基于组合赋权和云模型的风电机组健康状态评估

针对当前模糊评价隶属函数的确定具有主观性且未考虑随机性的问题,提出一种基于组合赋权和云模型的风电机组健康状态评估方法。在构建风电机组健康状态评估指标体系及等级划分基础上,通过组合赋权法确定各指标的权重,应用隶属云模型确定定量指标对各状态等级的隶属度,采用分层评估方法对风电机组健康状态开展综合评价。实例验证结果表明,该方法具有有效性和可行性。     

基于随机组合赋权模糊评价的风电机组健康状态评估

由于健康指标权重随机性会导致风电机组状态评估灵敏度降低,提出一种评估风电机组健康状态的随机组合赋权模糊评价方法。首先,通过相关性、方差、偏度等多角度分析风电场采集与监视控制系统（SCADA）数据,结合IEC61400-1标准建立机组健康状态评估指标架构,并基于随机因子优化组合权重得到赋权公式,提高评估指标层权重的准确性。其次,为充分覆盖评估指标数据劣化度,基于岭型分布函数建立健康指标劣化隶属度计算函数。结合随机组合权重和隶属度函数,构建风电机组健康状态模糊综合评价数学模型。通过分层评估风电机组健康状态指标架构,得到机组健康等级并实现故障预警。最后,对大连驼山风电场多台机组进行评估试验,结果表明：该文方法能准确评估出风电机组健康状态等级,相比组合赋权云模型方法,灵敏度提高了1.85%。     

基于动态阈值的风电轴承健康状态评估

针对现有的风电轴承健康状态评估方法需大量样本提取和模型训练、存在实现过程繁琐费时费力且泛化应用能力弱的问题,提出基于动态阈值的风电轴承健康状态评估方法。首先,考虑风的随机性和间歇性,利用风电轴承温度监测数据,引入劣化度概念,采用曲线拟合和机群聚类方法确定了劣化度的上、下限动态阈值;其次,通过健康状态评语集及其等级划分范围和劣化度计算,提出基于动态阈值的风电轴承健康状态评估方法;最后,以某风电机组的发电机后轴承超温故障为例,验证了所提评估方法可获得有效的风电轴承健康状态和及早获知故障征兆。     

考虑风电机组运行健康状态的风电场优化调度方法

当前风电场功率控制过程中多关注风电机组的发电能力,很少区别对待健康机组和带病机组。对此,以风电机组运行参数为评估指标,计算各指标劣化度,并以综合劣化度为风电机组健康状况的总体评判指标,再结合风电机组启停状态及功率控制要求建立风电场的多目标调度模型。采用混合编码遗传算法优化该模型,获得风电机组启停组合和目标功率值。仿真结果表明,该方法优化了风电机组启停计划,改善了风电机组的整体健康程度,提高了风电场有功输出的可靠性和稳定性,为功率调度过程提供了依据。     

基于多类证据体方法的风电机组健康状态评估

针对基于确定权重的评估方法难以适应风电机组特征量多且相互关系不明确的特点,提出基于多种类证据体的风电机组健康状态评估方法。首先考虑风速大小随机变化对机组振动和温度特征量波动范围的影响,提出基于动态阈值的评估指标劣化度量化方法;其次针对证据间信息可能存在的高冲突问题,按照证据间的优先度分布情况,依据证据源修正思想建立基于证据推理的风电机组健康状态评估模型;最后,以某风电机组健康状态评估为例,与传统的证据评估方法对比分析,验证所提出评估方法可均衡兼顾各评估指标的状态信息获得有效的风电机组健康状态。     

基于风电机组状态的超短期海上风电功率预测

提出一种基于风电机组状态的超短期海上风电功率预测模型。首先,综合考虑海上环境因素以及风电机组部件间的相互作用建立指标的预测模型,以长短期记忆神经网络的预测误差作为监测指标的动态劣化度;然后采用模糊综合评价法对风电机组的运行状态进行评估,依据评估结果对风电机组历史运行数据进行划分;最后根据分类后历史运行数据建立基于机组状态的超短期风电功率预测模型。结合国内某海上风电场实例数据进行分析,算例结果表明所提方法可有效提高风电功率预测精度。     

