Multiscale Entropy Research Articles

Intelligent fault diagnosis for rail transit switch machine based on adaptive feature selection and improved LightGBM

The turnout switch machine is the critical equipment of the signal system, which has a significant influence on the efficiency and safety of train operation. However, most fault diagnosis technologies of the switch machine are difficult to distinguish samples with similar categories, which leads to the low diagnostic accuracy. Thus, a fault diagnosis method based on improved LightGBM is proposed to deal with the above problems. Time domain features and multi-scale permutation entropy are extracted to capture the weak fault. Moreover, an adaptive feature selection (AFS) method is presented to reduce redundant features. Especially an improved Focal Loss (IFL) function is established, which improves the ability to distinguish samples of similar features in a multi-classification model. The three-phase action current from the switch machine is utilized to testify to the proposed method and compare it with other methods. The experimental results show that the diagnosis accuracies of this method in the normal-reverse and reverse-normal conversion process reach 98.47 % and 96.09 %, respectively, which is well-suitable for practical application.

Fatigue condition diagnosis of rolling bearing based on normalized balanced multiscale sample entropy

Rolling bearing is a key component of machinery, its fatigue failure will affect the reliability of machinery. The bearing vibration signal has strong nonlinearity, resulting in weak fault information. Multiscale sample entropy (MSE) is an effective technique for analyzing nonlinear time series. However, MSE has limitations, such as a large deviation and weak information mining abilities, and even the calculation results have no definition. To this end, a normalized balanced multiscale sample entropy (NBMSE) is proposed in this study. For NBMSE, the data are first normalized to zero mean and unit standard deviation by zero-mean normalization, which eliminates the influence of abnormal data. Secondly, the balanced multiscale approach is advanced to coarse-grain the time series, which takes into account the uniqueness of different amplitudes and the globality of the time series. The method not only avoids no-definition results, but also reduces the entropy calculation error, thus mining useful amplitude information. The comparison of synthetic signals shows that the proposed NBMSE is more robust than other methods. Furthermore, the results of two bearing cases show that NBMSE not only provides sensitive features for fatigue diagnosis but also has higher diagnostic accuracy.

Intelligent fault detection scheme for constant-speed wind turbines based on improved multiscale fuzzy entropy and adaptive chaotic Aquila optimization-based support vector machine

Timely and effective fault detection is essential to ensure the safe and reliable operation of wind turbines. However, due to the complex kinematic mechanisms and harsh working environments of wind turbine equipment, it is difficult to extract sensitive features and detect faults from acquired wind turbine signals. To address this challenge, a novel intelligent fault detection scheme for constant-speed wind turbines based on refined time-shifted multiscale fuzzy entropy (RTSMFE), supervised isometric mapping (SI), and adaptive chaotic Aquila optimization-based support vector machine (ACAOSVM) is proposed. In the first step, the RTSMFE method is used to fully extract features of the wind turbine system. The time-shifted coarse-grained construction technique and a refined computing technique are adopted in the RTSMFE method to enhance the capability of traditional multiscale fuzzy entropy for measuring the complexity of signals. Subsequently, an effective manifold learning approach, SI, is applied to obtain the important and low-dimensional feature set from the high-dimensional feature set. Finally, sensitive features are fed into the ACAOSVM classifier to identify faults. The proposed ACAO algorithm is used to optimize important parameters of the SVM, thereby improving its detection performance. Simulations and wind turbine experiments verified that the proposed RTSMFE outperforms existing entropy techniques in terms of complexity measurement and feature extraction. Furthermore, the proposed ACAOSVM classifier is superior to existing advanced classifiers for fault pattern recognition. Finally, the proposed intelligent fault detection scheme can more correctly and efficiently detect wind turbine single/hybrid faults than other recently published schemes.

