Wind Turbine Gearbox Research Articles

Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults

Both wear-induced bearing failure and misalignment of the powertrain between the rotor and the electrical generator are common failure modes in wind-turbine motors. In this study, Semi-Supervised Learning (SSL) is applied to a fault detection and diagnosis solution. Firstly, a dataset is generated containing both normal operating patterns and seven different failure classes of the two aforementioned failure modes that vary in intensity. Several datasets are then generated, maintaining different numbers of labeled instances and unlabeling the others, in order to evaluate the number of labeled instances needed for the desired accuracy level. Subsequently, different types of SSL algorithms and combinations of algorithms are trained and then evaluated with the test data. The results showed that an SSL approach could improve the accuracy of trained classifiers when a small number of labeled instances were used together with many unlabeled instances to train a Co-Training algorithm or combinations of such algorithms. When a few labeled instances (fewer than 10% or 327 instances, in this case) were used together with unlabeled instances, the SSL algorithms outperformed the result obtained with the Supervised Learning (SL) techniques used as a benchmark. When the number of labeled instances was sufficient, the SL algorithm (using only labeled instances) performed better than the SSL algorithms (accuracy levels of 87.04% vs. 86.45%, when labeling 10% of instances). A competitive accuracy of 97.73% was achieved with the SL algorithm processing a subset of 40% of the labeled instances.Graphical abstractSteps and processes for approaching semi-supervised FDD of wind-turbine gearbox misalignment and imbalance faults

Energy-based availability warranty policy with considering preventive maintenance and learning-forgetting effect

Ensuring reliable operation and maximum the output is crucial for energy production systems. Traditional time-based availability (TBA) warranty policies often overlook some factors, such as energy loss and the experience gained during the maintenance activities. In this paper, an innovative warranty policy which focuses on the energy-based availability (EBA) is proposed, where imperfect preventive maintenance (IPM) and minimal repair (MR) are taken into account, and hybrid hazard rate model is adopted to describe the effect of preventive maintenance. In addition, the learning-forgetting effect during the maintenance is considered. On this basis, six types of single-objective and multi-objective models are established, and they are solved by genetic algorithm (GA) and non-dominated sorting genetic algorithm-II (NSGA-II), respectively. To illustrate the effectiveness of the proposed warranty policy, a numerical case of wind turbine gearbox is conducted. The results show that the proposed EBA warranty policy can gain around 0.29% energy more than TBA policy. Compared to single-objective models, multi-objective models can provide more selectable maintenance options. Additionally, sensitivity analysis indicates that by considering the learning-forgetting effect, the gearbox can achieve higher EBA and lower warranty cost.

A fast method for robust estimation of gearbox instantaneous speed

Under non-stationary condition, estimating the instantaneous frequency (IF) of shaft from vibration signal is an ideal way for gearbox fault monitoring without tachometer. Among them, the method based on harmonic phase demodulation has always occupied a dominant position. In the low signal-to-noise ratio (SNR) condition, the noisy harmonic components may cause greater IF estimation error. In this work, an improved approach for estimating the IF of gearbox reference shaft is proposed based on the short time Fourier transform spectrogram. The theoretical derivation proves that the high-order meshing harmonic can reduce the IF estimation error of gearbox reference shaft. By constructing the spectrogram weight factor, an improved maximum tracking algorithm is proposed to redefine the IF estimation range. On this basis, the robust IF estimation of high-order meshing harmonic with low SNR is realized. Finally, it is equivalent to the estimated IF of gearbox reference shaft. The proposed strategy is compared with the two advanced IF estimation methods. The civil aircraft engine dataset and the wind turbine gearbox dataset provided in the Safran contest demonstrate that the proposed strategy works. In the case of heavy load and large speed change, the proposed method has extremely low consumption time while maintains good estimation accuracy.

Human-computer Interaction Perspectives on Condition Monitoring and Fault Diagnosis of Gearbox in Doubly-Fed Wind Turbines: An Exploration with Artificial Intelligence Technology

Human-computer Interaction Perspectives on Condition Monitoring and Fault Diagnosis of Gearbox in Doubly-Fed Wind Turbines: An Exploration with Artificial Intelligence Technology

