Wind Turbine Planetary Gearbox Fault Diagnosis via Proportion-Extracting Synchrosqueezing Chirplet Transform

Wind turbine planetary gearboxes usually work under time-varying conditions,leading to nonstationary vibration signals.These signals often consist of multiple time-varying components with close instantaneous frequencies.Therefore,high-quality time-frequency analysis(TFA)is needed to extract the time-frequency feature from such nonstationary signals for fault diagnosis.However,it is difficult to obtain high-quality timefrequency representations(TFRs)through conventional TFA methods due to low resolution and time-frequency blurs.To address this issue,we propose a new TFA method termed the proportion-extracting synchrosqueezing chirplet transform(PESCT).Firstly,the proportion-extracting chirplet transform is employed to generate highresolution underlying TFRs.Then,the energy concentration of the underlying TFRs is enhanced via the synchrosqueezing transform.Finally,wind turbine planetary gearbox fault can be diagnosed by analysis of the dominant time-varying components revealed by the concentrated TFRs with high resolution.The proposed PESCT is suitable for achieving high-quality TFRs for complicated nonstationary signals.Numerical and experimental analyses validate the effectiveness of the PESCT in characterizing the nonstationary signals from wind turbine planetary gearboxes.

Discussion on Maintenance Cases of Wind Turbine Components

At present,the greenhouse effect is caused by excessive emission of carbon dioxide.As a result the Arctic ice has melted and sea levels have risen.If it continues to deteriorate,it will cause human catastrophe.In order to avoid direct crisis and development,green energy is the only necessary way.Here,wind power plays an important role.Onshore wind power has been developed in Taiwan for more than 15 years.There are 341 onshore wind turbines that have been built so far.The total installed capacity is 678 MW high.Among them,Tai power occupies a total of 169 stations with a total installed capacity of 294 MW.Offshore wind turbines are also under construction.By 2025,the capacity will be 5 to 6 GW.It can be seen that the supply of wind power in the overall power market will become an important area in the future.Therefore,how to improve the availability and capacity factors of wind turbine power generation will become a top priority for owners.Since most of the world’s best wind farms are in the Taiwan Strait,this is a unique feature of Taiwan,although Taiwan lacks traditional fuels,petroleum,coal,natural gas and other resources.If these abundant solar and wind energy resources can be effectively utilized,in addition to reducing carbon emissions and contributing to the world,the development of green energy can also drive the development of the domestic green energy industry,also through the development of green energy to establish domestic operation and maintenance technology for wind turbines.

Development of Optimal Maintenance Policies for Offshore Wind Turbine Gearboxes Based on the Non-homogeneous Continuous-Time Markov Process

Gearbox in offshore wind turbines is a component with the highest failure rates during operation. Analysis of gearbox repair policy that includes economic considerations is important for the effective operation of offshore wind farms. From their initial perfect working states, gearboxes degrade with time, which leads to decreased working efficiency. Thus, offshore wind turbine gearboxes can be considered to be multi-state systems with the various levels of productivity for different working states. To efficiently compute the time-dependent distribution of this multi-state system and analyze its reliability, application of the nonhomogeneous continuous-time Markov process(NHCTMP) is appropriate for this type of object. To determine the relationship between operation time and maintenance cost, many factors must be taken into account, including maintenance processes and vessel requirements. Finally, an optimal repair policy can be formulated based on this relationship.

Real-Time Electrostatic Monitoring of Wear Debris for Wind Turbine Gearbox

Engineering practice has shown that early faults of gearboxes are a leading maintenance cost driver that can easily lower the profit from a wind turbine operation.A novel oil-lubricated electrostatic monitoring of wear debris for a wind turbine gearbox is presented.The continuous wavelet transform(CWT)is used to eliminate the noises of the original electrostatic signal.The kurtosis and root mean square(RMS)values of the time domain signal are extracted as the characteristic parameters to reflect the deterioration of the gearbox.The overall tendency of electrostatic signals in accelerated life test is analyzed.In the eighth cycle,the abnormal wear in the wind turbine gearbox is detected by electrostatic monitoring.A comparison with the popular MetalScan monitoring is given to illustrate the effectiveness of the electrostatic monitoring method.The results demonstrate that the electrostatic monitoring method can detect the fault accurately.

Reliability Analysis of Wind Turbine Gearbox Based on the Optimal Confidence Limit Method

Based on the zero-failure data of 30 Chinese 1. 5 MW wind turbine gearboxes( WTGs),the optimal confidence limit method was developed to predict the reliability and reliability lifetime of WTG. Firstly,Bayesian method and classical probability estimation method were introduced to estimate the value interval of shape parameter considering the engineering practice. Secondly,taking this value interval into the optimal confidence limit method,the reliability and reliability lifetime of WTG could be obtained under different confidence levels. Finally,the results of optimal confidence limit method and Bayesian method were compared. And the comparison results show that the rationality of this estimated range.Meantime, the rule of confidence level selection in the optimal confidence limit method is provided, and the reliability and reliability lifetime prediction of WTG can be acquired.

