A Deep Learning Model with Signal Decomposition and Informer Network for Equipment Vibration Trend Prediction.

Accurate equipment operation trend prediction plays an important role in ensuring the safe operation of equipment and reducing maintenance costs. Therefore, monitoring the equipment vibration and predicting the time series of the vibration trend is one of the effective means to prevent equipment failures. In order to reduce the error of equipment operation trend prediction, this paper proposes a method for equipment operation trend prediction based on a combination of signal decomposition and an Informer prediction model. Aiming at the problem of high noise in vibration signals, which makes it difficult to obtain intrinsic characteristics when directly using raw data for prediction, the original signal is decomposed once using the variational mode decomposition (VMD) algorithm optimized by the improved sparrow search algorithm (ISSA) to obtain the intrinsic mode function (IMF) for different frequencies and calculate the fuzzy entropy. The improved adaptive white noise complete set empirical mode decomposition (ICEEMDAN) is used to decompose the components with the largest fuzzy entropy to obtain a series of intrinsic mode components, fully combining the advantages of the Informer model in processing long time series, and predict equipment operation trend data. Input all subsequences into the Informer model and reconstruct the results to obtain the predicted results. The experimental results indicate that the proposed method can effectively improve the accuracy of equipment operation trend prediction compared to other models.

A Multi-Scale Anti-Multipath Algorithm for GNSS-RTK Monitoring Application.

During short baseline measurements in the Real-Time Kinematic Global Navigation Satellite System (GNSS-RTK), multipath error has a significant impact on the quality of observed data. Aiming at the characteristics of multipath error in GNSS-RTK measurements, a novel method that combines improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and adaptive wavelet packet threshold denoising (AWPTD) is proposed to reduce the effects of multipath error in GNSS-RTK measurements through modal function decomposition, effective coefficient sieving, and adaptive thresholding denoising. It first utilizes the ICEEMDAN algorithm to decompose the observed data into a series of intrinsic mode functions (IMFs). Then, a novel IMF selection method is designed based on information entropy to accurately locate the IMFs containing multipath error information. Finally, an optimized adaptive denoising method is applied to the selected IMFs to preserve the original signal characteristics to the maximum possible extent and improve the accuracy of the multipath error correction model. This study shows that the ICEEMDAN-AWPTD algorithm provides a multipath error correction model with higher accuracy compared to singular filtering algorithms based on the results of simulation data and GNSS-RTK data. After the multipath correction, the accuracy of the E, N, and U coordinates increased by 49.2%, 65.1%, and 56.6%, respectively.

Electric Field Detection System Based on Denoising Algorithm and High-Speed Motion Platform.

Effective denoising can ensure fast and accurate target detection. This paper presents an electric field measurement system based on a high-speed motion platform, which was built to analyze the characteristics of low frequency electric field noise. An offshore test has shown that it is possible to detect a low-frequency electric field using a high-speed motion platform. Low frequency electric field noise was then collected to analyze its characteristics in terms of time and frequency domains. Based on the noise characteristics, complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) was improved and combined with an adaptive threshold algorithm for denoising and reconstructing target containing noise signals. As revealed in the results, the proposed algorithm achieved highly effective denoising to overcome the line spectrum detection failure resulting from a high-speed motion platform. The detection range had also been improved from the original 853 m to 1306 m, a 53.1% increase.

Biometric Identification Method for Heart Sound Based on Multimodal Multiscale Dispersion Entropy.

In this paper, a new method of biometric characterization of heart sounds based on multimodal multiscale dispersion entropy is proposed. Firstly, the heart sound is periodically segmented, and then each single-cycle heart sound is decomposed into a group of intrinsic mode functions (IMFs) by improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN). These IMFs are then segmented to a series of frames, which is used to calculate the refine composite multiscale dispersion entropy (RCMDE) as the characteristic representation of heart sound. In the simulation experiments I, carried out on the open heart sounds database Michigan, Washington and Littman, the feature representation method was combined with the heart sound segmentation method based on logistic regression (LR) and hidden semi-Markov models (HSMM), and feature selection was performed through the Fisher ratio (FR). Finally, the Euclidean distance (ED) and the close principle are used for matching and identification, and the recognition accuracy rate was 96.08%. To improve the practical application value of this method, the proposed method was applied to 80 heart sounds database constructed by 40 volunteer heart sounds to discuss the effect of single-cycle heart sounds with different starting positions on performance in experiment II. The experimental results show that the single-cycle heart sound with the starting position of the start of the first heart sound (S1) has the highest recognition rate of 97.5%. In summary, the proposed method is effective for heart sound biometric recognition.