Condition Monitoring of Wind Turbine Drivetrain Bearings

Abstract As an extremely valuable and reliable energy source, the renewable energy is developing around the world at an unprecedented pace. By the end of 2022, the global installed capacity of offshore wind turbines is expected to reach 46.4 GW, among which 33.9 GW in Europe. Efficiencies in Operations and Maintenance (O&M) offer potential to achieve significant cost savings as it accounts for around 20%–30% of overall offshore wind farm costs. A recent study of approximately 350 offshore wind turbines indicates that gearboxes might have to be replaced as early as 6.5 years. Therefore sensing and condition monitoring (CM) systems are needed in order to obtain reliable information on the state and condition of different critical parts. The development and use of such technologies will allow companies to schedule actions at the right time. The reduced costs of O&M enable the wind energy at a competitive price thus strengthening productivity of the wind energy sector. At the academic level, a plethora of methodologies have been proposed during the last decades focusing toward early and accurate fault detection. Among others, Envelope Analysis is one of the most important methodologies, where the envelope of the vibration signal is estimated, usually after filtering around a selected frequency band excited by impacts due to the faults. Different tools, such as Kurtogram, have been proposed in order to accurately select the optimum filter parameters (center frequency and bandwidth). Cyclostationary analysis and corresponding methodologies, i.e., the cyclic spectral correlation and the cyclic spectral coherence, have been proved as powerful tools for CM. On the other hand the application, test, and evaluation of such tools in general industrial cases is still rather limited. Therefore the main aim of this paper is the application and evaluation of advanced diagnostic techniques and diagnostic indicators, including the Enhanced Envelope Spectrum and the Spectral Flatness on real-world vibration data collected from vibration sensors on gearboxes in multiple wind turbines over an extended period of time of nearly four years. The diagnostic indicators are compared with classical statistic time and frequency indicators, i.e., Kurtosis, Crest Factor, etc. and their effectiveness is evaluated based on the successful detection of two failure events.

An Envelope Time Synchronous Averaging for Wind Turbine Gearbox Fault Diagnosis

An Envelope Time Synchronous Averaging for Wind Turbine Gearbox Fault Diagnosis

Wind turbine gearbox temperature prediction based on improved whale optimized long short-term memory network

Aiming at the problem of low prediction accuracy of wind turbine gearbox temperature, the improved whale algorithm is used to optimize the long and short term memory network to predict the oil temperature of gearbox. The input data is based on the grey correlation degree to mine the parameters that are highly correlated with the oil temperature of the gear box, and the prediction model under healthy state is established. Finally, the experimental analysis shows that the method used in this paper has good accuracy in the oil temperature prediction of gearbox.

A surface study of failed planetary wind turbine gearbox Bearings to investigate the causes of the Bearing premature failure issue

The advanced software used in designing Wind Turbine Gearboxes (WTGs) does not solve the premature failure of the gearbox bearings, which still fail within 5%–20% of their design life by flaking. This issue increases the maintenance, downtime, and early replacement costs that limit the investment in the wind energy field. The majority of the previous research have focused on bearing subsurface investigation and the microstructural changes associated with the failure patterns. Conversely, surface investigation can elucidate significant information about the loading levels and contributors to the premature bearing failure. In this study, two bearings from a planetary stage of a failed multi-megawatt wind turbine gearbox underwent surface investigations and analyses. The analyses include indentations, hardness, roughness, and severe damage regions. The study shows that the contact loading stress exceeds the recommended and more than the compressive yield stresses of the bearing materials. The loading distribution on the bearing inner race during the gearbox operation is quite different from the theoretical loading. The transient loadings throughout the service reduce the Wind Turbine Gearbox Bearings (WTGBs) service life. Furthermore, the significant effects of skewing and slipping have been confirmed. Accordingly, the, lubricant filtration system and the design of the planetary stage are recommended to be improved to extend the fatigue life of the wind turbine gearbox bearings.

The influence of lubricants on white etching areas formation in DLC-coated bearing steel under severe boundary lubrication

White etching areas (WEAs) and white etching cracks (WECs) are the catastrophic premature failure modes associated with wind turbine gearbox bearings. Several drivers, including lubricant chemistry, influence the evolution of WEAs and WECs. This study investigated the performance of base oils with various lubricant chemistry against microstructural decay in DLC-coated AISI 52100 bearing steel. Tests were performed in sliding-dynamic loading conditions under severe boundary lubrication. The effect of base oils against WEAs formation in DLC-coated steel is explored by analysing the condition of oils, wear behaviour, and subsurface microstructural change. The study outcomes revealed that the selection of base oils plays a vital role against the WEAs formation in DLC-coated bearing steel subsurface.

Cross-machine deep subdomain adaptation network for wind turbines fault diagnosis

Recently, subdomain adaptation has gained extensive interest in addressing the problem of wind turbine (WT) fault diagnosis. However, current methods mainly focus on the subdomain adaptation of statistical features and scenarios with constant rotation speed. To overcome these limitations, a new cross-machine deep subdomain adaptation network (CMDSAN) is proposed in this paper for fault diagnosis of WT under multiple operating conditions. CMDSAN contains an improved subdomain adaptive (ISA) mechanism. In ISA, a subdomain distribution shift measure of jointed statistical and geometric features is constructed to boost domain confusion. Meanwhile, to further capture fine-grained information and discriminative features, a local correlation alignment (LCA) strategy is proposed. Additionally, a two-stage training trade-off factor is designed for balancing classification and ISA loss during the training process to improve the transferability of features. Subsequently, test rigs are constructed, i.e., a planetary gearbox test rig and a scaled-down test rig for WT gearbox with a reduction ratio of 110.11, to validate the effectiveness and superiority of CMDSAN. The case studies conducted under constant rotation speed, acceleration, and deceleration demonstrate that the proposed CMDSAN exhibits better fault transfer diagnostic ability than other domain adaptation methods.

