Healthy Wind Turbine Research Articles

Sensitivity analysis for multi-measurement points based SHM in the mooring lines of floating offshore wind turbines

Abstract Structural health monitoring in floating offshore wind turbines’ mooring lines is vital for detecting early faults and preventing disruptions. Currently, sporadic and expensive monitoring is conducted via remote-operating vehicles. Efficient, automated, economical monitoring methods based on a continuous stream of data acquired via multiple measurement points in the wind turbine, are required. Such methods based on vibration signals have been investigated limitedly for steel chains. Recently, faulty synthetic mooring lines of a simulated 10MW semi-submersible wind turbine have been detected under varying environmental conditions and via the Functional Model Based Method (FMBM) equipped with functional models. The uncertainty due to the conditions’ stochasticity has been addressed by training the models using ten signal realizations per condition (wind) under the healthy wind turbine and from each of two measurement points. The current study presents a preliminary sensitivity analysis of the FMBM’s capability in detecting the simulated wind turbine’s faulty mooring lines when the functional models are trained using one signal realization per varying condition (wind) from each measurement point. The method’s effectiveness is evaluated with acceleration signals from 11 healthy/ 66 faulty (reduced stifness in one mooring line) cases. The FMBM detects all cases even when trained using one signal realization.

Wind Turbine Blade Fault Diagnosis: Approximate Entropy as a Tool to Detect Erosion and Mass Imbalance

Wind energy is a clean, sustainable, and renewable source. It is receiving a large amount of attention from governments and energy companies worldwide as it plays a significant role as an alternative source of energy in reducing carbon emissions. However, due to long-term operation in reduced and difficult weather conditions, wind turbine blades are always seriously damaged. Hence, damage detection in blade structure is essential to evaluate its operational condition and ensure its structural integrity and safety. We aim to use fractal, entropy, and chaos concepts as descriptors for the diagnosis of wind turbine blade condition. They are, respectively, estimated by the correlation dimension, approximate entropy, and the Lyapunov exponent. Formal statistical tests are performed to check how they are different across wind turbine blade conditions. The experimental results follow. First, the correlation dimension is not able to distinguish between all conditions of wind turbine blades. Second, approximate entropy is suitable to distinguish between healthy and erosion conditions and between healthy and mass imbalance conditions. Third, chaos is not a discriminative feature to distinguish between wind turbine blade conditions. Fourth, wind turbine blades with either erosion or mass imbalance exhibit less irregularity in their respective signals than healthy wind turbine blades.

Implementation of Preventive and Corrective measures in SCADA based Wind Turbines

Wind energy is becoming increasingly important in addressing energy demand and environmental sustainability. It is driven by the outstanding offshore wind resource and the need to minimize carbon emissions from energy generation. A growing interest in wind turbine condition monitoring, which allows condition based rather than reactive or scheduled maintenance, stems from the difficulty of accessing and maintaining wind turbines offshore. Vibration analysis and oil debris detection are currently used wind turbine condition monitoring methods. The extra expenditures might be enormous when considering the number of turbines normally put in offshore wind farms, and specialist interpretation is usually required. However, extending SCADA data-based analysis could bring significant value to condition monitoring at little or no expense to the wind farm operator. This Research Paper focuses on wind turbine condition monitoring using only SCADA data. An early detection of operational defects or breakdowns allows for regular maintenance or repair, decreasing downtime and potentially preventing further damage. Comparing incoming operational SCADA data with results for relevant variables, like component temperature, produced from applicable models trained on SCADA data from a healthy wind turbine, yields useful component condition indicators. Anomalies in the variables of interest in the SCADA data indicate impending breakdowns. This method is used to derive machine-to-machine comparison of component condition Compared to developing separate turbine models, this saves significant computing work and model complexity. A real-time wind turbine power curve is also created using SCADA data and compared to a reference power curve to quickly discover abnormal behavior based on slight variations in the power curve.

