Complete Ensemble Empirical Mode Decomposition With Adaptive Noise Research Articles

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.

Carbon price prediction using multiple hybrid machine learning models optimized by genetic algorithm

Importance of the carbon trading has been escalating expeditiously not only because of the environmentalist purposes to mitigate the adverse effects of climate change but also the increasing diversification benefits of the carbon emission contracts due to the low correlation between the emission, equity, and commodity markets. In accordance with the promptly rising significance of accurate carbon price prediction, this paper develops and compares 48 hybrid machine learning models by using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Variational Mode Decomposition (VMD), Permutation Entropy (PE), and multiple types of Machine Learning (ML) models optimized by Genetic Algorithm (GA). The outcomes of this study present the performances of the implemented models at different levels of mode decomposition and the impact of genetic algorithm optimization by comparing the key performance indicators that the CEEMDAN-VMD-BPNN-GA optimized double decomposition hybrid model outperforms the others with a striking R2 value of 0.993, RMSE of 0.0103, MAE of 0.0097, and MAPE of 1.61%.

Research on Magnetohydrodynamic Angular Rate Sensor Denoising for a Space Laser Stabilization Control System

The magnetohydrodynamic angular rate sensor (MHD ARS) is a high-bandwidth, high-accuracy sensor that is increasingly used to measure spacecraft harmonic vibration. However, the amplitude of harmonic vibration is usually on the order of microradian to milliradian, and the induced electric potential signal of MHD ARS is only on the order of nanovolt to microvolt, which is easily disturbed by noise. In this paper, an improved method based on autocorrelation with Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Wavelet Threshold Denoising (WTD) is proposed to denoise the signal of MHD ARS. Firstly, CEEMDAN is used to decompose noisy signals and obtain intrinsic mode functions (IMFs), and autocorrelation is used to determine the relevant modes where the effective signals are located. Then, the improved threshold and thresholding function are used to denoise the relevant modes. Finally, the denoised signal is obtained by combining the denoised relevant modes. In the experiment, noisy MHD ARS signals were recorded in static and dynamic conditions, and the effects of the proposed method and conventional methods were compared. The results of the Allan variance in the static condition and root-mean-square error in the dynamic condition show that the proposed method can effectively overcome the shortcomings of conventional methods and obtain a better denoising effect.

A Novel ECG Signal Denoising Algorithm Based on Sparrow Search Algorithm for Optimal Variational Modal Decomposition.

ECG signal processing is an important basis for the prevention and diagnosis of cardiovascular diseases; however, the signal is susceptible to noise interference mixed with equipment, environmental influences, and transmission processes. In this paper, an efficient denoising method based on the variational modal decomposition (VMD) algorithm combined with and optimized by the sparrow search algorithm (SSA) and singular value decomposition (SVD) algorithm, named VMD-SSA-SVD, is proposed for the first time and applied to the noise reduction of ECG signals. SSA is used to find the optimal combination of parameters of VMD [K,α], VMD-SSA decomposes the signal to obtain finite modal components, and the components containing baseline drift are eliminated by the mean value criterion. Then, the effective modalities are obtained in the remaining components using the mutual relation number method, and each effective modal is processed by SVD noise reduction and reconstructed separately to finally obtain a clean ECG signal. In order to verify the effectiveness, the methods proposed are compared and analyzed with wavelet packet decomposition, empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm. The results show that the noise reduction effect of the VMD-SSA-SVD algorithm proposed is the most significant, and that it can suppress the noise and remove the baseline drift interference at the same time, and effectively retain the morphological characteristics of the ECG signals.

