scholarly journals Effect of Time History on Normal Behaviour Modelling Using SCADA Data to Predict Wind Turbine Failures

Energies ◽  
2020 ◽  
Vol 13 (18) ◽  
pp. 4745
Author(s):  
Conor McKinnon ◽  
Alan Turnbull ◽  
Sofia Koukoura ◽  
James Carroll ◽  
Alasdair McDonald
Keyword(s):  
Wind Turbine ◽  
Wind Farm ◽  
Signal Reconstruction ◽  
Significant Proportion ◽  
Model Performance ◽  
Time History ◽  
Normal Behaviour ◽  
Training Time ◽  
Behaviour Modelling ◽  
Cost Of Energy

Operations and Maintenance (O&M) can make up a significant proportion of lifetime costs associated with any wind farm, with up to 30% reported for some offshore developments. It is increasingly important for wind farm owners and operators to optimise their assets in order to reduce the levelised cost of energy (LCoE). Reducing downtime through condition-based maintenance is a promising strategy of realising these goals. This is made possible through increased monitoring and gathering of operational data. SCADA data are useful in terms of wind turbine condition monitoring. This paper aims to perform a comprehensive comparison between two types of normal behaviour modelling: full signal reconstruction (FSRC) and autoregressive models with exogenous inputs (ARX). At the same time, the effects of the training time period on model performance are explored by considering models trained with both 12 and 6 months of data. Finally, the effects of time resolution are analysed for each algorithm by considering models trained and tested with both 10 and 60 min averaged data. Two different cases of wind turbine faults are examined. In both cases, the NARX model trained with 12 months of 10 min average Supervisory Control And Data Acquisition (SCADA) data had the best training performance.

Site-Specific Design Optimization of 1.5–2.0 MW Wind Turbines

2001 ◽  
Vol 123 (4) ◽  
pp. 296-303 ◽  
Author(s):  
Peter Fuglsang ◽  
Kenneth Thomsen
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Wind Farm ◽  
Offshore Wind ◽  
Offshore Wind Farm ◽  
Load Prediction ◽  
Specific Design ◽  
Site Specific ◽  
Cost Of Energy ◽  
Fatigue Loads

A method is presented for site-specific design of wind turbines where cost of energy is minimized. A numerical optimization algorithm was used together with an aeroelastic load prediction code and a cost model. The wind climate was modeled in detail including simulated turbulence. Response time series were calculated for relevant load cases, and lifetime equivalent fatigue loads were derived. For the fatigue loads, an intelligent sensitivity analysis was used to reduce computational costs. Extreme loads were derived from statistical response calculations of the Davenport type. A comparison of a 1.5 MW stall regulated wind turbine in normal onshore flat terrain and in an offshore wind farm showed a potential increase in energy production of 28% for the offshore wind farm, but also significant increases in most fatigue loads and in cost of energy. Overall design variables were optimized for both sites. Compared to an onshore optimization, the offshore optimization increased swept area and rated power whereas hub height was reduced. Cost of energy from manufacture and installation for the offshore site was reduced by 10.6% to 4.6¢. This reduction makes offshore wind power competitive compared with today’s onshore wind turbines. The presented study was made for one wind turbine concept only, and many of the involved sub models were based on simplified assumptions. Thus there is a need for further studies of these models.

scholarly journals Evaluation of the impact of wind farm control techniques on fatigue and ultimate loads

2020 ◽  
Author(s):  
Alessandro Croce ◽  
Stefano Cacciola ◽  
Luca Sartori ◽  
Paride De Fidelibus
Keyword(s):  
Wind Turbine ◽  
Energy Production ◽  
Wind Farm ◽  
Dynamic Responses ◽  
Control Techniques ◽  
Cost Of Energy ◽  
The Individual ◽  
The Cost ◽  
The Impact ◽  
Do So

