Gearbox Fault Diagnosis Classification with Empirical Mode Decomposition Based on Improved Long Short-Term Memory

2021 ◽  
Author(s):  
Sheng-Nan Chen ◽  
Feng Liu ◽  
Chang-Xia Gao ◽  
Jinyang Li
Keyword(s):  
Fault Diagnosis ◽  
Empirical Mode Decomposition ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Mode Decomposition ◽  
Long Short Term Memory ◽  
Diagnosis Classification

scholarly journals Daily Runoff Forecasting Using Ensemble Empirical Mode Decomposition and Long Short-Term Memory

2021 ◽  
Vol 9 ◽  
Author(s):  
Ruifang Yuan ◽  
Siyu Cai ◽  
Weihong Liao ◽  
Xiaohui Lei ◽  
Yunhui Zhang ◽  
...  
Keyword(s):  
Empirical Mode Decomposition ◽  
Short Term Memory ◽  
Ensemble Empirical Mode Decomposition ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Runoff Forecasting ◽  
Mode Decomposition ◽  
Runoff Series ◽  
Long Short Term Memory

Hydrological series data are non-stationary and nonlinear. However, certain data-driven forecasting methods assume that streamflow series are stable, which contradicts reality and causes the simulated value to deviate from the observed one. Ensemble empirical mode decomposition (EEMD) was employed in this study to decompose runoff series into several stationary components and a trend. The long short-term memory (LSTM) model was used to build the prediction model for each sub-series. The model input set contained the historical flow series of the simulation station, its upstream hydrological station, and the historical meteorological element series. The final input of the LSTM model was selected by the MI method. To verify the effect of EEMD, this study used the Radial Basis Function (RBF) model to predict the sub-series, which was decomposed by EEMD. In addition, to study the simulation characteristics of the EEMD-LSTM model for different months of runoff, the GM(group by month)-EEMD-LSTM was set up for comparison. The key difference between the GM-EEMD-LSTM model and the EEMD-LSTM model is that the GM model must divide the runoff sequence on a monthly basis, followed by decomposition with EEMD and prediction with the LSTM model. The prediction results of the sub-series obtained by the LSTM and RBF exhibited better statistical performance than those of the original series, especially for the EEMD-LSTM. The overall GM-EEMD-LSTM model performance in low-water months was superior to that of the EEMD-LSTM model, but the simulation effect in the flood season was slightly lower than that of the EEMD-LSTM model. The simulation results of both models are significantly improved compared to those of the LSTM model.

scholarly journals A Novel OLTC Fault Diagnosis Method Based on Optimized Long Short-Term Memory Parameters

2021 ◽  
Author(s):  
Yan Yan ◽  
Hongzhong Ma
Keyword(s):  
Fault Diagnosis ◽  
Power Systems ◽  
Short Term Memory ◽  
Permutation Entropy ◽  
Short Term ◽  
Term Memory ◽  
Mode Decomposition ◽  
Diagnosis Method ◽  
Long Short Term Memory ◽  
Grasshopper Optimization

Recently, long short-term memory (LSTM) networks have been widely adopted to help with fault diagnosis for power systems. However, the parameters of LSTM networks are determined by prior knowledge and experience and thereby not capable of dealing with unexpected faults in volatile environments. In this paper, we propose and apply an improved grey wolf optimization (IGWO) algorithm to optimize the parameters of LSTM networks, aiming to circumvent the drawback of empirical LSTM parameters and enhance the fault diagnosis accuracy for on-load tap changers (OLTCs). The composite multiscale weighted permutation entropy and energy entropy yielded by the grasshopper optimization algorithm and variational mode decomposition (GOA-VMD) method are used as the inputs of LSTM networks. The IGWO algorithm is applied in an iterative manner to optimize the relevant super arithmetic of the LSTM. In this way, an IGWO-LSTM combination model is constructed to classify different faults diagnosed in OLTCs. Experimental results verify the diagnosis performance superiority of the proposed method over several widely used comparison benchmarks

Modeling of the dynamic hysteresis in DEAP actuator using an empirical mode decomposition based long-short term memory network