Fault diagnosis of real-scenario battery systems based on modified entropy algorithms in electric vehicles

Entropy algorithm is an efficient fault diagnosis technology gradually gaining popularity, which is highly promising in terms of battery safety protection in electric vehicles. This paper compares two entropy algorithms commonly used for battery fault diagnosis and their ability to diagnose abnormal fluctuations implied in the pre-fault phase. By exploring the influence of key calculation factors in the entropy algorithm on the fault diagnosis effect, this study pioneered the discovery of a significant normal distribution pattern and the logarithmic relationship between the diagnostic effect and the size of the Shannon entropy's calculation window and multi-scale sample entropy's scale factor, respectively. The relationship between computation time and computation factor was found to provide a theoretical basis for improving diagnosis efficiency through the rational selection of computation factors. Furthermore, based on actual vehicle fault data verification, a multi-level diagnosis strategy with strong robustness and generality is proposed using statistical methods. More importantly, this study continues to explore the importance of deeper mining of different entropy features, and the proposed control strategies are of high practical significance for battery fault diagnosis/prognosis in real-world vehicle applications.

Intelligent forecasting model of stock price using neighborhood rough set and multivariate empirical mode decomposition

Intelligent forecasting model of stock price is an effective way to obtain ideal investment returns. Due to the impact of quantitative transactions, traditional forecasting methods face challenges and pressures. How to find a reliable forecasting model and improve the forecasting accuracy will be a scientific problem worthy of further discussion. This paper proposes an intelligent forecasting model of stock price based on neighborhood rough set (NRS) and multivariate empirical mode decomposition (MEMD) by means of the ideal of “granular computing” and “decomposition ensemble”. Firstly, the multiscale permutation entropy (MPE) method is conducted to determine decision features, which can improve the stability of permutation entropy. Then, a new feature selection method, fusing mutual information (MI) and the NRS, is proposed to automatically capture and select the condition features from the stock market. Subsequently, aiming on revealing the more detailed feature information and maintaining relevance between features, the MEMD is utilized to simultaneously decompose all features. Finally, the decomposed features are inputted into the long short-term memory (LSTM) network to train the intelligent forecasting model and provide the forecasting results of stock price. The validity of our proposed model is assessed through the stocks of Shanghai and Shenzhen markets. The results show that our proposed intelligent forecasting model of stock price makes a beneficial attempt and discussion for the integration of “granular computing” and “decomposition ensemble”. And it will provide scientific support and reference for investors’ actual investment decisions.

Forecasting carbon price in China using a novel hybrid model based on secondary decomposition, multi-complexity and error correction

As global warming intensifies, the reduction of carbon emissions is imminent. Carbon price is directly related to whether carbon can be effectively reduced. Therefore, accurately forecasting carbon price has important practical significance. Aiming at the nonstationary and nonlinear characteristics of carbon price, this paper proposes a novel hybrid model for forecasting carbon price, which is based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), multiscale fuzzy entropy (MFE), complete ensemble empirical mode decomposition (CEEMD), improved random forest by salp swarm algorithm (SSARF), improved back propagation by cuckoo search (CSBP), improved extreme learning machine by whale optimization algorithm (WOAELM) and error correction (EC), named ICEEMDAN-MFE-CEEMD-SSARF-CSBP-WOAELM-EC. Firstly, carbon price is decomposed by ICEEMDAN, divided into high-, medium-, and low-complexity components by MFE. Secondly, high-complexity components are merged and secondarily decomposed by CEEMD, which are still recorded as high-complexity components. Then, SSARF, CSBP and WOAELM are used to forecast high-, medium-, and low-complexity components, respectively, and forecasting results are reconstructed. Finally, EC is carried out using an extreme learning machine to obtain the final forecasting results, and the Diebold-Mariano test is introduced for a comprehensive evaluation of the model. Taking carbon price in the pilot cities of Shenzhen and Hubei as examples, after 6 aspects and 20 comparative experiments, the results show that the proposed model has higher forecast accuracy, with MAPE, MAE and RMSE up to 0.03131, 0.00089 and 4.02e-06 in Hubei, and its forecasting ability is better than other commonly used international carbon financial price forecasting models, providing a theoretical and data basis for carbon pricing and formulating carbon reduction policies in China. The main contributions of this paper are the improved primary decomposition, the use of secondary decomposition, and the innovative combination of three optimal models to forecast carbon price, but it still needs to be optimized for practice.