A Novel Signal Separation and De-Noising Technique for Doppler Radar Vital Signal Detection.

Doppler radar for monitoring vital signals is an emerging tool, and how to remove the noise during the detection process and reconstruct the accurate respiration and heartbeat signals are hot issues in current research. In this paper, a novel radar vital signal separation and de-noising technique based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), sample entropy (SampEn), and wavelet threshold is proposed. First, the noisy radar signal was decomposed into a series of intrinsic mode functions (IMFs) using ICEEMDAN. Then, each IMF was analyzed using SampEn to find out the first few IMFs containing noise, and these IMFs were de-noised using the wavelet threshold. Finally, in order to extract accurate vital signals, spectrum analysis and Kullback-Leible (KL) divergence calculations were performed on all IMFs, and appropriate IMFs were selected to reconstruct respiration and heartbeat signals. Moreover, as far as we know, there is almost no previous research on radar vital signal de-noising based on the proposed technique. The effectiveness of the algorithm was verified using simulated and measured experiments. The results show that the proposed algorithm could effectively reduce the noise and was superior to the existing de-noising technologies, which is beneficial for extracting more accurate vital signals.

An Adaptive Noise Reduction Method for High Temperature and Low Voltage Electromagnetic Detection Signals Based on SVMD Combined with ICEEMDAN.

In view of the low signal-to-noise ratio (SNR) of shear wave electromagnetic acoustic transducers (EMAT) in the detection of high-temperature equipment, the use of low excitation voltage (LEV) further deteriorates the detection results, resulting in the echo signal containing defects being drowned in noise. For the extraction of the EMAT signal, an adaptive noise reduction method is proposed. Firstly, the minimum envelope entropy is taken as the fitness function for the Harris Hawks Optimizer (HHO), and the optimal successive variational mode decomposition (SVMD) balance parameter is searched by HHO adaptive iteration to decompose LEV EMAT signals at high temperatures. Then the filter is carried out according to the excitation center frequency and correlation coefficient threshold function. Then, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is used to decompose the filtered signal and combine the kurtosis factor to select the appropriate intrinsic mode functions. Finally, the signal is extracted by the Hilbert transform. In order to verify the effectiveness of the method, it is applied to the low-voltage detection of 40Cr from 25 °C to 700 °C. The results show that the method not only suppresses the background noise and clutter noise but also significantly improves the SNR of EMAT signals, and most importantly, it is able to detect and extract the 2 mm small defects from the echo signals. It has great application prospects and value in the LEV detection of high-temperature equipment.

Forecasting China carbon price using an error-corrected secondary decomposition hybrid model integrated fuzzy dispersion entropy and deep learning paradigm.

Forecasting China's carbon price accurately can encourage investors and manufacturing industries to take quantitative investments and emission reduction decisions effectively. The inspiration for this paper is developing an error-corrected carbon price forecasting model integrated fuzzy dispersion entropy and deep learning paradigm, named ICEEMDAN-FDE-VMD-PSO-LSTM-EC. Initially, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is used to primary decompose the original carbon price. Subsequently, the fuzzy dispersion entropy (FDE) is conducted to identify the high-complexity signals. Thirdly, the variational mode decomposition (VMD) and deep learning paradigm of particle swarm optimized long short-term memory (PSO-LSTM) models are employed to secondary decompose the high-complexity signals and perform out-of-sample forecasting. Finally, the error-corrected (EC) method is conducted to re-modify and strengthen the above-predicted accuracy. The results conclude that the forecasting performance of ICEEMDAN-type secondary decomposition models is significantly better than the primary decomposition models, the deep learning PSO-LSTM-type models have superiority in forecasting China carbon price, and the EC method for improving the forecasting accuracy has been proved. Noteworthy, the proposed model presents the best forecasting accuracy, with the forecasting errors RMSE, MAE, MAPE, and Pearson's correlation are 0.0877, 0.0407, 0.0009, and 0.9998, respectively. Especially, the long-term forecasting ability for 750 consecutive trading prices is outstanding. Those conclusions contribute to judging the carbon price characteristics and formulating market regulations.

