Impulsive feature extraction with improved singular spectrum decomposition and sparsity-closing morphological analysis

Duan, Rongkai; Liao, Yuhe

doi:10.1016/j.ymssp.2022.109436

Cited by 13 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the SSA models also have some limitations when they are applied in tourism demand forecasting. For example, when the SSA is used to process the tourism demand data with great fluctuations, the decomposed components may contain a lot of noise, and may undergo over-decomposition phenomenon; The filtering effect and calculation efficiency of SSA are seriously affected by the embedding dimension of trajectory matrix (Duan and Liao, 2022); The embedding dimension of each iteration is determined by the empirical formula, which may lead to the problem of mode mixing and over decomposition (Mao et al, 2020).…”

Section: Literature Reviewmentioning

confidence: 99%

Fine-grained tourism demand forecasting: A decomposition ensemble deep learning model

Han

Yao

2023

Tourism Economics

View full text Add to dashboard Cite

Compared with coarse-grained forecasting, fine-grained tourism demand forecasting is a more challenging task, but research on this issue is very scarce. To address this issue, a decomposition ensemble deep learning model is proposed by integrating CEEMDAN, CNNs, LSTM networks, and AR models. The CEEMDAN can decompose complex tourism demand data into multiple components with simpler characteristics, thereby reducing the complexity of forecasting. The CNNs and LSTM networks can fully capture the locally recurring patterns and the long-term dependencies of the components obtained by CEEMDAN. The AR model can capture the scale of tourism demand data, which can overcome the problem that the output scale of the deep neural networks (i.e., CNNs and LSTM networks) is not sensitive to the scale of the inputs. The effectiveness of the proposed model is verified by comparing with five benchmark models using real-time data on tourist volumes at two attractions.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Fine-grained tourism demand forecasting: A decomposition ensemble deep learning model

Han

Yao

2023

Tourism Economics

View full text Add to dashboard Cite

show abstract

“…where Hp represents the replacement entropy, p i is the probability value of each row in the reconstruction matrix m 1 × q of the input signal. The optimal parameters are [5,2346]. The simulated signals are decomposed into five sets of IMFs.…”

Section: The Simulation Analysismentioning

confidence: 99%

“…Hence, there is a great need to exactly diagnosis bearing faults early. Hitherto, extensive investigations have been carried out on bearing single fault diagnosis, and enormous achievements have emerged [3][4][5]. * Author to whom any correspondence should be addressed.…”

Section: Introductionmentioning

confidence: 99%

Composite fault feature extraction of rolling bearing using adaptive circulant singular spectrum analysis

Zhou,

Zhu,

Zhong

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Aiming to extract the weak composite fault characteristics of a rolling bearing under harsh operation conditions, a novel composite fault diagnosis method for bearings based on adaptive circulant singular spectrum analysis (ACiSSA) is proposed. The proposed method is able to adaptively obtain the eigenvalue of a non-stationary vibration signal in any dimension, and effectively reassemble the same frequency components and improve the signal-to-noise ratio (SNR). Specifically, circulant singular spectrum analysis is utilized to decompose the raw signal, and the optimal parameters, i.e. the embedding dimension and threshold value of cumulative contribution, are selected to maximum kurtosis through the grey wolf optimization method. The signal is reconstructed with high SNR according to the effective singular spectrum components. Envelope demodulation analysis is then implemented to extract the characteristic defect frequency in the reconstructed signal. Finally, feature extraction performance is quantitatively evaluated, and experimental results show that the proposed ACiSSA method is able to extract more sensitive features under more noisy conditions compared with other common methods, with higher computational efficiency.

show abstract

“…As an adaptive and efficient signal processing technology, sparse decomposition has been used widely in fault diagnosis, and most of them mainly focused on weak or compound fault diagnosis of rotating machinery [23][24]. The references relating to the application of sparse decomposition on BSS or UBSS is relative very few.…”

Section: Introductionmentioning

confidence: 99%

Single channel blind source separation of rolling bearing compound faults based on self-learning sparse decomposition and feature mode decomposition

Zhang

2024

J. vibroeng.

View full text Add to dashboard Cite

Feature mode decomposition (FMD) has advantages over the other newer time-frequency methods such as ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) in single channel blind source separation (SCBSS). However, FMD has the defect of needing to determine the precise number of fault sources manually. To solve the above defect of FMD, an adaptive method for determining the number of fault sources based on the shift invariant sparse code (SISC) is proposed. SISC was used to train a set of basis functions from the single channel signal, and the corresponding potential components were reconstructed firstly. Subsequently, the structural similarity of these potential components was used for clustering, and each of the obtained clustering signals represented one kind of fault. Then the number of clustering was determined by minimizing the structural correlation among the clustering signals. It was considered that the source separation had achieved the best effect when the structural difference among the clusters was the largest, and the number of clustering at this time was used as the optimal estimated value, which was used as the modal inputs number of FMD calculation model to realize SCBSS of rolling bearing. Simulation and experimental analysis were carried out to verify the effectiveness of the proposed method, and its superiority was also verified through comparison.

show abstract

Impulsive feature extraction with improved singular spectrum decomposition and sparsity-closing morphological analysis

Cited by 13 publications

References 45 publications

Fine-grained tourism demand forecasting: A decomposition ensemble deep learning model

Fine-grained tourism demand forecasting: A decomposition ensemble deep learning model

Composite fault feature extraction of rolling bearing using adaptive circulant singular spectrum analysis

Single channel blind source separation of rolling bearing compound faults based on self-learning sparse decomposition and feature mode decomposition

Contact Info

Product

Resources

About