Variational mode decomposition and sample entropy optimization based transformer framework for cloud resource load prediction

Zhu, Jiaxian; Bai, Weihua; Zhao, Jialing; Zuo, Liyun; Zhou, Teng; Li, Keqin

doi:10.1016/j.knosys.2023.111042

Cited by 13 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the signal sequence is complex, its own signal similarity is low, and the corresponding sample entropy is large. When the signal sequence is not complex, its own signal similarity is high, and the corresponding sample entropy is small [30,31]. Li Xuguang [32] extracted fault features from the processed rolling bearing signals through MEEMD sample entropy and realized rolling bearing fault diagnosis.…”

Section: Literature Analysismentioning

confidence: 99%

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Xu,

Li,

Zhang

et al. 2023

Actuators

View full text Add to dashboard Cite

As the main transportation equipment in ore mining, the wheel drive system of mining trucks plays a crucial role in the transportation capacity of mining trucks. The internal components of the hub drive system are mainly composed of bearings, gears, etc. The vibration signals caused during operation are nonlinear and nonstationary complex signals, and there may be more than one factor that causes faults, which causes certain difficulties for the fault diagnosis of the hub drive system. A fault diagnosis method based on local mean decomposition (LMD) multi-component sample entropy fusion and LS-SVM is proposed to address this issue. Firstly, the LMD method is used to decompose the vibration signals in different states to obtain a finite number of PF components. Then, based on the typical correlation analysis method, the distribution characteristics and correlation coefficients of vibration signals in the frequency domain under different states are calculated, and effective PF multi-component sample entropy features are constructed. Finally, the LS-SVM multi-fault classifier is used to train and test the extracted multi-component sample entropy features to verify the effectiveness of the method. The experimental results show that, even in small-sample data, the LMD multi-component sample entropy fusion and LS-SVM method can accurately extract fault features of vibration signals and complete classification, achieving fault diagnosis of wheel drive systems.

show abstract

Section: Literature Analysismentioning

confidence: 99%

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Xu,

Li,

Zhang

et al. 2023

Actuators

View full text Add to dashboard Cite

show abstract

“…Sample entropy (SE) is an effective nonlinear analysis method proposed by Chou et al to measure the complexity of signals [17]. It eliminates the impact of different signal lengths and pattern matching [18], making it more sensitive to the complexity of signal calculations [19,20]. SE is an improvement over approximate entropy, which measures the probability of new patterns emerging in a signal from the perspective of time-series complexity [21].…”

Section: Introductionmentioning

confidence: 99%

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation^*

Peng,

Hu,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Natural gas pipelines are an essential part of the economy. Natural gas pipelines may leak after aging, strong vibration signals may be generated in the pipeline when leakage occurs, and vibration signals may be noisy. Traditional variational mode decomposition (VMD) noise reduction methods need to set parameters in advance, and so may not achieve the best decomposition effect. To solve this problem, this paper proposes a method for pipeline leakage location based on the sparrow search algorithm (SSA) optimization of VMD combined with generalized quadratic cross-correlation. The method first calculates the original signal-to-noise ratio, and if the signal-to-noise ratio is low, wavelet threshold denoising is used to process the signal. Then, SSA optimization is used to refine the two key parameters of VMD (penalty parameter α and mode decomposition number K) based on sample entropy. Subsequently, the signal undergoes decomposition into K intrinsic mode function (IMF) components through VMD according to the obtained analysis parameter combination. Then, the IMF components are screened to obtain the reconstructed signal. Finally, the noise reduction signal is obtained. The signal delay after noise reduction is obtained through a generalized quadratic cross-correlation and the accurate leakage position is obtained using the delay. Experiments showed that the minimum relative error of this method could reach 0.6%, which was more accurate than the traditional VMD method, and effectively improved the accuracy of noisy signals in pipeline leakage locations.

show abstract

An error-corrected deep Autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction

Chen,

Peng,

Qian

et al. 2025

Applied Energy

View full text Add to dashboard Cite

Variational mode decomposition and sample entropy optimization based transformer framework for cloud resource load prediction

Cited by 13 publications

References 33 publications

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation^*

An error-corrected deep Autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction

Contact Info

Product

Resources

About

Variational mode decomposition and sample entropy optimization based transformer framework for cloud resource load prediction

Cited by 13 publications

References 33 publications

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Fault Diagnosis of Mine Truck Hub Drive System Based on LMD Multi-Component Sample Entropy Fusion and LS-SVM

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation*

An error-corrected deep Autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction

Contact Info

Product

Resources

About

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation^*