An Application of Instantaneous Spectral Entropy for the Condition Monitoring of Wind Turbines

Civera, Marco; Surace, Cecilia

doi:10.3390/app12031059

Cited by 28 publications

(19 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The generalised Morse wavelet was not very responsive to either linear or nonlinear damage as well, at least for the parameters set here; a larger sensitivity analysis on the two parameters 𝛾 and 𝛽 can be found in [20].…”

Section: Effects Of the Algorithm Selection For Tf Analysismentioning

confidence: 89%

“…In particular, ISE was previously validated as a suitable damage indicator for the condition monitoring of wind turbine gearboxes [20], even if this approach was limited to output signals recorded in similar environmental conditions (i.e., similar wind speed). As discussed before, this issue does not arise for buildings under AVs since this source of input is roughly constant along time and uniform along the frequency spectrum.…”

Section: Instantaneous Entropy Measurementsmentioning

confidence: 99%

“…For the sake of this research, γ = 3 and β = 20 were considered. A detailed analysis of the influence of the GMW parameters for ISE estimates can be found in [20].…”

Section: The Morse Waveletmentioning

confidence: 99%

See 2 more Smart Citations

Instantaneous Spectral Entropy: An Application for the Online Monitoring of Multi-Storey Frame Structures

Civera

Surace

2022

Buildings

Self Cite

View full text Add to dashboard Cite

Damage assessment techniques based on entropy measurements have been recently proposed for the structural health monitoring of civil structures and infrastructures. A quasi-real-time approach, based on the use of instantaneous spectral entropy (ISE) over an uninterrupted stream of data, is discussed here. The methodology is proposed for the detection of sudden damage-related structural changes (more specifically, linear stiffness reductions and nonlinear breathing cracks). The method operates by framing the continuous stream of vibration signals and comparing the single frames to a known baseline. The approach is also suitable for nonstationary signals originating from nonlinearly behaving structures. The procedure is validated on an experimental benchmark: a laboratory-scaled model of a three-storey single-span frame metallic structure. Three different definitions of entropy and six candidate time–frequency/time-scale transforms have been tested to find the optimal settings.

show abstract

Section: Effects Of the Algorithm Selection For Tf Analysismentioning

confidence: 89%

Section: Instantaneous Entropy Measurementsmentioning

confidence: 99%

See 1 more Smart Citation

Instantaneous Spectral Entropy: An Application for the Online Monitoring of Multi-Storey Frame Structures

Civera

Surace

2022

Buildings

Self Cite

View full text Add to dashboard Cite

show abstract

“…The spectral decomposition of the acoustic response was investigated using the CWT, but the authors did not disclose the Morse wavelet parameters. Finally, Civera et al [64] proposed to employ the instantaneous spectral entropy and CWT to analyze the gearbox vibrations of wind turbines for anomaly detection and defect diagnostics. This is one of the few studies in which an extensive explanation and analysis of different values of gamma and beta were presented while establishing the parameters to compute the CWT and performing a sensitivity analysis of the instantaneous spectral entropy estimation.…”

Section: ) Fluid Dynamicsmentioning

confidence: 99%

Applications of the Generalized Morse Wavelets: A Review

et al. 2023

View full text Add to dashboard Cite

The study of signals, processes, and systems has motivated the development of different representations that can be used to analyze and understand them. Classical ways of studying the behavior of signals are the time domain and frequency domain representations. For the analysis of non-stationary signals, time-frequency representations have become an essential tool to understand how the frequency content of signals changes with time. A common time-frequency technique employed in the literature is the wavelet transform. Nevertheless, selecting an adequate mother wavelet to perform the wavelet transform has become challenging due to the diverse available wavelet families. This paper reviews the applications and uses of a particular class of wavelet basis known as the Generalized Morse Wavelets. This class of wavelet family provides a systematic framework to choose and generate a wavelet for general-purpose use. This study reviews the application of Generalized Morse Wavelets in biomedical engineering, dynamical systems analysis, electrical engineering, geophysics, and communication systems. Moreover, the parameters of the Generalized Morse Wavelets used in each study are presented. The results of this study reveal that Generalized Morse Wavelets have proven helpful in studying signals, systems, and processes in areas ranging from biomedical engineering to geophysics. Nonetheless, the parameters of the Generalized Morse Wavelets are yet to be chosen through a rigorous methodology and argumentation. Therefore, there is an opportunity to generate methods for selecting the parameters of the Generalized Morse Wavelets based on the characteristics of the signals, systems, or processes under research.INDEX TERMS Generalized Morse wavelets, mother wavelet selection, continuous wavelet transform, applications, time-frequency analysis.

show abstract

“…Due to the influence of complex operating conditions and environment, the collected vibration signals of the rolling bearing are usually non-stationary and non-linear [20]. Many non-linear dynamic methods, such as sample entropy [21], permutation entropy [22], fuzzy entropy [23], Rényi entropy [24], Wiener entropy [25], Instantantaneous Spectral Entropy [26], dispersion entropy [27], are proposed, which can reflect the non-linear properties of vibration signal and characterize equipment health status. Sample Entropy is slow in calculating long time series, poor in real-time performance, and prone to a sudden change in similarity measurement [28].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Diagnosis of Rolling Element Bearing Based on Refined Composite Multiscale Reverse Dispersion Entropy and Random Forest

Liu

Yang²,

et al. 2022

Sensors

View full text Add to dashboard Cite

Rolling bearings are the vital components of large electromechanical equipment, thus it is of great significance to develop intelligent fault diagnoses for them to improve equipment operation reliability. In this paper, a fault diagnosis method based on refined composite multiscale reverse dispersion entropy (RCMRDE) and random forest is developed. Firstly, rolling bearing vibration signals are adaptively decomposed by variational mode decomposition (VMD), and then the RCMRDE values of 25 scales are calculated for original signal and each decomposed component as the initial feature set. Secondly, based on the joint mutual information maximization (JMIM) algorithm, the top 15 sensitive features are selected as a new feature set and feed into random forest model to identify bearing health status. Finally, to verify the effectiveness and superiority of the presented method, actual data acquisition and analysis are performed on the bearing fault diagnosis experimental platform. These results indicate that the presented method can precisely diagnose bearing fault types and damage degree, and the average identification accuracy rate is 97.33%. Compared with the refine composite multiscale dispersion entropy (RCMDE) and multiscale dispersion entropy (MDE), the fault diagnosis accuracy is improved by 2.67% and 8.67%, respectively. Furthermore, compared with the RCMRDE method without VMD decomposition, the fault diagnosis accuracy is improved by 3.67%. Research results prove that a better feature extraction technique is proposed, which can effectively overcome the deficiency of existing entropy and significantly enhance the ability of fault identification.

show abstract

An Application of Instantaneous Spectral Entropy for the Condition Monitoring of Wind Turbines

Cited by 28 publications

References 46 publications

Instantaneous Spectral Entropy: An Application for the Online Monitoring of Multi-Storey Frame Structures

Instantaneous Spectral Entropy: An Application for the Online Monitoring of Multi-Storey Frame Structures

Applications of the Generalized Morse Wavelets: A Review

Intelligent Diagnosis of Rolling Element Bearing Based on Refined Composite Multiscale Reverse Dispersion Entropy and Random Forest

Contact Info

Product

Resources

About