Prediction method of PM2.5 concentration based on decomposition and integration

With the acceleration of urbanization leading to a general decrease in air quality, accurate PM2.5 concentration prediction is of the utmost practical meaning for the control and prevention of air pollution in the region. Therefore, a new hybrid prediction model for PM2.5 concentration based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), approximate entropy (ApEn), variational mode decomposition optimized by capuchin search algorithm (CVMD), long short-term memory optimized by pelican optimization algorithm (POA-LSTM) and error correction (EC), named CEEMDAN-ApEn-CVMD-POA-LSTM-EC, is proposed. First, CEEMDAN is used to acquire a limited amount of intrinsic mode functions (IMFs). Second, calculate ApEn value for each IMF component, and divide each IMF component into high-complexity and low-complexity components by the size of ApEn values. Third, variational mode decomposition optimized by capuchin search algorithm (CVMD), named CVMD, is proposed. CVMD is used as a secondary decomposition method to further decompose high-complexity components adaptively into a finite number of IMFs. Fourth, long short-term memory optimized by pelican optimization algorithm, named POA-LSTM, is proposed. POA-LSTM predicts all IMF components, and the results of their predictions are combined to generate the original prediction results. Final, error sequence is decomposed and predicted again by the EC module CVMD-POA-LSTM to obtain prediction results of error sequence, and final prediction results are acquired by combining original prediction results and prediction results of error sequence. The datasets in Beijing, Shanghai, and Xi'an were selected for simulation experiments to demonstrate the superiority of the proposed model. Taking Beijing as an example, RMSE, MAE, MAPE and R2 values are 1.9947, 1.5577, 0.1157 and 0.9947, which are superior to other comparison models and have the best performance.

A combined wind speed prediction model based on data processing, multi-objective optimization and machine learning

The ability to estimate wind speed accurately is crucial for optimizing the utilization of wind energy in power systems. The randomness of wind speed and the performance of prediction models are the two issues that have the greatest impact on wind speed prediction. This paper starts from the two aspects of digging wind speed characteristics and optimizing model performance. A new wind speed combined prediction model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and improved artificial bee colony algorithm (IABC) to optimize least squares support vector machine (LSSVM) performance. In order to reduce the randomness of the wind speed sequence and increase its predictability, CEEMDAN is first used to break down the wind speed sequence. Secondly, an LSSVM prediction model optimized by an improved artificial bee colony algorithm is established for each subsequence obtained by decomposition; finally, the wind speed forecast value is created by superimposing the results of each subsequence’s prediction. Case studies demonstrate that the combined prediction model put out in this study outperforms other models in terms of prediction performance.

Displacement Monitoring of a Bridge Based on BDS Measurement by CEEMDAN-Adaptive Threshold Wavelet Method.

From the viewpoint of BDS bridge displacement monitoring, which is easily affected by background noise and the calculation of a fixed threshold value in the wavelet filtering algorithm, which is often related to the data length. In this paper, a data processing method of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), combined with adaptive threshold wavelet de-noising is proposed. The adaptive threshold wavelet filtering method composed of the mean and variance of wavelet coefficients of each layer is used to de-noise the BDS displacement monitoring data. CEEMDAN was used to decompose the displacement response data of the bridge to obtain the intrinsic mode function (IMF). Correlation coefficients were used to distinguish the noisy component from the effective component, and the adaptive threshold wavelet de-noising occurred on the noisy component. Finally, all IMF were restructured. The simulation experiment and the BDS displacement monitoring data of Nanmao Bridge were verified. The results demonstrated that the proposed method could effectively suppress random noise and multipath noise, and effectively obtain the real response of bridge displacement.

Short-Term Solar Power Forecasting Based on CEEMDAN and Kernel Extreme Learning Machine

The use of renewable energy sources contributes to environmental awareness and sustainable development policy. The inexhaustible and nonpolluting nature of solar energy has attracted worldwide attention. Accurate forecasting of solar power is vital for the reliability and stability of power systems. However, the effect of the intermittency nature of solar radiation makes the development of accurate prediction models challenging. This paper presents a hybrid model based on Kernel Extreme Learning Machine (Kernel-ELM) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for short-term solar power forecasting. The decomposition technique increases the number of stable, stationary, and regular patterns of the original signals. Each decomposed signal is fed into Kernel-ELM. To validate the performance of the hybrid model, solar power data from the BSEU Renewable Energy Laboratory, measured at 5-minute intervals, are used. To validate the proposed model, its performance is compared to some state-of-the-art forecasting models with seasonal data. The results highlight the good performance of the proposed hybrid model compared to other classical algorithms according to the metrics.