Bi-filter multiscale-diversity-entropy-based weak feature extraction for a rotor-bearing system

Multiscale-based entropy methods have proven to be a promising tool for extracting fault information due to their high feature extraction ability and easy application. Despite multiscale analysis showing great potential in extracting fault characteristics, it has some drawbacks, such as cutting the data length and neglecting high-frequency information. This paper proposes a bi-filter multiscale diversity entropy (BMDE) to filter comprehensive fault information and address the data length problem. First, the low-frequency information is filtered out by moving average in a multi-low procedure and the high-frequency information is filtered out by an adjacent subtraction in a multi-high procedure. Second, a modified coarse-grained process is introduced to overcome the issue of data length. The validity of the BMDE method is evaluated using both simulation signals and experimental measurements. Results demonstrate that the proposed method offers optimal feature extraction capability with the highest diagnostic accuracy compared with four other traditional entropy-based diagnosis methods.

Use of the cardiopulmonary coupling index based on refined composite multiscale entropy for prognostication of acute type A aortic dissection.

The aim of this study is to assess the influence of cardiopulmonary coupling (CPC) based on RCMSE on the prediction of complications and death in patients with acute type A aortic dissection (ATAAD). The cardiopulmonary system may be nonlinearly regulated, and its coupling relationship with postoperative risk stratification in ATAAD patients has not been studied. This study was a single-center, prospective cohort study (ChiCTR1800018319). We enrolled 39 patients with ATAAD. The outcomes were in-hospital complications and all-cause readmission or death at 2 years. Of the 39 participants, 16 (41.0%) developed complications in the hospital, and 15 (38.5%) died or were readmitted to the hospital during the two-year follow-up. When CPC-RCMSE was used to predict in-hospital complications in ATAAD patients, the AUC was 0.853 (p < 0.001). When CPC-RCMSE was used to predict all-cause readmission or death at 2 years, the AUC was 0.731 (p < 0.05). After adjusting for age, sex, ventilator support (days), and special care time (days), CPC-RCMSE remained an independent predictor of in-hospital complications in patients with ATAAD [adjusted OR: 0.8 (95% CI, 0.68-0.94)]. CPC-RCMSE was an independent predictor of in-hospital complications and all-cause readmission or death in patients with ATAAD.

A mechanical part fault diagnosis method based on improved multiscale weighted permutation entropy and multiclass LSTSVM

Multi-scale permutation entropy (MPE) has poor stability, accuracy and noise immunity, recognition accuracy of twin SVM is low, so a diagnosis method based on improved multi-scale weighted permutation entropy (IMWPE) and least squares TSVM (LSTSVM) is proposed. The innovations include that the improved variational mode decomposition (IVMD) based on energy and mutual information is used to suppress noise, and novel composite coarse-grained and permutation pattern weighting methods are introduced to construct IMWPE, after which the noise immunity, stability and accuracy of features have been improved. LSTSVM is extended to a multi-class LSTSVM through one vs one (OVO) and binary tree (BT) strategies, the performance of the proposed methodology is significantly improved. The results show that signal-to-noise ratio of signal is enhanced, the stability of IMWPE is improved, the diagnosis accuracies for bearing and check valve are increased by 17.084 % and 12.498 %, which provides a reference for fault diagnosis under noise.

Study on Denoising Method of Vibration Signal Induced by Tunnel Portal Blasting Based on WOA-VMD Algorithm

Because of the impact of the complex environment of tunnel portals, the measured blasting vibration signals in a tunnel portal contains a lot of high-frequency noise. To achieve effective noise reduction, a novel method of noise reduction for blasting vibration signals based on the whale optimization algorithm (WOA) optimized with the variational mode decomposition (VMD) algorithm was proposed. The WOA algorithm is used to optimize globally for the mode number K and penalty factor α of VMD for measured signals and to determine the optimal parameters of [K, α], and to obtain the intrinsic mode function (IMF). Multi-scale permutation entropy (MPE) was used to identify and remove noise components in IMF, and then the reserved IMF was reconstructed to achieve a denoised signal. The method is applied to the blasting vibration analysis of the Xiali tunnel of the Jixin expressway in the Henan Province. Results indicate that the novel method can acquire the optimal decomposition mode number and identify the high frequency noise. Its denoising effect is better than the conventional VMD algorithm and the complete ensemble empirical mode decomposition with adaptive ability (CEEMDAN), which verifies the self-adaptivity and effectiveness of the WOA-VMD denoising method.