Total process of fault diagnosis for wind turbine gearbox,from the perspective of combination with feature extraction and machine learning:A review

With the increasing of the installed capacity of wind power,the condition monitoring and maintains technique is becoming more important.Wind Turbines(WT)gearbox is one of the key wind power components as it plays the role of power transmission and speed regulation.Towards this,a number of scholars have pay attention to the fault diagnosis of WT gearbox.The efficiency of Machine Learning(ML)algorithms is highly correlated with signal type,data quality,and extracted features employed.The implementation of ML techniques has proven to be advantageous in simplifying the comprehension prerequisites for fault diagnosis technology concerning fault mechanisms.More and more current studies predominantly concentrate on the utilization and fine-tuning of ML algorithms,while providing limited insights into the features of the acquired data.Therefore,it is necessary to review the research in recent years from the perspective of the combination of feature extraction and ML algorithms,and provide a detailed direction for future WT gearbox fault diagnosis technology research.In this paper,data processing algorithms and typical fault diagnosis methods based on ML methods for WT gearbox are reviewed.For the using of ML method in WT gearbox fault diagnosis,the data prepared for training is very important.The paper firstly reviewed the data analysing method which will support the ML method.The data analysing methods include data acquisition,data preprocessing and feature extraction method.Feature extraction plays a pivotal role in the realm of gearbox fault diagnosis,as it serves as the essence of effective detection.This review will primarily focus on exploring methods that enable the utilization of efficient features in combination with ML techniques to achieve accurate gearbox fault diagnosis.Then typical ML method for WT gearbox fault diagnosis are carefully reviewed.Moreover,some prospects for future research directions are discussed in the end.

Preliminary Design Support by Integrating a Reliability Analysis for Wind Turbine

In the context of industrial competitiveness, taking into account the process design throughout the product life cycle is inevitable, from the expression of the need to recycle, the capitalization and knowledge management increasingly a target much sought after companies because of increased knowledge. Indeed, during the approval phase and use studies and scientific researches make have generated knowledge especially that concerning the reliability of system components. In this context, the capitalization and reuse of knowledge are necessary and have a particular interest in design and particularly in the preliminary design phase. Studies are already completed suggest a design process ranging from the need to solve the problem. At each phase of the process, structural characteristics are defined by the designer through the available knowledge already capitalized to make choice of component and their arrangement. This article proposes integrating the analysis of system reliability in this process. The objective is the use of knowledge in the vision safety and hazards of operating through the study of reliability and decision making for the selection of solution.

Wind Turbine Gearbox Fault Diagnosis Based on Multi-sensor Signals Fusion

This paper proposes a novel fault diagnosis method by fusing the information from multi-sensor signals to improve the reliability of the conventional vibration-based wind turbine drivetrain gearbox fault diagnosis methods.The method fully extracts fault features for variable speed,insufficient samples,and strong noise scenarios that may occur in the actual operation of a wind turbine planetary gearbox.First,multiple sensor signals are added to the diagnostic model,and multiple stacked denoising auto-encoders are designed and improved to extract the fault information.Then,a cycle reservoir with regular jumps is introduced to fuse multidimensional fault information and output diagnostic results in response to the insufficient ability to process fused information by the conventional Softmax classifier.In addition,the competitive swarm optimizer algorithm is introduced to address the challenge of obtaining the optimal combination of parameters in the network.Finally,the validation results show that the proposed method can increase fault diagnostic accuracy and improve robustness.

An Experiment on Power Properties in a Small-Scaled Wind Turbine Generator

This study configures a simple wind tunnel using a blower for generating wind energy, which is equivalent to natural wind, and a test system that measures properties of power. Also, the mechanical and electrical power in a small-scaled wind turbine are empirically measured to analyze the relationship between the mechanical and electrical power.

基于遗传算法的风电齿轮传动系统参数优化设计

齿轮箱是风力发电系统的重要部件,其体积大、重量高等问题制约了风电清洁能源的发展.以1.5 WM风力发电机组为研究对象,建立齿轮传动系统轻量化数学模型,并采用遗传算法进行优化求解.结果表明,采用遗传算法是可行的,优化后齿轮传动系统体积减少了4.59%,这将进一步减小齿轮传动系统箱体体积和总质量.通过计算行星轮系的传动效率,验证了优化结果的可行性,该研究将为风电齿轮传动系统轻量化设计提供新方法.

