Frequency Of Intrinsic Mode Functions Research Articles

Detekcija klimatskih kolebanja Hilbert-Huangovom metodom na podacima stoljetnog opservatorija Zagreb-Grič, Hrvatska

Advanced statistical methods are applied on long-term data sets from Zagreb-Grič centennial observatory in Croatia to address recent climate change and variabilities; annual averages are used. Hilbert-Huang transform (HHT), consisting of empirical mode decomposition (EMD) and Hilbert spectral analysis (HSA), is an empirically based data-analysis method for extracting periodic components embedded within generally nonlinear and non-stationary data. The EMD splits the original series into a so-called intrinsic mode functions (IMFs). First, using the EMD algorithm, intrinsic mode functions (IMFs) are obtained. The analysis of low frequency IMFs indicates significant influence of the North-Atlantic Oscillation on the air temperature, cloudiness and precipitation series in the part of northern Croatia. For the considered climatic elements, the analysis revealed mild deviations in natural fluctuations of the analyzed signal for the last 30 to 40 years, which are most likely caused by anthropogenic activities. Next, HSA is applied to each IMF obtained for the series of annual averages of sea level air pressure. In order to validate this approach and the results, an associated Hilbert spectrum (HS) is compared with the continuous wavelet analysis, i.e., this is another corresponding checkup. The comparison shows significantly improved time and frequency resolution in favor of HS. Moreover, HS provides a unique capability of displaying intra-wave frequency modulation, i.e., changes in frequency that occur within one cycle of oscillation.

Load forecasting for regional integrated energy system based on complementary ensemble empirical mode decomposition and multi-model fusion

The multiple loads of the Regional Integrated Energy System (RIES) possess characteristics of randomness and relatively higher complexity. The current forecasting methods struggle to effectively handle the non-stationary sequence of these multiple loads, leading to less accurate load forecasting. To address this problem, this paper proposes a multi-model fusion prediction method based on Complementary Ensemble Empirical Mode Decomposition (CEEMD), Genetic Algorithm-Long Short Term Memory (GA-LSTM), Radial Basis Fusion-Autoencoder (RBF-AE), and Particle Swarm Optimization-Support Vector Machine (PSO-SVM). First, the load sequence is decomposed into different frequency Intrinsic Mode Functions (IMFs) components using CEEMD. The IMFs components are then grouped based on their zero-crossing rate and Sample Entropy (SE), resulting in three distinct groups: high-, medium-, and low-frequency components. Next, the high-frequency load component, which exhibit strong randomness, are predicted using GA-LSTM. The medium-frequency load component, which have weaker randomness, are predicted using RBF-AE. The smooth and periodic low-frequency load component are predicted using PSO-SVM. The prediction results from these three models are reconstructed to obtain the final predictive value. Finally, experimental results confirm that the forecasting model can effectively handle non-stationary load sequences and demonstrate the highest level of forecasting accuracy.

A noise reduction method of rolling bearing based on empirical wavelet transform and adaptive time frequency peak filtering

The vibration signal of rolling bearing with variable operating conditions contains complex interference components, which will cause low fault diagnosis accuracy, especially in strong noise case. To solve this problem, we proposed a noise reduction method of rolling bearing with variable operating based on empirical wavelet transform and adaptive time-frequency peak filtering (EWT-ATFPF). Firstly, empirical wavelet transform is used to obtain different frequency intrinsic mode functions (IMFs). Secondly, a modified adaptive window length formula for time-frequency peak filtering (TFPF) is constructed by combining the sampling ratio index and a fault sensitivity indicator that calculated by kurtosis and correlation coefficients of IMFs, which can better characterize the impact components. Thirdly, to balance noise reduction effect and the fidelity of IMFs, we proposed an improved TFPF method by adaptively adjusting its windows length. The adaptive method could be carried out using the proposed fault sensitivity indicator and window length formula, and the denoising IMFs could be obtained by ATFPF. Finally, the denoising vibration signal is reconstructed by using the denoising IMFs. The performance of fault diagnosis of the proposed method is verified by using simulated signal and bearing fault test data. The results show that the proposed EWT-ATFPF method could effectively achieve noise reduction under variable operating conditions.

