Bearing performance degradation assessment based on optimized EWT and CNN

Hu, Mantang; Wang, Guofeng; Ma, Kaile; Cao, Zenghuan; Yang, Shuai

doi:10.1016/j.measurement.2020.108868

Cited by 33 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mao et al (2020) have proposed a Safe Semi-Supervised Support Vector Machine (S4VM) algorithm, which detects that the early abnormal point of bearing 1 is the sampling sequence 535. Hu et al (2020) have introduced the degradation index constructed based on Empirical Wavelet Transform (EWT) and CNN, which can detect that bearing 1 enters the early anomaly when the serial number is 533. These results are basically the same as the method proposed in this paper.…”

Section: Resultsmentioning

confidence: 99%

“…Singular values are used as input to construct a graph, and GMSVs are used to check whether the rolling bearing has a failure during continuous operation, which improves the sensitivity to early failure and the robustness of index. Hu et al (2020) have used the Convolutional Neural Network (CNN) to extract the sensitive features of the Short-Time Fourier Transform (STFT) envelope spectrum in bearing fault component, which can improve the sensitivity and stability of the early anomaly detection. The above methods are suitable for the case where the monitoring data are small, and when the sample size is large, problems such as low efficiency and large calculation amount occur.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An anomaly detection algorithm of rolling bearing combining random matrix eigenvalues and principal eigenvectors

Wang

Zhu

Zhang

et al. 2022

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

An anomaly detection algorithm combining eigenvalues and eigenvectors in random matrix is proposed, which can solve the problem that present algorithms based on random matrix theory overly rely on eigenvalues and ignore useful information contained in eigenvectors. Firtsly, the time window method is used to select the original data of rolling bearing, and the sampling feature matrix is constructed by extracting bearing feature. Secondly, the eigenvalues and principal eigenvector of sampling feature matrix are investigated and combined to construct comprehensive feature index and its corresponding threshold. Finally, an anomaly detection based on comprehensive feature index is proposed to detect the early anomaly of rolling bearing. The application research is carried out by using bearing datasets of intelligent maintenance center and Xi’an Jiaotong University; the result shows that compared with the single eigenvalue index and kurtosis index, the algorithm based on the comprehensive feature index can detect the abnormal condition of bearing earlier. And the accuracy and effectiveness of the anomaly detection algorithm are proved through spectrum analysis, which provides guidance and basis for fault warning and equipment maintenance.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An anomaly detection algorithm of rolling bearing combining random matrix eigenvalues and principal eigenvectors

Wang

Zhu

Zhang

et al. 2022

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…However, traditional machine learning methods like SVM require a priori knowledge of feature engineering, which is extremely difficult to implement with regard to bearings due to the complex working conditions they operate under. Deep learning-based algorithms provide an alternative solution to this problem [ 8 , 9 , 10 ]. Chen et al proposed a method based on neuro-fuzzy systems (NFSs) and Bayesian algorithms, which use trained NFSs as predictors to discern the degradation of a given machine’s fault state over time [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Performance Degradation Prediction Using LSTM with Optimized Parameters

Wei²,

Yang³

et al. 2022

Sensors

View full text Add to dashboard Cite

Predicting the degradation of mechanical components, such as rolling bearings is critical to the proper monitoring of the condition of mechanical equipment. A new method, based on a long short-term memory network (LSTM) algorithm, has been developed to improve the accuracy of degradation prediction. The model parameters are optimized via improved particle swarm optimization (IPSO). Regarding how this applies to the rolling bearings, firstly, multi-dimension feature parameters are extracted from the bearing’s vibration signals and fused into responsive features by using the kernel joint approximate diagonalization of eigen-matrices (KJADE) method. Then, the between-class and within-class scatter (SS) are calculated to develop performance degradation indicators. Since network model parameters influence the predictive accuracy of the LSTM model, an IPSO algorithm is used to obtain the optimal prediction model via the LSTM model parameters’ optimization. Finally, the LSTM model, with said optimal parameters, was used to predict the degradation trend of the bearing’s performance. The experiment’s results show that the proposed method can effectively identify the trends of degradation and performance. Moreover, the predictive accuracy of this proposed method is greater than that of the extreme learning machine (ELM) and support vector regression (SVR), which are the algorithms conventionally used in degradation modeling.

show abstract

“…The existing popular empirical mode decomposition [24] often has the problem of modal aliasing. Furthermore, the difficulty of wavelet decomposition [25] lies in how to effectively select the wavelet basis and decomposition scale. In addition, the decomposition methods may introduce some redundant decomposition information to the predictive models, degenerating the predictive computational cost.…”

Section: Introductionmentioning

confidence: 99%

A Stacking Learning Model Based on Multiple Similar Days for Short-Term Load Forecasting

Jiang

Cheng

et al. 2022

Mathematics

View full text Add to dashboard Cite

It is challenging to obtain accurate and efficient predictions in short-term load forecasting (STLF) systems due to the complexity and nonlinearity of the electric load signals. To address these problems, we propose a hybrid predictive model that includes a sliding-window algorithm, a stacking ensemble neural network, and a similar-days predictive method. First, we leverage a sliding-window algorithm to process the time-series electric load data with high nonlinearity and non-stationarity. Second, we propose an ensemble learning scheme of stacking neural networks to improve forecasting performance. Specifically, the stacking neural networks contain two types of networks: the base-layer and the meta-layer networks. During the pre-training process, the base-layer network integrates a radial basis function (RBF), random vector functional link (RVFL), and backpropagation neural network (BPNN) to provide a robust predictive model. The meta-layer network utilizes a deep belief network (DBN) and the improved broad learning system (BLS) to enhance predictive accuracy. Finally, the similar-days prediction method is developed to extract the relationship of electric load data in different time dimensions, further enhancing the robustness and accuracy of the model. To demonstrate the effectiveness of our model, it is evaluated using real data from five regions of the United States in three consecutive years. We compare our method with several state-of-the-art and conventional neural-network-based models. Our proposed algorithm improves the prediction accuracy by 16.08%, 16.83%, and 22.64% compared to DWT-EMD-RVFL, SWT-LSTM, and EMD-BLS, respectively. Empirical results demonstrate that our model achieves better accuracy and robustness compared with the baselines.

show abstract

Bearing performance degradation assessment based on optimized EWT and CNN

Cited by 33 publications

References 21 publications

An anomaly detection algorithm of rolling bearing combining random matrix eigenvalues and principal eigenvectors

An anomaly detection algorithm of rolling bearing combining random matrix eigenvalues and principal eigenvectors

Performance Degradation Prediction Using LSTM with Optimized Parameters

A Stacking Learning Model Based on Multiple Similar Days for Short-Term Load Forecasting

Contact Info

Product

Resources

About