A mathematical model of vibration signal for multistage wind turbine gearboxes with transmission path effect analysis

The sensor-perceived vibration signals of multistage wind turbine gearboxes have more complex frequency features than that of single-stage gearboxes since there are more meshing vibration sources and more complicated transmission paths inside them, which lead to difficulties in condition monitoring and fault diagnosis. Aiming to understand the vibration frequency features of multistage wind turbine gearboxes, a mathematical vibration model of healthy wind turbine gearboxes is developed and the spectral structure of the model is deduced by adopting Fourier series analysis. In the vibration model, the time-varying transmission paths from all the meshing vibration sources to the fixed sensor are considered, and the equivalent transmission path functions of the time-varying transmission paths are proposed for the first time. The theoretical derivations are validated by both simulations and engineering tests using two cases of 2.0MW industrial wind turbine gearboxes. The findings in this work are not only applicable to the gearboxes studied in this paper, but also to other similar multistage gearboxes, which can provide a priori spectral structure for the multistage gearbox to assist its condition monitoring and fault diagnosis.

Multi-Scale Wind Turbine Bearings Supervision Techniques Using Industrial SCADA and Vibration Data

Timely damage diagnosis of wind turbine rolling elements is a keystone for improving availability and eventually diminishing the cost of wind energy: from this point of view, it is a priority to integrate high-level practices into the real-world operation and maintenance of wind farms. On this basis, the present study is devoted to the formulation of reliable methodologies for the supervision of wind turbine bearings, which possibly can be integrated in the industrial practice. For this reason, this study is a collaboration between a company (ENGIE Italia), the University of Perugia and the Politecnico di Torino. The analysis is based on the exploitation of the data types which are available to wind farm managers from industrial control systems: SCADA (Supervisory Control And Data Acquisition) and TCM (Turbine Condition Monitoring). Due to the intrinsic sampling time difference between SCADA and TCM data (a few minutes the former, up to the millisecond for the latter), the proposed methodology is designed as multi-scale. At first, historical SCADA data are processed and the behavior of the oil filter pressure is analyzed for all the wind turbines in the farm: this provides preliminary advice for identifying presumably healthy wind turbines from those suspected of damage. A second step for the SCADA analysis is then represented by the study of the temperature trends of the bearings through a Support Vector Regression: the incoming damage is individuated from the analysis of the mismatch between measurements and estimates provided by the normal behavior model. Finally, the healthy units are selected as the reference and the faulty as the target for the analysis of TCM vibration data in the time domain: statistical features are computed on independent chunks of the signals and, using a Novelty Index, it was possible to distinguish the damaged wind turbines with respect to the reference ones. In light of the interest in application of the proposed methodology, good practice criteria in selecting and managing the data are discussed as well.

SCADA Data Analysis Methods for Diagnosis of Electrical Faults to Wind Turbine Generators

The electric generator is estimated to be among the top three contributors to the failure rates and downtime of wind turbines. For this reason, in the general context of increasing interest towards effective wind turbine condition monitoring techniques, fault diagnosis of electric generators is particularly important. The objective of this study is contributing to the techniques for wind turbine generator fault diagnosis through a supervisory control and data acquisition (SCADA) analysis method. The work is organized as a real-world test-case discussion, involving electric damage to the generator of a Vestas V52 wind turbine sited in southern Italy. SCADA data before and after the generator damage have been analyzed for the target wind turbine and for reference healthy wind turbines from the same site. By doing this, it has been possible to formulate a normal behavior model, based on principal component analysis and support vector regression, for the power and for the voltages and currents of the wind turbine. It is shown that the incipience of the fault can be individuated as a change in the behavior of the residuals between model estimates and measurements. This phenomenon was clearly visible approximately two weeks before the fault. Considering the fast evolution of electrical damage, this result is promising as regards the perspectives of exploiting SCADA data for individuating electric damage with an advance that can be useful for applications in wind energy practice.

