The Experts below are selected from a list of 77763 Experts worldwide ranked by ideXlab platform
Bo Zhou - One of the best experts on this subject based on the ideXlab platform.
-
Fault Diagnosis of the Wind Turbine Main Bearing through Multifractal Theory
Advanced Materials Research, 2013Co-Authors: Chang Zheng Chen, Xiang Jun Kong, Xian Ming Sun, Bo ZhouAbstract: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 Holder exponent corresponding to the maximum dimension. The results show that the range of Holder 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.
-
Wavelet-based multifractal analysis of large scale wind turbine Main Bearing
Journal of Renewable and Sustainable Energy, 2013Co-Authors: Chang Zheng Chen, Xian Ming Sun, Bo ZhouAbstract:The fault vibration signals of wind turbine are non-linear and non-stationary, thus it is difficult to obtain the obvious fault features. In this study, a multifractal method based on the wavelet transform modulus maxima (WTMM) method is used to investigate the Main Bearing incipient fault of large scale wind turbine. The real vibration signals are analyzed using the multifractal spectrum. The spectrum of the vibration signals is quantified by spectral characteristics including its range and the Holder exponent corresponding to the maximum dimension. We find that the range of Holder exponent of normal Bearing is narrower than that of the Bearing with incipient fault. And the results also indicate that the fault features are different at various wind turbine rotational frequencies. The results demonstrate that the multifractal spectrum obtained from WTMM method is effective to extract the incipient fault features of Main Bearing of large scale wind turbine.
-
State Recognition for Main Bearing of Wind Turbines Based on Multi-Fractal Theory
Applied Mechanics and Materials, 2012Co-Authors: Zi Qiang Sun, Chang Zheng Chen, Bo ZhouAbstract:The Main Bearing dynamic characteristics of megawatt wind turbines are complex system with strong non-linearity, strong coupling and time-varying. The vibration signals are mixed with background noise, so it is difficult to extract the characteristics of week signals. Based on the dynamic characteristics, multi-fractal theory is put forward to detect and recognize the working status of the Main Bearing of megawatt wind turbines. Different working states are recognized intuitively by different dimensions of multi-fractural which are sensitive to variety of working state. The paper justifies the method can detect and recognize different working states of Main Bearings quickly and accurately through the experiments on the Main Bearings of 3 WM wind turbines.
Jürgen Herp - One of the best experts on this subject based on the ideXlab platform.
-
Estimating the ReMaining Power Generation of Wind Turbines—An Exploratory Study for Main Bearing Failures
Energies, 2020Co-Authors: Benedikt Wiese, Niels Lovmand Pedersen, Esmaeil S. Nadimi, Jürgen HerpAbstract:Condition monitoring for wind turbines is tailored to predict failure and aid in making better operation and Maintenance (O&M) decisions. Typically the condition monitoring approaches are concerned with predicting the reMaining useful lifetime (RUL) of assets or a component. As the time-based measures can be rendered absolute when changing the operational set-point of a wind turbine, we propose an alternative in a power-based condition monitoring framework for wind turbines, i.e., the reMaining power generation (RPG) before a Main Bearing failure. The proposed model utilizes historic wind turbine data, from both run-to-failure and non run-to-failure turbines. Comprised of a recurrent neural network with gated recurrent units, the model is constructed around a censored and uncensored data-based cost function. We infer a Weibull distribution over the RPG, which gives an operator a measure of how certain any given prediction is. As part of the model evaluation, we present the hyper-parameter selection, as well as modeling error in detail, including an analysis of the driving features. During the application on wind turbine Main Bearing failures, we achieve prediction in the magnitude of 1 to 2 GWh before the failure. When converting to RUL this corresponds to predicting the failure, on average, 81 days beforehand, which is comparable to the state-of-the-art’s 94 days predictive horizon in a similar feature space.
Benedikt Wiese - One of the best experts on this subject based on the ideXlab platform.
