基于IICEEMDAN-PCA-GRU的风电机组齿轮箱故障预警方法研究

为充分挖掘数据采集与监控（SCADA）数据的隐藏信息,减少特征间的冗余性,提升模型预测和预警的精度,提出一种双重改进的完全噪声辅助聚合经验模态分解（IICEEMDAN）、主成分分析（PCA）、门控循环网络（GRU）融合的风电机组齿轮箱故障预警方法。使用皮尔逊相关系数法作特征提取,采用IICEEMDAN对特征进行分解,得到特征在不同时间尺度上的连续性信号;利用PCA提取分解特征的关键因素作为网络训练输入;GRU网络对输入时间序列特征进行建模训练,实现对齿轮箱油池温度的预测,使用统计学方法分析油池温度预测值与实际值的误差,根据实际情况设定预警阈值;使用滑动窗口理论实现齿轮箱故障预警。采用华北某风场实际数据进行验证,结果验证了所提方法对齿轮箱早期故障预警的有效性。     

基于CAE与BiLSTM结合的风电机组齿轮箱故障预警方法研究

针对风电机组故障频发且早期故障监测难的问题,为实现风电机组智能监测,提出基于卷积自编码(CAE)与双向长短期神经网络(BiLSTM)的风电机组齿轮箱故障预警方法。首先对风电场数据采集与监视控制(SCADA)系统的数据进行预处理,选择能表征风电机组齿轮箱运行状态的监测量作为输出量,根据相关性分析选择与输出量相关性高的监测量作为输入参数;然后根据特征选择特性和参数非线性特性构建深度学习网络模型,对输出的预测值和残差进行统计分析,设置自适应阈值来监测风电机组异常状态的趋势变化。将CAE-BiLSTM模型应用于某风电场的算例分析中,并与其他模型的预测效果进行对比。结果表明：该方法解决了模型输入与结构冗余问题,提高了模型精度,能够有效预警风电机组齿轮箱早期故障。     

基于DBSCAN和SDAE的风电机组异常工况预警研究

提出一种基于密度的聚类方法(DBSCAN)和堆栈式降噪自编码器(SDAE)结合的风电机组性能预测及异常运行工况预警方法.首先采用DBSCAN算法对机组监控与数据采集(SCADA)系统历史运行数据进行清洗,然后利用SDAE建立风电机组的正常运行性能预测模型.基于该模型,采用时移滑动窗口方法构建能准确反映风电机组异常状态的...     

基于S-SLLE的风电机组齿轮箱故障诊断方法研究

针对风电机组齿轮箱结构复杂、受交变载荷和恶劣工作环境影响容易出现故障导致停机的问题,提出基于统计学K-均值聚类理论的统计型监督式局部线性嵌入流形学习(S-SLLE)特征维数约简方法,首先通过对齿轮箱振动信号时频域故障特征提取,剔除冗余特征向量,减少诊断模型的复杂度和计算量,再利用RBF核支持向量机分类器建立诊断模型,对...     

风电机组故障统计分析研究

基于某实际运行的风电场,统计了场内风电机组全年的故障数量,结合风电场月度发电量、月平均风速和月平均气温,探讨了风电机组故障数量与机组运行状况和环境温度之间的关联性,同时分析了主要系统故障高发的原因。最后提出了降低机组故障发生率以及改善运行维护工作的一些措施。     

基于SCADA数据特征提取的风电机组偏航齿轮箱故障诊断方法研究

针对风力发电机组偏航系统故障处理难度大和危害严重等问题,开发出基于数据采集与监视控制(SCADA)数据的偏航齿轮箱神经网络诊断模型.利用ReliefF算法和核密度-均值法提取能反映出偏航齿轮箱运行工况的7个SCADA参数,并提取出6种故障特征指标作为神经网络诊断模型输入量,来诊断偏航齿轮箱的正常状态、磨损故障以及断齿故...     