Condition Monitoring of Wind Turbine Generators Using SCADA Data Analysis

Utility-scale wind turbines are equipped with a supervisory control and data acquisition (SCADA) system for remote supervision and control. The SCADA system accumulates a large amount of data that contains the health conditions of the wind turbines. Thus, it is interesting to mine the health status-related information from SCADA data for wind turbine condition monitoring. In this article, an ensemble approach is proposed to detect anomalies and diagnose faults in wind turbines. Historical SCADA data collected from healthy wind turbines are used to model their normal behaviors and build a Mahalanobis space as a reference space. By comparing the predicted behavior of the wind turbine by a trained model with the reference space, anomalies can be detected. Finally, wind turbine faults are diagnosed through the analysis of the distributions and correlations of their SCADA data. The proposed approach is validated by using the SCADA data collected from two field wind turbines. Results show that it can detect anomalies and diagnose the corresponding failure components before the wind turbines have to be shut down for maintenance.

Diagnosis of Faulty Wind Turbine Bearings Using Tower Vibration Measurements

Condition monitoring of gear-based mechanical systems in non-stationary operation conditions is in general very challenging. This issue is particularly important for wind energy technology because most of the modern wind turbines are geared and gearbox damages account for at least the 20% of their unavailability time. In this work, a new method for the diagnosis of drive-train bearings damages is proposed: the general idea is that vibrations are measured at the tower instead of at the gearbox. This implies that measurements can be performed without impacting the wind turbine operation. The test case considered in this work is a wind farm owned by the Renvico company, featuring six wind turbines with 2 MW of rated power each. A measurement campaign has been conducted in winter 2019 and vibration measurements have been acquired at five wind turbines in the farm. The rationale for this choice is that, when the measurements have been acquired, three wind turbines were healthy, one wind turbine had recently recovered from a planetary bearing fault, and one wind turbine was undergoing a high speed shaft bearing fault. The healthy wind turbines are selected as references and the damaged and recovered are selected as targets: vibration measurements are processed through a multivariate Novelty Detection algorithm in the feature space, with the objective of distinguishing the target wind turbines with respect to the reference ones. The application of this algorithm is justified by univariate statistical tests on the selected time-domain features and by a visual inspection of the data set via Principal Component Analysis. Finally, a novelty index based on the Mahalanobis distance is used to detect the anomalous conditions at the damaged wind turbine. The main result of the study is that the statistical novelty of the damaged wind turbine data set arises clearly, and this supports that the proposed measurement and processing methods are promising for wind turbine condition monitoring.

SCADA based nonparametric models for condition monitoring of a wind turbine

High operation and maintenance costs for offshore wind turbines push up the LCOE of offshore wind energy. Unscheduled maintenance due to unanticipated failures is the most prominent driver of the maintenance cost which reinforces the drive towards condition-based maintenance. SCADA based condition monitoring is a cost-effective approach where power curve used to assess the performance of a wind turbine. Such power curves are useful in identification of wind turbine abnormal behaviour. IEC standard 61400-12-1 outlines the guidelines for power curve modelling based on binning. However, establishing such a power curve takes considerable time and is far too slow to reflect changes in performance to be used directly for condition monitoring. To address this, data-driven, nonparametric models being used instead. Gaussian Process models and regression trees are commonly used nonlinear, nonparametric models useful in forecasting and prediction applications. In this paper, two nonparametric methods are proposed for power curve modelling. The Gaussian Process treated as the benchmark model, and a comparative analysis was undertaken using a Regression tree model; the advantages and limitations of each model will be outlined. The performance of these regression models is validated using readily available SCADA datasets from a healthy wind turbine operating under normal conditions.