Image denoising for laser ultrasonic inspection of wire arc additive-manufactured components with a rough surface

ABSTRACT Laser ultrasonic testing (LUT) is a non-contact and non-destructive testing (NDT) technique which can detect the wire arc additive manufacturing (WAAM) component defect in hot state. However, the complex surface topography of the WAAM component induces a low signal to noise ratio (SNR) and a poor detection sensitivity. In this paper, a denoising method based on improved empirical mode decomposition with adaptive noise (ICEEMDAN) and Wavelet Packet Transform (WPT) was applied in the LUT of the WAAM component. All the signals in the LUT scan maps with low SNR were decomposed into a series of intrinsic mode functions (IMFs) using ICEEMDAN. The Pearson correlation coefficient of the original signal and the IMFs were calculated. The high frequency (HF) and low frequency (LF) IMFs with correlation coefficients under the threshold were denoised using WPT and deleted, respectively. The denoised IMFs and the IMFs without processing were stacked up to compose the denoised signal and plot the denoised scan maps. The denoising results show that the proposed method improved the LUT efficiency and sensitivity. Finally, the denoising method was applied and verified in the LUT of the WAAM nuclear power pipeline nozzle.

A New Hybrid Short Term Solar Irradiation Forecasting Method Based on CEEMDAN Decomposition Approach and BiLSTM Deep Learning Network with Grid Search Algorithm

An accurate and efficient forecasting of solar energy is necessary for managing the electricity generation and distribution in today’s electricity supply system. However, due to its random character in its time series, accurate forecasting of solar irradiation is a difficult task; but it is important for grid management, scheduling and its balancing. To fully utilize the solar energy in order to balance the generation and consumption, this paper proposed an ensemble approach using CEEMDAN-BiLSTM combination to forecast short term solar irradiation. In this, Complete Ensemble Empirical Mode Decomposition with adaptive noise (CEEMDAN) extract the inherent characteristics of time series data by decomposing it into low and high frequency Intrinsic Mode Functions (IMF’s) and Bidirectional Long Short Term Memory (BiLSTM) used as a forecasting tool to forecast the solar Global Horizontal Irradiance (GHI). Furthermore, using extensive experimental analysis, the research minimizes the number of IMF’s by integrating the CEEMDAN decomposed component (IMF1–IMF14) in order to increase the prediction accuracy. Then, for each IMF subseries, the trained standalone BiLSTM network are assigned to carry out the forecasting. In last stage, the forecasted results of each BiLSTM network are aggregate to compile final results. Two year data (2012–13) of Delhi, India from National Solar Radiation Database (NSRDB) has been used for training while one year data (2014) used for testing purpose for the same location. The proposed model performance is measured in terms of root mean square error (RMSE), mean absolute percentage error (MAPE), Correlation coefficient (R22) and forecast skill (FS). For the comparative analysis of proposed model, several others models: persistence model, unidirectional deep learning models: long short term memory (LSTM), gated recurrent unit (GRU), BiLSTM and two CEEMDAN based BiLSTM models are developed. The proposed model achieved lowest annual average RMSE (18.86 W/m22, 22.24 W/m22, 26.25 W/m22) and MAPE (2.19%, 4.81%, 6.77%) among the other developed models for 1-hr, 2-hr and 3-hr ahead solar GHI forecasting respectively. The maximum correlation coefficient (R22) obtained by the proposed model is 96.4 for 1-hr ahead respectively; on the other hand, forecast skill (%) of 89% with reference to benchmark model. Various test such as: Diebold Mariano Hypothesis test (DMH) and directional change in forecasting (DC) are used to analyze the sensitivity with reference to the difference in forecasted and observed value.