Hierarchical Multiscale Fluctuation Dispersion Entropy for Fuel Injection System Fault Diagnosis

Abstract Marine electronically controlled (ME) two-stroke diesel engines occupy the highest market share in newly-built ships and its fuel injection system is quite different and important. Fault diagnosis in the fuel injection system is crucial to ensure the power, economy and emission of ME diesel engines, so we introduce hierarchical multiscale fluctuation dispersion entropy (HMFDE) and a support matrix machine (SMM) to realise it. We also discuss the influence of parameter changes on the entropy calculation’s accuracy and efficiency. The system simulation model is established and verified by Amesim software, and then HMFDE is used to extract a matrix from the features of a high pressure signal in a common rail pipe, under four working conditions. Compared with vectorised HMFDE, the accuracy of fault diagnosis using SMM is nearly 3% higher than that using a support vector machine (SVM). Experiments also show that the proposed method is more accurate and stable when compared with hierarchical multiscale dispersion entropy (HMDE), hierarchical dispersion entropy (HDE), multiscale fluctuation dispersion entropy (MFDE), multiscale dispersion entropy (MDE) and multiscale sample entropy (MSE). Therefore, the proposed method is more suitable for the modelling data. This research provides a new direction for matrix learning applications in fault diagnosis in marine two-stroke diesel engines.

Multi-Source Ensemble Learning With Acoustic Spectrum Analysis for Fault Perception of Direct-Buried Transformer Substations

The tremendous growth of electrical loads results in the capacity increase and underground installation of power distribution infrastructures due to the shortage of urban land resources. However, the closed and narrow underground space of direct-buried transformer substation (DBTS) brings great challenges to its fault perception. This article proposes an adaptive acoustic spectrum analysis method with refined composite multiscale dispersion entropy to extract informative fault-related time-frequency vocal features using the singular-value thresholded variable mode decomposition for facilitating fault diagnosis of DBTS. Then, a time-series generative adversarial network based fault data augmentation model is presented to enrich the training dataset while preserving temporal dynamics of the original fault data for boosting the generalization ability of DBTS fault perception. Furthermore, a multi-source ensemble learning strategy is developed to integrate heterogeneous sub-classifiers based on the dynamic weighted fusion of electrical monitoring data and acoustic signals for promoting fault diagnosis accuracy of DBTS. Comparative studies have been investigated to demonstrate the superior performance of the proposed multi-source ensemble learning strategy in improving the fault diagnosis accuracy of DBTS.

A novel fault diagnosis framework for rotating machinery with hierarchical multiscale symbolic diversity entropy and robust twin hyperdisk-based tensor machine

A novel fault diagnosis framework for rotating machinery with hierarchical multiscale symbolic diversity entropy and robust twin hyperdisk-based tensor machine

Impact of Macrocephaly, as an Isolated Trait, on EEG Signal as Measured by Spectral Power and Multiscale Entropy during the First Year of Life

Macrocephaly has been associated with neurodevelopmental disorders; however, it has been mainly studied in the context of pathological or high-risk populations and little is known about its impact, as an isolated trait, on brain development in general population. Electroencephalographic (EEG) power spectral density (PSD) and signal complexity have shown to be sensitive to neurodevelopment and its alterations. We aimed to investigate the impact of macrocephaly, as an isolated trait, on EEG signal as measured by PSD and multiscale entropy during the first year of life. We recorded high-density EEG resting-state activity of 74 healthy full-term infants, 50 control (26 girls), and 24 macrocephalic (12 girls) aged between 3 and 11 months. We used linear regression models to assess group and age effects on EEG PSD and signal complexity. Sex and brain volume measures, obtained via a 3D transfontanellar ultrasound, were also included into the models to evaluate their contribution. Our results showed lower PSD of the low alpha (8–10 Hz) frequency band and lower complexity in the macrocephalic group compared to the control group. In addition, we found an increase in low alpha (8.5–10 Hz) PSD and in the complexity index with age. These findings suggest that macrocephaly as an isolated trait has a significant impact on brain activity during the first year of life.