Full-Scale Wind Turbine Vibration Signature Analysis

A sample of healthy wind turbines from the same wind farm with identical sizes and designs was investigated to determine the average vibrational signatures of the drive train components during normal operation. The units were variable-speed machines with three blades. The rotor was supported by two bearings, and the drive train connected to an intermediate three-stage planetary/helical gearbox. The nominal 2 MW output power was regulated using blade pitch adjustment. Vibrations were measured in exactly the same positions using the same type of sensors over a six-month period covering the entire range of operating conditions. The data set was preliminary validated to remove outliers based on the theoretical power curves. The most relevant frequency peaks in the rotor, gearbox, and generator vibrations were detected and identified based on averaged power spectra. The amplitudes of the peaks induced by a common source of excitation were compared in different measurement positions. A wind speed dependency of broadband vibration amplitudes was also observed. Finally, a fault detection case is presented showing the change of vibration signature induced by a damage in the gearbox.

Comparative analysis of binning and Gaussian Process based blade pitch angle curve of a wind turbine for the purpose of condition monitoring

Several studies have used the power curve as a critical indicator to assess the performance of wind turbines. However, the wind turbine internal operation is affected by various parameters, particularly by blade pitch angle. Continuous monitoring of blade pitch angle can be useful for power performance assessment of wind turbines. The blade pitch curve describes the nonlinear relationship between pitch angle and hub height wind speed which to date has been little explored for wind turbine condition monitoring. Gaussian Process models are nonlinear and nonparametric technique, based on Bayesian probability theory. Such models have the potential give results quickly and efficiently. In this paper, we propose a Gaussian Process model to predict blade pitch curve of a wind turbine for condition monitoring purposes. The obtained Gaussian Process based blade pitch curve is then compared with a conventional approach based on a binned blade pitch curve for identifying operational anomalies purposes. Finally, the weaknesses and strengths of these methods are summarised. SCADA data from healthy wind turbines are used to train and evaluate the performance of these techniques.

A Wind Turbine Blade Damage Detection System Based on Data Analysis: An Academic Example on the Use of Histograms

The main objective of this paper is to introduce an academic example on the use of histograms to develop a wind turbine blade fault (or damage) detection system. This approach merely uses data analysis obtained from a generated wind turbine power. Then, and based on the power curve of a wind turbine, histograms are obtained, first, for the healthy wind turbine operation, and then, for two cases on faulty wind turbine operations. By comparing them, a faulty behaviour of a wind turbine is detectable. Finally, according to our numerical example, the proposed technique seems a realistic case to students on the statistic and probability fields as a useful academic example.

Wind Turbine Condition Monitoring Strategy through Multiway PCA and Multivariate Inference

This article states a condition monitoring strategy for wind turbines using a statistical data-driven modeling approach by means of supervisory control and data acquisition (SCADA) data. Initially, a baseline data-based model is obtained from the healthy wind turbine by means of multiway principal component analysis (MPCA). Then, when the wind turbine is monitorized, new data is acquired and projected into the baseline MPCA model space. The acquired SCADA data are treated as a random process given the random nature of the turbulent wind. The objective is to decide if the multivariate distribution that is obtained from the wind turbine to be analyzed (healthy or not) is related to the baseline one. To achieve this goal, a test for the equality of population means is performed. Finally, the results of the test can determine that the hypothesis is rejected (and the wind turbine is faulty) or that there is no evidence to suggest that the two means are different, so the wind turbine can be considered as healthy. The methodology is evaluated on a wind turbine fault detection benchmark that uses a 5 MW high-fidelity wind turbine model and a set of eight realistic fault scenarios. It is noteworthy that the results, for the presented methodology, show that for a wide range of significance, α ∈ [ 1 % , 13 % ] , the percentage of correct decisions is kept at 100%; thus it is a promising tool for real-time wind turbine condition monitoring.

