Intrinsic Mode Functions Research Articles

Fault diagnosis of rolling bearing under complex working conditions based on time-frequency joint feature extraction-deep learning

The same independent distribution is not obeyed for the data collected under complex working conditions such as time-varying speed or loading, and the fault characteristic information is insufficient, resulting in low accuracy by using traditional methods. To solve the above problem, a fault diagnosis method based on time-frequency joint feature extraction combined with deep learning is proposed. Firstly, the original vibration signal is processed by variational mode decomposition (VMD) to obtain several intrinsic mode functions (IMFs), then the sensitive components are selected by calculating the steepness values of each IMF. Subsequently, the characteristic features of the selected sensitive component in time-domain, frequency-domain and time-frequency domain are calculated to form the time-frequency joint feature. The sparse attention mechanism (SAM) is combined with the advantages of recurrent neural network (RNN) and convolutional neural network (CNN) to form a hybrid deep learning model (SAM-RNN-DCNN). Finally, the time-frequency joint features are combined with the hybrid model for fault diagnosis. Experimental verifications are carried out by using data sets under variable rotational speed, variable load and strong noise interference, and the analysis results show that the proposed method has high diagnostic accuracy, good diagnostic performance and robustness under complex working conditions.

EI-ISOA-VMD: Adaptive denoising and detrending method for nuclear circulating water pump impeller

As a key component of the nuclear circulating water pump, it is difficult to extract effective information from low-quality impeller signal because of the interference noise and non-stationary trend, such as water flow impact, vibrations from unrelated components, and sensor noise. Traditional signal denoising methods, particularly those utilizing variational mode decomposition, often require manual parameter tuning, resulting in unsatisfactory outcome. To address these issues, this paper proposes a signal denoising and detrending method based on the evaluation index driven the improved seagull algorithm optimized for variational mode decomposition (EI-ISOA-VMD). During the optimization process, sinusoidal chaotic mapping is utilized for initializing the seagull population, while a tanh function is employed to design nonlinearly decreasing inertia weights. Furthermore, the Levy flight mechanism enhances the randomness of position updates and optimizes seagull individuals beyond the boundary range in order to form the improved seagull optimization algorithm. The denoising, detrending process, and evaluation index proposed in this paper are utilized as the fitness function for the improved seagull optimization algorithm to optimize key parameters of variational mode decomposition. During the denoising and detrending process, the trend component is initially selected using the mean ratio method. The useful, low noise and high noise intrinsic mode functions are screened by correlation coefficient and weighted permutation entropy. Subsequently, the low noise components are denoised by wavelet thresholding method, and the high noise components are discarded to finally reconstruct the signal. The experimental results demonstrate that the proposed method effectively eliminates noise and trend components in low-quality signal while preserving more valuable information.

Diagnosing multiple faults in rotating machinery using empirical mode decomposition and blind source separation methods

It is a challenging task to accurately diagnose multiple faults in a rotating machinery. In this paper, the authors have used empirical mode decomposition (EMD) and blind source separation (BSS) methods for this purpose. A portable rotating machinery setup is made in the laboratory and faults such as bearing inner and outer race faults, angular misalignment are created into it. The vibration data is collected using SPM made LEONOVA DIAMOND(r) FFT analyzer and processed using CONDMASTER RUBY(r) and MATLAB(r) softwares. Firstly, wavelet transform is applied to the signal to denoise it. After this, EMD is implemented to decompose the signal into different intrinsic mode functions (IMFs). After preprocessing these IMFs using the principal component analysis (PCA), BSS is used to extract fault-related information from the IMFs. A comparison of the results obtained from EMD and PCA-BSS is also presented in the paper. Keywords: Rotating machinery, Multiple faults, Vibration data, Wavelet transform, Empirical mode decomposition, Blind source separation, Principal component analysis.

Fall Detection Based on Data-Adaptive Gaussian Average Filtering Decomposition and Machine Learning

Falls are a significant health concern leading to increased morbidity and healthcare costs, especially for the elderly. Early and accurate detection of fall events is critical for timely intervention and preventing severe complications. This study presents a novel approach to triaxial accelerometer signals by employing data-adaptive Gaussian average filtering (DAGAF) decomposition in conjunction with machine learning techniques for fall detection. The triaxial accelerometer signals from the FallAllD dataset were decomposed into intrinsic mode functions (IMFs) and a residual component, from which feature vectors were extracted to train support vector machine (SVM) and k-nearest neighbor (kNN) classifiers. Experimental results demonstrate that the combination of the first and the third IMFs with the residual component yields the highest classification accuracy of 96.34%, with SVM outperforming kNN across all performance metrics. This approach significantly improves fall detection accuracy compared to using raw accelerometer signals, highlighting its potential in enhancing wearable fall detection systems. The proposed DAGAF decomposition method not only enhances feature extraction but also provides a promising advancement in the field, suggesting its potential to increase the reliability and accuracy of fall detection in practical applications.