Fault location of flexible grounding distribution system based on multivariate modes and kurtosis calibration

Aiming at the problems of large fault location errors when the traditional traveling wave fault location is applied to flexible ground distribution systems. This paper proposed the fault location of flexible grounding distribution system based on multivariate modes and kurtosis calibration. Firstly, a disturbance signal is generated by putting a small resistor in parallel. This signal reaches the fault point and undergoes a sudden change, generating an aerial mode traveling wave signal. Secondly, it used the multivariate variational mode decomposition algorithm to decompose the aerial mode current and extracts the fault features. Then, the discrete kurtosis value is calculated for the highest frequency intrinsic mode function component. The moment of maximum kurtosis is the arrival time of the aerial mode current. Finally, it adopted the head-end detection device to calculate the fault distance. For the complex topology of the flexible ground distribution systems, the localization equation of the overhead line, cable line, and hybrid lines are studied, and the pseudo-fault points are excluded by adding auxiliary devices at the branch end. The simulation results demonstrate that the proposed method can accurately locate faults and is not affected by the fault's initial phase angle, transition resistance, and location.

Carbon price combination prediction model based on improved variational mode decomposition

Carbon price is one of the core factors in the carbon trading process, so it is of great significance to establish a carbon price prediction model for guiding the carbon trading market to make scientific and reasonable decision. In order to improve the accuracy of carbon price prediction, a carbon price combination prediction model with variational mode decomposition based on seagull optimization algorithm (SVMD), fluctuation-based dispersion entropy (FDE), extreme learning machine (ELM) and kernel extreme learning machine (KELM) optimized by JAYA algorithm (JAYA-KELM), named SVMD-FDE-ELM-JAYA-KELM, is proposed. To solve the selection of mode number K and the penalty factor α of VMD, SVMD is proposed, which realizes adaptive determination of the parameter K and α. The idea of the SVMD-FDE-ELM-JAYA-KELM is roughly as follows. Firstly, SVMD decomposes carbon price into a series of intrinsic mode functions (IMFs). According to the FDE value, these IMFs are divided into high frequency IMFs or low frequency IMFs. Secondly, JAYA-KELM is established for high frequency IMFs and ELM is established for low frequency IMFs. Finally, the predicted value of carbon price is reconstructed to complete the prediction. The experimental results show that the proposed model has best prediction accuracy, and provides a new method for carbon price prediction.

A novel method for frequency feature extraction of ship radiated noise based on variational mode decomposition, double coupled Duffing chaotic oscillator and multivariate multiscale dispersion entropy

The processing of ship radiated noise is a research hotspot in the field of military and marine resource exploration. Frequency characteristic is an important characteristic of ship radiated noise. Ship radiated noise consists of line spectrum and continuous spectrum, and the frequency features are mainly reflected by line spectrum. Accurate extraction of line spectrum frequency feature is of great significance to realize ship target classification and recognition. This paper proposes a novel method for frequency feature extraction of ship radiated noise based on variational mode decomposition (VMD), double coupled Duffing chaotic oscillator (DCDCO) and multivariate multiscale dispersion entropy (mvMDE), named VMD-DCDCO-mvMDE. For the first time, DCDCO and mvMDE are applied to the feature extraction of ship radiated noise. Firstly, ship radiated noise is decomposed into a series of intrinsic mode functions (IMFs) by VMD. The decomposition layers K of VMD are determined according to the decomposition results of EMD. Secondly, adjust γand let d = 2 to leave DCDCO in critical chaotic state and detect the frequency of low frequency IMF. The mvMDE of the output signal of chaotic oscillator is calculated in the frequency range of DCDCO in the large scale periodic state, and the accurate frequency is determined by the minimum value of mvMDE. Finally, the extracted frequency feature parameters are input into the self-organizing mapping (SOM) neural network to classify and recognize different ship targets. In the analog signal experiment, the maximum frequency error of VMD-DCDCO-MVMDE extraction is only 0.01%, while the minimum error of the current method is 0.33%. The proposed method can extract frequency feature more accurately. In the measured signal experiment, the results show that the correct rate of the proposed method can reach 100% for the classification and recognition of the three groups of ship radiated noise, while the correct rate of the current method is the highest at 84%. The proposed method can effectively extract the line spectrum frequency feature of ship radiated noise, and the classification accuracy is higher, and the recognition effect is better.

