Showing papers on "Turbine published in 2018"
TL;DR: An efficient machine learning method, random forests in combination with extreme gradient boosting (XGBoost), is used to establish the data-driven wind turbine fault detection framework that is robust to various wind turbine models including offshore ones in different working conditions.
Abstract: Wind energy has seen great development during the past decade. However, wind turbine availability and reliability, especially for offshore sites, still need to be improved, which strongly affect the cost of wind energy. Wind turbine operational cost is closely depending on component failure and repair rate, while fault detection and isolation will be very helpful to improve the availability and reliability factors. In this paper, an efficient machine learning method, random forests (RFs) in combination with extreme gradient boosting (XGBoost), is used to establish the data-driven wind turbine fault detection framework. In the proposed design, RF is used to rank the features by importance, which are either direct sensor signals or constructed variables from prior knowledge. Then, based on the top-ranking features, XGBoost trains the ensemble classifier for each specific fault. In order to verify the effectiveness of the proposed approach, numerical simulations using the state-of-the-art wind turbine simulator FAST are conducted for three different types of wind turbines in both the below and above rated conditions. It is shown that the proposed approach is robust to various wind turbine models including offshore ones in different working conditions. Besides, the proposed ensemble classifier is able to protect against overfitting, and it achieves better wind turbine fault detection results than the support vector machine method when dealing with multidimensional data.
341 citations
TL;DR: A review on different methods and techniques for gearbox condition monitoring in wind turbines aiming to increase lifetime expectancy of components while reducing operation and maintenance cost is gathered.
226 citations
TL;DR: Comparison of the statistical indices for the predicted and actual data indicate that the SVR-RBF model outperforms the MLFFNN and ANFIS-PSO models to predict the output power of the wind turbine.
209 citations
TL;DR: In this paper, a literature review of wind turbine control is presented dealing with the main wind energy control methods, which can be used as a starting point for new researches on WT control that can be decisive to energetic sustainability.
193 citations
TL;DR: A deep learning method based on a deep auto-encoder (DAE) network using operational supervisory control and data acquisition (SCADA) data of wind turbines can not only implement early warning of fault components but also deduce the physical location of a faulted component by DAE residuals.
181 citations
TL;DR: In this paper, the authors compare wind farm large eddy simulations with the EPFL wind tunnel measurement by Chamorro and Porte-Agel (Bound-Lay. 136, 515 (2010) and Energies 4, 1916 (2011)).
171 citations
154 citations
TL;DR: In this paper, the authors presented a new methodology based on cointegration analysis of Supervisory Control And Data Acquisition (SCADA) data for condition monitoring and fault diagnosis of wind turbines.
152 citations
TL;DR: A Danish innovation consortium was addressing this waste with a predominant focus on the blades from the wind power industry as discussed by the authors, and the outcomes from the consortium and the various tested tools are presented in this paper as well as the secondary applications that were proposed.
Abstract: The wind power industry is a fast growing, global consumer of glass fiber-reinforced plastics (GFRP) composites, which correlates with the industry’s rapid growth in recent years. Considering current and future developments, GFRP waste amounts from the wind industry are expected to increase. Therefore, a sustainable process is needed for dealing with wind turbines at the end of their service life in order to maximize the environmental benefits of wind power. Most components of a wind turbine such as the foundation, tower, gear box and generator are already recyclable and treated accordingly. Nevertheless, wind turbine blades represent a challenge due to the type of materials used and their complex composition. There are a number of ways to treat GFRP waste, depending on the intended application. The best available waste treatment technologies in Europe are outlined in this paper. However, there is a lack of practical experiences in applying secondary materials in new products. A Danish innovation consortium was addressing this waste with a predominant focus on the blades from the wind power industry. The outcomes from the consortium and the various tested tools are presented in this paper as well as the secondary applications that were proposed. The outcomes are structured using Ellen MacArthur’s circular economy diagram. The “adjusted” diagram illustrates the potentials for a continuous flow of composite materials through the value circle, where secondary applications were developed in respect to “reuse”, “resize and reshape”, “recycle”, “recover” and ‘conversion’. This included applications for architectural purposes, consumer goods, and industrial filler material. By presenting the outcomes of the consortium, new insights are provided into potential forms of reuse of composites and the practical challenges that need to be addressed.
