A time–frequency analysis approach for condition monitoring of a wind turbine gearbox under varying load conditions

Antoniadou, Ifigeneia; Manson, G.; Staszewski, Wiesław J.; Barszcz, Tomasz; Worden, Keith

doi:10.1016/j.ymssp.2015.03.003

Cited by 109 publications

(94 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An example of wavelet transforms applied for condition monitoring applications was presented in Fan and Zuo (2006). Several other frequency methods exist for monitoring applications, e.g., the Empirical Mode Decomposition, as presented in Antoniadou et al (2015), which can offer similar benefits to the wavelet transform. However, the latter method is chosen in this work because it is very easy to implement and a proven concept that is mathematically well grounded.…”

Section: Wavelet Coefficientsmentioning

confidence: 99%

Vibration Monitoring of Gas Turbine Engines: Machine-Learning Approaches and Their Challenges

Matthaiou

Khandelwal

Antoniadou

2017

Front. Built Environ.

View full text Add to dashboard Cite

In this study, condition monitoring strategies are examined for gas turbine engines using vibration data. The focus is on data-driven approaches, for this reason a novelty detection framework is considered for the development of reliable data-driven models that can describe the underlying relationships of the processes taking place during an engine's operation. From a data analysis perspective, the high dimensionality of features extracted and the data complexity are two problems that need to be dealt with throughout analyses of this type. The latter refers to the fact that the healthy engine state data can be non-stationary. To address this, the implementation of the wavelet transform is examined to get a set of features from vibration signals that describe the non-stationary parts. The problem of high dimensionality of the features is addressed by "compressing" them using the kernel principal component analysis so that more meaningful, lowerdimensional features can be used to train the pattern recognition algorithms. For feature discrimination, a novelty detection scheme that is based on the one-class support vector machine (OCSVM) algorithm is chosen for investigation. The main advantage, when compared to other pattern recognition algorithms, is that the learning problem is being cast as a quadratic program. The developed condition monitoring strategy can be applied for detecting excessive vibration levels that can lead to engine component failure. Here, we demonstrate its performance on vibration data from an experimental gas turbine engine operating on different conditions. Engine vibration data that are designated as belonging to the engine's "normal" condition correspond to fuels and airto-fuel ratio combinations, in which the engine experienced low levels of vibration. Results demonstrate that such novelty detection schemes can achieve a satisfactory validation accuracy through appropriate selection of two parameters of the OCSVM, the kernel width γ and optimization penalty parameter ν. This selection was made by searching along a fixed grid space of values and choosing the combination that provided the highest cross-validation accuracy. Nevertheless, there exist challenges that are discussed along with suggestions for future work that can be used to enhance similar novelty detection schemes.

show abstract

Section: Wavelet Coefficientsmentioning

confidence: 99%

Vibration Monitoring of Gas Turbine Engines: Machine-Learning Approaches and Their Challenges

Matthaiou

Khandelwal

Antoniadou

2017

Front. Built Environ.

View full text Add to dashboard Cite

show abstract

“…When there is a distributed error in the gear box, the amplitude of the vibration signal will change. The amplitude modulation function is shown in Equation (2). When the fault gear runs with the shaft one circle, the fault will appear once.…”

Section: Distributed Faultmentioning

confidence: 99%

“…So () m at is a periodic function with the rotating cycle of the shaft as the period. (2) In Equation (2) …”

Section: Distributed Faultmentioning

confidence: 99%

See 1 more Smart Citation

The Characteristics Analysis of Gear Box Fault Vibration Signal

Jiao¹

2017

Proceedings of the 3rd Annual International Conference on Mechanics and Mechanical Engineering (MME 2016)

View full text Add to dashboard Cite

Abstract. Gearbox is a critical component of mechanical equipment. Centralized fault and distributed fault are the two typical faults of gearbox. Both faults have their own features. In order to know them better, the characteristics in the time and frequency domain of the vibration signal were analyzed in detail. It was concluded that it was difficult to judge the type of faults only by the spectrum. Some simulation signals were used to verify the conclusions.

show abstract

“…Generally, recent advances in this direction can be classified into two groups. Since the signal measured in this condition is non-stationary in nature, the first group resorts to some non-stationary signal analysis tools such as short-time Fourier transform (STFT), empirical mode decomposition (EMD) [10,11], wavelet, chirplet, synchro-squeezing transform [12,13] and, more recently, proposed dynamic time warping. For instance, Meltzer et al [14] proposed a polar wavelet amplitude map to realize the fault diagnosis of gears operating under non-stationary rotation speeds.…”

Section: Introductionmentioning

confidence: 99%

Feature Mining and Health Assessment for Gearboxes Using Run-Up/Coast-Down Signals

Zhao

Lin

Miao

et al. 2016

Sensors

View full text Add to dashboard Cite

Vibration signals measured in the run-up/coast-down (R/C) processes usually carry rich information about the health status of machinery. However, a major challenge in R/C signals analysis lies in how to exploit more diagnostic information, and how this information could be properly integrated to achieve a more reliable maintenance decision. Aiming at this problem, a framework of R/C signals analysis is presented for the health assessment of gearbox. In the proposed methodology, we first investigate the data preprocessing and feature selection issues for R/C signals. Based on that, a sparsity-guided feature enhancement scheme is then proposed to extract the weak phase jitter associated with gear defect. In order for an effective feature mining and integration under R/C, a generalized phase demodulation technique is further established to reveal the evolution of modulation feature with operating speed and rotation angle. The experimental results indicate that the proposed methodology could not only detect the presence of gear damage, but also offer a novel insight into the dynamic behavior of gearbox.

show abstract

A time–frequency analysis approach for condition monitoring of a wind turbine gearbox under varying load conditions

Cited by 109 publications

References 38 publications

Vibration Monitoring of Gas Turbine Engines: Machine-Learning Approaches and Their Challenges

Vibration Monitoring of Gas Turbine Engines: Machine-Learning Approaches and Their Challenges

The Characteristics Analysis of Gear Box Fault Vibration Signal

Feature Mining and Health Assessment for Gearboxes Using Run-Up/Coast-Down Signals

Contact Info

Product

Resources

About