Light curve VMD-MI: simultaneous estimation of precession and spin rates of space targets using light curves.

Optical data are important data sources for operating state estimation of space targets. Inversion of the rotation rate of tumbling targets via light curves can help us perform on-orbit services. However, previous methods cannot estimate the precession and spin rates of tumbling targets from light curves simultaneously. To solve the problem, an efficient precession and spin rate estimation algorithm for tumbling targets is proposed in this paper. The method combines the variational mode decomposition (VMD) method and mutual information (MI). Specifically, VMD is utilized to decompose each light curve into discrete frequency intrinsic mode functions (IMFs). Then, the MI between each IMF and light curve is generated, and the IMF frequencies corresponding to the two maximum MI values are extracted as spin and precession frequencies. Finally, the two frequencies are converted into spin and precession rates. Experimental results show that the estimation accuracy of the precession and spin rates is no less than 97% for a small nutation angle (no greater than 20º). The method provides a simple way to invert a space target state and mine more information from light curves.

A hybrid prediction method based on empirical mode decomposition and multiple model fusion for chaotic time series

Chaotic time series exist in nature, such as in the field of meteorology or physics, with unpredictable features caused by their inherent high complexity and nonstationary motion. To improve the prediction effect of chaotic time series, a hybrid prediction method on the basis of the empirical mode decomposition (EMD) and neural networks (NN) is proposed. First, the original chaotic time series is decomposed into several intrinsic mode functions (IMFs) and one residual by EMD, whose components are divided into high, medium and low components by using the runs test. The high IMFs change dramatically, and the correlation among data is not high; therefore, we use the fuzzy first-order transition rules trained neural network (NN-FFOTR) model to predict the high frequency components. Autoregressive integrated moving average (ARIMA) models are applied according to the random characteristic exhibited by the medium frequency IMFs and residual. Finally, the prediction results of the two models are adaptively superimposed together to obtain the final prediction results. The proposed hybrid method is named EMD-ARIMA-NN-FFOTR for simplicity. The simulation results are verified through two typical chaotic time series including the Lorenz-63 system and Mackey-Glass time series. For the x-axis of the Lorenz-63 system, the experimental results indicates that the symmetric mean absolute percentage error (SMAPE) of the ARIMA, NN-FFOTR, ARIMA-NN-FFOTR and EMD-ARIMA-NN-FFOTR are 1.0657, 1.5281, 1.0657 and 0.0041;the root mean square error (RMSE) are 2.2591,0.6830,0.4231 and 0.0012; the mean absolute error (MAE) are 50.5149,15.2130,9.4610 and 0.0019; the sum of error squares (SSE) are 101.4,96.32,65.8300 and 21.6351; and the Theil inequality coefficient are 0.0674, 0.0741, 0.0213 and 0.0162, the proposed model's TIC are much lower than those of the comparison models. The values of the R square of the developed prediction approach utilizing ARIMA, NN-FFPTR, ARIMA-NN-FFOTR and EMD-ARIMA-NN-FFOTR method are 0.9674,0.9741, 0.9799 and 0.9963, and the index of agreement are 0.8992,0.9921,0.9845 and 0.9991, the value of the R-square and the index of agreement of the proposed model's are much higher than those of the comparison models. The Pearson's test results show that the association strength between the actual value and the predicted values of the proposed model is stronger. These results show the following: (a) compared with other related, recent studies, the prediction accuracy of the hybrid system EMD-ARIMA-NN-FFOTR proposed in this article is higher; (b) the proposed hybrid system attains superior performance compared with single models; and (c) the proposed hybrid system balances the forecast accuracy and convergence speed simultaneously during prediction. Therefore, it is feasible to apply the hybrid model to the prediction of chaotic time series.

