rotation component (PRC) of the same layer, which are obtained after decomposition and correspond to the sensors from different positions and cross-correlation function is introduced to embody information fusion. Thirdly, signals are reconstructed according to cross-correlation function of each PRC. Finally, based on the frequency spectrum of reconstructed signal, extract the characteristics of rolling bearing and identify the type of faults under different sensor combinations and multiple compound fault types. The result shows, the proposed method can effectively extract the characteristics of compound faults of bearing and precisely identify the type of faults under different sensor combinations and multiple compound fault types of rolling bearing.

A Time-Frequency based backup protection scheme for enhancing grid security against power system blackout

For the stable operation of the smart grid, the development of a faster, reliable, and secure protective relay algorithm is essential. From the past blackout reports, it is revealed that during different system critical operating conditions distance relay meets dependability and selectivity challenges and operates unnecessarily. To restrict the operation of distance relay only to fault conditions, an intrinsic time-scale decomposition (ITD) based backup protection scheme is proposed. The ITD method decomposes current signals into baseline and residual components. A reliable index is defined as the energy of a significant baseline component that has the highest kurtosis value. The energy-based index effectively accomplishes symmetrical fault-system stress events discrimination task. For technical evaluation of the method, different power system models such as the IEEE-39 bus test system and the Indian Eastern Region Grid (IERG) were considered and simulated using EMTDC/PSCAD software. The response of the method is compared with other existing techniques. The method uses an adaptive threshold selection approach to detect a fault condition and thus the response is independent of system configuration and structure. With this advantage, unintentional tripping of the power system during different critical operating conditions can be avoided.

A new method to identify rotor–stator rubbing positions based on intrinsic time scale decomposition

To effectively identify the rotor–stator rubbing positions in aero-engine, the paper has proposed the combination of intrinsic time-scale decomposition (ITD) and classification algorithm. Regarding that with larger noise component in proper rotation component (PRC) signals after ITD, it will be more difficult to extract the characteristic information of rubbing faults, the PRC correspondings to the largest noise was eliminated. Meanwhile, signals were reconstructed based on residual proper rotation components, and positions of rubbing faults were identified according to the reconstructed signal. As rubbing extent and other factors cannot be completely the same in each rubbing, energy of reconstructed signal has been normalized to reduce the difference. Normalized energy indexes were inputted into classification algorithm as feature vectors to identify the positions of rubbing faults. To identify the superiority of approach, a comparison has been made between the proposed approach and the method of directly extracting normalized energy indexes of acceleration signals. The result of comparison shows that the two methods both work well in the identification rate of training and test samples; as for the identification rate for an unknown sample, the proposed method is superior to the other, with identification rate increasing by 17% and 9.4%.

Faults Detection and Classification under Variable Condition Using Intrinsic Time - Scale Decomposition and Neural Network

Misalignment and unbalance are a common fault occurring in the rotor system. A new approach for detecting misalignment and unbalance problems combining the intrinsic time - scale decomposition (ITD), the root mean square (RMS) and perceptron multilayer network (MLP) is proposed in this paper. Vibration signals of normal condition, misalignment horizontal, misalignment vertical and unbalance with different level are collected under different speed. ITD, nonlinear analysis of signals, was applied to decompose the vibration signals into 8 proper rotation components. The RMS values of 8 components are calculated and using as features vector. Last, the perceptron multilayer network was used for fault identification and classification. The proposed approach accurately classified and detection of unbalance and misalignment; the average accuracy achieved is 97.99%.