Wind Turbine Gearbox Fault Detection Based on Multifractal Analysis

2013 ◽  
Vol 644 ◽  
pp. 312-316
Author(s):  
Chang Zheng Chen ◽  
Ping Ping Pan ◽  
Qiang Meng ◽  
Yan Ling Gu
Keyword(s):  
Wind Turbine ◽  
Structural Vibrations ◽  
Wind Turbine Gearbox ◽  
Vibration Signals ◽  
The Real ◽  
Signal Processing Method ◽  
Fault Features ◽  
Incipient Faults ◽  
Weak Fault ◽  
Multifractal Method

The presence of irregularity in periodical vibration signals usually indicates the occurrence of wind turbine gearbox faults. Unfortunately, detecting the incipient faults is a difficult job because they are rather weak and often interfered by heavy noise and higher level macro-structural vibrations. Therefore, a proper signal processing method is necessary. We used the wavelet-based multifractal method to extract the impulsive features buried in noisy vibration signals. We first calculated the wavelet transform modulo maxima lines from the real vibration signals, then, obtained the singularity spectrum from the lines. The analysis results of the real signals showed that the proposed method can effectively extract weak fault features.

The Effect of Operational Parameters on Vibration Signals of Wind Turbine Gearboxes

2019 ◽  
Author(s):  
Sofia Koukoura ◽  
Eric Bechhoefer ◽  
James Carroll ◽  
Alasdair McDonald
Keyword(s):  
Wind Turbine ◽  
Operating Conditions ◽  
Operating Costs ◽  
Normal Operation ◽  
Operational Parameters ◽  
Wind Turbine Gearbox ◽  
Vibration Signals ◽  
Gearbox Vibration ◽  
Maintenance Decisions ◽  
Yaw Angle

Abstract Vibration signals are widely used in wind turbine drivetrain condition monitoring with the aim of fault detection, optimization of maintenance actions and therefore reduction of operating costs. Signals are most commonly sampled by accelerometers at high frequency for a few seconds. The behavior of these signals varies significantly, even within the same turbine and depends on different parameters. The aim of this paper is to explore the effect of operational and environmental conditions on the vibration signals of wind turbine gearboxes. Parameters such as speed, power and yaw angle are taken into account and the change in vibration signals is examined. The study includes examples from real wind turbines of both normal operation and operation with known gearbox faults. The effects of varying operating conditions are removed using kalman filtering as a state observer. The findings of this paper will aid in understanding wind turbine gearbox vibration signals, making more informed decisions in the presence of faults and improving maintenance decisions.

scholarly journals The Enhancement of Weak Bearing Fault Signatures by Stochastic Resonance with a Novel Potential Function

Energies ◽  
2020 ◽  
Vol 13 (23) ◽  
pp. 6348
Author(s):  
Chao Zhang ◽  
Haoran Duan ◽  
Yu Xue ◽  
Biao Zhang ◽  
Bin Fan ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Stochastic Resonance ◽  
Operating Conditions ◽  
Detection Accuracy ◽  
Wind Turbine Gearbox ◽  
Resonance Model ◽  
Function Type ◽  
Vibration Signals ◽  
Fourier Decomposition ◽  
Bearing Fault

As the critical parts of wind turbines, rolling bearings are prone to faults due to the extreme operating conditions. To avoid the influence of the faults on wind turbine performance and asset damages, many methods have been developed to monitor the health of bearings by accurately analyzing their vibration signals. Stochastic resonance (SR)-based signal enhancement is one of effective methods to extract the characteristic frequencies of weak fault signals. This paper constructs a new SR model, which is established based on the joint properties of both Power Function Type Single-Well and Woods-Saxon (PWS), and used to make fault frequency easy to detect. However, the collected vibration signals usually contain strong noise interference, which leads to poor effect when using the SR analysis method alone. Therefore, this paper combines the Fourier Decomposition Method (FDM) and SR to improve the detection accuracy of bearing fault signals feature. Here, the FDM is an alternative method of empirical mode decomposition (EMD), which is widely used in nonlinear signal analysis to eliminate the interference of low-frequency coupled signals. In this paper, a new stochastic resonance model (PWS) is constructed and combined with FDM to enhance the vibration signals of the input and output shaft of the wind turbine gearbox bearing, make the bearing fault signals can be easily detected. The results show that the combination of the two methods can detect the frequency of a bearing failure, thereby reminding maintenance personnel to urgently develop a maintenance plan.

Wind Turbine Generator Fault Detection by Wavelet-Based Multifractal Analysis

2013 ◽  
Vol 644 ◽  
pp. 346-349
Author(s):  
Chang Zheng Chen ◽  
Yu Zhang ◽  
Quan Gu ◽  
Yan Ling Gu
Keyword(s):  
Wind Turbine ◽  
Multifractal Analysis ◽  
Vibration Signal ◽  
Rotational Frequency ◽  
Turbine Generator ◽  
Vibration Signals ◽  
Wind Turbine Generator ◽  
Fault Features ◽  
Multifractal Theory ◽  
Incipient Fault

It is difficult to obtain the obvious fault features of wind turbine, because the vibration signal of them are non-linear and non-stationary. To solve the problem, a multifractal analysis based on wavelet is presented in this research. The real signals of 1.5 MW wind turbine are studied by multifractal theory. The incipient fault features are extracted from the original signal. Using the Wavelet Transform Modulo Maxima Method, the multifractal was obtained. The results show that fault features of high rotational frequency of wind turbine are different from low rotational frequency, and the complexity of the vibration signals increases with the rotational frequency. These demonstrate the multifractal analysis is effective to extract the fault features of wind turbine generator.

scholarly journals Diagnostic Framework for Wind Turbine Gearboxes Using Machine Learning