基于灰色理论和变权模糊综合评判的风电机组性能评估

为了评估风电机组性能及优化其维修策略,保证风电机组安全稳定运行,提出基于灰色理论和变权模糊综合评判的风电机组性能评估方法。首先,分析风电机组控制系统所监测的物理量,采用层次分析法构建具有反映风电机组运行性能重要特征的项目层和子项目层框架,并针对子项目层中多项评判指标同时发生严重偏离的情况,引入劣化度指标。为避免层次分析确定指标常权值所引起计算误差过大的问题,利用灰色系统理论得到各评估指标的综合权重,并结合变权理论,对某些严重偏离正常值的指标进行权重修正,建立基于灰色理论和变权模糊综合评判的风电机组性能评估模型。然后,基于某1.5 MW风电场数据采集与监控系统(Supervisory Control andData Acquisition,SCADA)的运行数据进行计算,并与常规评估方法结果及实际运行分析进行比较和验证,结果表明所提出的风电机组性能评估方法和模型正确有效。     

一种提高风电机组调度可靠性的风电场功率控制策略

以提高风电机组调度可靠性为目标,提出一种考虑风电机组运行健康度的风电场功率优化调度策略。首先提出一种基于风电场数据采集与监视控制系统(SCADA)监测数据的风电机组健康状态评估策略,利用综合劣化度对机组的健康状况进行总体评估,为功率调度决策过程提供辅助依据。针对风电场实际运行中对机组启停以及功率控制的要求,结合机组健康度信息,建立风电场功率调度的复合目标多步优化模型,并设计基于遗传算法的求解策略。最后通过详细的算例验证了所提策略对改善运行风电机组的整体健康程度,优化机组的启停计划、提高风电场功率控制可靠性具有良好作用。     

基于温度参数的风电机组异常识别

文章针对风电机组运行过程中机组早期的异常状态识别问题,提出一种考虑有功功率的基于机组温度参数变化特性的风电机组异常识别模型。首先,分析风电机组各系统与温度相关的参数。然后,利用相关性理论,确定了与有功功率相关的温度参数:齿轮箱高速轴轴承前端温度、齿轮箱高速轴轴承后端温度、齿轮箱油温、发电机驱动端轴承温度、发电机非驱动端轴承温度、发电机定子绕组温度,形成了异常检测的参数体系。再次,以正常状态下机组温度参数的偏度和峰度的最大区间作为阈值,建立风电机组异常识别模型。最后,采用滑动窗口对机组运行状态进行在线监测。通过实例研究发现,当机组发生异常状态时,温度参数的偏度或者峰度超过了阈值,比警报提前了15 d。该识别模型为风电机组的早期故障预警提供了参考。     

基于改进果蝇算法优化支持向量机的风电机组性能评估

目前,关于风电机组性能的研究多集中于某一关键部件,文章针对风电机组整体提出一种性能评估的方法。首先采用支持向量回归(SVR)预测正常状态下的评价指标,并使用果蝇优化算法(FOA)来寻找其最优参数。为了克服FOA易陷入局部最优的缺点,引入免疫思想增加种群的多样性,并采用自适应搜索步长,提高其收敛精度;然后通过变权思想对预测误差进行组合,得到风电机组偏离正常状态的劣化度,实现对风电机组的性能评估;最后,采用某风电场的数据进行实验分析,验证了文章所提方法的可行性。     

A novel method for reliability and risk evaluation of wind energy conversion systems considering wind speed correlation

This paper investigates an analytical approach for the reliability modeling of doubly fed induction generator (DFIG) wind turbines. At present, to the best of the authors’ knowledge, wind speed and wind turbine generator outage have not been addressed simultaneously. In this paper, a novel methodology based on the Weibull- Markov method is proposed for evaluating the probabilistic reliability of the bulk electric power systems, including DFIG wind turbines, considering wind speed and wind turbine generator outage. The proposed model is presented in terms of appropriate wind speed modeling as well as capacity outage probability table (COPT), considering component failures of the wind turbine generators. Based on the proposed method, the COPT of the wind farm has been developed and utilized on the IEEE RBTS to estimate the well-known reliability and sensitive indices. The simulation results reveal the importance of inclusion of wind turbine generator outage as well as wind speed in the reliability assessment of the wind farms. Moreover, the proposed method reduces the complexity of using analytical methods and provides an accurate reliability model for the wind turbines. Furthermore, several case studies are considered to demonstrate the effectiveness of the proposed method in practical applications.     

