Refined Composite Multiscale Dispersion Entropy Research Articles

A multi-stage forecasting system for daily ocean tidal energy based on secondary decomposition, optimized gate recurrent unit and error correction

Tidal energy, as a new energy, has very high research potential and practical application value. For the characteristics of tidal energy such as nonstationarity and nonlinearity, a multi-stage forecasting system for daily ocean tidal energy is proposed. It is based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), refined composite multi-scale dispersion entropy (RCMDE), empirical mode decomposition based on time-varying filter modified by white shark optimizer (WSOTVFEMD), improved gate recurrent unit using parasitic salp swarm algorithm based on differential evolution (PDESSAGRU) and error correction using CNN (CNN-EC), named as ICEEMDAN-RCMDE-WSOTVFEMD-PDESSAGRU–CNN–EC. Firstly, decompose tidal energy into a series of intrinsic mode functions (IMFs) by ICEEMDAN, and divide IMFs into high-complexity and low-complexity components by RCMDE. Next, secondly decompose the reconstructed high-complexity components into high-complexity parts by WSOTVFEMD. Afterwards, separately predict each component of the high-complexity parts and the low-complexity components by PDESSA, and reconstruct the predicted results to obtain original predicting results. In the end, decompose the error into error IMFs (EIMFs) by ICEEMDAN, predict EIMFs with convolutional neural network (CNN) respectively to acquire error predicting results, and reconstruct original predicting results and error predicting results to acquire the final results. Taking the tidal energy of the American cities including San Francisco, Sitka, and Wauna as case studies, the results show that the proposed system has high prediction accuracy after experiments with 13 comparative models in each city.

A novel robust intelligent fault diagnosis method for rolling bearings based on SPAVMD and WOA-LSSVM under noisy conditions

Aiming at the problem that the fault information of rolling bearings under harsh operation environment is easily submerged by strong noise interference, which causes the traditional method to be difficult to identify bearing faults effectively, this paper proposes a novel robust intelligent fault diagnosis method for rolling bearings based on sparsity-assisted parameter adjustable variational mode decomposition (VMD) and whale optimization algorithm-based optimized least-squares support vector machine (WOA-LSSVM). Firstly, a sparsity measurement named the improved Gini index is introduced as the fitness function of grid search algorithm to adaptively adjust and search for the optimal decomposed mode number K and penalty factor α of VMD. Additionally, VMD containing the optimal parameters is adopted to decompose the original bearing vibration signal into several intrinsic mode function (IMF), and the effective signal reconstruction is performed by screening the sensitive IMF components according to the effective weighted kurtosis Gini index criterion. Subsequently, the refine composite multi-scale dispersion entropy of the reconstructed signal is further calculated to establish a multi-dimensional feature vector set. Finally, the constructed feature vector set is fed into the WOA-LSSVM to achieve automatic fault identification of rolling bearings. The effectiveness of the proposed method is verified by two experimental examples. Experimental results show that the proposed method has higher fault recognition accuracy and better robustness against noise than other homologous methods in noisy conditions. This study provides a new perspective for the developing of robust diagnosis methods.

Low-altitude small target detection in sea clutter background based on improved CEEMDAN-IZOA-ELM

