Wind Turbine Drivetrain Research Articles

Life Extension of Wind Turbine Drivetrains by means of SCADA Data: Case Study of Generator Bearings in an Onshore Wind Farm

Accurate predictions for remaining useful life (RUL) of wind turbine drivetrains is crucial in reducing downtime, optimising maintenance strategies, extending operational life and improving costs. The purpose of this study is to present a method which utilises SCADA data for RUL estimation. It aims to answer whether, by only having the basic SCADA data, normally collected from all wind turbines, valuable RUL prediction results can be obtained. The work intends to develop a reliable, accurate, user-friendly and informative tool to enable observation of any growing trends in the proposed metrics, such as temperature difference, cumulative sum of temperature difference and the moving average of the cumulative sum. These metrics are defined based on the differences between the actual temperatures of the components, that might have undergone some damage and the model predicted temperatures of those components if they would have remained healthy, throughout years of operation. A machine learning model is used, along with selected SCADA input parameters, to predict the healthy state temperature of components. The proposed method is implemented on SCADA data collected from an actual wind farm over seven years. The results of this study show that while the SCADA data analysis can contribute to fault detection, the estimation of RUL purely based on SCADA appears to be uncertain. Such tools however, can be used as a monitoring method, during operation, to record abnormality trend of the components over the years and can be used as important inputs for the life extension evaluation of wind turbine drivetrains.

Experimental investigation of the relation between operating conditions and offshore wind turbine drivetrain dynamics

Abstract This study investigates the impact of operating and environmental conditions on the vibration induced on an offshore wind turbine drivetrain. Furthermore, it explores the role of the dynamic response of the global wind turbine structure to vibration on the drivetrain. A prolonged experimental campaign dedicated to condition monitoring the drivetrain provides experimental vibration signals. These vibration signals are acquired under varying operating conditions across multiple locations of an offshore wind turbine drivetrain of a Belgian Offshore Wind farm and serve as the basis for analysis. The signals’ statistics facilitate establishing connections between dynamic behaviour and operational variables, such as active power, rotor speed, blade pitch angle, and turbulence intensity, sampled at every second and provided by Fast-SCADA. The initial phase of the analysis involves a comprehensive examination of various statistical properties of the vibration signals to link the drivetrain’s dynamic response to operational conditions. This exploration includes both active and standstill periods of the wind turbine. A comprehensive summary that relates the global vibration characteristics with the operating conditions is formed by scrutinizing the overall vibration signals. In the study’s second phase, a detailed investigation is conducted on the vibration signals recorded during standstill conditions. Investigation of standstill data ensures that the structural modes’ spectral content does not interfere with the machines’ kinematic content. The analysis of standstill data proceeds from determining the most energetic resonance frequencies through the average power spectral density of the vibration signals. These identified frequency bands enable a thorough exploration, revealing the interlink between the offshore wind turbine drivetrain’s dynamic response and the operating/environmental conditions.

Modelling and dynamic characteristics of wind turbine drivetrain based on the variable coefficient sliding mode controller

Vibration is inevitable in operation of mechanical equipment, but severe vibrations will cause serious harm to wind turbines (WTs). This paper takes the drivetrain of 8 MW WT as the object, established a multi-body electromechanical coupling model of WT and verified the accuracy of the established model through the WT drivetrain in the laboratory. Subsequently, based on this model, time-frequency domain analysis was conducted on the vibration response of the WT drivetrain under different control strategies of the generator, and the influence of the generator control strategy on the vibration of the drivetrain was studied. The result shows that the generator control strategy has a significant impact on the vibration response amplitude of the drivetrain, but has a relatively small impact on the frequency component. Meanwhile, the sliding mode controller designed in this paper has good anti-interference ability, which can make the system quickly reach dynamic stability, and effectively suppress the vibration of the main components in the drivetrain. Under the new controller’s control, the transverse vibration displacement of some parts of the WT drivetrain can be reduced by up to nearly 60 %. This paper provides new ideas and new methods for the active vibration reduction control of WT drivetrain.