Multi level perspectives in stock price forecasting: ICE2DE-MDL.

This study proposes a novel hybrid model, called ICE2DE-MDL, integrating secondary decomposition, entropy, machine and deep learning methods to predict a stock closing price. In this context, first of all, the noise contained in the financial time series was eliminated. A denoising method, which utilizes entropy and the two-level ICEEMDAN methodology, is suggested to achieve this. Subsequently, we applied many deep learning and machine learning methods, including long-short term memory (LSTM), LSTM-BN, gated recurrent unit (GRU), and SVR, to the IMFs obtained from the decomposition, classifying them as noiseless. Afterward, the best training method was determined for each IMF. Finally, the proposed model's forecast was obtained by hierarchically combining the prediction results of each IMF. The ICE2DE-MDL model was applied to eight stock market indices and three stock data sets, and the next day's closing price of these stock items was predicted. The results indicate that RMSE values ranged from 0.031 to 0.244, MAE values ranged from 0.026 to 0.144, MAPE values ranged from 0.128 to 0.594, and R-squared values ranged from 0.905 to 0.998 for stock indices and stock forecasts. Furthermore, comparisons were made with various hybrid models proposed within the scope of stock forecasting to evaluate the performance of the ICE2DE-MDL model. Upon comparison, The ICE2DE-MDL model demonstrated superior performance relative to existing models in the literature for both forecasting stock market indices and individual stocks. Additionally, to our knowledge, this study is the first to effectively eliminate noise in stock item data using the concepts of entropy and ICEEMDAN. It is also the second study to apply ICEEMDAN to a financial time series prediction problem.

Improved complete ensemble empirical mode decomposition with adaptive noise and composite multiscale permutation entropy for denoising blast vibration signal.

Monitoring the building blast vibration signal is an efficient way to determine the power of blast vibration hazards. Due to the harsh measurement environment, noise is inevitably introduced into the recorded signals. This research presents a denoising approach based on Improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN) and Composite Multiscale Permutation Entropy (CMPE). First, the noisy blast vibration signal is decomposed into different intrinsic mode functions using ICEEMDAN; then multiple intrinsic mode functions (IMFs) are separated into pure and noisy using CMPE, the noisy IMFs are denoised using wavelet thresholding; finally the blast wave is reconstructed using the pure and denoised mixed IMFs. The proposed approach was compared with four other approaches (CEEMDAN-CMPE, VMD-CMPE, SVMD-CMPE, and WST). The results indicate that the proposed approach has better performance and can be considered as an effective denoising method for building blast vibration signals.

A new rainfall prediction model based on ICEEMDAN-WSD-BiLSTM and ESN.

Precipitation, as an important indicator describing the evolution of the regional climate system, plays an important role in understanding the spatial and temporal distribution characteristics of regional precipitation. Scientific and accurate prediction of regional precipitation is helpful to provide theoretical basis for relevant departments to guide flood and drought control. To address the uncertainty and nonlinear characteristics of precipitation series, this paper uses the established improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN)-wavelet signal denoising (WSD)-bi-directional long short-term memory (BiLSTM), and echo state network (ESN) models to predict precipitation of four cities in southern Anhui Province. The BiLSTM is used to predict the high-frequency components and the ESN to predict the low-frequency components, thus avoiding the influence between the two neural network predictions. The results show that the ICEEMDAN-WSD-BiLSTM and ESN models are more accurate. The average relative error reached 2.64% and the NSE (Nash-Sutcliffe efficiency coefficient) was 0.91, which was significantly better than the other four models. The model reveals the temporal change pattern and evolution characteristics of future precipitation, guides flood prevention and mitigation, and has certain theoretical significance and application value for promoting regional sustainable development.