To effectively detect low-altitude small targets under complex sea surface environment, an innovative method has been developed. This method harnesses the chaotic characteristics of sea clutter and employs a combination of Adaptive Noise Complete Ensemble Empirical Modal Decomposition (CEEMDAN), Adaptive Wavelet Thresholding (AWT), and Polynomial Fitting Filtering (SG) for denoising sea clutter data. Subsequently, the Improved Zebra Optimization Algorithm-Extreme Learning Machine (IZOA-ELM) detector is utilized to identify low-altitude small targets amidst the sea clutter background. To begin, the CEEMDAN method is applied to disentangle the measured sea clutter data into a set of Intrinsic Mode Functions (IMFs). Afterwords, the Refined Composite Multiscale Dispersion Entropy (RCMDE) is computed for each individual IMF. This process categorizes the IMFs into three distinct components: noise-dominant, signal-noise mixture, and signal-dominant segments. The noise-dominate of IMF component is subjected to denoising through AWT, the signal-noise mixture of IMF components are processed using SG filtering, while the signal-dominant of IMF remains unaltered. The denoised sea clutter signal is reconstructed by concatenating the denoised and unprocessed IMFs. Based on the chaotic nature of sea clutter signals, first-order sea clutter data is transformed into high-dimensional data through phase space reconstruction. The initial weights and thresholds of the ELM are optimized through the IZOA to establish an optimal prediction model. This model is then used to detect small, low-altitude targets by analyzing the prediction error. The algorithm's effectiveness in noise removal is validated using IPIX and SPRR measured sea clutter data, demonstrating a significant improvement in the root mean square of prediction error (RMSE) by one order of magnitude after denoising compared to the pre-denoising state. Furthermore, we observed that the IZOA-ELM method can be effectively applied to detect small targets at low altitudes across various sea conditions. However, when the sea state is complex and greatly affected by the surrounding noise, an effective approach is to first employ CEEMDAN-AWT-SG to denoise the original signal, and then utilize IZOA-ELM for target detection.

EEG-based detection of driving fatigue using a novel electrode

In view of the serious harm caused by driving fatigue, this paper investigated driving fatigue detection based on electroencephalogram (EEG) features, designed a novel semi-dry electrode for acquisitioning drivers' EEG signals, and performed refined composite multiscale fluctuation dispersion entropy (RCMFDE) feature extraction of the θ and β bands rhythm signals in the acquisitioned EEG signals. The research results showed that the novel semi-dry electrode designed in this paper had the advantages of convenient replenishment of conductive liquid, early warning of insufficient conductive liquid, comfortable to wear compared with the traditional wet and dry electrodes under the premise of being able to collect EEG signals with qualified quality. And compared with traditional methods such as multiscale sample entropy (MSE), multiscale permutation entropy (MPE), multiscale symbolic dynamic entropy (MSDE), multiscale dispersion entropy (MDE), and refined composite multiscale dispersion entropy (RCMDE), the EEG features extracted by the RCMFDE method in this paper have a more obvious fatigue feature tendency, and thus can identify the driving fatigue state more effectively.

Fault Diagnosis of ME Marine Diesel Engine Fuel Injector with Novel IRCMDE Method

Abstract As an important component of the fuel injection system, the fuel injector is crucial for ensuring the power, economy, and emissions for a whole ME (machine electronically-controlled) marine diesel engine. However, injectors are most prone to failures such as reduced pressure at the opening valve, clogged spray holes and worn needle valves, because of the harsh working conditions. The failure characteristics are non-stationary and non-linear. Therefore, to efficiently extract fault features, an improved refined composite multi-scale dispersion entropy (IRCMDE) is proposed, which uses the energy distribution of sampling points as weights for coarse-grained calculation, then fast correlation-based filter(FCBF) and support vector machine (SVM) are used for feature selection and fault classification, respectively. The experimental results from a MAN B&W 6S35ME-B9 marine diesel engine show that the proposed algorithm can achieve 92.12% fault accuracy for injector faults, which is higher than multiscale dispersion entropy (MDE), refined composite multiscale dispersion entropy (RCMDE) and multiscale permutation entropy (MPE). Moreover, the experiment has also proved that, due to the double-walled structure of the high-pressure fuel pipe, the fuel injection pressure signal is more accurate than the vibration signal in reflecting the injector operating conditions.

Automatic detection method of epileptic seizures based on IRCMDE and PSO-SVM.

Multi-scale dispersion entropy (MDE) has been widely used to extract nonlinear features of electroencephalography (EEG) signals and realize automatic detection of epileptic seizures. However, information loss and poor robustness will exist when MDE is used to measure the nonlinear complexity of the time sequence. To solve the above problems, an automatic detection method for epilepsy was proposed, based on improved refined composite multi-scale dispersion entropy (IRCMDE) and particle swarm algorithm optimization support vector machine (PSO-SVM). First, the refined composite multi-scale dispersion entropy (RCMDE) is introduced, and then the segmented average calculation of coarse-grained sequence is replaced by local maximum calculation to solve the problem of information loss. Finally, the entropy value is normalized to improve the robustness of characteristic parameters, and IRCMDE is formed. The simulated results show that when examining the complexity of the simulated signal, IRCMDE can eliminate the issue of information loss compared with MDE and RCMDE and weaken the entropy change caused by different parameter selections. In addition, IRCMDE is used as the feature parameter of the epileptic EEG signal, and PSO-SVM is used to identify the feature parameters. Compared with MDE-PSO-SVM, and RCMDE-PSO-SVM methods, IRCMDE-PSO-SVM can obtain more accurate recognition results.