数据驱动的风电机组偏航参数适应性优化

为了增强风电机组偏航系统自适应水平,提升风能利用率,提出一种基于K近邻聚类（KNN）算法风电机组偏航控制参数优化方法。为准确描述风向变化,建立改进Weibull概率分布建立风向评估模型,即以风向波动的幅值（A）和波动持续时间（T）作为风况的数据标签来描述风向。对比风电机组不同偏航参数下的运行数据确定聚类中心（已知风况下的最佳偏航参数）,通过基于KNN算法的风电机组偏航控制参数优化模型,得到不同风况下风电机组最佳的偏航参数。通过对风电机组运行数据进行算例分析表明,该方法高风速时可提升风电机组发电效率,并在低风速时减少偏航启动次数。     

Performance evaluation of pairing between sites and wind turbines

This paper presents a simple method for determination of pairing between sites and wind generators. It requires six parameters to describe the matching between turbine models and site characteristics, and the energy output performance can thus be easily estimated and used as the index of pairing effectiveness. To describe a Weibull model of wind speed distribution, the shape parameter and the scale parameter are necessarily required. Besides, four other parameters are chosen to specify the characteristics of the power curve of a wind generator: the cut-in speed, the rated speed, the cut-off speed and the nominal power. By combining these six parameters, the average power output of some particular wind turbine at a specific site can be practically and quickly approximated as a reference for turbine siting consideration. An example is also shown to demonstrate the utilization of the proposed method to choose between a group of wind sites and a list of commercial wind turbines.     

Feasibility of using wind turbines for renewable hydrogen production in Firuzkuh,Iran

The present study was conducted with the objective of evaluating several proposed turbines from 25 kW to 1.65 MW in order to select the appropriate turbine for electricity and hydrogen production in Firuzkuh area using the decision making trial and evaluation (DEMATEL) and data envelopment analysis (DEA) methods. Initially, five important factors in selection of the best wind turbine for wind farm construction were determined using the DEMATEL technique. Then, technical-economic feasibility was performed for each of the eight proposed turbines using the HOMER software, and the performance score for each proposed wind turbine was obtained. The results show that the GE 1.5sl model wind turbine is suitable for wind farm construction. The turbine can generate 5515.325 MW of electricity annually, which is equivalent to $ 1103065. The average annual hydrogen production would be 1014 kg for Firuzkuh by using the GE 1.5sl model turbine.     

Condition based maintenance optimization for wind power generation systems under continuous monitoring

By utilizing condition monitoring information collected from wind turbine components, condition based maintenance (CBM) strategy can be used to reduce the operation and maintenance costs of wind power generation systems. The existing CBM methods for wind power generation systems deal with wind turbine components separately, that is, maintenance decisions are made on individual components, rather than the whole system. However, a wind farm generally consists of multiple wind turbines, and each wind turbine has multiple components including main bearing, gearbox, generator, etc. There are economic dependencies among wind turbines and their components. That is, once a maintenance team is sent to the wind farm, it may be more economical to take the opportunity to maintain multiple turbines, and when a turbine is stopped for maintenance, it may be more cost-effective to simultaneously replace multiple components which show relatively high risks. In this paper, we develop an optimal CBM solution to the above-mentioned issues. The proposed maintenance policy is defined by two failure probability threshold values at the wind turbine level. Based on the condition monitoring and prognostics information, the failure probability values at the component and the turbine levels can be calculated, and the optimal CBM decisions can be made accordingly. A simulation method is developed to evaluate the cost of the CBM policy. A numerical example is provided to illustrate the proposed CBM approach. A comparative study based on commonly used constant-interval maintenance policy demonstrates the advantage of the proposed CBM approach in reducing the maintenance cost.     

基于偏航尾流模型的风电场功率协同优化研究

为减小风电场尾流效应的影响,提升风电场整体发电量,提出一种基于偏航尾流模型的风电场功率协同优化方法。首先建立风电场偏航尾流模型,该模型包括用于计算单机组尾流速度分布的Jensen-Gaussian尾流模型、尾流偏转模型及多机组尾流叠加模型,对各机组风轮前来流风速进行求解;再根据来流风速计算风电场输出功率,并以风电场整体输出功率最大为优化目标,利用拟牛顿算法协同优化各机组轴向诱导因子和偏航角度。以4行4列方形布置的16台NREL-5 MW风电机组为对象进行仿真研究。结果表明,所提出的基于偏航尾流模型的风电场功率协同优化方法能显著提升风电场整体输出功率。     

A review of materials degradation in utility scale wind turbines

Abstract

This paper presents a comprehensive review of the state of knowledge of materials used in the major wind turbine components of both land based and offshore wind turbines. The paper is divided into the following seven major sections: utility scale wind turbine design overview; current state of wind turbine technology; review of degradation of materials used in wind turbines; a summary of materials degradation service experience; condition monitoring overview; review of materials based research and development for wind turbines; a summary of missing knowledge and future materials challenges. The review points out that the most important degradation mechanism is fatigue which limits the life, reliability and performance of current wind turbines. As even larger machines are built in the future, with pressures to cut weight and cost, continued materials research and development, as summarised in this paper, is warranted. This critical assessment and review of materials based degradation should be of interest to a wide range of technical energy specialists including those from manufacturers, research and development centres, end users (i.e. electric power generation companies) and financiers and insurers.     