Which Multivariate Multi-Scale Entropy Algorithm Is More Suitable for Analyzing the EEG Characteristics of Mild Cognitive Impairment?

So far, most articles using the multivariate multi-scale entropy algorithm mainly use algorithms to analyze the multivariable signal complexity without clearly describing what characteristics of signals these algorithms measure and what factors affect these algorithms. This paper analyzes six commonly used multivariate multi-scale entropy algorithms from a new perspective. It clarifies for the first time what characteristics of signals these algorithms measure and which factors affect them. It also studies which algorithm is more suitable for analyzing mild cognitive impairment (MCI) electroencephalograph (EEG) signals. The simulation results show that the multivariate multi-scale sample entropy (mvMSE), multivariate multi-scale fuzzy entropy (mvMFE), and refined composite multivariate multi-scale fuzzy entropy (RCmvMFE) algorithms can measure intra- and inter-channel correlation and multivariable signal complexity. In the joint analysis of coupling and complexity, they all decrease with the decrease in signal complexity and coupling strength, highlighting their advantages in processing related multi-channel signals, which is a discovery in the simulation. Among them, the RCmvMFE algorithm can better distinguish different complexity signals and correlations between channels. It also performs well in anti-noise and length analysis of multi-channel data simultaneously. Therefore, we use the RCmvMFE algorithm to analyze EEG signals from twenty subjects (eight control subjects and twelve MCI subjects). The results show that the MCI group had lower entropy than the control group on the short scale and the opposite on the long scale. Moreover, frontal entropy correlates significantly positively with the Montreal Cognitive Assessment score and Auditory Verbal Learning Test delayed recall score on the short scale.

Open-Circuit Fault Detection and Location in AC-DC-AC Converters Based on Entropy Analysis

Inverters and converters contain more and more power electronics switches which may subsequently affect their reliability. Therefore, fault detection and location are essential to improve their reliability and to ensure continuous operation. In this paper, an AC−DC−AC converter with three-phase inverter is investigated under permanent, single and multiple open-circuit fault scenarios. Many entropies and multiscale entropies are then proposed to evaluate the complexity of the output currents by quantifying their entropies over a range of temporal scales. Among the multitude of entropies, only some entropies are able to differentiate healthy from open-circuit faulty conditions. Moreover, the simulation results show that these entropies are able to detect and locate the arms of the bridge with open-circuit faults.

EEG Entropy in REM Sleep as a Physiologic Biomarker in Early Clinical Stages of Alzheimer's Disease.

Alzheimer's disease (AD) is associated with EEG changes across the sleep-wake cycle. As the brain is a non-linear system, non-linear EEG features across behavioral states may provide an informative physiologic biomarker of AD. Multiscale fluctuation dispersion entropy (MFDE) provides a sensitive non-linear measure of EEG information content across a range of biologically relevant time-scales. To evaluate MFDE in awake and sleep EEGs as a potential biomarker for AD. We analyzed overnight scalp EEGs from 35 cognitively normal healthy controls, 23 participants with mild cognitive impairment (MCI), and 19 participants with mild dementia due to AD. We examined measures of entropy in wake and sleep states, including a slow-to-fast-activity ratio of entropy (SFAR-entropy). We compared SFAR-entropy to linear EEG measures including a slow-to-fast-activity ratio of power spectral density (SFAR-PSD) and relative alpha power, as well as to cognitive function. SFAR-entropy differentiated dementia from MCI and controls. This effect was greatest in REM sleep, a state associated with high cholinergic activity. Differentiation was evident in the whole brain EEG and was most prominent in temporal and occipital regions. Five minutes of REM sleep was sufficient to distinguish dementia from MCI and controls. Higher SFAR-entropy during REM sleep was associated with worse performance on the Montreal Cognitive Assessment. Classifiers based on REM sleep SFAR-entropy distinguished dementia from MCI and controls with high accuracy, and outperformed classifiers based on SFAR-PSD and relative alpha power. SFAR-entropy measured in REM sleep robustly discriminates dementia in AD from MCI and healthy controls.