Damage location diagnosis of frame structure based on wavelet denoising and convolution neural network implanted with Inception module and LSTM

Accurate diagnosis of the damage location of the frame structure is very important for the overall damage assessment and subsequent maintenance of the frame structure. However, the frame structure generally works in the noise environment, which increases the difficulty of health monitoring and fault diagnosis of frame structure based on vibration data. In order to realize the accurate damage location diagnosis of structural frame under noise environment, this paper proposes a fault diagnosis method based on wavelet denoising, convolutional neural network, Inception module, and long short-term memory (LSTM) on the basis of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). In order to verify the effectiveness and superiority of the method proposed in this paper, the 4-story steel frame model of the University of British Columbia is taken as the research object, and the experiments are carried out with the method proposed in this paper, and under the same conditions, the comparative experiments are carried out with other similar methods. The experimental results show that the method proposed in this paper not only has high accuracy, but also has strong anti-noise ability, and its performance is better than other similar methods. Therefore, the fault diagnosis method proposed in this paper can effectively perform the accurate diagnosis of damage location of frame structure under noise environment.

Combined Improved CEEMDAN and Wavelet Transform Sea Wave Interference Suppression

Cross water–air interface acoustic and electromagnetic integrated communication (AEIC) technology refers to an underwater speaker that excites the water surface micro-amplitude wave (WSAW) on the water’s surface, and millimeter wave radar detects the vibrations of the WSAW to realize the transmission of information. The research on cross-media communication meets many challenges due to the large amplitude of the water surface disturbance and the small amplitude of the WSAW. In this paper, a novel sea wave interference suppression method based on improved complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and wavelet transform (WT) is presented. This method divides the phase change into different intrinsic mode functions (IMFs) and obtains a reconstructed scale of the WSAW signal through wavelet decomposition and correlation procession to separate the WSAW signal and the sea wave interference. It is proved to be better than the reference filtering method by experiment. By using this novel method, the bit error rate (BER) of the communication system can be reduced effectively.

Multi-scale spatiotemporal feature lithology identification method based on split-frequency weighted reconstruction

The accurate identification of lithology in thin and deep layers is a crucial task in logging. However, traditional logging lithology identification methods are often inefficient for thin and deep layers and sometimes require human intervention, which greatly reduces the efficiency of oil and gas production. Therefore, this study proposes a multi-scale spatiotemporal feature lithology identification method under split-frequency weighted reconstruction. First, split-frequency weighted reconstruction of the logging curves is performed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to improve their thin layer resolution. Subsequently, a feature fusion model of multi-scale convolutional neural networks and bidirectional gated recurrent neural networks (MCNN-BIGRU) is constructed to learn the spatiotemporal features of the logging curves. Finally, during feature propagation, the attention mechanism assigns weights to historical features to mitigate the accumulation of error information, thereby improving the lithology recognition effect. To verify the model's performance, we constructed a lithology dataset with five wells and conducted an experiment to show that the reconstructed logging curves have significantly higher vertical resolution than the original curves. Furthermore, the MCNN-BIGRU-AT model developed in this study exhibited a better lithology identification effect than the single-structure model, with a highest accuracy of 96.69%. In summary, the proposed method is a novel and efficient method for lithology identification.