Abstract. Wind farm control is one of the solutions recently proposed to increase the overall energy production of a wind power plant. A generic wind farm control is typically synthesized so as to optimize the energy production of the entire wind farm by reducing the detrimental effects due to wake-turbine interactions. As a matter of fact, the performance of a farm control is typically measured by looking mainly at the increase of produced power, possibly weighted with the wind Weibull and rose at a specific place, and, sometimes, by looking also at the fatigue loads. However, an aspect which is rather overlooked is the evaluation of the impact that a farm control law has on the maximum loads and on the dynamic responses under extreme conditions of the individual wind turbine. In this work, two promising wind farm controls, based respectively on Wake Redirection (WR) and Dynamic Induction Control (DIC) strategy, are evaluated at a single wind turbine level. To do so, a two-pronged analysis is performed. Firstly, the control techniques are evaluated in terms of the related impact on some specific key performance indicators (e.g. fatigue and ultimate loads, actuator duty cycle and annual energy production). Secondarily, an optimal blade redesign process, which takes into account the presence of the wind farm control, is performed with the goal of quantifying the possible modification in the structure of the blade and hence of quantifying the impact of the control on the Cost of Energy model.

scholarly journals Evaluation of the impact of active wake control techniques on ultimate loads for a 10 MW wind turbine

2022 ◽  
Vol 7 (1) ◽  
pp. 1-17
Author(s):  
Alessandro Croce ◽  
Stefano Cacciola ◽  
Luca Sartori
Keyword(s):  
Wind Turbine ◽  
Energy Production ◽  
Wind Farm ◽  
Control Techniques ◽  
Control Optimization ◽  
Cost Of Energy ◽  
The Individual ◽  
The Cost ◽  
Wind Statistics ◽  
The Impact

Abstract. Wind farm control is one of the solutions recently proposed to increase the overall energy production of a wind power plant. A generic wind farm control is typically synthesized so as to optimize the energy production of the entire wind farm by reducing the detrimental effects due to wake–turbine interactions. As a matter of fact, the performance of a farm control is typically measured by looking at the increase in the power production, properly weighted through the wind statistics. Sometimes, fatigue loads are also considered in the control optimization problem. However, an aspect which is rather overlooked in the literature on this subject is the evaluation of the impact that a farm control law has on the individual wind turbine in terms of maximum loads and dynamic response under extreme conditions. In this work, two promising wind farm controls, based on wake redirection (WR) and dynamic induction control (DIC) strategy, are evaluated at the level of a single front-row wind turbine. To do so, a two-pronged analysis is performed. Firstly, the control techniques are evaluated in terms of the related impact on some specific key performance indicators, with special emphasis on ultimate loads and maximum blade deflection. Secondarily, an optimal blade redesign process is performed with the goal of quantifying the modification in the structure of the blade entailed by a possible increase in ultimate values due to the presence of wind farm control. Such an analysis provides for an important piece of information for assessing the impact of the farm control on the cost-of-energy model.

scholarly journals Documenting Wind Speed and Power Deficits behind a Utility-Scale Wind Turbine

2013 ◽  
Vol 52 (1) ◽  
pp. 39-46 ◽  
Author(s):  
Brian D. Hirth ◽  
John L. Schroeder
Keyword(s):  
Wind Speed ◽  
Wind Turbine ◽  
Wind Farm ◽  
Horizontal Wind ◽  
Horizontal Wind Speed ◽  
Large Variability ◽  
Cost Of Energy ◽  
The Mean ◽  
Utility Scale ◽  
Turbine Wake

AbstractHigh-spatial-and-temporal-resolution radial velocity measurements surrounding a single utility-scale wind turbine were collected using the Texas Tech University Ka-band mobile research radars. The measurements were synthesized to construct the first known dual-Doppler analyses of the mean structure and variability of a single turbine wake. The observations revealed a wake length that subjectively exceeded 20 rotor diameters, which far exceeds the typically employed turbine spacing of 7–10 rotor diameters. The mean horizontal wind speed deficits found within the turbine wake region relative to the free streamflow were related to potential reductions in the available power for a downwind turbine. Mean wind speed reductions of 17.4% (14.8%) were found at 7 (10) rotor diameters downwind, corresponding to a potential power output reduction of 43.6% (38.2%). The wind speed deficits found within the wake also exhibit large variability over short time intervals; this variability would have an appreciable impact on the inflow of a downstream turbine. The full understanding and application of these newly collected data have the potential to alter current wind-farm design and layout practices and to affect the cost of energy.

scholarly journals A Novel Numerical Algorithm for Optimal Sizing of a Photovoltaic/Wind/Diesel Generator/Battery Microgrid Using Loss of Load Probability Index