Milling chatter detection of thin-walled parts based on GA-SE-SCK-VMD and RCMDE

In the milling process, it is easy to produce chatter due to the low rigidity of the thin-walled structure, which leads to the deterioration of workpiece surface quality and reduces the service life of cutting tools and machine tools. Therefore, a new chatter detection method for thin-walled parts based on optimal variational mode decomposition (OVMD) and refined composite multi-scale dispersion entropy (RCMDE) is proposed in this paper. Firstly, to solve the problem that the decomposition effect of the variational mode decomposition (VMD) algorithm is greatly affected by its parameter, a genetic algorithm (GA) is used to iteratively optimize the parameter of the VMD algorithm, and a new index, square envelope spectral correlated kurtosis (SE-SCK), is introduced as the fitness function of the genetic algorithm. Then, the energy ratio of the decomposed signal is calculated as the principle of selecting sub-components, and the sub-components with rich chatter information are selected for signal reconstruction. To solve the problem that the multi-scale dispersion entropy (MDE) will miss some information in the multi-scale process, RCMDE is introduced to detect milling chatter. Finally, the experiment of the variable cutting depth in side milling of titanium alloy thin-walled parts is carried out. The experimental results show that the OVMD algorithm proposed can solve the problem of difficult separation of chatter frequency bands caused by mode aliasing and lay a foundation for subsequent chatter feature extraction. RCMDE is more conducive to chatter detection than the single-scale DE when the scale factor is 4. The distinguishing effect of RCMDE on the machining state is more than 50% higher than that of MDE when the scale factor is 4.

Empirical Variational Mode Decomposition Based on Binary Tree Algorithm.

Aiming at non-stationary signals with complex components, the performance of a variational mode decomposition (VMD) algorithm is seriously affected by the key parameters such as the number of modes , the quadratic penalty parameter and the update step . In order to solve this problem, an adaptive empirical variational mode decomposition (EVMD) method based on a binary tree model is proposed in this paper, which can not only effectively solve the problem of VMD parameter selection, but also effectively reduce the computational complexity of searching the optimal VMD parameters using intelligent optimization algorithm. Firstly, the signal noise ratio (SNR) and refined composite multi-scale dispersion entropy (RCMDE) of the decomposed signal are calculated. The RCMDE is used as the setting basis of the , and the SNR is used as the parameter value of the . Then, the signal is decomposed into two components based on the binary tree mode. Before decomposing, the and need to be reset according to the SNR and MDE of the new signal. Finally, the cycle iteration termination condition composed of the least squares mutual information and reconstruction error of the components determines whether to continue the decomposition. The components with large least squares mutual information (LSMI) are combined, and the LSMI threshold is set as 0.8. The simulation and experimental results indicate that the proposed empirical VMD algorithm can decompose the non-stationary signals adaptively, with lower complexity, which is O(n2), good decomposition effect and strong robustness.

Study of the Load Forecasting of a Wet Mill Based on the CEEMDAN-Refined Composite Multiscale Dispersion Entropy and LSTM Nerve Net

To address the problem of wet ball milling in a strong noise environment, it is difficult to accurately detect the internal load parameters of the cylinder during grinding. In this paper, a mill load parameter prediction method is proposed based on complementary ensemble empirical mode decomposition (CEEMDAN)-refined composite multiscale dispersion entropy (RCMDE) and-long and short-term memory (LSTM) neural networks. Using this method, the vibration signals of the mill barrel under strong noise were decomposed using the CEEMDAN algorithm, sensitive modal components with strong correlation with the original signal were selected for reconstruction using the correlation coefficient method, and features of the reconstructed signals under different load parameters were extracted through RCMDE. The load characteristic vector of an RCMDE mill was used as the input of LSTM neural networks, and the filling rate, material and ball ratio, and grinding concentration were used as the output to establish the internal load prediction model of wet mill. Experiment results show that the prediction method has a high accuracy, with average absolute percentage errors of the filling rate, feed-to-ball ratio, and grinding concentration of 6.08%, 3.50%, and 3.47%, and average absolute errors were of 0.0167, 0.0146, and 0.0146, respectively.

