scholarly journals Unsupervised transfer learning for condition monitoring of a fleet of wind turbines

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Dandan Peng ◽  
Chenyu Liu ◽  
Wim Desmet ◽  
Konstantinos Gryllias
Keyword(s):  
Deep Learning ◽  
Health Status ◽  
Wind Turbine ◽  
Transfer Learning ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Working Environment ◽  
Generative Adversarial Networks ◽  
Physical Parameters ◽  
Scada Systems

The condition monitoring and health status prediction of a fleet of wind turbines are essential for the safety of wind turbines. At present, the Supervisory Control And Data Acquisition (SCADA) system has been widely used in wind turbines, which can monitor and collect various physical information and sensor information of wind turbines in real-time. Due to the fact that the amount of data obtained by SCADA systems is extremely large, developing an intelligent decision-making system based on deep learning is a very valuable research. Therefore, this paper is committed to exploring a health status prediction algorithm of wind turbines based on deep learning and SCADA systems. However, yet in actual industrial applications, it is very time-consuming and expensive to obtain a large amount of labeled data. In addition, as failures rarely occur, there is a serious sample imbalance problem in the datasets. More importantly, due to the difference in working environment and physical parameters, there are significant differences in the feature distribution of different wind turbines data, which lead to a significant drop in the performance of the deep learning model on unknown wind turbines. Therefore, we propose an unsupervised transfer learning algorithm based on Generative Adversarial Networks for wind turbine health status prediction (WT-GAN). WT-GAN can not only remove the domain shift between wind turbines, but also it is an unsupervised learning method. This practically means that only the unlabeled data for the target domain is required, which solves the problem of labeling data. In order to evaluate the effectiveness of WT-GAN on the condition monitoring of a fleet of wind turbines, we apply this method to one dataset about blade icing detection of wind turbines. The experimental results prove that the proposed method can predict the health of the wind turbine well. In addition, it can significantly reduce the domain shift among different wind turbines, thereby achieving excellent performance on unknown wind turbines.

An Improved 2DCNN With Focal Loss Function for Blade Icing Detection of Wind Turbines Under Imbalanced SCADA Data

2021 ◽  
Author(s):  
Dandan Peng ◽  
Chenyu Liu ◽  
Wim Desmet ◽  
Konstantinos Gryllias
Keyword(s):  
Power Generation ◽  
Deep Learning ◽  
Wind Turbine ◽  
Loss Function ◽  
Wind Turbines ◽  
Cold Climate ◽  
Detection Methods ◽  
Physical Parameters ◽  
Learning Abilities ◽  
Imbalance Problem

Abstract The deployment of wind power plants in cold climate becomes ever more attractive due to the increased air density resulting from low temperatures, the high wind speeds, and the low population density. However, the cold climate conditions bring some additional challenges as itt can easily cause wind turbine blades to freeze. The frizzing ice on blades not only increases the energy required for the rotation of blades, resulting in a reduction in the power generation, but also increases the amplitude of the blades’ vibrations, which may cause the blade to break, affecting the power generation performance of the wind turbine and poses a threat to its safe operation. Current published blade icing detection methods focus on studying the blade icing mechanism, building the model and then judging if it is iced or not. These models vary with different wind turbines and working conditions, so expertise knowledge is required. However, deep learning techniques may solve the abovementioned problem based on their excellent feature learning abilities but until now, there are only few studies on wind turbine blade icing detection based on the deep learning technology. Therefore, this paper proposes a novel blade icing detection model, named two-dimensional convolutional neural network with focal loss function (FL-2DCNN). The network takes the raw data collected by the Supervisory Control and Data Acquisition (SCADA) system as input, automatically learns the correlation between the different physical parameters in the dataset, and captures the abnormal information, in order to accurately output the detection results. However, the amount of normal data collected by SCADA systems is usually much larger than the one of blade icing fault data, leading to a serious data imbalance problem. This problem makes it difficult for the network to obtain enough features related to the blade icing fault. Therefore the focal loss function is introduced to the FL-2DCNN to solve the aforementioned data imbalanced problem. The focal loss function can effectively balance the importance of normal samples and icing fault samples, so that the network can obtain more icing-related feature information from the icing fault samples, and thus the detection ability of the network can be improved. The experimental results of the proposed FL-2DCNN based on real SCADA data of wind turbines show that the proposed FL-2DCNN can effectively solve the sample imbalance problem and has significant potential in the blade icing detection task compared with other deep learning methods.

scholarly journals A Survey of Deep Learning Approaches on Wind Turbine Condition Monitoring

2021 ◽  
Vol 2132 (1) ◽  
pp. 012015
Author(s):  
Sijia Li
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Control Charts ◽  
Original Data ◽  
Learning Approaches ◽  
Monitoring Methods ◽  
Effectiveness And Efficiency ◽  
Operational Data

