Tool Vibration Feature Extraction Method Based on SSA-VMD and SVM

Cai, Lihong; Dong, Hu; Zhang, Chengming; Song, Yu; Xie, Jufang

doi:10.1007/s13369-022-06635-6

Cited by 12 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of IVMD, optimized using the SSA, for the decomposition of PV power data marks a significant advancement in the preprocessing stage of forecasting [53][54][55]. This methodological choice allows for a refined extraction of the intrinsic modes within the power generation data, facilitating a more detailed and accurate analysis of the power output fluctuations.…”

Section: Discussionmentioning

confidence: 99%

A Novel Improved Variational Mode Decomposition-Temporal Convolutional Network-Gated Recurrent Unit with Multi-Head Attention Mechanism for Enhanced Photovoltaic Power Forecasting

Fu,

Zhang,

Xie

2024

Electronics

View full text Add to dashboard Cite

Photovoltaic (PV) power forecasting plays a crucial role in optimizing renewable energy integration into the grid, necessitating accurate predictions to mitigate the inherent variability of solar energy generation. We propose a novel forecasting model that combines improved variational mode decomposition (IVMD) with the temporal convolutional network-gated recurrent unit (TCN-GRU) architecture, enriched with a multi-head attention mechanism. By focusing on four key environmental factors influencing PV output, the proposed IVMD-TCN-GRU framework targets a significant research gap in renewable energy forecasting methodologies. Initially, leveraging the sparrow search algorithm (SSA), we optimize the parameters of VMD, including the mode component K-value and penalty factor, based on the minimum envelope entropy principle. The optimized VMD then decomposes PV power, while the TCN-GRU model harnesses TCN’s proficiency in learning local temporal features and GRU’s capability in rapidly modeling sequence data, while leveraging multi-head attention to better utilize the global correlation information within sequence data. Through this design, the model adeptly captures the correlations within time series data, demonstrating superior performance in prediction tasks. Subsequently, the SSA is employed to optimize GRU parameters, and the decomposed PV power mode components and environmental feature attributes are inputted into the TCN-GRU neural network. This facilitates dynamic temporal modeling of multivariate feature sequences. Finally, the predicted values of each component are summed to realize PV power forecasting. Validation using real data from a PV station corroborates that the novel model demonstrates a substantial reduction in RMSE and MAE of up to 55.1% and 54.5%, respectively, particularly evident in instances of pronounced photovoltaic power fluctuations during inclement weather conditions. The proposed method exhibits marked improvements in accuracy compared to traditional PV power prediction methods, underscoring its significance in enhancing forecasting precision and ensuring the secure scheduling and stable operation of power systems.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Improved Variational Mode Decomposition-Temporal Convolutional Network-Gated Recurrent Unit with Multi-Head Attention Mechanism for Enhanced Photovoltaic Power Forecasting

Fu,

Zhang,

Xie

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Therefore, Jin et al [19] employed grey wolf optimization (GWO) algorithm to optimize the parameters of VMD. Cai et al [20] applied sparrow search algorithm (SSA) to optimize the parameters of VMD to obtain optimized modal components, and extracted the kurtosis index and margin factor of the modal components to form feature vectors.…”

Section: Introductionmentioning

confidence: 99%

Improved DBO-VMD and optimized DBN-ELM based fault diagnosis for control valve

Zhang,

Han

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Control valves play a vital role in process production. In practical applications, control valves are prone to blockage and leakage faults. At the small control valve openings, the vibration signals exhibit the drawbacks of significant interference and weak fault characteristics, which causes subpar fault diagnosis performance. To address the issue, a diagnostic model based on optimized Variational Mode Decomposition (VMD) and improved Deep Belief Network-Extreme Learning Machine (DBN-ELM) is proposed. Firstly, good point set population initialization, nonlinear convergence factor, and adaptive Gaussian-Cauchy mutation strategies are applied in the dung beetle optimization algorithm (DBO) to escape local optima. Then, the improved DBO (IDBO) is used to optimize VMD parameters to obtain a series of modal components. Next, the generalized dispersion entropy (GDE) is formed by the combination of Generalized Gaussian Distribution and refined composite multiscale fluctuation-based dispersion entropy. The maximum correlation coefficient modal components are applied to extract generalized dispersion entropy. Finally, the IDBO is applied to optimize the parameters of the DBN-ELM network to improve the classification performance of control valve faults. The comparative experiment results demonstrate that the proposed model can extract effective features and the diagnostic accuracy reaches 99.87%.

show abstract

“…In different working conditions and operation stages, the vibration signals are obviously different. The main problems and difficulties in vibration signal processing and feature extraction include complex mechanical structures, multiple elastic elements, dense natural frequencies and disordered excitation factors, which increase the difficulty of vibration feature extraction [8,9]. Representative studies on fault diagnosis techniques are as follows: Wang [10] proposed a vibration signal acquisition and computer simulation detection method for mechanical equipment faults.…”

Section: Introductionmentioning

confidence: 99%

Application of vibration signal detection in mine hoist fault monitoring system

Fan¹,

Zhang²,

Han³

2023

J. meas. eng.

View full text Add to dashboard Cite

Due to the harsh working environment and various types of faults in mine hoists, the implementation of conventional detection is relatively difficult. In order to improve the maintenance and fault detection efficiency of mine hoist, a portable vibration detection system is designed and applied in this paper, which can judge the type and characteristics of mechanical faults according to the different responses of vibration signals. According to the test conditions of the vibration system, the overall structure and functional composition of the hardware system are established. The key functional modules are designed, including signal conditioning module, main control module, vibration sensor and power management module. The main reasons that affect and produce the hoist fault and mechanical vibration are analyzed. The wavelet packet analysis method is proposed to realize the decomposition of low frequency and high frequency signals to improve the signal resolution of the whole frequency band in the frequency domain. The vibration test system has the function of real-time data transmission and control. The realization methods include WiFi and reserved RS485 communication interface, which can match the communication rate with the data sampling rate. The amplifying circuit of the electric signal is designed to effectively ensure that the output voltage of the charge amplifier is within the input range of the amplified ADC value. In order to verify the working effect of the system, the most common gearbox and bearing failures are taken as examples. The response signals of vibration test and diagnosis can be effectively obtained, and the fault types and characteristics can be accurately judged. Through confusion matrix analysis, the reliability of the system detection index is effectively verified. The research results show that the data of the vibration detection system is stable and reliable, and can achieve good troubleshooting effect. It also can be known that different fault types can excite different vibration responses, especially at resonance frequencies. According to the verification, the data of the vibration detection system is stable and reliable, and can achieve good troubleshooting effect.

show abstract

Tool Vibration Feature Extraction Method Based on SSA-VMD and SVM

Cited by 12 publications

References 21 publications

A Novel Improved Variational Mode Decomposition-Temporal Convolutional Network-Gated Recurrent Unit with Multi-Head Attention Mechanism for Enhanced Photovoltaic Power Forecasting

A Novel Improved Variational Mode Decomposition-Temporal Convolutional Network-Gated Recurrent Unit with Multi-Head Attention Mechanism for Enhanced Photovoltaic Power Forecasting

Improved DBO-VMD and optimized DBN-ELM based fault diagnosis for control valve

Application of vibration signal detection in mine hoist fault monitoring system

Contact Info

Product

Resources

About