A Novel Bearing Faults Detection Method Using Generalized Gaussian Distribution Refined Composite Multiscale Dispersion Entropy

Rolling element bearings are a critical component of rotating machines and the presence of defects in the bearings may eventually lead to machine failure. Hence, early identification of such defects and severity assessment may avoid malfunctioning and breakdown of machines. Vibration signal features are often used to build fault diagnosis and fault classification systems. In this paper, a novel Refined Composite Multiscale Dispersion Entropy (RCMDE) based feature is proposed using a nonlinear mapping approach using the Generalized Gaussian Distribution (GGD)–Cumulative Distribution Function (CDF) with the different shape parameter β. This work combines the GGD Dispersion Entropy (DE) algorithm within the RCMDE framework with a feature selection algorithm, which is then used as input to a Multi-class Support Vector Machine (MCSVM) model for categorizing rolling element bearings fault conditions. The proposed method is validated using Case Western Reserve University (CWRU), Jiangnan University (JNU), and Southeast University (SEU) datasets. The experimental analysis shows that the GGD–RCMDE features are better in terms of classification accuracy, precision, recall and F1–score as compared to existing approaches.

Detection of Interturn Short-Circuit Faults in DFIGs Based on External Leakage Flux Sensing and the VMD-RCMDE Analytical Method

Fault detection based on external leakage flux can address various faults, such as short circuit faults in stators and rotors. External leakage flux sensing technology, as a noninvasive method, has been attracting increasing attention and research. However, for a high-power doubly fed induction generator (DFIG), the external leakage flux signals of the generator are easily overwhelmed by a strong noise background, and the fault diagnosis and recognition of stator and rotor interturn short circuits is complicated, which limits the practical engineering application of leakage flux sensing technology. Aiming at addressing interturn short circuit faults in DFIGs, this paper proposes a method for fault feature extraction and recognition of stator and rotor short circuits based on variational mode decomposition (VMD) and the refined composite multiscale dispersion entropy (RCMDE) analytical method for the external flux leakage of the generator. The optimized parameters of VMD are selected automatically by the genetic algorithm (GA), and VMD is adopted to adaptively decompose the external leakage flux signals into a series of intrinsic mode function (IMF) components. The evaluation criterion based on the correlation number in the frequency domain combined with the autocorrelation function is used to select the best IMF components with clear features. Two different components are chosen to reconstruct the flux leakage signal. The characteristic frequency of the reconstructed signal is analyzed by the Hilbert-Huang transform (HHT) and the total harmonic effective value of the characteristic component. To effectively identify and diagnose the generator stator and rotor interturn short circuit fault, RCMDE is used for the flux leakage reconstructed signal. The experimental results under different stator and rotor short-circuit levels show that this diagnosis method can effectively extract the weak feature information from the external flux leakage signals and perform fault feature extraction and recognition for stator and rotor short circuits.

Bearing Fault Diagnosis Based on Refined Composite Multi‐Scale Dispersion Entropy and Extenics

Considering the difficulty of extracting bearing fault signals of pumping unit and the complexity of diagnosis, a bearing fault diagnosis method based on refined composite multi‐scale dispersion entropy (RCMDE) and Extenics is proposed. Firstly, RCMDE is used to extract the features of bearing data. Using Fisher Ratio to reduce the dimensionality of RCMDE features and select them. The selected RCMDE features are used as the feature parameters of the matter element models to construct the classical domains and node domain of the four matter element models, and build the matter element models of the four healthy states of the bearing. Finally, the sample sets to be tested are input into the four health state models to calculate the comprehensive correlation degree value. The fault diagnosis is realized according to the principle of maximum comprehensive correlation degree. The results show that the detection rate of the proposed method for the four health states of the bearing is 98.8%. In order to verify the superiority of the proposed method, the method proposed in this paper is compared with the fault diagnosis method based on the combination of MDE and extenics, and the results verify the superiority of the proposed method in this paper. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Coordinated Approach Fusing RCMDE and Sparrow Search Algorithm-Based SVM for Fault Diagnosis of Rolling Bearings.