-
Estimating the ReMaining Power Generation of Wind Turbines—An Exploratory Study for Main Bearing Failures
Energies, 2020Co-Authors: Benedikt Wiese, Niels Lovmand Pedersen, Esmaeil S. Nadimi, Jürgen HerpAbstract:Condition monitoring for wind turbines is tailored to predict failure and aid in making better operation and Maintenance (O&M) decisions. Typically the condition monitoring approaches are concerned with predicting the reMaining useful lifetime (RUL) of assets or a component. As the time-based measures can be rendered absolute when changing the operational set-point of a wind turbine, we propose an alternative in a power-based condition monitoring framework for wind turbines, i.e., the reMaining power generation (RPG) before a Main Bearing failure. The proposed model utilizes historic wind turbine data, from both run-to-failure and non run-to-failure turbines. Comprised of a recurrent neural network with gated recurrent units, the model is constructed around a censored and uncensored data-based cost function. We infer a Weibull distribution over the RPG, which gives an operator a measure of how certain any given prediction is. As part of the model evaluation, we present the hyper-parameter selection, as well as modeling error in detail, including an analysis of the driving features. During the application on wind turbine Main Bearing failures, we achieve prediction in the magnitude of 1 to 2 GWh before the failure. When converting to RUL this corresponds to predicting the failure, on average, 81 days beforehand, which is comparable to the state-of-the-art’s 94 days predictive horizon in a similar feature space.
Chang Zheng Chen - One of the best experts on this subject based on the ideXlab platform.
-
Fault Diagnosis of the Wind Turbine Main Bearing through Multifractal Theory
Advanced Materials Research, 2013Co-Authors: Chang Zheng Chen, Xiang Jun Kong, Xian Ming Sun, Bo ZhouAbstract: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 Holder exponent corresponding to the maximum dimension. The results show that the range of Holder 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.
-
Wavelet-based multifractal analysis of large scale wind turbine Main Bearing
Journal of Renewable and Sustainable Energy, 2013Co-Authors: Chang Zheng Chen, Xian Ming Sun, Bo ZhouAbstract:The fault vibration signals of wind turbine are non-linear and non-stationary, thus it is difficult to obtain the obvious fault features. In this study, a multifractal method based on the wavelet transform modulus maxima (WTMM) method is used to investigate the Main Bearing incipient fault of large scale wind turbine. The real vibration signals are analyzed using the multifractal spectrum. The spectrum of the vibration signals is quantified by spectral characteristics including its range and the Holder exponent corresponding to the maximum dimension. We find that the range of Holder exponent of normal Bearing is narrower than that of the Bearing with incipient fault. And the results also indicate that the fault features are different at various wind turbine rotational frequencies. The results demonstrate that the multifractal spectrum obtained from WTMM method is effective to extract the incipient fault features of Main Bearing of large scale wind turbine.
-
State Recognition for Main Bearing of Wind Turbines Based on Multi-Fractal Theory
Applied Mechanics and Materials, 2012Co-Authors: Zi Qiang Sun, Chang Zheng Chen, Bo ZhouAbstract:The Main Bearing dynamic characteristics of megawatt wind turbines are complex system with strong non-linearity, strong coupling and time-varying. The vibration signals are mixed with background noise, so it is difficult to extract the characteristics of week signals. Based on the dynamic characteristics, multi-fractal theory is put forward to detect and recognize the working status of the Main Bearing of megawatt wind turbines. Different working states are recognized intuitively by different dimensions of multi-fractural which are sensitive to variety of working state. The paper justifies the method can detect and recognize different working states of Main Bearings quickly and accurately through the experiments on the Main Bearings of 3 WM wind turbines.
Esmaeil S. Nadimi - One of the best experts on this subject based on the ideXlab platform.
-
Estimating the ReMaining Power Generation of Wind Turbines—An Exploratory Study for Main Bearing Failures
Energies, 2020Co-Authors: Benedikt Wiese, Niels Lovmand Pedersen, Esmaeil S. Nadimi, Jürgen HerpAbstract:Condition monitoring for wind turbines is tailored to predict failure and aid in making better operation and Maintenance (O&M) decisions. Typically the condition monitoring approaches are concerned with predicting the reMaining useful lifetime (RUL) of assets or a component. As the time-based measures can be rendered absolute when changing the operational set-point of a wind turbine, we propose an alternative in a power-based condition monitoring framework for wind turbines, i.e., the reMaining power generation (RPG) before a Main Bearing failure. The proposed model utilizes historic wind turbine data, from both run-to-failure and non run-to-failure turbines. Comprised of a recurrent neural network with gated recurrent units, the model is constructed around a censored and uncensored data-based cost function. We infer a Weibull distribution over the RPG, which gives an operator a measure of how certain any given prediction is. As part of the model evaluation, we present the hyper-parameter selection, as well as modeling error in detail, including an analysis of the driving features. During the application on wind turbine Main Bearing failures, we achieve prediction in the magnitude of 1 to 2 GWh before the failure. When converting to RUL this corresponds to predicting the failure, on average, 81 days beforehand, which is comparable to the state-of-the-art’s 94 days predictive horizon in a similar feature space.