基于卷积神经网络的风电机组齿轮箱状态监测方法

为了实现对风电机组齿轮箱的状态监测,文章提出了一种基于卷积神经网络的风电机组齿轮箱状态监测方法。首先,提取风电机组数据采集与监视控制(SCADA)数据和振动信号作为参数,组成齿轮箱状态矩阵。其次,建立了一种卷积神经网络模型,该模型针对输入数据设计了特定结构和池化层规则,提高了计算效率,能够从齿轮箱状态信息中提取特征并判断其状态。最后,利用实际运行的风电机组数据对卷积神经网络模型进行了训练和验证,最终取得了96.3%的识别精度。同时,将该模型应用于对同一风场其他机组的状态监测,结果验证了卷积神经网络模型对齿轮箱状态监测的有效性。     

基于改进小波包的风电机组齿轮箱复合故障特征提取研究

针对小波包分解振动信号时会产生频谱混叠从而导致齿轮箱复合故障特征能量谱提取困难的问题,提出基于旁路滤波改进小波包的方法对双馈风电机组齿轮箱复合故障振动信号进行研究,并以风电场的大量齿轮箱振动信号为基础,运用传统小波包及旁路滤波改进小波包分别对齿轮箱振动信号提取特征能量谱。实验结果表明：运用旁路滤波改进小波包对双馈风电机组齿轮箱复合故障振动信号进行分析,可有效避免传统小波包分析振动信号的频谱混叠现象,准确提取每种故障状态的特征能量谱。     

一种基于非线性偏最小二乘的风电机组齿轮箱状态监测方法北大核心CSCD

风电机组状态监测是提升机组运行水平和经济效益的重要手段。文章提出了一种基于非线性偏最小二乘(PLS)的风电机组齿轮箱状态监测方法,利用数据采集与监控系统(SCADA)数据对齿轮箱油温进行建模和监测。首先,基于无监督聚类对SCADA数据进行预处理,利用相关性分析选取与齿轮箱油温相关的输入变量;然后,构建用于表征非线性关系的输入变量,建立正常运行工况下齿轮箱油温的非线性PLS模型;最后,根据模型输出结果与齿轮箱油温的残差分布,设置合理阈值,用于齿轮箱状态监测。应用该模型对某大型风电机组齿轮箱进行状态监测。监测结果表明,相比于BP神经网络模型,该模型具有更高的拟合优度和预测精度。     

基于SCADA数据的风电机组齿轮箱状态监测方法

为解决故障劣化渐变过程的长时间序列对齿轮箱状态监测模型的影响问题,提升其决策精度,提出一种基于数据采集与监控(SCADA)数据的组合建模方法.首先,采用主成分分析法(PCA)选取与齿轮箱温度密切相关的输入观测向量,并应用长短期记忆(LSTM)神经网络分别对齿轮箱正常工况和异常工况独立建立温度模型;其次,结合模型输出结果...     

Condition monitoring of spar‐type floating wind turbine drivetrain using statistical fault diagnosis

Operation and maintenance costs are significant for large‐scale wind turbines and particularly so for offshore. A well‐organized operation and maintenance strategy is vital to ensure the reliability, availability, and cost‐effectiveness of a system. The ability to detect, isolate, estimate, and perform prognoses on component degradation could become essential to reduce unplanned maintenance and downtime. Failures in gearbox components are in focus since they account for a large share of wind turbine downtime. This study considers detection and estimation of wear in the downwind main‐shaft bearing of a 5‐MW spar‐type floating turbine. Using a high‐fidelity gearbox model, we show how the downwind main bearing and nacelle axial accelerations can be used to evaluate the condition of the bearing. The paper shows how relative acceleration can be evaluated using statistical change‐detection methods to perform a reliable estimation of wear of the bearing. It is shown in the paper that the amplitude distribution of the residual accelerations follows a t‐distribution and a change‐detection test is designed for the specific changes we observe when the main bearing becomes worn. The generalized likelihood ratio test is extended to fit the particular distribution encountered in this problem, and closed‐form expressions are derived for shape and scale parameter estimation, which are indicators for wear and extent of wear in the bearing. The results in this paper show how the proposed approach can detect and estimate wear in the bearing according to desired probabilities of detection and false alarm.     