Design and implementation of wind energy system in Saudi Arabia

This paper introduces an accurate procedure to choose the best site from many sites and suitable wind turbines for these sites depending on the minimum price of kWh generated (Energy Cost Figure (ECF)) from wind energy system. In this paper a new proposed computer program has been introduced to perform all the calculations and optimization required to accurately design the wind energy system and matching between sites and wind turbines. Some of cost calculations of energy methods have been introduced and compared to choose the most suitable method. The data for five sites in Saudi Arabia and hundred wind turbines have been used to choose the best site and the optimum wind turbine for each site. These sites are Yanbo, Dhahran, Dhulom, Riyadh, and Qaisumah. One hundred wind turbines have been used to choose the best one for each site. This program is built in a generic form which allows it to be used with unlimited number of sites and wind turbines in all over the world. The program is written by using Visual Fortran and it is verified with simple calculation in Excel. The paper showed that the best site is Dhahran and the suitable wind turbine for this site is KMW-ERNO with 5.85 Cents/kWh. The worst site to install wind energy system is Riyadh with minimum price of kWh of 12.81 Cents/kWh in case of using GE Energy 2 wind turbine.     

Sustainability assessment of wind turbines using fuzzy logic

Renewable energy systems provide opportunities for developing methods to evaluate their sustainability claims, inclusive of their life cycles, and to rank them based on their broader impact. In this paper, a fuzzy-logic-based method is proposed to evaluate and rank wind turbines as sustainable systems handling wind energy, in terms of renewability and environmental friendliness. Implementation of the proposed method is demonstrated in two steps: First, major factors defining life cycle and sustainability characteristics of wind turbines are identified. These factors are: Capital Cost, Greenhouse Gas Emission, and wind turbine Energy Efficiency. Nevertheless, the method allows expansion to include other factors, which may later be deemed as critical to the evaluation process. Second, a fuzzy-logic-based model is built and tested using hypothetical data to prove the concept. As a result, the relatively best sustainability is decided on a single dimension scale. The proposed method produced reliable results in terms of ordinally ranking the sustainability of wind turbines, but with interdependencies based on the entire group of wind turbine cases being examined. The proposed method formulates a satisfactory stepping stone on the way to establish a unified method and process to rank wind turbines based on sustainability.     

Global sensitivity analysis of wind turbine power output

The dynamics of wind turbine behavior are complex and a critical area of study for the wind industry. Identification of factors that cause changes in turbine performance can sometimes prove to be challenging, whereas other times, it can be intuitive. The quantification of the effect that these factors have is valuable for making improvements to both power performance and turbine health. In commercial farms, large quantities of meteorological and performance data are commonly collected to monitor daily operations. These data can also be used to analyze the relationship between each parameter in order to better understand the interactions that occur and the information contained within these signals. In this global sensitivity analysis, a neural network is used to model select wind turbine supervisory control and data acquisition system parameters for an array of turbines from a commercial wind farm that exhibit signs of wake interaction. An extended Fourier amplitude sensitivity test is then performed for 2 years of 10‐min averaged data. The study examines the primary and combined sensitivities of power output to each selected parameter for two turbines in the array. The primary sensitivities correspond to single parameter interactions, whereas combined sensitivities account for interactions between multiple parameters simultaneously. Highly influential parameters such as wind speed and rotor rotation frequency produce expected results; the extended Fourier amplitude sensitivity test method proved effective at quantifying the sensitivity of a wide range of more subtle inputs. These include blade pitch, yaw position, main bearing and ambient temperatures as well as wind speed and yaw position standard deviation. The technique holds promise for application in full‐scale wake studies where it might be used to determine the benefits of emerging power optimization strategies such as active wake management. The field of structural health monitoring can also benefit from this method. Copyright © 2013 John Wiley & Sons, Ltd.