Fault Diagnosis Based on Interpretable Convolutional Temporal-spatial Attention Network for Offshore Wind Turbines

Fault diagnosis(FD)for offshore wind turbines(WTs)are instrumental to their operation and maintenance(O&M).To improve the FD effect in the very early stage,a condition monitoring based sample set mining method from supervisory control and data acquisition(SCADA)time-series data is proposed.Then,based on the convolutional neural network(CNN)and attention mechanism,an interpretable convolutional temporal-spatial attention network(CTSAN)model is proposed.The proposed CTSAN model can extract deep temporal-spatial features from SCADA time-series data sequentially by:(1)a convolution feature extraction module to extract features based on time intervals;(2)a spatial attention module to extract spatial features considering the weights of different features;and(3)a temporal attention module to extract temporal features considering the weights of intervals.The proposed CTSAN model has the superiority of interpretability by exposing the deep temporal-spatial features extracted in a human-understandable form of the temporal-spatial attention weights.The effectiveness and superiority of the proposed CTSAN model are verified by real offshore wind farms in China.

改进MFO-LSTM网络的风电机组齿轮箱故障预警研究

风电机组齿轮箱在数据采集与监控系统(SCADA)的帮助下,通过监控齿轮箱油温是否超过阈值实现故障报警,其判断精度不高且问题发现不及时,因此使用长短期记忆网络模型(LSTM)融合SCADA数据实现对齿轮箱油温状态的预测。用齿轮箱正常运行状态下的数据训练LSTM模型,计算油温预测值与真实值之间的残差,根据正态分布的原则设置残差的上下预警阈值,用来对齿轮箱故障进行预警。为简化训练模型的复杂度,在SCADA数据中选用与齿轮箱油温相关性较为密切的参数作为LSTM模型的输入项。为降低因LSTM模型超参数设置不当造成的预测准确度表现不佳,提出改进飞蛾火焰算法(MFO)与LSTM的组合模型,在保留MFO算法强大的全局搜索能力的同时,使其避免陷入局部搜索的陷阱,通过改进MFO对LSTM模型参数进行迭代优化,最终构建合适的模型。最后通过某风电机组SCADA数据验证该方法能够有效预警齿轮箱的故障,并且与其他方法相比准确度更高,预警更及时,迭代效果更好。

应用滑动轴承的风电齿轮箱行星轮系动力学建模及解耦方法

在行星轮系动力学建模中,常以非线性油膜力或线性刚度-阻尼形式考虑其对系统动力学特性的影响,前者仿真精度高但计算成本也高,后者计算效率高却忽略了油膜力和轴颈-轴套偏心量的时变性,仿真精度有限。为此,以2MW级风电齿轮箱为研究对象,建立滑动轴承时变线性刚度-阻尼模型,提出计入轴颈-轴套时变偏心量的滑动轴承附加偏心修正力计算方法;利用行星架销轴-行星轮变形协调关系,将时变线性刚度-阻尼模型与附加偏心修正力进行耦合;建立应用滑动轴承的风电齿轮箱行星轮系动力学模型,对比了工况和轴承参数对模型计算精度与系统动态响应的影响,并通过试验加以验证。研究结果表明,齿轮副动态啮合力波动会使滑动轴承刚度-阻尼系数和附加偏心修正力产生周期性变化;在稳定和瞬态工况下,提出的模型可以很好地预测系统响应,尤其是行星轮振动响应;减小滑动轴承宽径比与间隙、增大输入转矩可以改善系统均载性能。

变转速下基于改进多阶概率方法的风电齿轮箱故障诊断研究

阶次跟踪是一种有效的解决变转速故障诊断问题的方法,其关键前提是存在转速信号作为参考。然而,由于强背景噪声和弱谐波关系的影响,现有转速估计方法的准确性和自适应性有待进一步提高。因此,提出一种融合多传感器信号的改进多阶概率方法(MOPA)用以估计瞬时转速。首先,依据不同传感器信号的基频统一性和主导分量差异性,通过时频图瞬时切片归一化融合的方式,构建具有强谐波关系的时频图;其次,为消除时变工况下时频图中横纵方向上的间歇恒频和短时宽频背景噪声,提出滑动消噪方法;最后,基于处理后的时频图执行MOPA,实现瞬时转速自动估计,结合阶次跟踪解决风电齿轮箱变转速故障诊断问题。经实测数据验证,改进MOPA估计的瞬时频率的准确性和自适应性均优于对方法,平均绝对百分比误差为0.56%,均小于对比方法的15.73%、13.99%和1.21%。结合阶次分析诊断了变转速下风电齿轮箱异常。

风电机组用滑动轴承研究现状与发展趋势

首先,分析滚动轴承在风电传动系统中应用的局限性,探讨滑动轴承“以滑代滚”的可行性。然后,从风电机组用滑动轴承结构设计、轴承材料、性能分析及优化、试验测试及应用4个关键环节,综述滑动轴承风电应用的现有技术手段和面临的困难。最后,对风电机组滑动轴承的材料改性、一体化设计、延寿技术发展趋势做出展望。