Power Quality Disturbance Monitoring in PV Integrated Power System with Mode Decomposition and Ensemble Extreme Learning Machine

Power quality disturbance (PQD) monitoring has become an important issue in modern power system due to integration of several renewable energy sources such as photovoltaic (PV), wind energy system (WES), Fuel cells etc. This research presents a mode decomposed based ensemble extreme learning machine (EELM) to recognise and classify the PQD events with higher accuracy in terms of rapid learning speed and smaller computational burden in a complete PV based power system, The PQD signals are decomposed using a variational mode decomposition (VMD) to obtain effective band limited intrinsic mode functions (BIIMF) which leads to compute robust features and improves classification accuracy. For Power Quality Disturbances detection and classification, an ensemble extreme learning machine is suggested since an ensemble outperforms any single contributing model in terms of performance and prediction. The proposed VMD-EELM approach is validated in a modified IEEE 13 Bus system integrating PV with eleven types of PQDs. The proposed research having 100% classification accuracy for no noise and 99.88%, 99.94% 99.94% for 20dB, 30dB and 40dB noises respectively. It is being demonstrated that the suggested method can reliably identify and track PQD occurrences both with and without noise.

MD-BiMamba: An aero-engine inter-shaft bearing fault diagnosis method based on Mamba with modal decomposition and bidirectional features fusion strategy

Inter-shaft bearing fault diagnosis can greatly save maintenance costs and guarantee the normal operation of aero-engines. However, existing methods are limited in their ability to handle sensor signals with high dimensional and complex noise. To tackle the above problems, we propose a Mamba network structure with Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and bidirectional feature fusion for aero-engine inter-shaft bearing fault diagnosis, called MD-BiMamba. Firstly, we utilize the CEEMDAN technique to decompose the sensor signals of inter-shaft bearings and extract the intrinsic modal function by improving the noise addition method and decomposition strategy. Then, bidirectional Mamba is designed to extract the bidirectional long-range correlation of the sequence to achieve global feature extraction and fast detection of fault types with linear complexity. Moreover, an adaptive attention fusion method is proposed to achieve bidirectional feature fusion. Finally, we use the label smoothing regularization strategy to optimize the cross-entropy loss and enhance the generalization performance. Experimental results on real inter-shaft bearing datasets and noisy datasets show that the proposed method achieves 99.88 % and 95.81 % accuracy in the standard dataset and −10 dB noise environment, respectively, which is superior to other remarkable methods, in addition to achieving lower model complexity.

Quantitative Assessment of Sand Particulates in Gas-Water Slug Flow Using Deep Learning

Summary The weak collision response excited by micrometer-scale sand particulates is prone to overmixing with strong slug noise, significantly reducing the characterization and monitoring accuracy of sand particulate information in slug flows. Therefore, we developed a quantitative assessment method for sand particulates in slug flow that combines triaxial vibration monitoring and deep learning. First, a migration behavior characterization method of sand particulates is proposed combining nonlinear statistics, multifrequency coherence, and multiscale time frequency. The multifrequency response characteristics corresponding to the multiscale flow behavior of the sand-carrying slug flow were successfully characterized on the 2D time-frequency plane, namely, the mixed sand migration behavior [Intrinsic Mode Function 1 (IMF1)], liquid slug sand carrying (IMF2), forward liquid film and Taylor bubble sand carrying (IMF3), and reflux liquid film sand carrying (IMF4). Furthermore, the influence mechanism of gas superficial velocity (1.5–3.5 m/s), liquid superficial velocity (0.95–2.14 m/s), and sand content (0–20 g) on the triaxial vibration response of slug particulate flow with different migration behaviors is elucidated. Finally, a convolutional neural network (CNN)-gated recurrent unit (GRU)-self-attention mechanism (SATT) model for sand content assessment is developed based on the characterized multiscale migration behavior information and achieves an average recognition accuracy of 95.55% for data sets representing different sand migration behaviors in slug flow. This provides a new method for precisely identifying and monitoring sand production information of multiphase pipe flow.

