改进BiLSTM-GRU-DMD的风机叶片结冰故障检测与状态评估模型

针对风电机组运行监测数据的不平衡性与时序性，提出一种新的风机叶片结冰故障诊断与状态评估方法。首先，利用自适应过采样方法均衡风机结冰样本数据集的不平衡性；然后，改进堆叠双向长短时记忆网络和门控循环单元检测风机叶片结冰故障，利用焦点损失函数作为损失函数侧重于难分类样本优化模型，并结合改进非洲秃鹫优化算法优化超参数，从而提升检测准确性；最后，测度结冰样本与非结冰样本的动态马氏距离，并转换为结冰指数评估叶片结冰状态。真实风场数据验证表明：提出的风机结冰故障检测与状态评估方法，在结冰检测方面，其F1分数、精确率和召回率分别达到0.967 8、0.960 7和0.975 1，优于其他基线模型和优化算法，有效地减少了错报率和漏报率。同时，在定量化评估风机叶片不同阶段的结冰状态方面具有优势，可以为风电设备视情维修提供支持。     

基于残差神经网络的风机叶片结冰故障诊断

风力发电机叶片结冰故障直接影响风力发电机的运行安全和发电效率.针对这一问题,提出一种基于一维残差神经网络(1DRes-CNN)的叶片结冰诊断模型,该模型通过风机SCADA数据进行风机叶片结冰故障诊断.首先通过标记标签、数据分割、类间平衡和归一化对SCADA数据进行预处理;然后基于叶片结冰物理机制和XGBoost特征重要...     

基于气动信号分析的风机叶片裂纹故障识别

针对风机叶片裂纹故障,提出通过分析风机出口气动信号,实现在线动态检测裂纹的方法。采集叶片不同状态下的风机出口气动信号,利用db4小波对气动信号进行5层分解,并单支重构,将各频带归一化能量构成6维特征向量;对能量向量进行主成分分析,基于贡献率实现特征选择;采用K均值聚类方法进行叶片状态识别。实验结果表明,气动信号能有效反映风机叶片状态的变化,该方法可以实现叶片正常、异常状态检测及裂纹长度状态区分,提供了风机叶片裂纹在线实时检测依据和手段。     

基于残差神经网络的风机叶片结冰故障诊断

风力发电机叶片结冰故障直接影响风力发电机的运行安全和发电效率。针对这一问题，提出一种基于一维残差神经网络(1DRes-CNN)的叶片结冰诊断模型，该模型通过风机SCADA数据进行风机叶片结冰故障诊断。首先通过标记标签、数据分割、类间平衡和归一化对SCADA数据进行预处理；然后基于叶片结冰物理机制和XGBoost特征重要性计算选取与叶片结冰最相关的特征；最后利用构建好的1DRes-CNN模型进行叶片结冰诊断、实验结果表明，经过优化选取的特征，相较于SCADA全部特征作为1DRes-CNN模型输入，风叶结冰诊断准确率提升约为7 %。此外，与卷积神经网络、支持向量机和随机森林模型相比，该模型具有更高的诊断性能和泛化能力。     

基于等效风速的风机功率波动特性分析

自然界的风随机性强,风速和风向变化频繁。风机在实际运行中,经常因风的变化和控制策略问题引起风机频繁偏航、振动超限、故障停机等一系列工程问题。通过建立包含风剪切、塔影效应及偏航误差的等效风速模型,采用Matlab进行仿真分析,与风场实际运行数据进行对比,研究风机在等效风速下功率波动特性。结果表明,等效风速各分量对机组功率特性影响差异明显。可据此进行相关控制策略的优化设计以提高风机运行稳定性和风能利用率。     

基于机器学习的风机叶片开裂预测研究

为了预测风机叶片开裂的状态,使用机器学习的方法对风机叶片状态进行分类预测.首先对SCADA采集的原始数据进行预处理,然后采用逻辑回归与XGBoost集成学习算法对预处理后的数据进行建模,并通过性能度量的评价指标比较两种算法的效果与泛化能力.结果表明,XGBoost在风机叶片开裂的分类预测上有更好的效果,其预测准确率达到了97.31％,而逻辑回归预测的准确率只为69.05％,从而将XG-Boost集成学习算法用于精准预测风机叶片开裂的状态,为风电场对风机叶片状态检测提供了参考依据.另外为了提高模型训练的效率,使用嵌入式特征选择方法将430维数据降到100维,训练时间从67.06s降到13.50s,准确度从97.04％提升到97.65％.     

