基于深度变分自编码网络融合SCADA数据的风电齿轮箱故障预警

现有深度学习模型在融合风电SCADA数据时,仅考虑数据结构特征而未充分考虑数据分布规则,导致风电齿轮箱故障预警鲁棒性差。针对此问题,提出基于深度变分自编码网络融合SCADA数据的风电齿轮箱故障预警方法。选择SCADA多源异构监测数据作为深度变分自编码网络的训练输入,通过将输入数据映射为高斯分布参数并进行采样重构输出,使得网络在学习数据结构特征的同时能够充分挖掘数据分布规则,从而建立深度变分自编码网络预测模型;选择在线状态量的模型重构误差作为齿轮箱状态监测量,采用基于高斯分布理论的阈值评判准则进行齿轮箱故障预警;利用某风场实测数据进行对比分析,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,结合模型输出结果与SCADA数据提取残差分布特征向量,建立随机森林残差分布模型对机组齿轮箱运行状态进行监测;最后,对某大型风电场机组进行模型建立和仿真研究。结果表明,基于LSTM神经网络结合随机森林算法对风电机组齿轮箱状态监测有较强的实用性和较高的准确率,为后续开展齿轮箱健康度评价提供了新的方法和思路。     

基于KECA-GRNN的风电机组齿轮箱状态监测与健康评估

为及时准确地评价风电机组齿轮箱的健康程度,提出一种基于KECA-GRNN的性能监测与评估方法。该方法分为状态监测、故障预测、健康评估3个阶段。在状态监测阶段,将KECA算法应用到风电机组的性能监测中,并采用SPE统计量监测齿轮箱状态。在故障预测阶段,将KECA算法提取的主元数据作为GRNN模型输入,建立KECA-GRNN预测模型,并采用预测残差的变化趋势定义报警限,实现故障的早期预警。在健康评估阶段,将多变量预测残差进行融合,增强评估的可靠性。最后,将该方法应用于某风场一台1.5 WM风电机组在故障前近2个月的部分SCADA数据中,结果表明可提前2周获知齿轮箱发生异常,实现了对风电机组齿轮箱健康状态的准确评估。     

基于轴承温度的风机齿轮箱故障预警研究

齿轮箱轴承作为能量传递的关键部件,对风机状态评估具有重要意义。文章针对齿轮箱故障,提出了基于改进的粒子群算法(APSO)优化的BP神经网络齿轮箱轴承温度预测模型。首先,基于主成分分析法,选取SCADA系统中影响齿轮箱轴承温度的参数,建立正常状态下的齿轮箱轴承温度预测模型,通过对轴承温度残差值进行分析,得出风机故障告警和报警阈值,从而实现对齿轮箱故障的有效预警;最后,利用华北某风电场的数据进行实验仿真,对比分析粒子群(PSO)优化的BP神经网络预测模型和传统BP神经网络预测模型。结果表明,提出的预测方法拥有精度高、收敛速度快等优点。     

基于深度卷积自编码器的风电机组故障预警方法研究

通过风电机组状态监测进行故障预警,可防止故障进一步发展,降低风场运维成本。为充分挖掘风电机组监控与数据采集（SCADA）各状态参数时序信息,以及不同参数之间的非线性关系,该文将深度学习中自动编码器（AE）与卷积神经网络（CNN）相结合,提出基于深度卷积自编码（DCAE）的风电机组状态监测故障预警方法。首先基于历史SCADA数据离线建立基于DCAE的机组正常运行状态模型,然后分析重构误差确定告警阈值,使用EMWA控制图对实时对机组状态监测并进行故障预警。以北方某风电场2 MW双馈型风电机组叶片故障为实例进行实验分析,结果表明该文提出DCAE状态监测故障预警方法,可有效对机组故障提前预警,且优于现有基于深度学习的风电机组故障预警方法,可显著提升重构精度、减少模型参数和训练时间。     

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。     

基于数据融合的风电变桨系统故障预警研究

随着风电机组装机容量的不断攀升,同时带来并网发电率低、机组故障率高等缺点,导致风电机组整体利用率较低。为此提出一种基于数据融合的风电变桨系统故障预警方法。首先结合SCADA系统中的运行统计信息和历史数据,采用Relief特征参数选择方法筛选出与风电变桨系统故障相关的特征参数;然后采用数据融合的方法,建立基于MSET技术的风电变桨系统故障预测模型,并采用滑动窗口法进行故障预警阈值的确定;最后以上海某风场1.5 MW双馈异步风电机组进行实例分析,结果表明该方法可提前发现风电变桨系统故障征兆,实现对风电变桨系统的早期故障预警。     