Time‐dependent intrinsic correlation analysis of crude oil and the US dollar based on CEEMDAN

AbstractIn this article, we analyze the dynamic linkage between crude oil price and the US dollar at multi‐scale frequencies using time‐dependent intrinsic correlation analysis based on the complete ensemble empirical mode decomposition with adaptive noise. After applying a refined method to extract the trend, we reveal that the overall correlation and the long‐term trend correlation exhibit very similar patterns. The correlation coefficients between crude oil and the US dollar are negative at most of the time; however, the coefficients become positive in certain periods, such as 2013–2014 and 2017–2018. Furthermore, the negative correlations in high frequency intrinsic mode functions (IMFs), with a shorter time horizon, are weaker and display time‐varying characteristics, whereas the correlation in low frequency IMFs, with a longer time horizon, are stronger and more static. The findings of this article may have important implications for investors to construct optimal portfolio diversification.

Revealing stroke survivor gait deficits during rehabilitation using ensemble empirical mode decomposition of surface electromyography signals

In this paper, an attempt is made to explain the stroke survivor gait recovery mechanism using Ensemble Empirical Mode Decomposition (EEMD) of surface electromyography signals (sEMG). The existing gait functionality indices could describe the gait recovery through the improvement of gait parameters such as stride length, heel clearance, stance and swing time etc. However these indices reveal little information related to the kinesiology status. To address this knowledge gap, we propose an approach to decompose the sEMG signals acquired during the rehabilitation treatment using EEMD so as to reveal gait deficits in the perspective of motor unit recruitment and its firing patterns. 15 stroke survivors were recruited and their sEMG signals acquired from Gastrocnemius Lateral (GL) and Tibialis Anterior (TA) muscles were further decomposed into different intrinsic mode functions (IMF) using EEMD. Each IMF contains superimposed motor unit action potential (MUAP) with its specific frequency range. The evolvement of IMFs over three recovery stages was observed. Results show that foot drop can be caused by lack of high frequency IMF components in TA during the swing phase. Besides that, spasticity was observed in all IMF components from GL muscle that leads to counteract with TA muscle. Lack of high frequency IMF components in GL during the stance phase would increase the stance time. Co-activation from TA during the stance phase could contribute to this effect as well. In conclusion, the proposed approach could reveal additional information at kinesiology level to explain how well a stroke survivor recovers.

Method for Structural Frequency Extraction from GNSS Displacement Monitoring Signals

Abstract This article focused on the obstacles and the solution of the structural frequency extraction from the global navigation satellite system (GNSS) displacement monitoring signals. Based on the analysis of the signals obtained from a real-time dynamic displacement monitoring system of a compound cable-stayed bridge in Guangzhou, China, it was found that the ultra-low frequency components and the noise in the signal result in the errors and distortion in the structural frequency extraction. Accordingly, a method was proposed. The empirical mode decomposition was firstly carried out to decompose the GNSS signal into a set of intrinsic mode functions (IMFs). A coefficient was used, and the cut-off frequency was set to distinguish effective IMFs, which contain structural oscillation information, from high frequency noise IMFs and trends (including ultra-low frequency IMFs). Then the wavelet was applied to remove the noise of the effective IMFs. A reconstructed signal was obtained by summing up the denoised effective IMFs. The structural frequency was obtained from the reconstructed signal using the fast Fourier transform. The results demonstrate the proposed method can reduce the influence of the ultra-low frequency components and the noise and extract the accurate structure frequency from GNSS displacement monitoring signals.