基于深度学习模型的风机叶片结冰故障诊断

风力发电机叶片出现结冰现象时若照常工作，不仅会影响经济效益，严重时还会直接损坏叶片等设备引发安全事故。为此提出一种使用KmeansSMOTE的数据平衡方法与应用结冰相关的机理构建新特征和RFECV-DT特征筛选算法相结合的特征工程互补的数据处理方式，之后采用卷积神经网络模型进行训练与预测。实验结果表明，在卷积神经网络模型中采用KmeansSMOTE算法比SMOTE算法准确率提升2.78%。模型采用特征工程时比不采用特征工程相比准确率高出4.77%。与KNN、SVM、LR这些传统模型相比，所有衡量指标均有提升且不存在过拟合现象。所提出的方法，可解决应用SMOTE插值机制所带来的不足并且对特征工程进行精细化设计，也为风机叶片结冰故障诊断问题提供一种新的解决思路。     

海上风电场运营期水下噪声测量及特性初步分析

海上风电场运营期间产生的水下噪声影响了海洋生态环境。针对国内对风机水下噪声定量研究的缺乏,测量分析了海上风电场运营期单机容量3.0 MW和5.0 MW风机产生的水下噪声,并利用简正波模型仿真噪声分布。数据处理结果表明,风机产生的水下噪声强度较低,集中分布在800 Hz以下的低频段,噪声谱具有主频特性,高风速下主频更加明显;噪声强度随风速的增加而增大,而与风机功率差异不明显;噪声谱主频分布与风机功率、风速、桩基结构等有关。总体看,单个风机运营期间产生的水下噪声对海洋生态环境影响区域小。现场测量数据及结果可为海上风电工程环境影响评价提供技术参考,具有较大的工程应用价值。     

电力市场下网损分摊问题的研究

现在,电力行业引入市场竞争机制,如何公正、公平、合理地分摊网损到各个用户,是当前电力市场改革所要考虑的关键问题,考虑有功功率与无功功率的藕合性,给出向发电侧或负荷侧进行分摊的新方法。     

旋涡风机算法研究

利用CFD方法,对加装离心叶片的旋涡风机的加压效果进行计算,对单个旋涡叶片在不同环境压力下的加压效果进行比较,并利用叶片出口的速度三角形估算出气体进出叶片的次数,通过单次进出叶片的压升,从而得到旋涡风机整体升压。结果表明：叶片的加压能力随叶片距离风机入口的转角增大而增大,但叶片出口处速度的圆周分量也随之增大,从而使进出次数减少。而通过与实际风机实验数据的比较,证明利用速度三角形估算风机压升的方法是具有实际意义并且是可行的。     

Anti-icing and de-icing techniques for wind turbines: Critical review

Precipitation, atmospheric and in-cloud icing affect wind turbine operation in various ways, including measurement and control errors, power losses, mechanical and electrical failures and safety hazard. Anti-icing and de-icing strategies are used to minimize these effects. Many active and passive methods are in development but few are available on the market. Active heating of blades is the most tested, used and reliable way to prevent icing effects. It is used in parallel with passive hydrophobic coating to lower energy consumption. Precise icing evaluation of the site should be done during the assessment phase to evaluate the necessity and benefits of installing an anti-icing and/or a de-icing system. This evaluation shall continue during operation in order to optimize production and avoid component failure related to icing events. Multiple anemometry in combination with relative humidity measurements is a cheap and reliable icing detection method during assessment while the use of ice sensors and the power curve method is recommended during operation.     

考虑不同截面翼型选取的风电机组叶片优化设计方法

传统叶片优化设计中缺乏对截面翼型的考虑,导致叶片设计难以达到最优效果。为解决此问题,提出了考虑不同截面翼型的风电机组叶片优化设计方法,以截面翼型、弦长和扭角为设计变量,以年发电量最大化为目标,兼顾考虑相对厚度和相对弯度限制,建立了叶片参数设计遗传算法优化模型。以某1.5 MW风电机组为例,验证所提出优化设计方法的有效性。结果表明：考虑截面翼型等参数优化后的叶片功率系数明显增大;机组特性曲线在较大范围内均能保持在最佳功率系数附近,更易控制在最大风能捕捉效率点运行,从而提升了年发电量;同时,增加考虑相对厚度和相对弯度限制以更贴近实际工程应用。     

Fluid–structure interaction of FRP wind turbine blades under aerodynamic effect

Structural analysis of FRP wind turbine blades must take into account phenomena associated with aerodynamics as well as fluid–structure coupling, because aerodynamic loading causes blades to bend mostly in the flapwise direction, and simultaneously causes foil sections to rotate to create new fluid fields around the foils. This study developed an analytical process for calculating fluid–structure interaction, while considering the effects of aerodynamic pressure and finite element analysis in the design of wind turbine blades. In addition, we calculated turbine power efficiency to evaluate the results of fluid–structure interaction displaying approximately power capacity loss of 17% at a wind speed of 25 m/s, and proposed three feasible improvements to enhance the performance of wind turbines. The presented study provided a comprehensible means by which to interpret changes in the aeroelastic response of blades, and was helpful to modify the original wind turbine model.     