Graph constrained empirical wavelet transform and its application in bearing fault diagnosis

The signal decomposition based on frequency domain distribution is a fundamental methodology for mechanical component fault diagnosis. However, existing methods face challenges such as susceptibility to noise interference and limited adaptability. Therefore, this paper proposes the graph constrained empirical wavelet transform (GCEWT) method. This method introduces structured information, such as the interrelationships among different parts of the frequency domain distribution of vibration signals, into the boundary detection process of empirical wavelet transform. The high-dimensional connectivity among different parts of the time-frequency distribution is utilized to construct an adjacency matrix. By constructing an adjacent graph, the proposed method encodes the adjacency relationships among frequency bands to constrain the low-dimensional spatial relationships between them. In conjunction with spectral clustering algorithms, the GCEWT method determines the boundaries for empirical wavelet transformation in the frequency domain. This approach achieves structured and adaptive decomposition of vibration signals from components of critical equipment, facilitating the structured and adaptive extraction of fault features. The effectiveness of the proposed method is validated using vibration data from both wind turbine drivetrain systems and aircraft engines. The experimental results demonstrate that the proposed method yields more reasonable signal decomposition results compared to traditional algorithms. Additionally, the proposed method proves to be more effective in extracting weak fault features of bearings in the presence of noise.

Deviation of drive torque and rotational speed of a wind turbine drivetrain between test bench and wind turbine simulations

Wind turbines are a major contributor to a clean and independent energy mix in the future and therefore need to have as little downtime as possible. Downtime can be minimised by increasing the robustness of the wind turbine. The drivetrain is one of the major contributors of downtime in wind turbines. One way of increasing the robustness of wind turbine drivetrains is extensive drivetrain testing and loop-back optimization of the design and control. On the drivetrain test bench torque and other wind loads are applied. To ensure that the drivetrain reaction to the loads is the same as of the erected wind turbine the accuracy of the application of the loads needs to be sufficient. Only if the reaction loads of the drivetrain are similar to the rotor loads of the erected wind turbine a robustness increase can be achieved via the loop-back optimization after the tests. This paper therefore quantifies the deviations occurring in torque and rotational speed of the hub between the erected wind turbine and the test bench for a specific wind turbine. To do so the results of a test bench simulation are compared to results of an aerodynamic simulation of the wind turbine. For the investigated wind turbine drivetrain, the deviation in drive torque increases slightly with higher windspeeds. The torque values are maximum 2 % higher at the wind turbine compared to the rated torque. The rotational speed values are represented very well regarding the time series as well as the occurring frequencies. The speed values deviate maximum 0.5 % compared to the rated speed. The deviations are a result of differences in an underestimation of the drivetrain efficiency in the aerodynamic simulation and the inertia of the drivetrain on the test bench and wind turbine. Since the deviations are small the abstraction losses at the test bench regarding torque and speed are acceptable.

Experimental Characterization of Common-Mode Voltages and Currents in Gearbox Bearings of a Doubly-Fed Induction Generator Wind Turbine on a Test Bench

Wind turbine (WT) drivetrain failures can lead to expensive repairs and downtime, significantly impacting the Levelized Costs of Electricity (LCOE). Gearbox failures are a major contributor to maintenance costs, with High-Speed-Shaft (HSS) bearings having the highest failure rate. Frequently occurring premature HSS bearing damage indicates design inadequacies. Currently, bearing design standards (DIN/ISO 281) are primarily based on fatigue. Other damage mechanisms like adhesion or damages due to electrical currents passing through the bearings are not considered. WT gearbox bearings are exposed to electrical currents, mainly caused by common-mode (CM) voltages. Bearing currents lead to surface damages and also may promote the formation of white etching areas (WEA) or cracks (WEC) and thus need to be investigated further. The CM voltage is an inherent feature of the power converter, which generates CM currents in the electrical machine. The resulting high voltages at the HSS bearings can lead to electrical discharge currents in the rolling contact, which damage the raceways of the bearing. This paper presents an experimental method for characterization of the currents and voltages that pass from the generator to the HSS of the gearbox in a multi-megawatt WT drivetrain on a test bench. CM currents and voltages measured at the converter are correlated with the shaft voltages at the HSS bearing. The results indicate, that the CM currents directly pass the HSS and its bearings into the gearbox housing. The CM currents show peaks indicating discharge events with over 100 A. Furthermore, at the discharge events, high-frequency oscillations with over 20 MHz are observed in CM current and bearing voltage.