基于改进集成KNN回归算法的风电机组齿轮箱状态监测

风电机组齿轮箱是容易发生故障的重要部件,维修费用高昂,因此有必要对其进行实时状态监测。针对集成K近邻(KNN)算法对随机采样不敏感的问题,提出了一种基于规则采样的改进集成KNN模型。首先利用距离相关系数进行变量选择,然后基于正则化互信息对变量进行排序,将其用于规则采样,构造子训练集,最后基于统计过程控制方法设置预警阈值对实时残差进行分析,根据健康度曲线对风电机组齿轮箱健康度进行监测,并利用某风电机组实际数据对所提方法进行验证。结果表明：所提方法显著提升了模型估计精度,该模型优于常规集成KNN模型,可以实现齿轮箱的早期故障预警。     

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。     

Monitoring wind turbine gearboxes

Concerns amongst wind turbine (WT) operators about gearbox reliability arise from complex repair procedures, high replacement costs and long downtimes leading to revenue losses. Therefore, reliable monitoring for the detection, diagnosis and prediction of such faults are of great concerns to the wind industry. Monitoring of WT gearboxes has gained importance as WTs become larger and move to more inaccessible locations. This paper summarizes typical WT gearbox failure modes and reviews supervisory control and data acquisition (SCADA) and condition monitoring system (CMS) approaches for monitoring them. It then presents two up‐to‐date monitoring case studies, from different manufacturers and types of WT, using SCADA and CMS signals. The first case study, applied to SCADA data, starts from basic laws of physics applied to the gearbox to derive robust relationships between temperature, efficiency, rotational speed and power output. The case study then applies an analysis, based on these simple principles, to working WTs using SCADA oil temperature rises to predict gearbox failure. The second case study focuses on CMS data and derives diagnostic information from gearbox vibration amplitudes and oil debris particle counts against energy production from working WTs. The results from the two case studies show how detection, diagnosis and prediction of incipient gearbox failures can be carried out using SCADA and CMS signals for monitoring although each technique has its particular strengths. It is proposed that in the future, the wind industry should consider integrating WT SCADA and CMS data to detect, diagnose and predict gearbox failures.Copyright © 2012 John Wiley & Sons, Ltd.     

PCA-PSO/GS-SVM组合方法在风电齿轮箱故障预测中的应用研究

在标准支持向量机(SVM)的基础上,引入主成分分析法(PCA)、粒子群算法(PSO)以及网格算法(GS),构建针对风力机故障的PCA-PSO/GS-SVM组合预测模型。相对于标准SVM,该模型采用PSO以及GS算法寻优参数,能够更准确地建立各变量间的相关关系以提高模型的预测准确性。以中国北方某风场2 MW风电齿轮箱在2017年上半年某2个月的SCADA监测数据为例进行分析。结果表明,对于以齿轮箱输出功率为例的骤变信号的预测,采用PSO算法寻优后的绝对误差均值是采用GS算法的3.0647倍,而对于以高速侧轴端温度为例的缓变信号的预测,则采用PSO算法更加合理;同时发现剔除训练样本数据中的奇异点能够有效提高模型的预测精度及其泛化能力。     

Wind turbine gearbox failure and remaining useful life prediction using machine learning techniques

This research investigates the prediction of failure and remaining useful life (RUL) of gearboxes for modern multi‐megawatt wind turbines. Failure and RUL are predicted through the use of machine learning techniques and large amounts of labelled wind turbine supervisory control and data acquisition (SCADA) and vibration data. The novelty of this work stems from unprecedented access to one of the world's largest wind turbine operational and reliability databases, containing thousands of turbine gearbox failure examples and complete SCADA and vibration data in the build up to those failures. Through access to that data, this paper is unique in having enough failure examples and data to draw the conclusions detailed in the remainder of this abstract. This paper shows that artificial neural networks provide the most accurate failure and RUL prediction out of three machine learning techniques trialled. This work also demonstrates that SCADA data can be used to predict failure up to a month before it occurs, and high frequency vibration data can be used to extend that accurate prediction capability to 5 to 6 months before failure. This paper demonstrates that two class neural networks can correctly predict gearbox failures between 72.5% and 75% of the time depending on the failure mode when trained with SCADA data and 100% of the time when trained with vibration data. Data trends in the build up to failure and weighting of the SCADA data inputs are also provided. Lastly, this work shows how multi‐class neural networks demonstrate more potential in predicting gearbox failure when trained with vibration data as opposed to training with SCADA data.     

