Showing papers on "Turbine published in 2022"

The Multiclass Fault Diagnosis of Wind Turbine Bearing Based on Multisource Signal Fusion and Deep Learning Generative Model

Abstract: Low fault diagnosis accuracy in case of insufficient and imbalanced samples is a major problem in the wind turbine fault diagnosis. The imbalance of samples refers to the large difference in the number of samples of different categories or the lack of a certain fault sample, which requires good learning of the characteristics of a small number of samples. Sample generation in the deep learning generation model can effectively solve this problem. In this study, we proposed a novel multiclass wind turbine bearing fault diagnosis strategy based on the conditional variational generative adversarial network (CVAE-GAN) model combining multisource signals fusion. This strategy converts multisource 1-D vibration signals into 2-D signals, and the multisource 2-D signals were fused by using wavelet transform. The CVAE-GAN model was developed by merging the variational autoencoder (VAE) with the generative adversarial network (GAN). The VAE encoder was introduced as the front end of the GAN generator. The sample label was introduced as the model input to improve the model’s training efficiency. Finally, the sample set was used to train encoder, generator, and discriminator in the CVAE-GAN model to supplement the number of the fault samples. In the classifier, the sample set is used to do experimental analysis under various sample circumstances. The results show that the proposed strategy can increase wind turbine bearing fault diagnostic accuracy in complex scenarios.

Short-Term Wind Power Prediction via Spatial Temporal Analysis and Deep Residual Networks

Abstract: Wind power is a rapidly growing source of clean energy. Accurate short-term forecasting of wind power is essential for reliable energy generation. In this study, we propose a novel wind power forecasting approach using spatiotemporal analysis to enhance forecasting performance. First, the wind power time-series data from the target turbine and adjacent neighboring turbines were utilized to form a graph structure using graph neural networks (GNN). The graph structure was used to compute the spatiotemporal correlation between the target turbine and adjacent turbines. Then, the prediction models were trained using a deep residual network (DRN) for short-term wind power prediction. Considering the wind speed, the historic wind power, air density, and historic wind power in adjacent wind turbines within the supervisory control and data acquisition (SCADA) system were utilized. A comparative analysis was performed using conventional machine-learning approaches. Industrial data collected from Hami County, Xinjiang, China, were used for the case study. The computational results validate the superiority of the proposed approach for short-term wind-power forecasting.

A reference open-source controller for fixed and floating offshore wind turbines

Abstract: Abstract. This paper describes the development of a new reference controller framework for fixed and floating offshore wind turbines that greatly facilitates controller tuning and represents standard industry practices. The reference wind turbine controllers that are most commonly cited in the literature have been developed to work with specific reference wind turbines. Although these controllers have provided standard control functionalities, they are often not easy to modify for use on other turbines, so it has been challenging for researchers to run representative, fully dynamic simulations of other wind turbine designs. The Reference Open-Source Controller (ROSCO) has been developed to provide a modular reference wind turbine controller that represents industry standards and performs comparably to or better than existing reference controllers. The formulation of the ROSCO controller logic and tuning processes is presented in this paper. Control capabilities such as tip speed ratio tracking generator torque control, minimum pitch saturation, wind speed estimation, and a smoothing algorithm at near-rated operation are included to provide modern controller features. A floating offshore wind turbine feedback module is also included to facilitate growing research in the floating offshore arena. All of the standard controller implementations and control modules are automatically tuned such that a non-controls engineer or automated optimization routine can easily improve the controller performance. This article provides the framework and theoretical basis for the ROSCO controller modules and generic tuning processes. Simulations of the National Renewable Energy Laboratory (NREL) 5 MW reference wind turbine and International Energy Agency 15 MW reference turbine on the University of Maine semisubmersible platform are analyzed to demonstrate the controller's performance in both fixed and floating configurations, respectively. The simulation results demonstrate ROSCO's peak shaving routine to reduce maximum rotor thrusts by over 10 % compared to the NREL 5 MW reference wind turbine controller on the land-based turbine and to reduce maximum platform pitch angles by nearly 30 % when using the platform feedback routine instead of a more traditional low-bandwidth controller.

Boundary Feedback Control of a Nonhomogeneous Wind Turbine Tower With Exogenous Disturbances

Abstract: This article studies a vibration and disturbance rejection problem of a wind turbine tower under exogenous perturbations. The tower dynamics is captured by a nonhomogeneous Euler–Bernoulli beam model. The dissipativity of the system is realized by a boundary feedback control solution with a multivalued symbolic function. A Lyapunov-based stability analysis is established to assess the deflection of the tower is uniformly bounded even subject to exogenous disturbances. The extended Filippov framework and Galerkin approximation scheme are introduced to tackle the existence of the solution to the system with a discontinuous control input. Simulation results demonstrate the performance of the proposed control scheme.

A Comprehensive Review on Signal-Based and Model-Based Condition Monitoring of Wind Turbines: Fault Diagnosis and Lifetime Prognosis

Abstract: Wind turbines play an increasingly important role in renewable power generation. To ensure the efficient production and financial viability of wind power, it is crucial to maintain wind turbines’ reliability and availability (uptime) through advanced real-time condition monitoring technologies. Given their plurality and evolution, this article provides an updated comprehensive review of the state-of-the-art condition monitoring technologies used for fault diagnosis and lifetime prognosis in wind turbines. Specifically, this article presents the major fault and failure modes observed in wind turbines along with their root causes, and thoroughly reviews the techniques and strategies available for wind turbine condition monitoring from signal-based to model-based perspectives. In total, more than 390 references, mostly selected from recent journal articles, theses, and reports in the open literature, are compiled to assess as exhaustively as possible the past, current, and future research and development trends in this substantial and active investigation area.