Lithium-Ion Battery Remaining Useful Life Prediction Based on Hybrid Model

Accurate prediction of the remaining useful life (RUL) is a key function for ensuring the safety and stability of lithium-ion batteries. To solve the capacity regeneration and model adaptability under different working conditions, a hybrid RUL prediction model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and a bi-directional gated recurrent unit (BiGRU) is proposed. CEEMDAN is used to divide the capacity into intrinsic mode functions (IMFs) to reduce the impact of capacity regeneration. In addition, an improved grey wolf optimizer (IGOW) is proposed to maintain the reliability of the BiGRU network. The diversity of the initial population in the GWO algorithm was improved using chaotic tent mapping. An improved control factor and dynamic population weight are adopted to accelerate the convergence speed of the algorithm. Finally, capacity and RUL prediction experiments are conducted to verify the battery prediction performance under different training data and working conditions. The results indicate that the proposed method can achieve an MAE of less than 4% with only 30% of the training set, which is verified using the CALCE and NASA battery data.

CSFPre: Expressway key sections based on CEEMDAN-STSGCN-FCM during the holidays for traffic flow prediction.

The implementation of the toll free during holidays makes a large number of traffic jams on the expressway. Real-time and accurate holiday traffic flow forecasts can assist the traffic management department to guide the diversion and reduce the expressway's congestion. However, most of the current prediction methods focus on predicting traffic flow on ordinary working days or weekends. There are fewer studies for festivals and holidays traffic flow prediction, it is challenging to predict holiday traffic flow accurately because of its sudden and irregular characteristics. Therefore, we put forward a data-driven expressway traffic flow prediction model based on holidays. Firstly, Electronic Toll Collection (ETC) gantry data and toll data are preprocessed to realize data integrity and accuracy. Secondly, after Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) processing, the preprocessed traffic flow is sorted into trend terms and random terms, and the spatial-temporal correlation and heterogeneity of each component are captured simultaneously using the Spatial-Temporal Synchronous Graph Convolutional Networks (STSGCN) model. Finally, the fluctuating traffic flow of holidays is predicted using Fluctuation Coefficient Method (FCM). Through experiments of real ETC gantry data and toll data in Fujian Province, this method is superior to all baseline methods and has achieved good results. It can provide reference for future public travel choices and further road network operation.

Hybrid scheme through read-first-LSTM encoder-decoder and broad learning system for bearings degradation monitoring and remaining useful life estimation

This paper proposes a novel hybrid scheme through read-first-LSTM (RLSTM) encoder-decoder and broad learning system (BLS) for bearings degradation monitoring and remaining useful life (RUL) estimation, which aims to describe the nonlinear characteristics of the degradation process. Firstly, the raw signals are processed premier by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and a novel dimensionality reduction method composed of t-distribution stochastic neighbor embedding (t-SNE) and density-based spatial clustering of application with noise algorithm (DBSCAN). Then, the health indicator is constructed with the Hilbert-Huang transform (HHT) corresponding to the bearings’ natural fault frequency, which can be employed as the hybrid scheme training label. Linear rectification technology (LRT) and exponentially weighted moving average (EWMA) control chart are adapted to define the exact process of the degradation. Secondly, a novel RLSTM is proposed. And simultaneously, an encoder-decoder model, where RLSTM is utilized as an encoder, and LSTM is adopted as a decoder, is designed for degradation monitoring. Finally, a broad learning system (BLS), which differs from deep learning with a deeper structure, is established in a flat network to estimate the RUL of bearings. Compared with the state-of-the-art techniques, the better efficacy of the proposed hybrid scheme is illustrated using the PRONOSTIA platform dataset.

An enhanced monthly runoff time series prediction using extreme learning machine optimized by salp swarm algorithm based on time varying filtering based empirical mode decomposition