Nonlinear system identification for model-based condition monitoring of wind turbines

This paper proposes a data driven model-based condition monitoring scheme that is applied to wind turbines. The scheme is based upon a non-linear data-based modelling approach in which the model parameters vary as functions of the system variables. The model structure and parameters are identified directly from the input and output data of the process. The proposed method is demonstrated with data obtained from a simulation of a grid-connected wind turbine where it is used to detect grid and power electronic faults. The method is evaluated further with SCADA data obtained from an operational wind farm where it is employed to identify gearbox and generator faults. In contrast to artificial intelligence methods, such as artificial neural network-based models, the method employed in this paper provides a parametrically efficient representation of non-linear processes. Consequently, it is relatively straightforward to implement the proposed model-based method on-line using a field-programmable gate array.     

基于油液光谱监测的风电机组齿轮箱磨损状态的研究

风电机组齿轮箱的磨损微粒主要是铁颗粒,铁颗粒含量的增长趋势能直接反映出风电机组齿轮箱的磨损状态.以Spectro油液光谱分析仪监测风电机组齿轮箱在用齿轮油中的铁元素含量,通过一段时间内铁元素的增加量和风电机组可利用小时数,可计算得到单位可利用小时数下的铁元素增加量ΔQFe;引入可靠性理论研究了ΔQFe的分布规律,并以风...     

基于WD-LSTM的风电机组叶片结冰状态评测

为有效识别叶片结冰状态,尽早采取除冰措施,提出基于小波去噪的长短期记忆神经网络（WD-LSTM）的评测方法。首先基于过采样与欠采样相结合的方法解决SCADA系统数据中的类别不平衡问题,通过对叶片结冰相关的26项指标进行分析,并从结冰机理和数据探索的角度筛选特征量,小波去噪处理后建立WD-LSTM模型,进一步完成模型的训练和测试。分别以15号和21号风电机组为例进行模型验证,通过与LSTM、概率神经网络（PNN）模型和BP神经网络模型进行对比。结果表明,WD-LSTM方法在风电机组叶片结冰评测中的准确率可达98%,优于其他方法。     

An artificial neural network‐based condition monitoring method for wind turbines,with application to the monitoring of the gearbox

Major failures in wind turbines are expensive to repair and cause loss of revenue due to long downtime. Condition‐based maintenance, which provides a possibility to reduce maintenance cost, has been made possible because of the successful application of various condition monitoring systems in wind turbines. New methods to improve the condition monitoring system are continuously being developed. Monitoring based on data stored in the supervisory control and data acquisition (SCADA) system in wind turbines has received attention recently. Artificial neural networks (ANNs) have proved to be a powerful tool for SCADA‐based condition monitoring applications. This paper first gives an overview of the most important publications that discuss the application of ANN for condition monitoring in wind turbines. The knowledge from these publications is utilized and developed further with a focus on two areas: the data preprocessing and the data post‐processing. Methods for filtering of data are presented, which ensure that the ANN models are trained on the data representing the true normal operating conditions of the wind turbine. A method to overcome the errors from the ANN models due to discontinuity in SCADA data is presented. Furthermore, a method utilizing the Mahalanobis distance is presented, which improves the anomaly detection by considering the correlation between ANN model errors and the operating condition. Finally, the proposed method is applied to case studies with failures in wind turbine gearboxes. The results of the application illustrate the advantages and limitations of the proposed method. Copyright © 2017 John Wiley & Sons, Ltd.     

基于优化VMD复合多尺度散布熵及LSTM的风力发电机齿轮箱故障诊断方法研究

以风力发电机齿轮箱加速度信号为研究对象,提出一种数据驱动的风力发电机齿轮箱故障诊断方法,该方法以灰狼优化的变分模态分解方法(AGWO-VMD)、复合多尺度规范化散布熵(NCMDE)及长短期记忆网络(LSTM)为基础,实现齿轮箱故障的快速诊断.首先将时域信号转换至角域;然后通过AGWO-VMD方法对角域信号进行自适应分解...