A new fault feature extraction method of rolling bearings based on the improved self-selection ICEEMDAN-permutation entropy.

The vibration signals of rolling bearings are complex and changeable, and extracting meaningful features is difficult. Currently, the commonly used empirical mode decomposition (EMD) algorithms have the problem of mode aliasing. In this paper, a new feature extraction method based on the improved complete ensemble empirical mode decomposition with adapted noise (ICEEMDAN) and permutation entropy is proposed. In this method, the ICEEMDAN algorithm is first improved and optimized to enable a self-selection function The vibration signal is then decomposed into several intrinsic modal functions using this algorithm, and the permutation entropy is extracted as the fault feature of rolling bearings, which improves the accuracy of fault classification and realizes the intelligent feature extraction of different fault states. Then, the Case Western Reserve University dataset is used for verification, and the results show that this scheme can effectively separate the vibration signal characteristics of bearings in different states, and can be used to characterize the characteristics of different bearing signals. Finally, based on the mechanical transmission system bearing experimental platform independently developed by our school, the experimental results show that compared with the unimproved ICEEMDAN algorithm, the diagnostic accuracy rate of the proposed method is 99.5%, which is increased by 6.4%, and it can be effectively used for feature extraction of rolling bearings.

Fetal phonocardiogram signals denoising using improved complete ensemble (EMD) with adaptive noise and optimal thresholding of wavelet coefficients.

Although fetal phonocardiogram (fPCG) signals have become a good indicator for discovered heart disease, they may be contaminated by various noises that reduce the signals quality and the final diagnosis decision. Moreover, the noise may cause the risk of the data to misunderstand the heart signal and to misinterpret it. The main objective of this paper is to effectively remove noise from the fPCG signal to make it clinically feasible. So, we proposed a novel noise reduction method based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), wavelet threshold and Crow Search Algorithm (CSA). This noise reduction method, named ICEEMDAN-DWT-CSA, has three major advantages. They were, (i) A better suppress of mode mixing and a minimized number of IMFs, (ii) A choice of wavelet corresponding to the study signal proven by the literature and (iii) Selection of the optimal threshold value. Firstly, the noisy fPCG signal is decomposed into Intrinsic Mode Functions (IMFs) by the (ICEEMDAN). Each noisy IMFs were decomposed by the Discrete Wavelet Transform (DWT). Then, the optimal threshold value using the (CSA) technique is selected and the thresholding function is carried out in the detail's coefficients. Secondly, each denoised (IMFs) is reconstructed by applying the Inverse Discrete Wavelet Transform (IDWT). Finally, all these denoised (IMFs) are combined to get the denoised fPCG signal. The performance of the proposed method has been evaluated by Signal to Noise Ratio (SNR), Mean Square Error (MSE) and the Correlation Coefficient (COR). The experiment gave a better result than some standard methods.

[Vegetation cover change and its response to climate change on the Loess Plateau, Northwest China based on ICEEMDAN method]. / 基于ICEEMDANæ–¹æ³•çš„é»„åœŸé«˜åŽŸæ¤è¢«è¦†ç›–å˜åŒ–åŠå ¶å¯¹æ°”å€™å˜åŒ–çš„å“åº”.