Abstract Current physics-based wind turbine monitoring methods often need extra sensors installed on wind turbines, thus increasing the operation and maintenance (O&M) cost. Besides, physical methods are only effective under some constraints. The real effectiveness needs to be further checked in real conditions. Recent advances in data acquisition systems allow collection of large volumes of operational data of wind turbines. Learning knowledge from the data allows us to do monitoring in another direction. In this paper, a survey of deep learning algorithms applied to wind turbine condition monitoring is given. Compared with original data, more meaning features were extracted through feature extraction of deep learning. Monitoring these new signals, outliers were detected by applying suitable control charts. Several industrial cases confirmed the effectiveness and efficiency of these frameworks.

scholarly journals Hardware-in-the-loop simulator of wind turbine emulator using labview

2019 ◽  
Vol 10 (2) ◽  
pp. 971
Author(s):  
Himani Himani ◽  
Navneet Sharma
Keyword(s):  
Wind Turbine ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Control Strategies ◽  
Hardware In The Loop ◽  
Data Acquisition Card ◽  
Terminal Voltage ◽  
The Uk ◽  
The University ◽  
University Of Manchester

<p><span>This paper describes the design and implementation of Hardware in the Loop (HIL) system D.C. motor based wind turbine emulator for the condition monitoring of wind turbines. Operating the HIL system, it is feasible to replicate the actual operative conditions of wind turbines in a laboratory environment. This method simply and cost-effectively allows evaluating the software and hardware controlling the operation of the generator. This system has been implemented in the LabVIEW based programs by using Advantech- USB-4704-AE Data acquisition card. This paper describes all the components of the systems and their operations along with the control strategies of WTE such as Pitch control and MPPT. Experimental results of the developed simulator using the test rig are benchmarked with the previously verified WT test rigs developed at the Durham University and the University of Manchester in the UK by using the generated current spectra of the generator. Electric subassemblies are most vulnerable to damage in practice, generator-winding faults have been introduced and investigated using the terminal voltage. This wind turbine simulator can be analyzed or reconfigured for the condition monitoring without the requirement of actual WT’s.</span></p>

Health Assessment Methods for Wind Turbines Based on Power Prediction and Mahalanobis Distance

2018 ◽  
Vol 33 (02) ◽  
pp. 1951001 ◽  
Author(s):  
Jun Zhan ◽  
Ronglin Wang ◽  
Lingzhi Yi ◽  
Yaguo Wang ◽  
Zhengjuan Xie
Keyword(s):  
Health Status ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Mahalanobis Distance ◽  
Wind Farm ◽  
Health Status Assessment ◽  
Power Prediction ◽  
Residual Set ◽  
Scada System ◽  
Status Assessment

The output power of wind turbine has great relation with its health state, and the health status assessment for wind turbines influences operational maintenance and economic benefit of wind farm. Aiming at the current problem that the health status for the whole machine in wind farm is hard to get accurately, in this paper, we propose a health status assessment method in order to assess and predict the health status of the whole wind turbine, which is based on the power prediction and Mahalanobis distance (MD). Firstly, on the basis of Bates theory, the scientific analysis for historical data from SCADA system in wind farm explains the relation between wind power and running states of wind turbines. Secondly, the active power prediction model is utilized to obtain the power forecasting value under the health status of wind turbines. And the difference between the forecasting value and actual value constructs the standard residual set which is seen as the benchmark of health status assessment for wind turbines. In the process of assessment, the test set residual is gained by network model. The MD is calculated by the test residual set and normal residual set and then normalized as the health status assessment value of wind turbines. This method innovatively constructs evaluation index which can reflect the electricity generating performance of wind turbines rapidly and precisely. So it effectively avoids the defect that the existing methods are generally and easily influenced by subjective consciousness. Finally, SCADA system data in one wind farm of Fujian province has been used to verify this method. The results indicate that this new method can make effective assessment for the health status variation trend of wind turbines and provide new means for fault warning of wind turbines.

Comparison of Blind Diagnostic Indicators for Condition Monitoring of Wind Turbine Gearbox Bearings

2021 ◽  
Author(s):  
Junyu Qi ◽  
Alexandre Mauricio ◽  
Konstantinos Gryllias
Keyword(s):  
Wind Turbine ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Fossil Fuels ◽  
Conditional Entropy ◽  
Approximate Entropy ◽  
Permutation Entropy ◽  
Wind Turbine Gearbox ◽  
Data Set ◽  
Wind Turbine Gearbox Bearings

Abstract Under the pressure of climate change, renewable energy gradually replaces fossil fuels and plays nowadays a significant role in energy production. The O&M costs of wind turbines may easily reach up to 25% of the total leverised cost per kWh produced over the lifetime of the turbine for a new unit. Manufacturers and operators try to reduce O&M by developing new turbine designs and by adopting condition monitoring approaches. One of the most critical assembly of wind turbines is the gearbox. Gearboxes are designed to last till the end of asset's lifetime, according to the IEC 61400-4 standards but a recent study indicated that gearboxes might have to be replaced as early as 6.5 years. A plethora of sensor types and signal processing methodologies have been proposed in order to accurately detect and diagnose the presence of a fault but often the gearbox is equipped with a limited number of sensors and a simple global diagnostic indicator is demanded, being capable to detect globally various faults of different components. The scope of this paper is the application and comparison of a number of blind global diagnostic indicators which are based on Entropy, on Negentropy, on Sparsity and on Statistics. The performance of the indicators is evaluated on a wind turbine data set with two different bearing faults. Among the different diagnostic indicators Permutation entropy, Approximate entropy, Samples entropy, Fuzzy entropy, Conditional entropy and Wiener entropy achieve the best results detecting blindly the two failure events.