An experimental study on the applicability of acoustic emission for wind turbine gearbox health diagnosis

Condition monitoring of wind turbine gearboxes has mainly relied upon vibration, oil analysis and temperature monitoring. However, these techniques are not well suited for detecting early stage damage. Acoustic emission is gaining ground as a complementary condition monitoring technique as it offers earlier fault detection capability compared with other more established techniques. The objective of early fault detection in wind turbine gearboxes is to avoid unexpected catastrophic breakdowns, thereby reducing maintenance costs and increase safety. The aim of this investigation is to present an experimental study the impact of operational conditions (load and torque) in the acoustic emission activity generated within the wind turbine gearbox. The acoustic emission signature for a healthy wind turbine gearbox was obtained as a function of torque and power output, for the full range of operational conditions. Envelope analysis was applied to the acoustic emission signals to investigate repetitive patterns and correlate them with specific gearbox components. The analysis methodology presented herewith can be used for the reliable assessment of wind turbine gearbox subcomponents using acoustic emission.

A novel order tracking method for wind turbine planetary gearbox vibration analysis based on discrete spectrum correction technique

Wind turbine gearboxes generally exhibit complex vibration characteristics due to wide variations in the operating conditions, and dynamics of the structure coupled with flexible supports. Conventional spectral analysis method may not provide reliable health monitoring and fault diagnosis of the gearbox. In this study, a novel order tracking method based on discrete spectrum correction technique is proposed to analyze wind turbine gearbox vibration for the purposes of health monitoring and fault diagnosis. The effectiveness and robustness of the proposed method are demonstrated through simulations and engineering tests. The results show that the shaft rotating speed could be accurately identified from the vibration signal together with amplitudes of significant gear meshing components. Modulation sidebands of both the planetary and fixed-shaft gears in a healthy wind turbine gearbox were further analyzed, which revealed inherent shaft misalignment in the fixed-shaft gear. Meshing frequency of the planetary gear was modulated by both the rotating frequencies of sun gear and planetary carrier, while fundamental modulation frequency of the planetary carrier was found to be related to rotating frequency of the carrier multiplied by the number of planet gears. The monitoring of such particular vibration features would be helpful in enhancing the operational performance of wind turbines through reliable health monitoring of gearboxes and reducing the misdiagnosis of faults.

Supervisory control and data acquisition data‐based non‐linear state estimation technique for wind turbine gearbox condition monitoring

Offshore wind energy is catching increasing worldwide interest. However, access and maintenance offshore can be difficult and will be more costly than onshore, and hence, availability is correspondingly lower. As a result, there is a growing interest in wind turbine condition monitoring with condition-based rather than responsive and scheduled maintenance. A non-linear state estimation technique (NSET) model is presented here to model a healthy wind turbine gearbox using stored historical data. These data capture the inter-relationship between the model input and output parameters. The state vectors comprising the data should cover as much as turbine operational range, including the extreme conditions in order to obtain an accurate model performance. A model so constructed can be applied to assess the operational data. Welch's t-test is employed in the fault detection algorithm, together with suitable time series filtering, to identify incipient anomalies in the turbine gearbox before they develop into catastrophic faults. Two case studies based on 10-minute supervisory control and data acquisition data from a commercial wind farm are presented to demonstrate the model's effectiveness. Comparison is made with neural network modelling, and the NSET approach is demonstrated to be superior.

Determination of the combined vibrational and acoustic emission signature of a wind turbine gearbox and generator shaft in service as a pre-requisite for effective condition monitoring

A review of current progress in Condition Monitoring (CM) of wind turbine gearboxes and generators is presented, as an input to the design of a new continuous CM system with automated warnings based on a combination of vibrational and Acoustic Emission (AE) analysis. For wind turbines, existing reportage on vibrational monitoring is restricted to a few case histories whilst data on AE is even scarcer. In contrast, this paper presents combined vibration and AE monitoring performed over a continuous period of 5 days on a wind turbine. The vibrational and AE signatures for a healthy wind turbine gearbox and generator were obtained as a function of wind speed and turbine power, for the full normal range of these operational variables. i.e. 5–25 m/s and 0–300 kW respectively. The signatures have been determined as a vital pre-requisite for the identification of abnormal signatures attributable to shaft and gearbox defects. Worst-case standard deviations have been calculated for the sensor data. These standard deviations determine the minimum defect signal that could be detected within the defined time interval without false alarms in an automated warning system.