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Hussein A. Kazem ◽  
Tamer Khatib
Keyword(s):  
Wind Turbine ◽  
Energy Demand ◽  
Wind Farm ◽  
Minimum Cost ◽  
Integrated System ◽  
Diesel Generator ◽  
Pv Array ◽  
Load Demand ◽  
Cost Of Energy ◽  
Daily Energy

This paper presents a method for determining optimal sizes of PV array, wind turbine, diesel generator, and storage battery installed in a building integrated system. The objective of the proposed optimization is to design the system that can supply a building load demand at minimum cost and maximum availability. The mathematical models for the system components as well as meteorological variables such as solar energy, temperature, and wind speed are employed for this purpose. Moreover, the results showed that the optimum sizing ratios (the daily energy generated by the source to the daily energy demand) for the PV array, wind turbine, diesel generator, and battery for a system located in Sohar, Oman, are 0.737, 0.46, 0.22, and 0.17, respectively. A case study represented by a system consisting of 30 kWp PV array (36%), 18 kWp wind farm (55%), and 5 kVA diesel generator (9%) is presented. This system is supposed to power a 200 kWh/day load demand. It is found that the generated energy share of the PV array, wind farm, and diesel generator is 36%, 55%, and 9%, respectively, while the cost of energy is 0.17 USD/kWh.

scholarly journals Assessment of the apparent performance characterization along with levelized cost of energy of wind power plants considering real data

2018 ◽  
Vol 36 (6) ◽  
pp. 1708-1728 ◽  
Author(s):  
Zahid H Hulio ◽  
Wei Jiang
Keyword(s):  
Wind Speed ◽  
Wind Turbine ◽  
Wind Power ◽  
Power Plants ◽  
Wind Farm ◽  
Power Coefficient ◽  
Speed Ratio ◽  
Data Set ◽  
Levelized Cost ◽  
Cost Of Energy

Pakistan pursued the renewable energy policy to minimize the cost of energy per kWh as well as dependence on costly imported oil. Jhimpir site is termed as wind corridor and has tremendous proven wind power potential. The site is hosted for the first installed wind power plant. The aim of paper is to investigate the performance and levelized cost of energy of a wind farm. The methodology covers assessment of wind characteristics, performance function and levelized cost of energy model. The measured mean wind speed was found to be 8 m/s at 80 m above the ground level. The average values of standard deviation, Weibull k and c parameters, obtained using entire data set, were found to be 2.563, 3.360 and 8.940 m/s at 80 m. Performance assessment including technical, real availability and average capacity factor was found to be 97, 90 and 34.50%, respectively. It is evident that the power coefficient dropped if wind speed crosses the rated power. So it can be concluded that the efficiency of wind turbine decreased by increased wind speed. Tip speed ratio shows that a wind turbine operating close to optimal lift and drag will exhibit the performance level. Wind turbine performs better at the wind speed between 6 and 10 m/s. The estimated average levelized cost of energy was US $0.11371 and US $0.04092/kWh for 1–10 and 11–20 years, respectively. This makes it competitive in terms of low production cost per kWh to other energy technologies.

Numerical Optimization and Noise Analysis of High-Tip-Speed Wind Turbine

2017 ◽  
Vol 9 (6) ◽  
pp. 1461-1484 ◽  
Author(s):  
Long Wang ◽  
Guoping Chen ◽  
Tongguang Wang ◽  
Jiufa Cao
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Wind Farm ◽  
Noise Analysis ◽  
Wind Farms ◽  
Offshore Wind ◽  
Class Iii ◽  
Offshore Wind Farms ◽  
Multi Objective ◽  
Cost Of Energy

AbstractWith lower turbulence and less rigorous restrictions on noise levels, offshore wind farms provide favourable conditions for the development of high-tip-speed wind turbines. In this study, the multi-objective optimization is presented for a 5MW wind turbine design and the effects of high tip speed on power output, cost and noise are analysed. In order to improve the convergence and efficiency of optimization, a novel type of gradient-based multi-objective evolutionary algorithm is proposed based on uniform decomposition and differential evolution. Optimization examples of the wind turbines indicate that the new algorithm can obtain uniformly distributed optimal solutions and this algorithm outperforms the conventional evolutionary algorithms in convergence and optimization efficiency. For the 5MW wind turbines designed, increasing the tip speed can greatly reduce the cost of energy (COE). When the tip speed increases from 80m/s to 100m/s, under the same annual energy production, the COE decreases by 3.2% in a class I wind farm and by 5.1% in a class III one, respectively, while the sound pressure level increases by a maximum of 4.4dB with the class III wind farm case.