We propose a novel fault-diagnosis approach for rolling bearings by integrating variational mode decomposition (VMD), refined composite multiscale dispersion entropy (RCMDE), and support vector machine (SVM) optimized by a sparrow search algorithm (SSA). Firstly, VMD was selected from various signal decomposition methods to decompose the original signal. Then, the signal features were extracted by RCMDE as the input of the diagnosis model. Compared with multiscale sample entropy (MSE) and multiscale dispersion entropy (MDE), RCMDE proved to be superior. Afterwards, SSA was used to search the optimal parameters of SVM to identify different faults. Finally, the proposed coordinated VMD–RCMDE–SSA–SVM approach was verified and evaluated by the experimental data collected by the wind turbine drivetrain diagnostics simulator (WTDS). The results of the experiments demonstrate that the proposed approach not only identifies bearing fault types quickly and effectively but also achieves better performance than other comparative methods.

Automated detection of epileptic seizures using multiscale and refined composite multiscale dispersion entropy

Epilepsy is one of the most common neurological disorders. The electroencephalogram (EEG) is a valuable tool for the detection of epileptic seizures. The diagnosis of epilepsy requires the neurologists to continuously monitor the long-term EEG recordings of patients, which is a time-consuming and error-prone procedure. Therefore, automatic epileptic seizure detection becomes essential. Entropy-based methods are widely used for the automated detection of seizures from EEG signals due to the nonlinear and chaotic nature of these signals. In this work, we propose two recently introduced entropy features, multiscale dispersion entropy (MDE) and refined composite multiscale dispersion entropy (RCMDE) for detection of seizures. We assess the ability of MDE and RCMDE to discriminate the normal EEGs of healthy subjects, interictal (in between seizures), and ictal (during seizures) EEGs of epilepsy patients. We also investigate the two parameters namely, number of classes c and embedding dimension m of MDE and RCMDE that provide the best performance for seizure detection. For this purpose, the MDE and RCMDE values are estimated from normal, interictal, and ictal EEG signals, one-way ANOVA test is employed, and significant features are fed to a support vector machine (SVM) classifier. The experimental results demonstrate that both MDE and RCMDE are promising feature extraction methods that can quantify the complexity of EEG signals successfully and the highest classification accuracies were obtained when c=5 and m=3 for both MDE and RCMDE frameworks. Besides, we have compared the proposed MDE and RCMDE classification results with that of multiscale entropy (MSE) and multiscale permutation entropy (MPE) methods that have been previously applied for the study of seizure detection. It was found that MDE and RCMDE contribute significantly in improving the accuracy of seizure detection.

Separation of magnetotelluric signals based on refined composite multiscale dispersion entropy and orthogonal matching pursuit

Magnetotelluric (MT) data processing can increase the reliability of measured data. Traditional MT data denoising methods are usually applied to entire MT time-series, which results in the loss of useful MT signals and a decrease of imaging accuracy of electromagnetic inversion. However, targeted MT noise separation can retain part of the signal unaffected by strong noise and enhance the quality of MT responses. Thus, we propose a novel method for MT noise separation that uses the refined composite multiscale dispersion entropy (RCMDE) and the orthogonal matching pursuit (OMP) algorithm. First, the RCMDE is extracted from each segment of the MT data. Then, the RCMDEs for each segment are input to the fuzzy c-mean (FCM) clustering algorithm for automatic identification of the MT signal and noise. Next, the OMP method is utilized to remove the identified noise segments independently. Finally, the reconstructed signal consists of the denoised signal segments and the identified useful signal segments. We conducted simulation experiments and algorithm evaluations on electromagnetic transfer function (EMTF) data, simulated data and measured sites. The results indicate that the RCMDE can improve the stability of multiscale dispersion entropy (MDE) and multiscale entropy (ME) by analyzing the characteristics of the signal samples library, effectively distinguishing MT signals and noise. Compared with the existing technique of denoising entire time series, the proposed method uses the RCMDE as characteristic parameter and uses the OMP algorithm for noise separation, simplifies the multi-feature fusion, and improves the accuracy of signal-noise identification. Moreover, the denoising efficiency is accelerated, and the MT response in the low-frequency band is greatly improved.