Pump as turbine cavitation performance for both conventional and reverse operating modes: A review

Abstract: With the increasing adoption of renewable energy sources globally, hydropower contributes significantly to energy generation through various schemes ranging from big to small-scale plants. In small-scale hydropower plants, the preference for reverse-operated pumps (known as pump as turbines or PATs) over small-scale hydroturbines has increased. However, apart from the associated economic advantages, PATs, like any other hydraulic machinery, are not free from common problems such as cavitation. Cavitation is a phenomenon in which air bubbles are formed within the fluid medium due to substantial local pressure drop and their eventual collapse causes material erosion and degrades the overall machine efficiency. Several studies have focused on PAT conventional operating mode, while its reverse mode just begun to gain research interest. Nevertheless, cavitation remains a common problem in PATs at various hydro-sites. Therefore, to analyze PAT cavitation performance and highlight the differences between its two operating modes in terms of their development mechanisms, this article presents a thorough review of PAT cavitation dynamics and influencing parameters, as well as the future research directions. It is found that PAT reverse mode is more prone to cavitation, but more damages would occur in the conventional mode. Nevertheless, modifying the PAT geometric design parameters can considerably improve its cavitation performance. However, this approach has not been sufficiently investigated for PAT reverse operating mode and hence requires further research. Note that the terms “PAT conventional mode,” “PAT pumping mode,” and “pump” are equally used throughout this paper. • Studies on cavitation performance in hydraulic pumps as turbines (PATs) are reviewed. • Both pump and turbine modes are considered in the review. • PATs are found to have gained importance due to their applicability in remote areas. • PAT reverse mode operations require high heads and flows; prone to cavitation. • Geometric design modification is widely used for PAT cavitation performance improvement.

A Condition Monitoring and Fault Isolation System for Wind Turbine Based on SCADA Data

Abstract: Condition monitoring of the wind turbine based on supervisory control and data acquisition (SCADA) data has attracted much attention in recent years. Nevertheless, there are some inherent challenges in SCADA data analysis, including the low sampling rate, time-varying working conditions of the wind turbine, and a lack of historical fault data. To solve these problems, this article develops a novel condition monitoring and fault isolation system. First, a covariate-adjusted preprocessing procedure is proposed to account for the various working conditions of the wind turbine. Next, we construct a global monitoring statistic based on all temperature variables contained in the SCADA data, with a view to monitoring the overall health status of the wind turbine. If an alarm is raised, we isolate the fault through a variable selection method without relying on expert knowledge or historical fault data. Simulation and real cases are provided to demonstrate the effectiveness of this system.

Simulation study on transient performance of a marine engine matched with high-pressure SCR system

Abstract: The high-pressure SCR system is suitable for low-speed marine engines that burn high-sulfur fuel, but it will cause the increase of the exhaust back pressure of main engine, which will affect the main engine’s performance and fuel consumption. At the same time, due to the large weight and size of the SCR reactor, the overall heat storage performance of the SCR reactor is large, which makes the temperature difference between the front and back of the turbine in the start-up and shutdown of the main engine and transient conditions, affecting the transient response performance of the turbine. In this paper, 6S46ME marine low-speed diesel engine and its high-pressure SCR system are taken as the research object, the co-simulation model is constructed by using GT-Suite coupled with a programming software, and the accuracy of the test model is verified. The influence of high-pressure SCR system on the performance of main engine is analyzed, and it finds that the fuel consumption of the main engine at low load increases significantly greater than that at high load, and the exhaust temperature of the main engine changes differently at different loads. On this basis, the co-simulation model was used to analyze the matching performance of high-pressure SCR system under the transient conditions such as the main engine Tier II/Tier III mode switching process, fast-loading, normal-loading and fast-unloading. The results show that the slow cut-in/cut-out of SCR reactor is beneficial to the stable operation of the main engine system, and the cut-in/cut-out time of high-pressure SCR system greatly affects the transient fuel consumption of the main engine, and the maximum increase of fuel consumption is about 3.6 g/kW·h; In addition, the thermal inertia of the reactor has a greater impact on the performance of the main engine at low load, but not at high load.

Collective wind farm operation based on a predictive model increases utility-scale energy production

Abstract: In wind farms, turbines are operated to maximize only their own power production. Individual operation results in wake losses that reduce farm energy. Here we operate a wind turbine array collectively to maximize array production through wake steering. We develop a physics-based, data-assisted flow control model to predict the power-maximizing control strategy. We first validate the model with a multi-month field experiment at a utility-scale wind farm. The model is able to predict the yaw-misalignment angles which maximize array power production within ± 5° for most wind directions (5–32% gains). Using the validated model, we design a control protocol which increases the energy production of the farm in a second multi-month experiment by 3.0% ± 0.7% and 1.2% ± 0.4% for wind speeds between 6 m s−1 and 8 m s −1 and all wind speeds, respectively. The predictive model can enable a wider adoption of collective wind farm operation. Individual operation of turbines in wind farms results in energy losses from wake interactions. Here Howland et al. report on an experimentally validated model to implement collective operation of turbines, which increases the farm’s energy production.