GEAR FAULT DIAGNOSIS BASEDONCONTINUOUS WAVELET TRANSFORM

Faults that may occur in mechanical systems such as gears show up in vibration signals in the form of transients and shock pulses yielding non-stationary signals. The analysis of non-stationary signals requires specific techniques which go far beyond the conventional spectral analysis. Wavelet transform (WT) is considered a powerful tool to locate transient information in signals. It has been successfully used for early detection and diagnosis of local gear faults in the last 10 years. This paper outlines the development of signal analysis techniques employed in early detection of different faults. It gives the basic theoretical background of wavelet analysis. The short-time Fourier transform (STFT) which is the classical time-frequency analysis technique is also reviewed. The development of adaptive wavelet filters based upon Morlet wavelet function is introduced. Also, a numerical simulation of a gear fault is presented to demonstrate the advantages of the wavelet transform over the fast Fourier transform (FFT) and the short-time Fourier transform. The results of the study showed that: FFT is not efficient in locating impulses in time domain. STFT has fixed resolution that depends upon the selection of the window half- width. Continuous Wavelet transform (CWT) is very efficient in localizing impulses and detecting periodic events as well due to its multi-resolution property. Complex CWT is very sensitive to any abrupt changes in the time signal so it can detect impulses. DWT is efficient in locating impulses but it is difficult to specify frequencies of periodic events.

2012

The methodology of vibration analysis for condition monitoring has been evolving at a rapid stage in the recent years. The ability to efficiently detect non-stationary, non-periodic, transient features of the vibration signal makes the wavelet analysis a demanding tool for condition monitoring. In this paper the application of Laplace wavelet kurtosis for processing vibration signal to detect faults in gears is presented. A gear testing apparatus is used for experimental studies to obtain vibration signal from a healthy and faulty gears. An experimental data is processed to compare the fault diagnostic capability of wavelet kurtosis with various wavelet statistical parameters such as Crest Factor, Impulse Factor and Shape Factors as obtained from Laplace wavelet. Further the Laplace wavelet kurtosis method is investigated for various working condition of the gear.Finally application of ANN is used for automated gear fault diagnosis by using the features extracted from wavelet transf...

In this work, automatic detection and diagnosis of gear condition monitoring technique is presented. The vibration signals in time domain wereobtained from a fault simulator apparatus from a healthy gear and an induced faulty gear. These time domain signals were processed using Laplace and Morlet wavelet based enveloped power spectrum to detect the faults in gears. The vibration signals obtained were filtered to enhance the signal components before the application of wavelet analysis. The time and frequency domain features extracted from Laplace wavelet based wavelet transform are used as input to ANN for gear fault classification. Genetic algorithm was used to optimize the wavelet and ANN classification parameters. The result shows the successful classification of ANN test process.

2013

The methodology of vibration based condition monitoring technology has been developing at a rapid stage in the recent years suiting to the maintenance of sophisticated and complicated machines. The ability of wavelet analysis to efficiently detect non-stationary, non-periodic, transient features of the vibration signal makes it a demanding tool for condition monitoring. In this paper, the vibration condition monitoring based on Laplace and Morlet wavelet enveloped power spectrum analysis to detect the faults in gears is presented. The experimental studies were conducted on the gear testing apparatus to obtain the vibration signal from a healthy gear and a faulty gear. The vibration signals obtained were filtered to enhance the signal components before the application of wavelet analysis. A study detailing features of fault characterization is also given in order to understand the effectiveness of signal processing methods. Keywords-Continuous wavelet transform, Envelope power spectr...

Shock and Vibration, 2016

Vibration diagnosis is one of the most common techniques in condition evaluation of wind turbine equipped with gearbox. On the other side, gearbox is one of the key components of wind turbine drivetrain. Due to the stochastic operation of wind turbines, the gearbox shaft rotating speed changes with high percentage, which limits the application of traditional vibration signal processing techniques, such as fast Fourier transform. This paper investigates a new approach for wind turbine high speed shaft gear fault diagnosis using discrete wavelet transform and time synchronous averaging. First, the vibration signals are decomposed into a series of subbands signals with the use of a multiresolution analytical property of the discrete wavelet transform. Then, 22 condition indicators are extracted from the TSA signal, residual signal, and difference signal. Through the case study analysis, a new approach reveals the most relevant condition indicators based on vibrations that can be used f...