A hybrid denoising method for low-field nuclear magnetic resonance data

Low-field nuclear magnetic resonance (NMR) has broad application prospects in the exploration and development of unconventional oil and gas reservoirs. However, NMR instruments tend to acquire echo signals with relatively low signal-to-noise ratio (SNR), resulting in poor accuracy of T2 spectrum inversion. It is crucial to preprocess the low SNR data with denoising methods before inversion. In this paper, a hybrid NMR data denoising method combining empirical mode decomposition-singular value decomposition (EMD-SVD) was proposed. Firstly, the echo data were decomposed with the EMD method to low- and high-frequency intrinsic mode function (IMF) components as well as a residual. Next, the SVD method was employed for the high-frequency IMF components denoising. Finally, the low-frequency IMF components, the denoised high-frequency IMF components, and the residual are summed to form the denoised signal. To validate the effectiveness and feasibility of the EMD-SVD method, numerical simulations, experimental data, and NMR log data processing were conducted. The results indicate that the inverted NMR spectra with the EMD-SVD denoising method exhibit higher quality compared to the EMD method and the SVD method.

Data-driven forecasting framework for daily reservoir inflow time series considering the flood peaks based on multi-head attention mechanism

Accurate and reliable daily reservoir inflow forecast plays an essential role in several applications involving the management and planning of water resources, such as hydroelectric generation, flood control, water supply, and basin ecological dispatching. Runoff usually exhibits strong non-linearity, high uncertainty, and spatial and temporal variability. Existing techniques fail to capture complete dynamics change processes effectively. A data-driven forecasting framework for daily reservoir inflow time series considering the flood peaks based on a multi-head attention mechanism was developed, referred to as the GWOCS-VMD-CNN-Transformer (GCVCT). First, the model utilize Grey Wolf Optimizer coupled with Cuckoo Search (GWO-CS) algorithms to optimize parameters in variational mode decomposition model (VMD). This approach helps obtain highly correlated intrinsic mode function (IMF) components, enhancing the frequency resolution of the input dataset. The proposed method overcomes the bottleneck of other available methods by decomposing the time series to capture the main long-term and short-term properties of hydrological processes. Second, the convolution neural network and Transformer (CNN-Transformer) are based on a multi-head attention mechanism as the objective predictive method. Finally, six evaluation indicators verify the performance of the proposed approach. The approach’s reliability was evaluated using the historical daily reservoir inflow data from the Xiluodu (XLD) and Wudongde (WDD) reservoirs in the Jinsha River Basin, China. Several single and hybrid models were developed for comparative analysis. The results indicate that the proposed ensemble approach fits better than other developed model methods. The GCVCT model showed excellent performance in forecasting the inflows of XLD and WDD reservoirs, with NSE values of 0.985 and 0.984, respectively. Furthermore, the GCVCT framework forecast capacity for peak inflow was further verified through discussion and analysis of the 48 peak flows during the validation period, consistently outperforming other models in predicting peak flow for both study reservoirs. This framework provides an effective method for the scientific optimal scheduling of hydropower reservoirs, enabling more sustainable and efficient management practices. It also demonstrates the potential of powerful deep-learning models in intelligent hydrological forecasting.

Enhanced rolling bearing fault diagnosis using DBO-VMD-KELM

Abstract To enhance the extraction of fault signal characteristics from rolling bearings and enhance fault classification precision, this paper presents an approach for diagnosing rolling bearing faults, integrating Variational Mode Decomposition (VMD) and Kernel Extreme Learning Machine (KELM). Furthermore, the Dung Beetle Optimizer (DBO) algorithm is employed to optimize VMD and KELM, addressing the challenge of determining critical parameters effectively. Initially, VMD is employed to break down the fault data from rolling bearings, and the pivotal parameters [k, α] of VMD are globally fine-tuned via the DBO algorithm, with the minimum envelope entropy serving as the optimization criterion. The ideal components of the decomposed intrinsic mode function (IMF) are then determined by comparing their minimal arranged entropy. Nine time-domain indicators are then computed to create the feature vector. Finally, in the KELM diagnostic model, the constructed feature vector is input, and DBO is combined with KELM for optimization to achieve the final fault diagnosis. Simulation results show that the fault diagnosis rate of KELM is 92%, and the fault diagnosis rate of KELM optimized by DBO is 99%, effectively identifying the fault categories of rolling bearings.