A Harmonic Based Pilot Protection Scheme for VSC-MTDC Grids with PWM Converters

This paper presents a selective harmonic-based pilot protection scheme for detecting faults happened in the DC transmission section of VSC-MTDC grids with pulse width modulation (PWM) voltage source converters (VSCs). When a DC fault occurs in VSC-MTDC grids with PWM converters, first carrier frequency harmonic (FCFH) currents will be generated by all VSCs through the grid. FCFH currents have different flowing directions depending on the characteristics and the location of the fault. According to the characteristics of the existing FCFH in the fault currents, a selective pilot protection algorithm is designed for VSC-MTDC grids. Considering the internal and external DC transmission faults for specific zones, and the circulating flow of FCFH current in the DC link capacitors, the relays cannot detect FCFH currents for external faults, while for the internal faults, FCFH currents are clearly detected. To design the selective protection algorithm, Hilbert-Huang transform (HHT) is used to detect the instantaneous frequency and the instantaneous amplitude of the high frequency intrinsic mode function (IMF)s, which are extracted from the fault current waves. Multiple faults with different characteristics are applied to CIGRE DCS-2 VSC-MTDC grid with two-level and three-level VSCs modeled in PSCAD, and the HHT-based selective protection scheme is designed in MATLAB. According to the results, the proposed algorithm can truly discriminate between internal and external faults.

Fault feature extraction for rolling element bearing diagnosis based on a multi-stage noise reduction method

To extract impulsive feature from vibration signals with strong background noise and interference components for accurate bearing diagnostics. A multi-stage noise reduction method is proposed based on ensemble empirical mode decomposition (EEMD), wavelet thresholding (WT) and modulation signal bispectrum (MSB). Firstly, noisy vibration signals are applied with EEMD to obtain a list of intrinsic mode functions (IMFs) that leverage the desired modulation components to different degrees. Then, a number of initial IMFs in the high frequency range, which are separated by using the mean of the standardized accumulated modes (MSAM) to have more modulation contents, are further denoised by a wavelet thresholding approach. These cleaned IMFs in the high frequency are combined with the low frequency IMFs to construct a pre-denoised signal that maintains the modulation properties of the raw signal. Finally, modulation signal bispectrum (MSB) is used to extract the modulation signature by suppressing further the residual random noise and deterministic interference components. This multi-stage noise reduction method was validated through a simulation study and two experimental fault cases studies of rolling element bearing. The results were more accurate and reliable in diagnosing the bearing inner and outer race defects in comparison with the individual use of the state-of-the-art EEMD and MSB.

High-G Calibration Denoising Method for High-G MEMS Accelerometer Based on EMD and Wavelet Threshold.

High-G MEMS accelerometers have been widely used in monitoring natural disasters and other fields. In order to improve the performance of High-G MEMS accelerometers, a denoising method based on the combination of empirical mode decomposition (EMD) and wavelet threshold is proposed. Firstly, EMD decomposition is performed on the output of the main accelerometer to obtain the intrinsic mode function (IMF). Then, the continuous mean square error rule is used to find energy cut-off point, and then the corresponding high frequency IMF component is denoised by wavelet threshold. Finally, the processed high-frequency IMF component is superposed with the low-frequency IMF component, and the reconstructed signal is denoised signal. Experimental results show that this method integrates the advantages of EMD and wavelet threshold and can retain useful signals to the maximum extent. The impact peak and vibration characteristics are 0.003% and 0.135% of the original signal, respectively, and it reduces the noise of the original signal by 96%.

Two-Level W-ESMD Denoising for Dynamic Deflection Measurement of Railway Bridges by Microwave Interferometry

Aiming to reduce the influences of noise for dynamic deflection measurements of railway bridges by microwave interferometry, this paper proposes a two-level wavelet-based extreme-point symmetric mode decomposition (ESMD) denoising algorithm on the basis of the characteristics of different noise frequency scales. First, the ESMD method is adopted to decompose the obtained dynamic deflection signal into a series of intrinsic mode functions (IMFs) from high to low frequency. Second, the first-level denoising is performed to eliminate the influences of high frequency noise by integrating the heursure threshold rule, soft thresholding, and different decomposition scales for high or low frequency IMFs, respectively. Third, the reconstructed first-level denoised signal is further decomposed into a series of IMFs, from high to low frequency, by the ESMD method. Last, the second-level denoising is performed to eliminate the influences of low frequency noise and some residual high frequency noise. For the low frequency noise, by using the heursure threshold rule, soft thresholding and a lower decomposition scale, and for some residual high frequency noise by using minimax threshold rule, hard thresholding and a moderate decomposition scale, the results on both simulated and real dynamic deflection signals show that the proposed two-level denoising algorithm is superior to wavelet threshold denoising and conventional empirical mode decomposition-based denoising techniques.