A method to identify wet ball mill’s load based on CEEMDAN, RCMDE and SRNN classification

Ball mill plays a key role in mineral processing plant, and its load identification for optimal control has great significance for the energy consumption reduction and production efficiency improvement. The vibration signal of ball mill shell contains abundant load information, which can be used to identify ball mill load. However, due to the non-linear and non-stationary characteristics of vibration signals, as well as the heavy background noises, the load identification becomes a challenging task in practice. In this paper, a novel method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), refined composite multi-scale dispersion entropy (RCMDE), and stacked recurrent neural network (SRNN) is proposed. First, CEEMDAN algorithm is used to decompose the ball mill’s vibration signals and obtain the intrinsic mode function (IMF) components. Then, the sensitive IMF components are selected through the correlation coefficient method, and the signal is reconstructed with the sensitive IMF components. Secondly, the RCMDE of the reconstructed signal is calculated to obtain the load feature vector, and the dimension of the feature vector is reduced by principle component analysis (PCA). Thirdly, the SRNN is applied to establish a load recognition model, taking the feature vector as its input and the load state as its output. The experimental results show encouraging accuracy to apply this approach to recognize the wet ball mill’s load, with a recognition rate of 98.67%.

Integrated approach for ball mill load forecasting based on improved EWT, refined composite multi-scale dispersion entropy and fireworks algorithm optimized SVM

Shell vibration signals generated during grinding have useful information related to ball mill load, while usually contaminated by noises. It is a challenge to recognize load parameters with these signals. In this paper, a novel approach is proposed based on the improved empirical wavelet transform (EWT), refined composite multi-scale dispersion entropy (RCMDE) and fireworks algorithm (FWA) optimized SVM. Firstly, vibration signals are denoised by improved EWT, which uses cubic spline interpolation to calculate envelope spectrum for segmentation. Then, RCMDEs of the denoised signals are calculated as feature vectors. The vectors’ dimensionalities are reduced by principal component analysis (PCA). Finally, a mill load prediction model is established based on the FWA optimized SVM. The reduced feature vectors are fed to the model, thus material-to-ball ratio and filling rate being outputs. Grinding experiments show that the extracted features by RCMDE can effectively distinguish three load states. Meanwhile, experiments also show that FWA reduces the forecasting errors of material-to-balls ratio and filling rate by 1.9% and 2.9% compared with genetic algorithm (GA), as well as by 1.92% and 4.21% compared with particle swarm optimization (PSO) algorithm. It demonstrates that the proposed approach for ball mill load forecasting has high accuracy and stability.

A Method for Constructing Automatic Rolling Bearing Fault Identification Model Based on Refined Composite Multi-Scale Dispersion Entropy

In this paper, one of most widely utilized rolling bearings in rotating machinery is selected as the research object. Automatic rolling bearing fault identification model including support vector machine (SVM) training module, fault classification knowledge base module, and fault automatic identification module is proposed. A generalized method for automatic identification of rolling bearing faults based on refined composite multi-scale dispersion entropy (RCMDE) is developed. First, in order to solve the problem of setting the value range of the decomposition level K based on empirical knowledge for variational modal decomposition (VMD), a maximum kurtosis value method is proposed to determine the preset value range of K in whale optimization algorithm. Then, an improved VMD method is used to adaptively decompose the signal into a series of intrinsic mode function components. Next, the correlation coefficient method is employed to screen effective feature components of bearings in different health states for reconstruction. Through theoretical analysis, the calculated RCMDE value of reconstructed signal is screened and input as a feature value into the optimized SVM classifier for fault pattern recognition. The input of rolling bearing vibration data without preprocessing and the output of the fault identification which don't rely on empirical knowledge of external experts is realized. Experimental and engineering case data of rolling bearings under different equipment and operating environments are tested and validated. The results indicate that the model proposed in this paper shows good fault identification, demonstrates good generalization performance, and has beneficial industrial application prospect.