Data-adaptive hybrid control for power quality improvement using H-bridge circuit

The extraction of fundamental current and controlling the H-bridge circuit, called shunt active power filter (SAPF), for power quality support have always been major research concerns. The effectiveness of a SAPF depends on its fundamental component estimation. In this context, empirical mode decomposition (EMD) is applied to SAPF operations due to its effectiveness in complex signal analysis. Being a data-driven, adaptive tool, EMD decomposes the distorted nonlinear signal into signal- and noise-dominated signals, called intrinsic mode functions (IMFs). However, its exploitation has been hindered by its mode mixing issue. As a remedy, a second-order generalized integrator (SOGI) is integrated with the EMD approach to extract the required fundamental active component of distorted load current. Thus, this work investigates the effect of an EMD-based SOGI hybrid control approach in extracting the fundamental active component of distorted load current. The MATLAB/Simulink results demonstrate the effectiveness of the proposed hybrid control strategy for nonlinear load current generated by the diode bridge rectifier. Furthermore, the simulated results are validated through a real-time simulation result using the OPAL-RT OP4510 test bench. Results are analyzed under sinusoidal and distorted voltage scenarios at the point of common coupling. The simulation results showed that the proposed hybrid control approach provides better active filtering efficiency, support for reactive power, and improved total harmonic distortion, which meets the IEEE 1547-2018 standard.

A Novel Fault Feature Selection and Diagnosis Method for Rotating Machinery with SI-IR2CMSE and SSGMM-SR

Abstract In the field of fault diagnosis, machine learning is highly valued for its broad applicability and efficiency. Feature extraction and feature selection are key steps in the application of machine learning, and the performance of fault diagnosis methods relies heavily on the effective execution of these two steps. For this reason, this paper aims to enhance the performance of fault diagnosis methods by improving these two aspects. Firstly, to address the non-linearity and non-stationarity of rotating machinery vibration signals under variable operation conditions, this paper proposes an improved rapid refined composite multiscale sample entropy (IR2CMSE) feature extraction method. In addition, this paper decomposes the vibration signals with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and extracts the sensitive intrinsic modal functions’ (IMFs') IR2CMSE values (SI-IR2CMSE) as the initial feature vector, which more accurately reveals the intrinsic time-scale characteristics of the vibration signals. Secondly, to address the problem of over-reliance on sample labels in most feature selection methods, this paper proposes a semi-supervised Gaussian mixing model with sparse regularization (SSGMM-SR) feature selection model. The model does not require complete fault labels and can automatically identify important features. Finally, validation with two rotating machinery fault datasets shows that the method proposed in this study exhibits high diagnostic accuracy and stability across multiple classifiers.

Underwater acoustic signal feature extraction of mixed flow pump based on empirical wavelet transform

The pump converts mechanical energy into potential energy, and a mixed-flow-pump combines the characteristics of an axial flow pump and a centrifugal pump. When the mixed-flow-pump operates at low flow conditions, performance instability in the hump region appears on the performance curve. This study investigates the underwater acoustic signal in this area through experiments, computational fluid dynamics (CFD), and computational aero acoustics (CAA). The hysteresis factor calculated by cross correlation (CC) is utilized to improve the dynamic time warping (DTW) signal comparison verification method. The improved method (CC-DTW) improves the ability of DTW in signal comparison and verification. Compared with the fast Fourier transform (FFT) method, it is more convincing in the comparison of experimental and simulation pressure pulsation signals. After verifying the effectiveness of pressure pulsation signals and underwater acoustic signals, a combined empirical wavelet transform and FFT method is used to analyze underwater acoustic signal in instability regions. The results indicate that the depth of instability aligns with the FFT frequence ratio of the intrinsic mode function. Based on the feature, a criterion for determining instability states in mixed-flow-pumps is proposed.