150 citations
TL;DR: In this article, the authors conducted dynamic simulations of an entire 660MW supercritical coal-fired power plant via GSE software, and the models were validated in the steady state and transient processes.
147 citations
TL;DR: Compared to the wind turbine with semicircular blades, the Savonius turbine with optimal blades and a tip speed ratio (TSR) of 0.8 achieved significant improvement on the time-averaged power coefficient, suggesting that the Sav onius wind turbine has great potential to be applied in the real urban environment.
TL;DR: In this paper, the authors investigate the impact of these parameters on the simulation results to guide the execution of accurate CFD simulations of VAWTs at different tip speed ratios (λ) and solidities (σ).
TL;DR: A probabilistic framework for fatigue life prediction and reliability assessment of an engine high pressure turbine disc is proposed to incorporate the effects of load variations and mean stress, which provides a reference for engine structural design under a given target failure probability.
Abstract: In the present work, a probabilistic framework for fatigue life prediction and reliability assessment of an engine high pressure turbine disc is proposed to incorporate the effects of load variatio...
TL;DR: In this paper, a Darrieus H-type VAWT has been employed to investigate the effect of operational parameters such as tip speed ratio (λ), Reynolds number (Rec) and turbulence intensity (TI) on the aerodynamic performance of VAWTs.
TL;DR: In this paper, a multi-dimensional variational decomposition (MDVD) method was proposed for bearing-crack detection in wind turbine gearboxes, where variational mode decomposition was incorporated into convolutive blind-source separation (BSS) to address the challenge of substantial driving-speed variations.
TL;DR: In this article, the authors present a review of system design and analysis, and transient control and optimization of solid oxide fuel cell-gas turbine (SOFC-GT) hybrid systems for different system configurations.
TL;DR: In this article, the authors view a yawed turbine as a lifting surface with an elliptic distribution of transverse lift and use it as initial conditions in a wake model of the downstream evolution of the turbulent wake flow and compare predicted wake deflection with measurements from wind tunnel experiments.
Abstract: Yawing wind turbines has emerged as an appealing method for wake deflection. However, the associated flow properties, including the magnitude of the transverse velocity associated with yawed turbines, are not fully understood. In this paper, we view a yawed turbine as a lifting surface with an elliptic distribution of transverse lift. Prandtl’s lifting line theory provides predictions for the transverse velocity and magnitude of the shed counter-rotating vortex pair known to form downstream of the yawed turbine. The streamwise velocity deficit behind the turbine can then be obtained using classical momentum theory. This new model for the near-disk inviscid region of the flow is compared to numerical simulations and found to yield more accurate predictions of the initial transverse velocity and wake skewness angle than existing models. We use these predictions as initial conditions in a wake model of the downstream evolution of the turbulent wake flow and compare predicted wake deflection with measurements from wind tunnel experiments.
TL;DR: In this paper, a three dimensional pendulum tuned mass damper (3d-PTMD) was proposed to mitigate the tower and nacelle dynamic response in the fore-aft and side-side directions.
TL;DR: In this article, a CCHP system combined with solar and compressed air energy storage (CCHP-S-CAES) was proposed to balance the electricity load and improve the energy efficiency of a combined cooling, heating and power system.
TL;DR: A comprehensive review of the up-to-date efforts and advances in the research of prognostic techniques and remaining useful life estimation methods applied to the critical components of wind turbines and analyse its advantages, capabilities and limitations can be found in this article.