Impact of 3D segment profiling on friction losses of plain bearings in wind turbines main bearings

Wind power is a crucial technology in transitioning to a carbon-free energy future. To increase the economic competitiveness, the levelized cost of electricity of wind power needs to be further reduced. A critical factor contributing to maintenance expenses is the failure of main rolling bearings. Replacing these rolling bearings in the case of damages is a costly procedure as it necessitates dismantling the wind turbine drivetrain. Unlike conventional rolling bearings, segmented plain bearings allow for the up-tower replacement of individual faulty segments, significantly reducing downtime and maintenance costs. The FlexPad plain bearing concept specifically addresses the need for an easy-to-maintain main bearing for wind turbines. While the current FlexPad design guideline focuses on global geometrical parameters disregarding a detailed segment profile optimization, literature suggests that a 3D-profile on the segments can enhance bearing performance by reducing frictional losses. However, the investigations conducted in literature were limited to stationary thrust bearings. The FlexPad bearing's inherent flexibility and conical shape preclude direct application of the findings in literature. Therefore, a coupled elastohydrodynamic-multi-body simulation model was developed to account for the bearing's flexibility while investigating different 3D-profiles. This study quantifies the impact 3D-profiles on friction power, solid contact, and maximum hydrodynamic pressure, demonstrating the advantages. The best 3D-profiles achieve a decrease in friction power of 18.3% with an increase of the maximum hydrodynamic pressure of just 4.9%.

Digital twin‐driven online intelligent assessment of wind turbine gearbox

AbstractRemaining useful fatigue life monitoring of wind turbine drivetrains is important. However, the implementation of real‐time monitoring often faces efficiency and accuracy challenges. In order to resolve this, this paper proposes a vibration‐based damage monitoring digital twin (VBDM‐DT) that enables the online intelligent evaluation of wind turbine gearboxes, using gear tooth surface durability as an example fatigue mode. The VBDM‐DT integrates a random wind load model, a high‐fidelity dynamics model, and a fatigue damage model. The random wind load model takes the wind speed from the supervisory control and data acquisition (SCADA) as input to estimate the input torque of the drivetrain in real time. Simultaneously, VBDM‐DT uses the vibration signals from the condition monitoring system (CMS) to intelligently calibrate the dynamics model, allowing it to be continuously adjusted and optimized in response to actual vibrations. The fatigue damage model takes the real‐time dynamic loads estimated by the high‐fidelity dynamic model as input to achieve real‐time fatigue damage monitoring of key components in the wind turbine gearbox. Applying the VBDM‐DT model to a 2 MW wind turbine gearbox, the results indicate that the model provides satisfactory accuracy in estimating input loads and good adaptability in intelligent calibration of the dynamic model. Based on this model, the fatigue life estimation for gears and bearings is more credible and reliable.