EEG FEATURE EXTRACTION AND RECOGNITION BASED ON MULTI-FEATURE FUSION

In response to the issue of insufficient information and low classification accuracy in single-channel feature extraction algorithms for EEG signals, the paper proposed a method based on Adaptive Noise-assisted Complete Ensemble Empirical Mode Decomposition (CEEMDAN) and multi-feature fusion. Firstly, we acquired multi-channel motor imagery EEG data and preprocessed it. Next, utilized CEEMDAN with adaptive noise to adaptively decompose the channel data. Secondly, extracted features from the Intrinsic Mode Functions (IMFs) which we obtained after CEEMDAN decomposition for different feature layers and fused them, obtaining the original feature matrices for each feature layer. Finally, we fused and reduced the dimensionality of the original feature matrices from each layer, input the resulting matrix into a classification model for classification, and output the classification results. We achieve an average classification accuracy of 88.59% on the BCI Competition II Data Set III, and validate the results on self-collected single-channel motor imagery EEG data, achieving a classification accuracy of 89.72%. Experimental results indicate that multi-feature fusion outperforms single features, and the combination of CEEMDAN decomposition with multi-feature fusion achieves higher classification accuracy.

Operating modal parameter identification of railway vehicle bogie based on k-value optimization variational mode decomposition and second-order blind identification method

Due to the variable operating conditions and strong background noise, the accuracy of modal parameter identification of the railway vehicle bogie is low. This paper proposes a method for identifying operational modal parameters by combining the K-value optimization variational mode decomposition (KVMD) and second-order blind identification (SOBI) method (KVMD–SOBI method). Firstly, the variational mode decomposition (VMD) algorithm is used to adaptively decompose a single-channel vibration signal into intrinsic mode function (IMF) components with different scale characteristics. The feature IMF components are selected through the K-value optimization method based on energy ratio and stability graph. Then, the SOBI algorithm is used to separate the matrix composed of the feature IMF components. And the mode shape and single-mode signal are obtained. Finally, the natural frequency and damping ratio of each order mode are extracted by the single-mode parameter recognition method. Through simulation and experimental verification, it is shown that the proposed method has good noise robustness and can effectively identify the first three modal parameters of railway vehicle bogies in variable-speed operation. At the same time, the feature IMF components extracted by KVMD algorithm eliminate the sensitivity of sensor installation positions and operating conditions to detection results. Therefore, this method is an excellent operational mode identification method based on a single-channel signal with good noise and working condition robustness.

Fault Diagnosis of Pumped Storage Units—A Novel Data-Model Hybrid-Driven Strategy

Pumped storage units serve as a crucial support for power systems to adapt to large-scale and high-proportion renewable energy sources by providing a stable and flexible energy supply. However, due to the coupling effects of electric power load demands and the complex multi-source factors within the water–mechanical–electrical system, the interrelationship between unit parameters becomes more intricate, posing significant threats to the operational reliability and health status of the units. The complexity of fault diagnosis is further aggravated by the intricate and varied nature of fault characteristics, as well as the challenges in signal extraction under conditions of strong electromagnetic interference and high noise levels. To address these issues, this paper proposes a novel data-model hybrid-driven strategy that analyzes vibration signals to achieve rapid and accurate fault diagnosis of the units. Firstly, the spectral kurtosis theory is employed to enhance the traditional empirical mode decomposition, achieving optimal decomposition and noise reduction effects for vibration signals. Secondly, the intrinsic mode functions (IMFs) obtained from the decomposition are reconstructed, and the entropy values of effective IMFs are calculated as fault feature vectors. Subsequently, the CNN-LSTM model is utilized for fault diagnosis. The effectiveness and feasibility of the proposed method are verified through actual operational data from pumped storage units in a specific region. Through analysis, the fault diagnosis accuracy of the method proposed in this paper can be maintained above 95%, demonstrating robustness in complex engineering environments and effectively ensuring the safe and stable operation of pumped storage units.

Fault identification of rolling bearing based on improved salp swarm algorithm

Due to the rapid development of industrial manufacturing technology, modern mechanical equipment involves complex operating conditions and structural characteristics of hardware systems. Therefore, the state of components directly affects the stable operation of mechanical parts. To ensure engineering reliability improvement and economic benefits, bearing diagnosis has always been a concern in the field of mechanical engineering. Therefore, this article studies an effective machine learning method to extract useful fault feature information from actual bearing vibration signals and identify bearing faults. Firstly, variational mode decomposition decomposes the source signal into several intrinsic mode functions according to the actual situation. The vibration signal of the bearing is decomposed and reconstructed. By iteratively solving the variational model, the optimal modulus function can be obtained, which can better describe the characteristics of the original signal. Then, the feature subset is efficiently searched using the wrapper method of feature selection and the improved binary salp swarm algorithm (IBSSA) to effectively reduce redundant feature vectors, thereby accurately extracting fault feature frequency signals. Finally, support vector machines are used to classify and identify fault types, and the advantages of support vector machines are verified through extensive experiments, improving the ability of global search potential solutions. The experimental findings demonstrate the superior fault recognition performance of the IBSSA algorithm, with a highest recognition accuracy of 97.5%. By comparing different recognition methods, it is concluded that this method can accurately identify bearing failure.