Rolling Bearing Sub-Health Recognition via Extreme Learning Machine Based on Deep Belief Network Optimized by Improved Fireworks

Rolling bearings, as the main components of the large industrial rotating equipment, usually work under complex conditions and are prone to break down. It can provide a certain theoretical basis for identifying the sub-health state of the industrial equipment by the analysis from the incipient weak signals. Thus, a sub-health recognition offline algorithm based on Refined Composite Multiscale Dispersion Entropy (RCMDE) and Deep Belief Network-Extreme Learning Machine (DBN-ELM) optimized by Improved Firework Algorithm (IFWA) is proposed. First of all, in light of the drawbacks that it is easy to fall into local optima and cross the boundary for exploding fireworks in Firework Algorithm (FWA), Cauchy mutation and adaptive dynamic explosion radius factor coefficient is introduced into IFWA. Secondly, Maximum Correlation Kurtosis Deconvolution (MCKD) optimized by the improved parameters is used to process the incipient vibration signals with nonlinearity, nonstationary, and IFWA is used to adaptively adjust to the period T and the filter length L in MCKD(IFWA-MCKD). Then, each sequence of signals is further extracted the feature-RCMDE to rich sample diversity. Finally, combining the powerful unsupervised learning capability from DBN and the generalization capability from ELM, DBN-ELM can be established. What's more, in order to avoid the interference of human on the parameters, IFWA is used to optimize the number of hidden nodes in DBN-ELM, and the IFWA-DBN-ELM is established. It shows that the algorithm has the higher sub-health recognition accuracy, better robustness and generalization, which has a better industrial application prospect.

EEpileptic electroencephalogram signal classification method based on elastic variational mode decomposition

Epilepsy is an extensive nervous system disease nowadays. Electroencephalogram (EEG) can capture the abnormal discharge of nerves in the brain duration of seizure and provide a non-invasive way to identify epileptogenic sites in the brain. In order to distinguish between focal epilepsy EEG signal and non-focal epilepsy EEG signal, in this paper we propose an automated epileptic EEG detection method based on the elastic variational mode decomposition (EVMD). The proposed EVMD algorithm is a method of analyzing the signals and also a processing method in time-frequency domain, in which the elastic net regression is used to reconstruct a constrained variational model in variational mode decomposition (VMD). Used in the VMD algorithm is the Tikhonov regularization that is also statistically called ridge regression as a solution of recovering the unknown signal and assessing the bandwidth of a mode, namely the variational equation constructed by VMD only has L2 norm. However, the ridge regression cannot select variables when the equation has multiple variables. Another regression method, called lasso regression, only has L1 norm and can select a more accurate model from multiple variables, but it has worse performance when variables have group effect or co-linearity. The elastic net regression has advantages of ridge regression and lasso regression, in other word, the variational equation constructed by EVMD has both L1 regularization item and L2 regularization item, so in this paper we propose the EVMD by elastic net regression. In addition, in this paper the EVMD is used to distinguish between focal epilepsy EEG signal and non-focal epilepsy EEG signal. Firstly, the original EEG signals are divided into several sub-signals where the test signals are divided into sub-signals with shorter durations by time series and a reasonable time overlap is kept between successive sub-signals. After that each sub-signal is decomposed into intrinsic mode functions by using the EVMD. Furthermore, the refined composite multiscale dispersion entropy (RCMDE) as feature is extracted from each intrinsic mode function where a Student’s t-test is used to assess the statistical differences between RCMDEs extracted from focal and non-focal EEG signals respectively. Finally, the support vector machine (SVM) is used to classify their features. For an epilepsy EEG signalspublic data set, the final experimental results show that the performance indices of accuracy, sensitivity, and specificity can reach 92.54%, 93.22% and 91.86% respectively.