Monitoring the Wear Trends in Wind Turbines by Tracking Fourier Vibration Spectra and Density Based Support Vector Machines

To make wind power more competitive, it is necessary to reduce turbine downtime and reduce costs associated with wind turbine operation and maintenance (O&M). Incorporating machine learning in the development of condition-based predictive maintenance methodologies for wind turbines can enhance their efficiency and reliability. This paper presents a monitoring method that utilizes Density Based Support Vector Machines (DBSVM) and the evolutionary Fourier spectra of vibrations. This method allows for the smart monitoring of the function evolution of the turbine. A complex optimal function (FO) for 5-degree order has been developed that will be the boundary function of the DBSVM to be timely determined from the Fourier spectrum through the magnitude–frequency and place of the failure occurring in the wind turbine drivetrains. The trend of the failure was constructed with the maximal values of the optimal frequency function for both yesthe cases of the upwind and downwind parts of the gearbox.

Offshore field experimentation for novel hybrid condition monitoring approaches

This study details the development of a fully automated pipeline for the condition monitoring of wind turbine drive trains. Vibration data is collected using hardware designed and manufactured in-house and used directly to monitor the condition of the drive trains. The complex nature of wind turbine vibration signals, due to the large number of components and highly variable operating conditions, makes drive train condition monitoring a challenging task. This paper details the full data measurement and analysis flow from sensor to insights and proposes a hybrid automated pipeline with signal processing and data-driven techniques to address the complexity of dealing with wind turbine vibration data. The vibration signals are directly employed to estimate the wind turbine’s instantaneous angular speed to compensate for any rotation speed fluctuations. Pre-processing is performed on the speed-independent signals to evaluate condition indicators in both the time and spectral domain for the vibration signals and their envelopes. Machine learning is then employed to distinguish the healthy state of the machine from a faulty one using the computed condition indicators. Besides the scalar indicators, also two-dimensional vibration decompositions such as the cyclic spectral correlation maps are used as inputs to the machine learning pipeline. This comprehensive and automated approach ensures both an early and reliable fault detection. Experimental results demonstrate that the fully automated hybrid pipeline can effectively be used for fleet-based health tracking of offshore wind turbine drivetrains.

Analysis of torsional vibration characteristics for wind turbine drivetrain under external excitation

This work studies the torsional vibration characteristics analysis of the wind turbine drivetrain with the variation of internal parameter and external excitation. The electromechanically coupled torsional vibration model for wind turbine drivetrain is first established by taking into account the torsional vibration angle of the PMSG. Then, frequency response analysis of main parametric resonance is illustrated by multiple scale method, and the influences of the system parameters involving power factor angle, number of pole pairs, torsional stiffness, and wind speed excitation on the torsional vibration characteristics of wind turbine drivetrain are investigated. Moreover, the critical condition for homoclinic chaos in terms of the system parameters is derived by means of Melnikov’s method. The function relationship and the boundary curve of chaos threshold are obtained. Meanwhile, the effects of excitation amplitude and damping factor on the system transition to chaos are studied in detail. The analytical predictions including phase portrait, bifurcation diagram and Lyapunov exponent are investigated. The research results can offer a theoretical basis for further the parameter design and control of wind turbine drivetrain.

Condition Monitoring of Wind Turbine Drivetrain Bearings

Abstract As an extremely valuable and reliable energy source, the renewable energy is developing around the world at an unprecedented pace. By the end of 2022, the global installed capacity of offshore wind turbines is expected to reach 46.4 GW, among which 33.9 GW in Europe. Efficiencies in Operations and Maintenance (O&M) offer potential to achieve significant cost savings as it accounts for around 20%–30% of overall offshore wind farm costs. A recent study of approximately 350 offshore wind turbines indicates that gearboxes might have to be replaced as early as 6.5 years. Therefore sensing and condition monitoring (CM) systems are needed in order to obtain reliable information on the state and condition of different critical parts. The development and use of such technologies will allow companies to schedule actions at the right time. The reduced costs of O&M enable the wind energy at a competitive price thus strengthening productivity of the wind energy sector. At the academic level, a plethora of methodologies have been proposed during the last decades focusing toward early and accurate fault detection. Among others, Envelope Analysis is one of the most important methodologies, where the envelope of the vibration signal is estimated, usually after filtering around a selected frequency band excited by impacts due to the faults. Different tools, such as Kurtogram, have been proposed in order to accurately select the optimum filter parameters (center frequency and bandwidth). Cyclostationary analysis and corresponding methodologies, i.e., the cyclic spectral correlation and the cyclic spectral coherence, have been proved as powerful tools for CM. On the other hand the application, test, and evaluation of such tools in general industrial cases is still rather limited. Therefore the main aim of this paper is the application and evaluation of advanced diagnostic techniques and diagnostic indicators, including the Enhanced Envelope Spectrum and the Spectral Flatness on real-world vibration data collected from vibration sensors on gearboxes in multiple wind turbines over an extended period of time of nearly four years. The diagnostic indicators are compared with classical statistic time and frequency indicators, i.e., Kurtosis, Crest Factor, etc. and their effectiveness is evaluated based on the successful detection of two failure events.