This paper presents a novel time-frequency-based feature recognition system for gear fault diagnosis using autocorrelation of continuous wavelet coefficients (CWC). Furthermore, it introduces an original mathematical approximation of gearbox vibration signals which approximates sinusoidal components of noisy vibration signals generated from gearboxes, including incipient and serious gear failures using autocorrelation of CWC. First, the drawbacks of the continuous wavelet transform (CWT) have been eliminated using autocorrelation function. Secondly, the autocorrelation of CWC is introduced as an original pattern for fault identification in machine condition monitoring. Thirdly, a sinusoidal summation function consisting of eight terms was used to approximate the periodic waveforms generated by autocorrelation of CWC for normal gearboxes (NGs) as well as occurrences of incipient and severe gear fault (e.g. slight-worn, medium-worn, and broken-tooth gears). In other words, the size of vibration signals can be reduced with minimal loss of significant frequency content by means of the sinusoidal approximation of generated autocorrelation waveforms of CWC as reported in this paper.

Journal of Vibroengineering, 2018

Vibration signal of gearbox systems carries the important dynamic information for fault diagnosis. However, vibration signals always show non stationary behavior and overwhelmed by a large amount of noise make this task challenging in many cases. Thus, a new fault diagnosis method combining the Hilbert empirical wavelet transform (HEWT), the singular value decomposition (SVD) and Elman neural network is proposed in this paper. Vibration signals of normal gear, gear with tooth root crack, gear with chipped tooth in width, gear with chipped tooth in length, gear with missing tooth and gear with general surface wear are collected in different speed and load conditions. HEWT, a new self-adaptive time-frequency analysis, was applied to the vibration signals to obtain the instantaneous amplitude matrices. Singular value vectors, as the fault feature vectors were then acquired by applying the SVD. Last, the Elman neural network was used for automatic gearbox fault identification and classification. Through experimental results, it was concluded that the proposed method can accurately extract and classify the gear fault features under variable conditions. Moreover, the performance of the proposed HEWT-SVD method has an advantage over that of Hilbert-Huang transform (HHT)-SVD, local mean decomposition (LMD)-SVD or wavelet packet transform (WPT)-PCA for feature extraction.

This paper presents a novel time-frequency-based feature recognition system for gear fault diagnosis using autocorrelation of continuous wavelet coefficients (CWC). Furthermore, it introduces an original mathematical approximation of gearbox vibration signals which approximates sinusoidal components of noisy vibration signals generated from gearboxes, including incipient and serious gear failures using autocorrelation of CWC. First, the drawbacks of the continuous wavelet transform (CWT) have been eliminated using autocorrelation function. Secondly, the autocorrelation of CWC is introduced as an original pattern for fault identification in machine condition monitoring. Thirdly, a sinusoidal summation function consisting of eight terms was used to approximate the periodic waveforms generated by autocorrelation of CWC for normal gearboxes (NGs) as well as occurrences of incipient and severe gear fault (e.g. slight-worn, medium-worn, and broken-tooth gears). In other words, the size of vibration signals can be reduced with minimal loss of significant frequency content by means of the sinusoidal approximation of generated autocorrelation waveforms of CWC as reported in this paper.

iaeme

Monitoring of rotating machines by vibration analysis is a topic that has aroused great interest in the field of research in recent years. Moreover, the vibrations from a machine are very affected by the conditions of its operation (speed, load, etc.). Vibration analysis is especially applicable to the monitoring of enclosed systems, such as gearboxes. A significant challenge remains with the monitoring of gears under fluctuating operating conditions. Gear is one of the most important and frequently encountered components in rotating machinery, whose operation condition directly affects the whole performance of rotating machinery. An unexpected fault of gear may cause huge economic losses, even personal injury. Among the techniques used for this purpose is the signal processing. To diagnose early fault of rotating machinery, feature extraction of vibration signals is a very important and difficult research task on engineering. The signal of rotating machinery is usually non-stationary, non-linear, and with strong noise interference, meantime, the early signal energy is too low to extract fault features in time domain. In this paper, the wavelet packet transform (WPT) is applied to the analysis of vibration signals delivered from a rotating machine to detect early the presence of defects. The mother wavelet used is wavelet of Haar

Applied Soft Computing, 2011

The features of non-stationary multi-component signals are often difficult to be extracted for expert systems. In this paper, a new method for feature extraction that is based on maximization of local Gaussian correlation function of wavelet coefficients and signal is presented. The effect of empirical mode decomposition (EMD) to decompose multi-component signals to intrinsic mode functions (IMFs), before using of local Gaussian correlation are discussed. The experimental vibration signals from two gearbox systems are used to show the efficiency of the presented method. Linear Support Vector Machine (SVM) is utilized to classify feature sets extracted with the presented method. The obtained results show that the features extracted in this method have excellent ability to classify faults without any additional feature selection; it is also shown that EMD can improve or degrade features according to the utilized feature reduction method.