2021 ◽  
pp. 1045389X2098699
Author(s):  
Zhaoguo Jiang ◽  
Yuan Li ◽  
Qinglin Wang
Keyword(s):  
Empirical Mode Decomposition ◽  
Prediction Accuracy ◽  
Short Term Memory ◽  
Hysteresis Phenomenon ◽  
Short Term ◽  
Term Memory ◽  
Mode Decomposition ◽  
Hysteresis Nonlinearity ◽  
Memory Network ◽  
Long Short Term Memory

As a smart material-based actuator, the dielectric electro-active polymer (DEAP) actuator is widely considered to be a potential driving mechanism for many applications, especially in intelligent bio-inspired robotics. However, the DEAP actuator demonstrates rate-dependent and asymmetrical hysteresis phenomenon which leads to great tracking inaccuracy and even oscillatory response, severely limiting its further development. Feedforward Neural Network (FNN) model has already become a widely used method to describe this kind of strong hysteresis nonlinearity in recent years. However, the FNN has no ability to remember the historical state of long period of time which is also a very important factor to restrict hysteresis phenomenon. In this paper, a novel hybrid model, Long-Short Term Memory (LSTM) network combined with Empirical Mode Decomposition (EMD), is proposed to model the dynamic hysteresis nonlinearity in DEAP actuator. At first, the original control signal sequence is preprocessed into a series of sub-sequence by the EMD method and is reshaped by one-sided dead-zone operator. Then the input space of LSTM is conducted using the original control signal, the sub-sequence, and reshaped signal. Finally, the input space and the displacement signal are applied to train the long-short term memory network. In order to verify the performance of the proposed model, the traditional artificial back propagation neural network (BPNN) model, rate-dependent Prandtl-Ishlinskii (RPI) model, and nonlinear electromechanical (NEM) model are compared from prediction accuracy. The results demonstrate that: (1) the proposed model has a higher prediction accuracy than the traditional artificial BPNN, RPI, and NEM model; and (2) the prediction accuracy of LSTM network is significantly improved by using EMD. Therefore, the long-short term memory network combined with empirical mode decomposition is a competitive method compared to the existing state-of-the-art approach.

scholarly journals Improving Significant Wave Height Forecasts Using a Joint Empirical Mode Decomposition–Long Short-Term Memory Network

2021 ◽  
Vol 9 (7) ◽  
pp. 744
Author(s):  
Shuyi Zhou ◽  
Brandon J. Bethel ◽  
Wenjin Sun ◽  
Yang Zhao ◽  
Wenhong Xie ◽  
...  
Keyword(s):  
Empirical Mode Decomposition ◽  
Wave Height ◽  
Significant Wave Height ◽  
Short Term Memory ◽  
Ocean Engineering ◽  
Short Term ◽  
Term Memory ◽  
Significant Wave ◽  
Mode Decomposition ◽  
Long Short Term Memory

Wave forecasts, though integral to ocean engineering activities, are often conducted using computationally expensive and time-consuming numerical models with accuracies that are blunted by numerical-model-inherent limitations. Additionally, artificial neural networks, though significantly computationally cheaper, faster, and effective, also experience difficulties with nonlinearities in the wave generation and evolution processes. To solve both problems, this study employs and couples empirical mode decomposition (EMD) and a long short-term memory (LSTM) network in a joint model for significant wave height forecasting, a method widely used in wind speed forecasting, but not yet for wave heights. Following a comparative analysis, the results demonstrate that EMD-LSTM significantly outperforms LSTM at every forecast horizon (3, 6, 12, 24, 48, and 72 h), considerably improving forecasting accuracy, especially for forecasts exceeding 24 h. Additionally, EMD-LSTM responds faster than LSTM to large waves. An error analysis comparing LSTM and EMD-LSTM demonstrates that LSTM errors are more systematic. This study also identifies that LSTM is not able to adequately predict high-frequency significant wave height intrinsic mode functions, which leaves room for further improvements.

Sign in / Sign up

Export Citation Format

Share Document