基于粒子群混合算法的风力发电机齿轮箱故障诊断

针对传统方法在风力发电机齿轮箱故障诊断中存在精度不高的问题,引入了一种改进粒子群算法优化神经网络的方法。该算法的惯性权重可进行自适应调整,以平衡全局和局部搜索能力。同时,收缩因子可加快算法的收敛速度,以更快收敛到全局最优。仿真结果表明,该方法能较好地识别故障模式,具有一定的实用性。     

Vibration‐based wind turbine planetary gearbox fault diagnosis using spectral averaging

Planetary gearboxes (PGBs) are widely used in the drivetrain of wind turbines. Any PGB failure could lead to a significant breakdown or major loss of a wind turbine. Therefore, PGB fault diagnosis is very important for reducing the downtime and maintenance cost and improving the safety, reliability, and lifespan of wind turbines. The wind energy industry currently utilizes vibratory analysis as a standard method for PGB condition monitoring and fault diagnosis. Among them, the vibration separation is considered as one of the well‐established vibratory analysis techniques. However, the drawbacks of the vibration separation technique as reported in the literature include the following: potential sun gear fault diagnosis limitation, multiple sensors and large data requirement, and vulnerability to external noise. This paper presents a new method using a single vibration sensor for PGB fault diagnosis using spectral averaging. It combines the techniques of enveloping, Welch's spectral averaging, and data mining‐based fault classifiers. Using the presented approach, vibration fault features for wind turbine PGB are extracted as condition indicators for fault diagnosis and condition indicators are used as inputs to fault classifiers for PGB fault diagnosis. The method is validated on a set of seeded localized faults on all gears: sun gear, planetary gear, and ring gear. The results have shown a promising PGB fault diagnosis performance with the presented method. Copyright © 2015 John Wiley & Sons, Ltd.     

Load sharing behavior analysis method of wind turbine gearbox in consideration of multiple-errors

Conducting a further analysis on loading sharing among compound planetary gear system in wind turbine gearbox, and making a meshing error analysis on the eccentricity error, gear thickness error, base pitch error, assembly error, and bearing error of wind turbine gearbox respectively. In view of the floating meshing error resulting from meshing clearance variation caused by the simultaneous floating of all gears, this paper establishes a refined mathematical model of two-stage power split loading sharing coefficient calculation in consideration of multiple errors. Also obtains the regular curves of the load sharing coefficient and floating orbits of center gears, and conducts a load sharing coefficient test experiment of compound planetary gear system to verify the research results, which can provide scientific theory evidence for proper tolerance distribution and control in design and process.     

An engineering condition indicator for condition monitoring of wind turbine bearings

Condition monitoring (CM) of wind turbine becomes significantly important part of wind farms in order to cut down operation and maintenance costs. The large amount of CM system vibration data collected from wind turbines are posing challenges to operators in signal processing. It is crucial to design sensitive and reliable condition indicator (CI) in wind turbine CM system. Bearing plays an important role in wind turbine because of its high impact on downtime and component replacement. CIs for wind turbine bearing monitoring are reviewed in the paper, and the advantages and disadvantages of these indicators are discussed in detail. A new engineering CI (ECI), which combined the energy and kurtosis representation of the vibration signal, is proposed to meet the requirement of easy applicability and early detection in wind turbine bearing monitoring. The quantitative threshold setting method of the ECI is provided for wind turbine CM practice. The bearing run‐to‐failure experiment data analysis demonstrates that ECI can evaluate the overall condition and is sensitive to incipient fault of bearing. The effectiveness in engineering of ECI is validated though a certain amount of real‐world wind turbine generator and gearbox bearing vibration data.     

A novel wind turbine health condition monitoring method based on common features distribution adaptation

Aimed at the difficulty of diagnosing the transmission system of wind turbine under variable working conditions, a novel health condition monitoring method based on common features distribution adaptation is proposed in this article. In the method, envelope analysis is first performed on the collected signals, and then the time-frequency features are extracted to be combined as new input samples. The feature set under the working condition similar to target working condition is selected as the auxiliary sample set in source domain through the evaluation of the transferability. The kernel function is used to map the labeled auxiliary samples and unlabeled target samples to a reproduced kernel Hilbert space, which effectively reduces the data distribution discrepancy between source and target domains. The problem of class imbalance in each domain is taken into account when performing fault recognition, which improves the effect of transfer learning. Finally, the adjusted source domain is used to train the classifier, which is applied to the target domain to get the predicted labels of the test data. Experiment shows that the proposed method has better working performance than traditional fault diagnosis methods.     