Reliable runoff prediction plays a significant role in reservoir scheduling, water resources management, and efficient utilization of water resources. To effectively enhance the prediction accuracy of monthly runoff series, a hybrid prediction model (TVF-EMD-SSA-ELM) combining time varying filtering (TVF) based empirical mode decomposition (EMD), salp swarm algorithm (SSA) and extreme learning machine (ELM) is proposed. Firstly, the monthly runoff series is decomposed into several sub-series using TVF-EMD. Secondly, SSA is used to optimize the input weights and hidden layer biases of the selected ELM model. Finally, the prediction results are generated by summing and reconstructing each sub-series based on the SSA optimized ELM model. This hybrid model is applied to the monthly runoff prediction of Manwan hydropower, Hongjiadu hydropower, and Yingluoxia hydrological station, and compared with back propagation (BP), ELM, SSA-ELM, PSO-ELM, GSA-ELM, TVF-EMD-ELM, EMD-SSA-ELM, extreme-point symmetric mode decomposition (ESMD)-SSA-ELM, wavelet decomposition (WD)-SSA-ELM and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)-SSA-ELM models. The prediction performance of various models is reflected by four evaluation indicators (R, NSEC, NRMSE, MAPE). Results reveal that the prediction effect of the ELM model is better than that of BP, the optimization accuracy of SSA is better than those of particle swarm optimization (PSO) and gravitational search algorithm (GSA), and the prediction accuracy of the hybrid TVF-EMD and SSA is better than that of only TVF-EMD or SSA. TVF-EMD-SSA-ELM model has the highest prediction accuracy. When compared with the single ELM model, it’s NRMSE and MAPE at Manwan hydropower decrease by 84.4% and 72.38%, those of Hongjiadu hydropower decrease by 85.21% and 78.38%, and those of Yingluoxi hydrological station decrease by 68.42% and 39.51%, respectively. R and NSEC of the three sites are close to 1. Therefore, the proposed model provides a new method for the prediction of monthly runoff, and the results can provide a reference for the prediction of monthly runoff in the study area.

State of health and remaining useful life prediction of lithium-ion batteries based on a disturbance-free incremental capacity and differential voltage analysis method

State of health (SOH) and remaining useful life (RUL) prediction are crucial for battery management systems (BMS). However, accurate SOH and RUL prediction still need to be improved due to the complicated battery aging mechanism. This work combines incremental capacity analysis (ICA) and differential voltage analysis (DVA) based on the second-order RC model with an improved Bidirectional Gated Recurrent Unit (BiGRU) to develop SOH and RUL prediction framework. Firstly, the voltage is reconstructed through the second-order RC model to obtain the incremental capacity (IC) and differential voltage (DV) curves to avoid the influence of measurement noise and the complex parameter adjustment process in the filtering method on the IC and DV curves. Then, a new set of battery aging features are extracted from the reshaped IC and DV curves to improve SOH and RUL prediction accuracy and robustness. Next, the BiGRU method with attention mechanism (BiGRU-AM) is used to build the prediction models for battery aging features, SOH, and RUL. To reduce the impact of the capacity regeneration phenomenon, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method is used to decompose the SOH prediction results, and the decomposed residual is used as the input to improve the prediction accuracy of RUL. The uncertainty of RUL prediction results is analyzed by Monte Carlo (MC) simulation. Finally, the proposed method is verified by experimental battery data from Center for Advanced Life Cycle Engineering (CALCE) and Sandia National Laboratory. Experimental results show that the voltage reconstruction results based on the second-order RC model are applied to ICA and DVA analysis, effectively avoiding the influence of noise. The RMSE of voltage reconstruction is within 0.0006, and the Pearson correlation coefficient between the four aging features extracted from the reconstructed IC/DV curve and SOH is above 0.9. Moreover, this method has good robustness to the cell inconsistency, temperature uncertainty, and a satisfied generalization ability to different battery chemistries, which the maximum RUL predicted AE of CALCE and Sandia battery is within 10 and 5, respectively.

A Solar Irradiance Forecasting Framework Based on the CEE-WGAN-LSTM Model.