A class-imbalance-aware domain adaptation framework for fault diagnosis of wind turbine drivetrains under different environmental conditions

This paper proposes a new fault diagnosis model for wind turbine drivetrains addressing time-varying environmental conditions and the limited availability of fault-related data. Wind turbines continuously work under variable conditions, making it difficult to generalize a baseline-trained machine learning model to these conditions with different domain distributions. On the other hand, limited labeled data are usually available for failure events in real wind turbines, leading to class-imbalanced training data for the machine learning model. Particularly, offshore wind turbines face increasing challenges from harsh environmental conditions and dynamic wave loading affecting data collection. This study proposes an improved domain adaptation model called ”class-imbalance-aware deep adversarial adaptive network (CIDAA)” for wind turbine drivetrain fault diagnosis. This model utilizes a class-imbalance-aware layer to learn different domain-invariant features while improving the discriminative structure of the class-imbalanced feature space. Therefore, the model can efficiently generalize from a labeled source domain to an unlabeled target domain, even in the case of class imbalance. The proposed model is verified by a bearing damage dataset obtained from a high-fidelity 5-MW reference drivetrain model mounted on a spar-type floating wind turbine under three environmental conditions. The results demonstrate that the CIDAA model can diminish the effect of time-varying environmental conditions and class-imbalance data, leading to higher fault classification accuracy than standard models.

Sensorless control for active damping of torsional vibrations in wind turbine drivetrains with doubly-fed induction generator

Until now, the most common drivetrain concept for multi megawatt wind turbines is still the classic design with multi-stage gearbox and fast running doubly-fed induction generator (DFIG). Some control strategies for damping of drivetrain torque oscilla tions already exist, but they based on mechanical sensors, e.g. speed and rotary encoders which can fail within the harsh envi ronment of a wind turbine. To reach the highest possible system reliability it is obvious trying to minimize the number of installed sensors. This contribution shows an innovative sensorless control method with great performance for DFIG coupled to highly oscillatory mechanical drive systems, such as in wind turbine drivetrains. The aim of the approach is, to reduce wear and increase service life by means of active damping torsional vibrations in the me chanical drivetrain during normal operation using a high reliable sensorless control system for the converter-fed generator. The outstanding feature of the control method is, that it requires no sensors for rotational angle, speed or shaft torque and considers the inherent highly oscillatory characteristic of geared drivetrains mostly equipped with DFIG. Therefore measuring of electrical quantities, that is the stator phase voltages and currents and rotor phase currents of a DFIG is sufficient, when using a combination of different observer struc tures for the electrical and mechanical subsystem of the drivetrain. The outcome is a sensorless field oriented vector and a state controller for effective active damping. The presented algo rithms are tested on a laboratory test rig, some of the results and measurements are presented here.