Using transfer path analysis to assess the influence of bearings on structural vibrations of a wind turbine gearbox

Noise and vibration issues can be dealt with using several approaches. Using the source–transfer path–receiver approach, a vibration issue could be solved by attenuating the source, modifying the transfer path or by influencing the receiver. Applying this approach on a wind turbine gearbox would respectively correspond with lowering the gear excitation levels, modifying the gearbox housing or by trying to isolate the gearbox from the rest of the wind turbine. This paper uses a combination of multi‐body modelling and typical transfer path analysis (TPA) to investigate the impact of bearings on the total transfer path and the resulting vibration levels. Structural vibrations are calculated using a flexible multi‐body model of a three‐stage wind turbine gearbox. Because the high‐speed mesh is often the main source of vibrations, focus is put on the four bearings of this gear stage. The TPA method using structural vibration simulation results shows which bearing position is responsible for transmitting the highest excitation levels from the gears to the gearbox housing structure. Influences of bearing stiffness values and bearing damping values on the resulting vibration levels are investigated by means of a parameter sensitivity study and are confirmed with the results from the TPA. Because both the TPA and the parameter sensitivity analysis revealed a big influence on radial stiffness for a certain bearing, this was investigated in more detail and showed the big importance of correct axial bearing position. The main conclusions of this paper are that the total vibration behaviour of a wind turbine gearbox can be altered significantly by changing both bearing properties such as stiffness, damping and position, and bearing support stiffness. Copyright © 2014 John Wiley & Sons, Ltd.     

Sensor and actuator fault diagnosis for wind turbine systems by using robust observer and filter

In this paper, we consider sensor and actuator fault detection and estimation issues for large scale wind turbine systems where individual pitch control (IPC) is used for load reduction. The faults considered are the blade root bending moment sensor faults and blade pitch actuator faults. In the first part, with the aid of a dynamical model of the wind turbine system, a so‐called H_∞/H_? observer in the finite frequency range, is applied to generate the residual for fault detection. The observer is designed to be sensitive to faults but insensitive to disturbances, such as wind turbulence. When there is a detectable fault, the observer sends an alarm signal if the residual evaluation is larger than a predefined threshold. In addition to the fault detection, we also consider the fault estimation problem, where a dynamic filter is used to estimate the fault magnitude. The effectiveness of the proposed approach is demonstrated by simulation results for several fault scenarios. Copyright © 2010 John Wiley & Sons, Ltd.     

Multi‐body modelling and analysis of a planet carrier in a wind turbine gearbox

There have been some recent efforts to numerically model and analyse the wind turbine gearbox. To date, much of the focus has been on increasing model refinement and demonstrating its added value. This paper takes a step back and examines in detail the modelling and analysis of an important wind turbine gearbox component, the planet carrier, in a multi‐body setting. The planet carrier studied in this work comes from the 750 kW wind turbine gearbox used in the National Renewable Energy Laboratory's Gearbox Reliability Collaborative project. The study is performed in two parts. First, the influence of subcomponents mated to the planet carrier in the gearbox assembly is investigated in detail. These components consist of the planet pins, bearings and the main shaft. In the second part of the study, the flexible body modelling of the planet carrier for use in multi‐body simulations is examined through the use of condensed finite element and multi‐body simulation models. Both eigenvalue analyses and time domain simulations are performed. Comparisons are made regarding the eigenfrequencies, categorized mode shapes and the maximum and minimum planet carrier rim deflections from the time domain simulations. The mode shapes are categorized into seven distinct deformation patterns. An actual load case from the dynamometer tests, a 100% rated torque loading, is used in the time domain simulations. The results from this comprehensive study provide an insight into the proper modelling of a wind turbine planet carrier in a multi‐body setting. Copyright © 2012 John Wiley & Sons, Ltd.