Research on Shaft Current Damage Identification of Variable Condition Motor Bearings Based on Multiscale Feature Label Propagation and Manifold Metric Transfer

The current damage is the most stubborn and difficult fault of high-power motor bearings because its vibration characteristics are easily confused with those of ordinary bearing mechanical faults. If it is discriminated as an ordinary mechanical fault without electrical insulation protection, the current damage of bearing shafts will still repeatedly appear. Aiming at the problem that it is difficult to identify the bearing current damage fault under variable working conditions, a bearing shaft current damage identification method based on multiscale feature label propagation and manifold metric transfer (MFLP-MMT) is proposed. Firstly, the multiscale sub-band signal is obtained by wavelet packet decomposition, and the multiscale sub-band fuzzy entropy is obtained by calculating its fuzzy entropy. Then, according to the extracted features, a neighbor graph is constructed on the source domain of the known fault label to obtain the pseudo label of the target domain sample, and the source domain label information is gradually diffused by way of the graph label propagation. The multiscale sub-band fuzzy entropy of the sample is mapped to the low-dimensional manifold space by locality preserving projections (LPP), and the source domain samples close to the target domain are given higher weights by cross-domain density ratio estimation to solve the problem of domain offset. Combined with the label samples of the target domain in label propagation, the manifold distance metric is learned to minimize the intra-class distance and maximize the inter-class distance in the domain and eliminate the overlapping phenomenon in the domain. By increasing the range of label propagation after each iteration, the label propagation error of the leading graph is gradually reduced, and unsupervised metric transfer learning is realized. The experimental results show that the new method is superior to the semi-supervised transfer learning method in fault identification ability; the highest fault identification accuracy can reach 100% and it has a good robustness.

Disease identification method based on graph features between pulse cycles

The pulse signal at the wrist communicates a range of cardiovascular information and reflects a person’s state of health. In recent years pulse signals have been used extensively in the field of disease identification. As a typical quasi-cyclic physiological signal, many researchers have simply used single-cycle pulse signals for disease diagnosis, ignoring the influence of inter-cycle differences on the diagnosis. In this paper, we propose a disease identification method based on graph features between pulse cycles, to focus on the differences in pulse cycles brought about by the disease. The pulse was pre-processing using a Sliding Window, followed by the construction of the correlation coefficient matrix, the setting of a threshold and the construction of the connection graph to obtain the graph features; the Multiscale Permutation Entropy method was used to extract the pulse’s entropy features. The ReliefF algorithm is then used to select a total of 18 features and a classification algorithm is used to distinguish between patients and healthy people. Both the self-constructed dataset and the open dataset from the PLA 211 Hospital had high recognition rates for the experiments. The accuracy of identifying hypertension was 94.16% with a precision of 90.41%; the accuracy of identifying chronic diseases was 97.23% with a precision of 97.81%. The experimental results from the two datasets demonstrate both the validity of the difference between cycles for disease classification and the applicability of the method proposed in this paper.

Long-Term Effects and Potential Impact of Early Nutrition with Breast Milk or Infant Formula on Glucose Homeostasis Control in Healthy Children at 6 Years Old: A Follow-Up from the COGNIS Study.

There is scarce evidence about early nutrition programming of dynamic aspects of glucose homeostasis. We analyzed the long-term effects of early nutrition on glycemic variability in healthy children. A total of 92 children participating in the COGNIS study were considered for this analysis, who were fed with: a standard infant formula (SF, n = 32), an experimental formula (EF, n = 32), supplemented with milk fat globule membrane (MFGM) components, long-chain polyunsaturated fatty acids (LC-PUFAs), and synbiotics, or were breastfed (BF, n = 28). At 6 years old, BF children had lower mean glucose levels and higher multiscale sample entropy (MSE) compared to those fed with SF. No differences in MSE were found between EF and BF groups. Normal and slow weight gain velocity during the first 6 months of life were associated with higher MSE at 6 years, suggesting an early programming effect against later metabolic disorders, thus similarly to what we observed in breastfed children. Conclusion: According to our results, BF and normal/slow weight gain velocity during early life seem to protect against glucose homeostasis dysregulation at 6 years old. EF shows functional similarities to BF regarding children's glucose variability. The detection of glucose dysregulation in healthy children would help to develop strategies to prevent the onset of metabolic disorders in adulthood.