斜齿轮啮合弯矩对风电齿轮箱行星轮滑动轴承瞬态润滑性能影响分析

风电齿轮箱行星轮滑动轴承常被设计为以行星轮内孔和销轴分别作为轴套和轴颈,然而斜齿轮啮合弯矩容易使行星轮与销轴之间产生轴线不对中,导致边缘接触风险高,影响运行寿命。以6 MW级传动链齿轮箱行星轮滑动轴承为研究对象,考虑滑动轴承径向载荷、弯矩以及转速的动态影响,建立了行星轮滑动轴承瞬态摩擦-动力学耦合模型,并以风电机组传动链SIMPACK动力学模型提取的行星轮动态啮合力与时变转速作为行星轮滑动轴承的载荷与运动边界输入,分析了斜齿轮啮合弯矩、输入扭矩和滑动轴承半径间隙对行星轮滑动轴承润滑性能的影响规律,并进行了实验验证。研究结果表明,行星轮动态啮合力及其产生的啮合弯矩会造成行星轮轴心位置与偏斜角产生动态循环变化,并且随着载荷的增加,行星轮滑动轴承油膜/固体接触压力与不对中弯矩会逐渐增大;减小行星轮滑动轴承半径间隙可以有效提高其瞬态润滑性能。

基于雪消融算法优化长短时网络的齿轮箱油温预警方法

风电机组数据的复杂多变导致所采集数据的数据特征之间深度冗余。数据特征深度冗余导致常规预测模型容易陷入局部最优,进而使模型预测精度较低。为提高齿轮箱油温预测精度,首先,采用随机森林进行特征提取,利用改进的自适应噪声集合经验模态分解对选定的特征数据进行分解,使用主成分分析法对数据进行降维处理;然后,运用雪消融优化算法来搜索长短期记忆递归神经网络模型最佳超参数设置。实验结果证明,该方法可以有效提高齿轮箱油温异常预警模型的精度。

考虑齿面闪温的风电齿轮箱裂纹故障特征分析

为了研究齿面闪温对风电齿轮箱裂纹故障时系统动力学响应的影响,利用Blok闪温理论分析齿轮啮合时的齿面温度,应用热变形公式计算齿廓形变,进而通过Hertz接触理论获得计及齿面闪温影响的轮齿刚度。考虑齿面闪温、阻尼、时变啮合刚度、综合啮合误差和齿侧间隙,建立含有高速级齿轮齿根裂纹的齿轮箱扭转动力学模型。通过时域图、频谱图、相图和Poincaré截面分析不同裂纹长度下系统振动特性随齿面闪温变化的规律,并比较裂纹故障仿真与实验的时频域结果。结果表明:齿面闪温使时域图上裂纹产生的冲击幅值增大、频域图中故障边频结构更为复杂、相图曲线向外扩展以及Poincaré截面离散点增多,且变化均随裂纹长度的增加越为明显。研究结论可为齿轮裂纹故障状态的诊断与监测提供依据。

基于场景判别的风电齿轮箱温度预测及趋势异常预警方法

将齿轮箱温度划分为正常、温升异常和温度异常3种场景,并利用所构建的卷积神经网络(Conventional neural network,CNN)结合双向长短期记忆(Bidirectional long short term memory,BiLSTM)网络模型对场景进行判别。在此基础上,采用分位数回归(Quantile regression,QR)结合门控循环单元(Gate recurrent unit,GRU)方法,分别预测不同温度场景下的油温及轴承点预测及温度区间,并根据GRU温度异常诊断模型对2种预测温度进行诊断。算例分析结果表明,用该方法能准确预测各状态下齿轮箱温度,且预测区间可靠,可实现齿轮箱温度异常的高效诊断。依托某风场实测数据对所提方案进行验证,验证结果表明所提方法有效且性能优越。

风电机组齿轮箱故障预警算法研究及应用

齿轮箱健康状态直接影响风电机组的发电量,为了在工程实际中尽早实现齿轮箱故障状态的预警,提出一种基于改进狮群优化的K-means聚类算法。将监督机制及考虑非线性权重的正余弦优化算法引入狮群算法实现算法改进,通过改进狮群优化算法对狮王位置的迭代,选择最优解作为K-means算法聚类中心,以解决传统聚类算法对初始聚类中心依赖性强的问题。选择UCI数据对算法进行对比验证,结果表明,基于改进狮群优化的K-means聚类算法的分类准确度和稳定性有较好的提升。将该算法应用于某风电场内4台同一型号机组齿轮箱振动加速度有效值的对比测试,发现该算法的分类中心分布与齿轮箱实际运行状态相吻合,且与标准规定的齿轮箱不同状态所对应的振动能量分布相一致,证明该算法可实现风电机组齿轮箱早期故障预警。