2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Sofia Koukoura ◽  
James Carroll ◽  
Alasdair McDonald
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Domain Knowledge ◽  
Failure Modes ◽  
Offshore Wind ◽  
False Alarms ◽  
Wind Turbine Gearbox ◽  
Vibration Signals ◽  
Diagnostic Framework ◽  
Rule Based Approach

Operation and maintenance costs of wind turbines are highlydriven by gearbox failures, especially offshore were the logisticsof replacements are more demanding. It is therefore verycritical to foresee incipient gearbox faults before they becomecatastrophic failures. Wind turbine gearbox condition monitoringis usually performed using vibration signals comingfrom accelerometers installed on the gearbox surface. Thecurrent monitoring practice is a rule-based approach, wherealarms are activated based on thresholds. However, too muchmanual analysis may be required for some failure modes andthis can become quite challenging as the installed wind capacitygrows. Also, since false alarms have to be avoided,these thresholds are set quite high, resulting in late stage diagnosisof components. Given the fact there is a large amountof historic operating data with confirmed gearbox failure incidents,this paper proposes a framework that uses a machinelearning approach. Vibration signals are used from the gearboxsensors and processed in the frequency domain. Featuresare extracted from the processed signals based on the fault locationsand failure modes, using domain knowledge. Thesefeatures are used as inputs in a layer of pattern recognitionmodels that can determine a potential component fault locationand failure mode. The proposed framework is illustratedusing failure examples from operating offshore wind turbines.

scholarly journals Application of Generalized Composite Multiscale Lempel–Ziv Complexity in Identifying Wind Turbine Gearbox Faults

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1372
Author(s):  
Xiaoan Yan ◽  
Daoming She ◽  
Yadong Xu ◽  
Minping Jia
Keyword(s):  
Wind Turbine ◽  
Signal To Noise Ratio ◽  
Vibration Signal ◽  
Identification Accuracy ◽  
Health Conditions ◽  
Permutation Entropy ◽  
Strong Nonlinearity ◽  
Wind Turbine Gearbox ◽  
Softmax Classifier ◽  
Fault Features

Wind turbine gearboxes operate in harsh environments; therefore, the resulting gear vibration signal has characteristics of strong nonlinearity, is non-stationary, and has a low signal-to-noise ratio, which indicates that it is difficult to identify wind turbine gearbox faults effectively by the traditional methods. To solve this problem, this paper proposes a new fault diagnosis method for wind turbine gearboxes based on generalized composite multiscale Lempel–Ziv complexity (GCMLZC). Within the proposed method, an effective technique named multiscale morphological-hat convolution operator (MHCO) is firstly presented to remove the noise interference information of the original gear vibration signal. Then, the GCMLZC of the filtered signal was calculated to extract gear fault features. Finally, the extracted fault features were input into softmax classifier for automatically identifying different health conditions of wind turbine gearboxes. The effectiveness of the proposed method was validated by the experimental and engineering data analysis. The results of the analysis indicate that the proposed method can identify accurately different gear health conditions. Moreover, the identification accuracy of the proposed method is higher than that of traditional multiscale Lempel–Ziv complexity (MLZC) and several representative multiscale entropies (e.g., multiscale dispersion entropy (MDE), multiscale permutation entropy (MPE) and multiscale sample entropy (MSE)).

Fault Diagnosis of the Wind Turbine Main Bearing through Multifractal Theory

2013 ◽  
Vol 644 ◽  
pp. 337-340
Author(s):  
Quan Gu ◽  
Chang Zheng Chen ◽  
Xiang Jun Kong ◽  
Xian Ming Sun ◽  
Bo Zhou ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Large Scale ◽  
Spectral Characteristics ◽  
Multifractal Spectrum ◽  
Hölder Exponent ◽  
Main Bearing ◽  
Vibration Signals ◽  
Fault Features ◽  
Multifractal Theory ◽  
Incipient Fault

Because the vibration signals of faulty wind turbine are non-linear and non-stationary, to obtain the obvious fault features become difficult. In this study, the incipient fault of the main bearing used in large scale wind turbine is studied by using a multifractal method based on the Wavelet Modulus Maxima (WTMM) method. The real vibration signals from the main bearings are analyzed using the multifractal spectrum. The spectrum of the vibration signals is quantified by spectral characteristics including its range and the Hölder exponent corresponding to the maximum dimension. The results show that the range of Hölder exponent of the main bearing which worked normally is much narrower. While the ranges of the vibration signals of the main bearing with incipient fault are wider. We also found that the fault features are different at various wind turbine rotational frequencies. Those demonstrate that the incipient fault features of main bearing of large scale wind turbine can be extract effectively using the multifractal spectrum obtained from WTMM method.

Application of FastICA Algorithm in Wind Turbine Condition Monitoring

2012 ◽  
Vol 217-219 ◽  
pp. 2750-2753
Author(s):  
Guang Kun Shan ◽  
Hai Long Zhang ◽  
Xiao Dong Wang ◽  
Ying Ming Liu
Keyword(s):  
Wind Turbine ◽  
Condition Monitoring ◽  
Processing Method ◽  
Vibration Signals ◽  
Signal Processing Method ◽  
Ideal Position ◽  
Fastica Algorithm ◽  
The Common ◽  
Common Signal ◽  
The Ideal

In wind turbine condition monitoring, the sensors often can not be installed to the ideal position. Compare the common signal processing method comprehensively and give the advantage of the fastICA algorithm in the wind turbine condition monitoring. Give the basic principle and mathematical model of the fastICA algorithm, while monitor and analysis the wind turbine state data based on the fastICA algorithm. The results show that this algorithm can separate the vibration characteristics of the tested compenent of the wind turbine from the vibration signals quickly and accurately.

Sign in / Sign up

Export Citation Format

Share Document