Overview of Subsynchronous Oscillation in Grid-connected Wind Farm

2020 ◽  
Vol 13 (7) ◽  
pp. 969-979
Author(s):  
Xu Pei-Zhen ◽  
Lu Yong-Geng ◽  
Cao Xi-Min
Keyword(s):  
Power Systems ◽  
Wind Turbine ◽  
Large Scale ◽  
Wind Farm ◽  
Wind Farms ◽  
Induction Generator ◽  
Future Research ◽  
Stable Operation ◽  
Subsynchronous Oscillation ◽  
Different Types

Background: Over the past few years, the subsynchronous oscillation (SSO) caused by the grid-connected wind farm had a bad influence on the stable operation of the system and has now become a bottleneck factor restricting the efficient utilization of wind power. How to mitigate and suppress the phenomenon of SSO of wind farms has become the focus of power system research. Methods: This paper first analyzes the SSO of different types of wind turbines, including squirrelcage induction generator based wind turbine (SCIG-WT), permanent magnet synchronous generator- based wind turbine (PMSG-WT), and doubly-fed induction generator based wind turbine (DFIG-WT). Then, the mechanisms of different types of SSO are proposed with the aim to better understand SSO in large-scale wind integrated power systems, and the main analytical methods suitable for studying the SSO of wind farms are summarized. Results: On the basis of results, using additional damping control suppression methods to solve SSO caused by the flexible power transmission devices and the wind turbine converter is recommended. Conclusion: The current development direction of the SSO of large-scale wind farm grid-connected systems is summarized and the current challenges and recommendations for future research and development are discussed.

Experimental Study for SPAR Type Floating Offshore Wind Turbine With Blade-Pitch Control

2013 ◽  
Author(s):  
Toshiki Chujo ◽  
Yoshimasa Minami ◽  
Tadashi Nimura ◽  
Shigesuke Ishida
Keyword(s):  
Wind Turbine ◽  
Wind Farm ◽  
Offshore Wind ◽  
Scale Model ◽  
Offshore Wind Turbine ◽  
Experimental Proof ◽  
Pitch Control ◽  
Model Experiments ◽  
North Eastern ◽  
North Eastern Part

The experimental proof of the floating wind turbine has been started off Goto Islands in Japan. Furthermore, the project of floating wind farm is afoot off Fukushima Prof. in north eastern part of Japan. It is essential for realization of the floating wind farm to comprehend its safety, electric generating property and motion in waves and wind. The scale model experiments are effective to catch the characteristic of floating wind turbines. Authors have mainly carried out scale model experiments with wind turbine models on SPAR buoy type floaters. The wind turbine models have blade-pitch control mechanism and authors focused attention on the effect of blade-pitch control on both the motion of floater and fluctuation of rotor speed. In this paper, the results of scale model experiments are discussed from the aspect of motion of floater and the effect of blade-pitch control.

scholarly journals Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

2021 ◽  
Vol 11 (6) ◽  
pp. 2838
Author(s):  
Nikitha Johnsirani Venkatesan ◽  
Dong Ryeol Shin ◽  
Choon Sung Nam
Keyword(s):  
Neural Network ◽  
Radiation Dose ◽  
Convolutional Neural Network ◽  
Model Performance ◽  
Performance Comparison ◽  
Apache Spark ◽  
Training Time ◽  
Learning Framework ◽  
Proposed Model

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance the quality of the medical images by intensifying the radiation dose. High radiation dose provokes cancer, which forces experts to use limited radiation. Using abrupt radiation generates noise in CT scans. We propose an optimal Convolutional Neural Network model in which Gaussian noise is removed for better classification and increased training accuracy. Experimental demonstration on the LUNA16 dataset of size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, and area under the ROC curve (AUC) of the model performance are taken as evaluation metrics. We conducted a performance comparison of our proposed model on numerous platforms, like Apache Spark, GPU, and CPU, to depreciate the training time without compromising the accuracy percentage. Our results show that Apache Spark, integrated with a deep learning framework, is suitable for parallel training computation with high accuracy.

Sign in / Sign up

Export Citation Format

Share Document