scholarly journals Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements

Energies ◽  
2020 ◽  
Vol 13 (6) ◽  
pp. 1474 ◽  
Author(s):  
Francesco Castellani ◽  
Luigi Garibaldi ◽  
Alessandro Paolo Daga ◽  
Davide Astolfi ◽  
Francesco Natili
Keyword(s):  
Wind Turbine ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Statistical Tests ◽  
Novelty Detection ◽  
General Idea ◽  
Data Set ◽  
Vibration Measurements ◽  
Bearing Fault ◽  
Operation Conditions

Condition monitoring of gear-based mechanical systems in non-stationary operation conditions is in general very challenging. This issue is particularly important for wind energy technology because most of the modern wind turbines are geared and gearbox damages account for at least the 20% of their unavailability time. In this work, a new method for the diagnosis of drive-train bearings damages is proposed: the general idea is that vibrations are measured at the tower instead of at the gearbox. This implies that measurements can be performed without impacting the wind turbine operation. The test case considered in this work is a wind farm owned by the Renvico company, featuring six wind turbines with 2 MW of rated power each. A measurement campaign has been conducted in winter 2019 and vibration measurements have been acquired at five wind turbines in the farm. The rationale for this choice is that, when the measurements have been acquired, three wind turbines were healthy, one wind turbine had recently recovered from a planetary bearing fault, and one wind turbine was undergoing a high speed shaft bearing fault. The healthy wind turbines are selected as references and the damaged and recovered are selected as targets: vibration measurements are processed through a multivariate Novelty Detection algorithm in the feature space, with the objective of distinguishing the target wind turbines with respect to the reference ones. The application of this algorithm is justified by univariate statistical tests on the selected time-domain features and by a visual inspection of the data set via Principal Component Analysis. Finally, a novelty index based on the Mahalanobis distance is used to detect the anomalous conditions at the damaged wind turbine. The main result of the study is that the statistical novelty of the damaged wind turbine data set arises clearly, and this supports that the proposed measurement and processing methods are promising for wind turbine condition monitoring.

scholarly journals Condition Monitoring of Wind Turbine Gearbox Bearing Based on Deep Learning Model

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 57078-57087 ◽  
Author(s):  
Jian Fu ◽  
Jingchun Chu ◽  
Peng Guo ◽  
Zhenyu Chen
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Learning Model ◽  
Wind Turbine Gearbox ◽  
Deep Learning Model

scholarly journals Numerical Investigations of the Effects of the Rotating Shaft and Optimization of Urban Vertical Axis Wind Turbines

Energies ◽  
2018 ◽  
Vol 11 (7) ◽  
pp. 1870 ◽  
Author(s):  
Lidong Zhang ◽  
Kaiqi Zhu ◽  
Junwei Zhong ◽  
Ling Zhang ◽  
Tieliu Jiang ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Suction Side ◽  
Vertical Axis ◽  
Power Coefficient ◽  
Small Scale ◽  
Physical Parameters ◽  
Rotating Shaft ◽  
Vertical Axis Wind Turbines ◽  
Negative Effect

The central shaft is an important and indispensable part of a small scale urban vertical axis wind turbines (VAWTs). Normally, it is often operated at the same angular velocity as the wind turbine. The shedding vortices released by the rotating shaft have a negative effect on the blades passing the wake of the wind shaft. The objective of this study is to explore the influence of the wake of rotating shaft on the performance of the VAWT under different operational and physical parameters. The results show that when the ratio of the shaft diameter to the wind turbine diameter (α) is 9%, the power loss of the wind turbine in one revolution increases from 0% to 25% relative to that of no-shaft wind turbine (this is a numerical experiment for which the shaft of the VAWT is removed in order to study the interactions between the shaft and blade). When the downstream blades pass through the wake of the shaft, the pressure gradient of the suction side and pressure side is changed, and an adverse effect is also exerted on the lift generation in the blades. In addition, α = 5% is a critical value for the rotating shaft wind turbine (the lift-drag ratio trend of the shaft changes differently). In order to figure out the impacts of four factors; namely, tip speed ratios (TSRs), α, turbulence intensity (TI), and the relative surface roughness value (ks/ds) on the performance of a VAWT system, the Taguchi method is employed in this study. The influence strength order of these factors is featured by TSRs > ks/ds > α > TI. Furthermore, within the range we have analyzed in this study, the optimal power coefficient (Cp) occurred under the condition of TSR = 4, α = 5%, ks/ds = 1 × 10−2, and TI = 8%.

Sign in / Sign up

Export Citation Format

Share Document