The long-term series of geographic data and remote sensing data contain noise and perio-dic fluctuation. We used the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) to decompose the data of the normalized difference vegetation index (NDVI), precipitation, and temperature from 1982 to 2015 on per-pixels in the Loess Pla-teau to obtain residuals. Using the residual with less noise and periodic fluctuations, we examined the changes of NDVI and the relationship between NDVI and climatic factors. The results showed that the spatial change trend of NDVI was mainly increasing from 1982 to 2015 in the Loess Plateau. The significance of the change trend of residual NDVI (95.9%) was greater than the original NDVI (72.3%), with spatial variations. Temperature and precipitation could largely explain the changes in vegetation coverage. The proportions of areas with extremely significant positive and negative correlations between temperature and NDVI on the Loess Plateau were 83.7% and 13.9%, respectively, while that between precipitation and NDVI were 54.4% and 37.2%, respectively. There were obvious spatial variations in the responses of vegetation to climate change on the Loess Plateau. Different climatic factors had different effects on different types of vegetation. In general, temperature had stronger correlation with different vegetation than precipitation. Therefore, temperature was the main driving factor for the changes of vegetation cover in the Loess Plateau.

A hybrid air quality early-warning framework: An hourly forecasting model with online sequential extreme learning machines and empirical mode decomposition algorithms.

Modelling air quality with a practical tool that produces real-time forecasts to mitigate risk to public health continues to face significant challenges considering the chaotic, non-linear and high dimensional nature of air quality predictor variables. The novelty of this research is to propose a hybrid early-warning artificial intelligence (AI) framework that can emulate hourly air quality variables (i.e., Particulate Matter 2.5, PM2.5; Particulate Matter 10, PM10 and lower atmospheric visibility, VIS), the atmospheric variables associated with increased respiratory induced mortality and recurrent health-care cost. Firstly, hourly air quality data series (January-2015 to December-2017) are demarcated into their respective intrinsic mode functions (IMFs) and a residual sub-series that reveal patterns and resolve data complexity characteristics, followed by partial autocorrelation function applied to each IMF and residual sub-series to unveil historical changes in air quality. To design the prescribed hybrid model, the data is partitioned into training (70%), validation (15%) and testing (15%) sub-sets. The online sequential-extreme learning machine (OS-ELM) algorithm integrated with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is designed as a data pre-processing system to robustly extract predictive patterns and fine-tune the model generalization to a near-optimal global solution, which represents modelled air quality at hourly forecast horizons. The resulting early warning AI-based framework denoted as ICEEMDAN-OS-ELM model, is individually constructed by forecasting each IMF and residual sub-series, with hourly PM2.5, PM10, and VIS obtained by the aggregated sum of forecasted IMFs and residual sub-series. The results are benchmarked with many competing predictive approaches; e.g., hybrid ICEEMDAN-multiple-linear regression (MLR), ICEEMDAN-M5 model tree and standalone versions: OS-ELM, MLR, M5 model tree. Statistical metrics including the root-mean-square error (RMSE), mean absolute error (MAE), Willmott's Index (WI), Legates & McCabe's Index (ELM) and Nash-Sutcliffe coefficients (ENS) are used to evaluate the model's accuracy. Both visual and statistical results show that the proposed ICEEMDAN-OS-ELM model registers superior results, outperforming alternative comparison approaches. For instance, for PM2.5,ELM values ranged from 0.65-0.82 vs. 0.59-0.77 for ICEEMDAN-M5 tree, 0.59-0.74 for ICEEMDAN-MLR, 0.28-0.54 for OS-ELM, 0.27-0.54 for M5 tree and 0.25-0.53 for the MLR model. For remaining air quality variables (i.e., PM10 & VIS), the objective model (ICEEMDAN-OS-ELM) outperformed the comparative models. In particular, ICEEMDAN-OS-ELM registered relatively low RMSE/MAE, ranging from approximately 0.7-1.03 µg/m3(MAE), 1.01-1.47 µg/m3(RMSE) for PM2.5 whereas for PM10, these metrics registered a value of 1.29-3.84 µg/m3(MAE), 3.01-7.04 µg/m3(RMSE) and for Visibility, they were 0.01-3.72 µg/m3 (MAE (Mm-1)), 0.04-5.98 µg/m3 (RMSE (Mm-1)). Visual analysis of forecasted and observed air quality through a Taylor diagram illustrates the objective model's preciseness, confirming the versatility of early warning AI-model in generating air quality forecasts. The excellent performance ascertains the hybrid model's potential utility for air quality monitoring and subsequent public health risk mitigation.