An adaptive optimization EEMD method and its application in bearing fault detection

Liu, Xinming; Chen, Wenzhuang; Mao, Aikun

doi:10.21203/rs.3.rs-2615109/v1

Cited by 3 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-task learning is an active research area that attempts to learn jointly multiple tasks, commonly using a shared representation (Ruder, 2017;Navon et al, 2022;Liu et al, 2023;Elich et al, 2023;Shi et al, 2023;Yun & Cho, 2023). Learning a shared representation for multiple tasks imposes some challenges.…”

Section: Related Workmentioning

confidence: 99%

Self-Supervised Learning for Domain Adaptation on Point Clouds

Achituve

Maron²,

Chechik

2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

131

View full text Add to dashboard Cite

As machine learning becomes more prominent there is a growing demand to perform several inference tasks in parallel. Running a dedicated model for each task is computationally expensive and therefore there is a great interest in multi-task learning (MTL). MTL aims at learning a single model that solves several tasks efficiently. Optimizing MTL models is often achieved by computing a single gradient per task and aggregating them for obtaining a combined update direction. However, these approaches do not consider an important aspect, the sensitivity in the gradient dimensions. Here, we introduce a novel gradient aggregation approach using Bayesian inference. We place a probability distribution over the task-specific parameters, which in turn induce a distribution over the gradients of the tasks. This additional valuable information allows us to quantify the uncertainty in each of the gradients dimensions, which can then be factored in when aggregating them. We empirically demonstrate the benefits of our approach in a variety of datasets, achieving state-of-the-art performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Self-Supervised Learning for Domain Adaptation on Point Clouds

Achituve

Maron²,

Chechik

2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

131

View full text Add to dashboard Cite

show abstract

“…Subsequently, the components of the multiple decomposed IMFs are averaged to mitigate the impact of random noise (Huang et al, 1917;Yi et al, 2022). The specific steps are as follows (Peng et al, 1971;Liu et al, 2023):…”

Section: Principle and Methodsmentioning

confidence: 99%

“…The larger the set average number, the smaller the decomposition error, but the increase will reduce the computational efficiency. Therefore, it is important to balance both white noise amplitude and set average number, which represents the adaptivity in EEMD (Liu et al, 2023). The adaptive EEMD method can avoid a large number of parameters setting manually and significantly improve decomposition efficiency and accuracy.…”

Section: Principle and Methodsmentioning

confidence: 99%

Extraction of periodic signals in GNSS vertical coordinate time series using adaptive Ensemble Empirical Modal Decomposition method

Li,

Guo

2023

Preprint

View full text Add to dashboard Cite

Abstract. Ensemble Empirical Mode Decomposition (EEMD) has been widely used in the data analysis. Adaptive EEMD further improves computational efficiency through the adaptability in the white noise amplitude and set average number. However, its effectiveness of the periodic signal extraction in Global Navigation Satellite System (GNSS) coordinate time series regarding on the inevitable missing data and offsets issues have not been comprehensively validated. It is verified with 5- year time series through 300 simulations for each case. The results show that high accuracy could reach for the overall random missing rate below 15 % and avoiding consecutive missing epochs exceeding 30. Meanwhile, offsets should be corrected in advance regardless of their magnitudes. The analysis of vertical component of 13 stations within the Australian Global Sea Level Observing System (GLOSS) monitoring network, demonstrates the advantage in revealing the time-varying characteristics of periodic signals. From the perspectives of correlation coefficients, power spectral density (PSD) indices and signal noise ratio (SNR), the means for adaptive EEMD are 0.36, -0.18 and 0.48, respectively, while for least squares (LS), they are 0.27, -0.50 and 0.23. Meanwhile, significance test of the residuals further substantiate the effectiveness in periodic signal extraction, which shows there is no annual signal remained. Also, the longer the series, the higher accuracy of extracted periodic signal is reasonable concluded via the significance test. Furthermore, the time-varying periodic characteristics is more conducive to analyze the driving factors. Overall, the application of adaptive EEMD could achieve high accuracy in analyzing GNSS time series, but it should be based on the proper dealing with missing data and offsets.

show abstract

Extraction of periodic signals in Global Navigation Satellite System (GNSS) vertical coordinate time series using the adaptive ensemble empirical modal decomposition method

Li,

Guo

2024

Nonlin. Processes Geophys.

View full text Add to dashboard Cite

Abstract. Empirical modal decomposition (EMD) is an efficient tool for extracting a signal from stationary or non-stationary time series and is enhanced in stability and robustness by ensemble empirical mode decomposition (EEMD). Adaptive EEMD further improves computational efficiency through adaptability in the white noise amplitude and set average number. However, its effectiveness in the periodic signal extraction in Global Navigation Satellite System (GNSS) coordinate time series regarding the inevitable missing data and offset issues has not been comprehensively validated. In order to thoroughly investigate their impacts, we simulated 5 years of daily time series data with different missing data percentages or a different number of offsets and conducted them 300 times for each simulation. The results show that high accuracy could reach the overall random missing rate below 15 % and avoid consecutive misses exceeding 30 d. Meanwhile, offsets should be corrected in advance regardless of their magnitudes. The analysis of the vertical components of 13 stations within the Australian Global Sea Level Observing System (GLOSS) monitoring network demonstrates the advantage of adaptive EEMD in revealing the time-varying characteristics of periodic signals. From the perspectives of correlation coefficients (CCs), root mean square error (RMSE), power spectral density indices (κ) and signal-to-noise ratio (SNR), the means for adaptive EEMD are 0.36, 0.81, −0.18 and 0.48, respectively, while for least squares (LS), they are 0.27, 0.86, −0.50 and 0.23. Meanwhile, a significance test of the residuals further substantiates the effectiveness in periodic signal extraction, which shows that there is no annual signal remaining. Also, the longer the series, the higher the accuracy of the reasonable extracted periodic signal concluded via the significance test. Moreover, driving factors are more effectively facilitated by the time-varying periodic characteristics compared with the constant periodic signal derived by LS. Overall, the application of adaptive EEMD could achieve high accuracy in analyzing GNSS time series, but it should be based on properly dealing with missing data and offsets.

show abstract

An adaptive optimization EEMD method and its application in bearing fault detection

Cited by 3 publications

References 14 publications

Self-Supervised Learning for Domain Adaptation on Point Clouds

Self-Supervised Learning for Domain Adaptation on Point Clouds

Extraction of periodic signals in GNSS vertical coordinate time series using adaptive Ensemble Empirical Modal Decomposition method

Extraction of periodic signals in Global Navigation Satellite System (GNSS) vertical coordinate time series using the adaptive ensemble empirical modal decomposition method

Contact Info

Product

Resources

About