With the rapid development of solar energy plants in recent years, the accurate prediction of solar power generation has become an important and challenging problem in modern intelligent grid systems. To improve the forecasting accuracy of solar energy generation, an effective and robust decomposition-integration method for two-channel solar irradiance forecasting is proposed in this study, which uses complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), a Wasserstein generative adversarial network (WGAN), and a long short-term memory network (LSTM). The proposed method consists of three essential stages. First, the solar output signal is divided into several relatively simple subsequences using the CEEMDAN method, which has noticeable frequency differences. Second, high and low-frequency subsequences are predicted using the WGAN and LSTM models, respectively. Last, the predicted values of each component are integrated to obtain the final prediction results. The developed model uses data decomposition technology, together with advanced machine learning (ML) and deep learning (DL) models to identify the appropriate dependencies and network topology. The experiments show that compared with many traditional prediction methods and decomposition-integration models, the developed model can produce accurate solar output prediction results under different evaluation criteria. Compared to the suboptimal model, the MAEs, MAPEs, and RMSEs of the four seasons decreased by 3.51%, 6.11%, and 2.25%, respectively.

Automatic prediction modeling for Time-Series degradation data via Genetic algorithm with applications in nuclear energy

Time-series data prediction, a predominant problem in fault prediction, enables effective and efficient predictive maintenance. For time-series data, hybrid methods combining data decomposition, component-wise prediction, and aggregation are frequently reported. However, most hybrid models merely use a single model for all components and adopt the equal-weighted aggregating strategy. This may easily overfit or underfit the decomposed data and reduce the generalization capability, especially in long-term predictions. This study proposed a novel decomposition-based framework for time-series data fault predictions. Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) disintegrates the raw data into several components, and different prediction models were considered as the modeling candidates. Joint modeling optimization was performed automatically based on the Genetic Algorithm to optimize the prediction model, modeling parameters, and aggregation weight of each component. To verify the effectiveness of the proposed method, a case study concerning leakage of reactor coolant pumps in nuclear power plants was carried out. The experimental results indicated the superior performance of the proposed method for various prediction horizons.

Deep Learning-Based Fault Diagnosis for Marine Centrifugal Fan

Abstract Marine centrifugal fans usually work in harsh environments. Their vibration signals are non-linear. The traditional fault diagnosis methods of fans require much calculation and have low operating efficiency. Only shallow fault features can be extracted. As a result, the diagnosis accuracy is not high. It is difficult to realize the end-to-end fault diagnosis. Combining the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and lightweight neural network, a fault classification method is proposed. First, the CEEMDAN can decompose the vibration signal into several intrinsic modal functions (IMF). Then, the original signals can be transformed into 2-D images through pseudo-colour coding of the IMFs. Finally, they are fed into the lightweight neural network for fault diagnosis. By embedding a convolutional block attention module (CBAM), the ability of the network to extract critical feature information is improved. The results show that the proposed method can adaptively extract the fault characteristics of a marine centrifugal fan. While the model is lightweight, the overall diagnostic accuracy can reach 99.3%. As exploratory basic research, this method can provide a reference for intelligent fault diagnosis systems on ships.

Interval prediction of ultra-short-term photovoltaic power based on a hybrid model

Accurate photovoltaic (PV) power prediction facilitates large-scale PV grid connection and ensures the safe and reliable operation of power system. However, the information obtained from traditional point forecasting results is limited and not reliable enough for decision-makers to execute operational strategies. To obtain more abundant forecasting information than the point prediction method, we develop a hybrid interval forecasting model by combining fuzzy information granulation (FIG), improved long and short-term memory network (ILSTM) and differential autoregressive moving average (ARIMA) model to predict the interval of PV output power. First, the original PV power is decomposed into some components by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), then the new sequences are obtained by fuzzy entropy (FE). Second, FIG is applied to mine the reconstructed sequences and obtain the maximum, minimum and average value. Third, the high frequency components are predicted by ILSTM, while low frequency components and residual are predicted by ARIMA. The final interval prediction result is obtained by summing up the interval prediction results of each component. The performance of the proposed model is verified by comparing with other models. Experimental results demonstrate that the presented model can accurately cover the actual PV power values and deliver more valuable decision information for power system dispatch.