Abstract: Wind turbine installation is growing consistently and fast. Wind turbines are getting bigger in size and power, what incurs that a simple unit breakdown causes large energy losses. They operate under varying, complex and dynamic loads due to the environmental conditions, such as wind shear, turbulence, gusts, etc. Condition-based and prognostic and health maintenance is key to assure reliable and efficient performance of wind farms, especially offshore. Fault diagnosis is important, but given the operational complexity of the wind turbines, previous knowledge about the condition of a wind turbine component and fault prognostics are the state of the art of wind farm operation. Although some advance has been made in the diagnostics of faults of wind turbines, very little research has been carried out in the field of fault prognostics of wind turbines. Then, there is an urgent need to develop prognostic techniques for such complex systems operating in real conditions. This article aims to present a comprehensive, specific and concise review of the up to date efforts and advances in the research of prognostic techniques and remaining useful life estimation methods applied to the critical components of wind turbines and analyse its advantages, capabilities and limitations.
TL;DR: In this paper, the authors defined and assessed an off-grid hybrid renewable energy with hydrogen storage system, where the system combines solar and wind energy, hydrogen production unit and fuel cell.
TL;DR: In this article, a fault-tolerant control (FTC) scheme was proposed for wind turbine pitch actuator faults to recover the nominal pitch dynamics, which is based on estimation of pitch system states and fault indicator function using an adaptive step-by-step sliding mode observer.
TL;DR: This study gives a comprehensive overview of large electric machines for aircraft electric propulsion applications, with a focus on methods for mass reduction and SP improvement.
Abstract: To achieve benefits similar to those seen in hybrid-/all-electric ground-based and marine vehicles, electric propulsion has been proposed for large commercial aircraft. Among the main drivers of this are improved fuel economy, reduced harmful emissions, and lower audible noise. In converting to electric propulsion, the added electrical components' masses must be minimised so that the benefits that the components enable - improved turbine efficiency, distributed propulsion and propulsion-airframe integration - are not cancelled out by their weight penalty. This puts stringent requirements on the large electric machines used in the system, both those that generate electric power from the turbine shaft and those that drive propellers or ducted fans, because they are among the heaviest of the added electric components. A key machine design metric in this application is the specific power (SP), or the power-to-mass ratio. This study gives a comprehensive overview of large electric machines for aircraft electric propulsion applications, with a focus on methods for mass reduction and SP improvement.
TL;DR: In this paper, the performance of three wind-lens configurations with different diffuser types is investigated (i.e., flat-panel, curved-surface, and cycloidal-surface).
TL;DR: In this article, a concept of strain energy gradient is elaborated and a general procedure combining this concept with theory of critical distance is established for LCF life prediction of notch components, which relates its life with the strain energy distributed within the effective damage zone.
TL;DR: In this article, the impact of solidity and number of blades on the aerodynamic performance of 2-, 3-and 4-bladed Darrieus H-type vertical axis wind turbines was analyzed.
24 Mar 2018
TL;DR: In this article, the authors proposed a methodology to predict the remaining useful life of an offshore wind turbine power converter in digital twin frame work as a means of predictive maintenance strategy for both diagnostic and prognostic health monitoring specific for offshore operating environment.
Abstract: The growing number of Offshore wind farms demands highly reliable wind turbines to curtail the maintenance cost and to shorten the downtime. Power converter is one of the critical components that undergoes high rate of medium and short term thermal cycles especially in Offshore floating wind turbines compared to fixed bottom turbines. The current study proposes a novel methodology to predict the remaining useful life of an offshore wind turbine power converter in digital twin frame work as a means of predictive maintenance strategy. The remaining useful life is estimated for both diagnostic and prognostic health monitoring specific for offshore operating environment.
TL;DR: In this article, the performance of the Savonius hydrokinetic turbine (SHT) has been evaluated through simulation and experimental and computational fluid dynamics (CFD) analysis.
TL;DR: The researches on the structural vibration characteristics and operational modal analysis of offshore wind turbine not only provide powerful data and technology support for the operation safety evaluation, but also provide the necessary theoretical and practical bases for the design and maintenance of wind turbine structures.
TL;DR: In this paper, a combination of CFD and Taguchi method is applied to optimize the aerodynamic performance of a typical three-bladed VAWT at a low TSR of 2.