Fault Feature Extraction of Rolling Bearing Based on Maximum Second-Order Cyclostationarity Blind Deconvolution and CEEMD-Teager

The operation of rolling bearings is directly related to the reliability of the whole rotating machinery. If the rolling bearing failure cannot be diagnosed and repaired in time, it will probably lead to equipment shutdown. The feature extraction process is an important part of bearing fault diagnosis. Some existing feature extraction methods are sensitive to noise and interference, and cannot fully explore and characterize useful information in nonlinear and non-stationary signals in complex scenes, and sometimes even lose important information contained in the data, resulting in low diagnostic accuracy. Therefore, a new method combining Maximum Second-order Cyclostationarity Blind Deconvolution (CYCBD) and Complementary Ensemble Empirical Mode Decomposition (CEEMD) was proposed for feature extraction of rolling bearing faults. Firstly, the cyclic frequency is set according to the failure frequency, and the original signal is filtered by CYCBD. Then, the filtered signal is decomposed into multiple Intrinsic Mode Function (IMF) by CEEMD, and the effective IMF components are selected by kurtosis criterion for reconstruction. Finally, the Teager energy operator is used to enhance the transient impact of the reconstructed signals. The results of simulation and comparison experiments show that the proposed method can extract bearing characteristics in different fault states more effectively, and the accuracy of network model diagnosis is improved compared with the traditional methods.

Enhanced Foreign Exchange Volatility Forecasting Using Ceemdan with Optuna-Optimized Ensemble Deep Learning Model

Foreign Exchange (FX) is the largest financial market in the world, with a daily trading volume that significantly exceeds that of stock and futures markets. The prediction of FX volatility is a critical financial concern that has garnered significant attention from researchers and practitioners due to its far-reaching implications in the financial markets. This paper presents a novel hybrid ensemble forecasting model integrating a decomposition strategy and three deep learning (DL) models: Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Convolutional Neural Network (CNN). This combination addresses individual models' limitations and further improves the accuracy and stability of FX volatility forecasting. The proposed approach utilizes the CEEMDAN technique to decompose volatility into multiple distinct intrinsic mode functions (IMFs) and merges these IMFs with GARCH and EGARCH volatilities to form the input dataset for the DL models. In addition, we employed an attention mechanism to improve the effectiveness of the DL techniques. Furthermore, the hyperparameters for the DL models are optimized using the Optuna algorithm. Finally, a hybrid ensemble model for forecasting exchange rate volatility is developed by combining the predictions of three distinct DL models. The proposed approach is evaluated against various benchmark models using evaluation measures such as MSE, MAE, HMSE, HMAE, RMSE, Q-LIKE, and the model confidence set (MCS) approach. The results demonstrate that our proposed approach provides accurate and reliable forecasts of FX volatility under different forecasting regimes, making it a valuable tool for financial practitioners and researchers.

Prediction of state-of-health of lithium-ion battery based on CEEMDAN-SG-LSTM combined model

State-of-health (SOH) is an important indicator for the maintenance and safe operation of batteries, and it is crucial for accurately predicting SOH. To address problems that the noise present in the original data lead to inaccurate prediction results. An Long-Short-Term-Memory (LSTM) method for SOH prediction is proposed based on the joint noise reduction model of complete ensemble empirical mode decomposition adaptive noise (CEEDMAN) and Savitzky-Golay (SG) filtering. Firstly, seven health indicators (HIs) were extracted by analyzing the voltage and current curves, and HIs with higher correlation with SOH were selected using Pearson correlation coefficient. Then, Intrinsic Mode Functions (IMF) components generated from SOH by CEEMDAN are divided into noise-component, noise-dominant-component, useful-signal-dominant-component, filtered noise-dominant-component and useful-signal-dominant-component are reconstructed into filtered SOH. Finally, the LSTM model is used for SOH prediction. Experiments show that proposed model captures the capacity regeneration phenomenon well with high prediction accuracy, and errors are all below 1.9%.