Impact of Gearbox Oil Contamination on the Performance of the Wind Turbine Drivetrain

Wind turbine gearbox is a key component in any wind energy conversion system and online monitoring of the gearbox is essential to maintain system reliability. This paper investigates the impact of gearbox lubrication oil contamination on the performance of wind turbine drivetrain. In this context, vibration signal of the gearbox is measured and analyzed under various contamination levels of the gearbox oil. A thermal camera is used to identify the hot spot location within the gearbox during the investigated case studies. Results show that quality of gearbox oil has a significant impact on the overall performance of the wind energy conversion system.

Digital Model of a Wind Turbine Oriented to Broken Tooth Analysis

Digital Twins are a valuable tool for managing the health of industrial components, thanks to their ability to detect and diagnose failures. This paper presents a novel Digital Model as the foundational step towards developing a Digital Twin. It enables the detection of broken tooth failure in wind turbine drive-trains by using wind data and vibration analysis. The model is projected into the future as a monitoring tool by allowing visual indicators of failure patterns to be identified and subsequently compared with real signals of this critical component.

Effect of sliding friction on torsional vibration of wind turbine drivetrain system under constant wind load

Effect of sliding friction on torsional vibration of wind turbine drivetrain system under constant wind load

Evaluating the effect of control gains on wind turbine drive-train deterioration: An experimental study

In this paper we present experimental results concerning the impact of the chosen torque control gain on the deterioration of the drive-train in wind turbines. Here the deterioration is considered to be produced by the mechanical stress, on the drive-train, and it is measured as the dissipated power at this level. The wind turbine is assumed to be controlled, into the variable-speed region, by using the optimal torque control method, commonly used for maximum power tracking. In this work, we present and discuss the obtained results of produced energy and dissipated one (at the drive-train level), for different choices of the torque control gain under the presence of high turbulence intensity of the wind speed. The tests have been performed in simulation by using real wind-speed data and by a combined simulated drive-train and a real mini wind turbine available at GIPSA-lab.

Using acoustic emission for condition monitoring of the main shaft bearings in 4-point suspension wind turbine drivetrains

ABSTRACT The continuous growth of wind power technology makes condition monitoring of wind turbine components crucially important for their operational efficiency. The main shaft bearings in wind turbines have been identified as one of the most critical components in the system, especially with the ongoing increase in rotor size and weight. This increase made the 4-point suspension drivetrain more preferable. In this study, we present a novel approach for condition monitoring of the main shaft bearings in a 2 Megawatt wind turbine with 4-point suspension drivetrain using primarily acoustic emission (AE). The focus was on the analysis of time and frequency domains of the AE signal, where the dominant frequency of each AE hit was identified and plotted back in the time domain to create the so-called dominant frequency map in specific time intervals for each bearing. A comparison between the two dominant frequency maps of the two bearings gives valuable insights into the condition of the two bearings. The distinctive nature of the dominant frequency bands in the dominant frequency maps presented promising potential for this method. The presented method is straightforward and can be automated and then integrated into a planned predictive maintenance programme for this wind turbine.

Torsional vibration characteristics analysis and adaptive fixed‐time control of wind turbine drivetrain

AbstractThe drivetrain has an important impact on the stability and reliability of wind turbines operating in complex conditions, which belongs to the electromechanical coupling system. This work studies the two domains of research on drivetrain vibration analysis and control method in detail. The electromechanically coupled torsional vibration model is first established by considering the air gap magnetic field energy of the PMSG. Preliminary analysis in terms of Hamiltonian energy indicates that there is sufficient energy to sustain the exciting oscillation behaviors. Moreover, to reduce the vibration amplitude caused by wind speed or torsional stiffness, a novel adaptive fixed‐time control method is proposed to solve the issue of wind turbine drivetrain chaotic oscillation with uncertainties and disturbances. Furthermore, the proposed method not only can prevent the jumping and bifurcation of torsional vibration from happening, but also there are the advantages of the control scheme with high accuracy, fast convergence rate and strong robustness. For the fair comparison, three different control methods have been used to demonstrate the superiority of the control scheme by the simulation results. The research results can provide a theoretical basis for the parameter design and control of wind turbine drivetrain.