A Novel Decomposition-Ensemble Based Carbon Price Forecasting Model Integrated with Local Polynomial Prediction

Abstract This study proposes a decomposition-ensemble based carbon price forecasting model, which integrates ensemble empirical mode decomposition (EEMD) with local polynomial prediction (LPP). The EEMD method is used to decompose carbon price time series into several components, including some intrinsic mode functions (IMFs) and one residue. Motivated by the fully local characteristics of a time series decomposed by EEMD, we adopt the traditional LPP and regularized LPP (RLPP) to forecast each component. This led to two forecasting models, called the EEMD-LPP and EEMD-RLPP, respectively. Based on the fine-to-coarse reconstruction principle, an auto regressive integrated moving average (ARIMA) approach is used to forecast the high frequency IMFs, and LPP and RLPP is applied to forecast the low frequency IMFs and the residue. The study also proposes two other forecasting models, called the EEMD-ARIMA-LPP and EEMD-ARIMA-RLPP. The empirical study results showed that the EEMD-LPP and EEMD-ARIMA-LPP outperform the two other models. Furthermore, we examine the robustness and effects of parameter settings in the proposed model. Compared with existing state-of-art approaches, the results demonstrate that EEMD-ARIMA-LPP and EEMD-LPP can achieve higher level and directional predictions and higher robustness. The EEMD-LPP and EEMD-ARIMA-LPP are promising approaches for carbon price forecasting.

Multi-step wind speed forecasting based on a hybrid decomposition technique and an improved back-propagation neural network

Abstract Precise and reliable wind-speed prediction is vital for wind-farm operational planning. However, wind speed series usually have complex features, such as non-linearity and volatility, which makes the wind energy forecasting highly difficult. Aimed at this challenge, this paper proposes a forecasting architecture based on a new hybrid decomposition technique (HDT) and an improved flower-pollination algorithm (FPA)-back propagation (BP) neural network prediction algorithm. The proposed HDT combines the complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) and the empirical wavelet transform (EWT), which is unique, since the EWT is specifically employed to further decompose the high frequency intrinsic mode functions (IMFs) generated by CEEMDAN to reduce prediction complexity. And then an improved BPNN with the flower-pollination algorithm is applied to forecast all of the decomposed IMFs and modes. To investigate the forecasting ability of the proposed model, the wind speed data collected from two different wind farms in Shandong, China were used for multi-step ahead forecasting. The experimental results show that the proposed model performs remarkably better than all of the other considered models in one-step to five-step wind speed forecasting, which indicates that the proposed model is highly suitable for non-stationary multi-step wind speed forecasting.

A Combined Methodology to Eliminate Artifacts in Multichannel Electrogastrogram Based on Independent Component Analysis and Ensemble Empirical Mode Decomposition

Cutaneous measurements of electrogastrogram (EGG) signals are heavily contaminated by artifacts due to cardiac activity, breathing, motion artifacts, and electrode drifts whose effective elimination remains an open problem. A common methodology is proposed by combining independent component analysis (ICA) and ensemble empirical mode decomposition (EEMD) to denoise gastric slow-wave signals in multichannel EGG data. Sixteen electrodes are fixed over the upper abdomen to measure the EGG signals under three gastric conditions, namely, preprandial, postprandial immediately, and postprandial 2 h after food for three healthy subjects and a subject with a gastric disorder. Instantaneous frequencies of intrinsic mode functions that are obtained by applying the EEMD technique are analyzed to individually identify and remove each of the artifacts. A critical investigation on the proposed ICA-EEMD method reveals its ability to provide a higher attenuation of artifacts and lower distortion than those obtained by the ICA-EMD method and conventional techniques, like bandpass and adaptive filtering. Characteristic changes in the slow-wave frequencies across the three gastric conditions could be determined from the denoised signals for all the cases. The results therefore encourage the use of the EEMD-based technique for denoising gastric signals to be used in clinical practice.