Modeling Smart Structure of Wind Turbine Blade

With the increasing size of wind turbine blades, the need for more sophisticated load control techniques has induced the interest for aerodynamic control systems with build-in intelligence on the blades. The paper aims to provide a way for modeling the adaptive wind turbine blades and analyze its ability for vibration suppress. It consists of the modeling of the adaptive wind turbine blades with the wire of piezoelectric material embedded in blade matrix, and smart sandwich structure of wind turbine blade. By using this model, an active vibration method which effectively suppresses the vibrations of the smart blade is designed.     

复合材料风电叶片避雷防护研究进展

复合材料风电叶片作为风力发电机组的一个重要组成部件,一旦受雷击损坏,经济损失巨大。因此对风力叶片避雷防护的研究越来越受到人们的关注。本文主要分析了风力叶片受雷击后的几种损伤形式和损伤机理,还总结了目前常用的几种避雷接收器的形式,并对国外在叶片避雷防护方面的研究进展进行了介绍。     

A computational procedure for prebending of wind turbine blades

Prebending of wind turbine blades constitutes a viable engineering solution to the problem of tower clearance, that is, ensuring that during wind turbine operation there is sufficient distance between the rotor blades and the tower to avoid collision. The prebent shape of the blade must be such that when the turbine rotor is subjected to wind and inertial loads, the blades are straightened into their design configuration. In this paper, we propose a method for accurate prediction of the prebent shape of wind turbine blades. The method relies on a stand‐alone aerodynamics simulation that provides the wind loads on a rigidly spinning rotor, followed by a series of structural mechanics simulations to determine the stress‐free prebent shape of the blade. This procedure involves only one‐way coupling between the fluid and structural mechanics, which avoids the challenges of solving the coupled fluid–structure interaction problem. The proposed methodology, which has no limitations on the blade geometry and structural modeling, is successfully applied to prebending of a 63‐m offshore wind turbine blade. Copyright © 2011 John Wiley & Sons, Ltd.     

风力机叶片挥舞摆振气弹失稳分析

为避免风机叶片在强风作用下发生破坏,需对其采取停机保护措施。该文研究叶片处于非旋转状态时的挥舞摆振气弹失稳现象发生的条件。基于风力机叶片简化模型,采用迭代法求解叶片的自振频率及振型,建立了非旋转叶片挥舞摆振气弹效应响应的振型叠加法,该方法可以便捷地进行叶片多工况气动弹性响应分析。计算了在不同风速不同攻角条件下叶片的挥舞摆振气弹效应响应,得到了叶片挥舞摆振响应随风速和风攻角的变化规律以及不稳定风攻角的分布特征。结果表明:在某些风攻角下,风机叶片挥舞摆振失稳现象在风速较低的情况就有可能发生,其响应幅值与结构阻尼联系紧密。另外,挥舞摆振失稳会大大增加作用于叶片上的风荷载,并进一步造成叶片结构的损伤破坏。     

Safety evaluation of a collapsed turbine wind on the buried pipeline

In order to study the impact of the collapse of a wind turbine on the buried pipeline, three conditions are explored. With the formula of penetrating power, the impact force and impact depth resulted from the wind turbine collapse are estimated for safety evaluation. The evaluation results show that if the impact is only from the wind turbine collapse, the pipeline is not damaged, but it is difficult to ensure the normal operation of the pipeline. If the damage is caused by the wing turbine with blades or only by blades, the downward penetrating force is so large that the pipeline is directly sheared off. Although the probability of wind turbine collapse is low, it is harmful to the pipeline and appropriate protective measures should be adopted.     

国内风电叶片产业现状

介绍了全球风能产业前景及复合材料风机叶片的未来;分析了国内风电叶片企业情况及叶片市场供需情况;较详细叙述了国内叶片原材料供需问题,并对风电产能过剩问题提出了看法。     

Aerodynamic design and analysis of a 10 kW horizontal-axis wind turbine for Tainan,Taiwan

The purpose of the present study is to develop a small-scale horizontal-axis wind turbine (HAWT) suitable for the local wind conditions of Tainan, Taiwan. The wind energy potential was first determined through the Weibull wind speed distribution and then was adapted to the design of the turbine blade. Two numerical approaches were adopted in the design and analysis of the HAWT turbine blades. The blade element momentum theory (BEMT) was used to lay out the shape of the turbine blades (S822 and S823 airfoils). The geometry of the root region of the turbine blade was then modified to facilitate integration with a pitch control system. A mathematical model for the prediction of aerodynamic performance of the S822 and S823 airfoils, in which the lift and drag coefficients are calculated using BEMT equations, was then developed. Finally, computational fluid dynamics (CFD) was used to examine the aerodynamic characteristics of the resulting turbine blades. The resulting aerodynamic performance curves obtained from CFD simulation are in agreement with those obtained using BEMT. It is also observed that separation flow occurred at the turbine blade root at the tip speed ratios of 5 and 7.