Wind turbine gearbox multi-scale condition monitoring through operational data

Since wind is expected to play a crucial role on the worldwide electricity production scenario, the reliability of the turbines is attracting attention of both industry and academia. New techniques for efficient condition monitoring of key components can be fundamental to optimising the performance and maintenance of a large fleet of turbines. The gearbox and bearings are the most critical mechanical components as they are responsible for a large proportion of the downtime of a wind turbine over its lifetime. However, the monitoring of wind turbine gearboxes is challenging due to the non-stationary nature of the operation and the lack of noise-free vibration measurements. In the present work, a new approach for efficient long to short term monitoring of wind turbine gearboxes has been developed based on real data. An turbine drivetrain failure was used as a test case to develop a new approach based on the use of multi-scale data sources. On the one hand, SCADA (Supervisory Control And Data Acquisition) data were used for general monitoring of the condition of the machine component on long to medium term time scales, while on the other hand, high resolution, triggered event data collected by a CMS (Condition Monitoring System) were used to refine the diagnosis and prognosis of the fault on a shorter time scale. Even though triggered spot events are very difficult to manage, the results show that the use of multi-scale high resolution CMS data can be fast and useful in fault diagnosis to classify a target machine with a healthy reference one. In the present work, the one-class SVM (Support Vector Method) was used for novelty detection. The approach, when applied to all available time scales, can be very precise in detecting the faulty machine and can therefore be proposed as a fast detection approach requiring less data compared to the classical data-driven regression normal behaviour model developed with continuously available SCADA data.

Reliability based design optimization of a two-stage wind turbine gearbox

This paper describes a multi-objective reliability-based design optimization (MORBDO) of a two-stage wind turbine gearbox. The optimization process incorporates the gear's reliability of accounting for the uncertainty of its internal geometric parameters. It also ensures that constraints relating to the gear's reliability index and efficiency are respected. The objective functions are to minimize both the total volume and the center distance. A specific reliability target is established, and to address the multi-objective reliability-based design optimization (MORBDO), the hybrid method (HM) in conjunction with the constrained non-dominated sorting genetic algorithm (C-NSGA-II) is employed. The outcomes demonstrate that applying C-NSGA-II to solve the multi-objective reliability-based design optimization problem yields dependable Pareto solutions that are well-distributed in relation to the desired reliability level. The optimization using C-NSGA-II with a population size of 300 particles and 1000 generations produced the most favorable outcomes. This research significantly contributes to the multi-objective design optimization of wind turbine gear while simultaneously considering their reliability.

An Improved Conditional Generative Adversarial Method for Wind Turbine Gearbox Fault Diagnosis with Imbalance Data

An Improved Conditional Generative Adversarial Method for Wind Turbine Gearbox Fault Diagnosis with Imbalance Data

Sparsity and Periodicity-Induced Symplectic Geometry Decomposition for Incipient Fault Diagnosis of Wind Turbine Gearbox

Sparsity and Periodicity-Induced Symplectic Geometry Decomposition for Incipient Fault Diagnosis of Wind Turbine Gearbox

Tacholess Order Tracking Method Based on STFrFT for Fault Diagnosis of Wind Turbine Gearbox Under Variable Operating Conditions

Tacholess Order Tracking Method Based on STFrFT for Fault Diagnosis of Wind Turbine Gearbox Under Variable Operating Conditions

Research on Carbon Emission for Preventive Maintenance of Wind Turbine Gearbox Based on Stochastic Differential Equation

Research on Carbon Emission for Preventive Maintenance of Wind Turbine Gearbox Based on Stochastic Differential Equation

Design of floating wind turbine gearboxes using Gaidai risk assessment method

Generating renewable energy sources, rather than relying on world’s finite natural resources, becoming now increasingly crucial as world agenda focuses on climate issues. System’s high-dimensionality, along with nonlinear cross-correlations between various floating wind turbine mechanical parts, subjected to environmental wind and wave-induced loads, are not always easily handled by traditional risk assessment approaches, dealing with complex environmental energy systems. Empirical bending moments of drivetrain, have been produced using SIMPACK (Multibody Simulation Method), based on in situ wind loads. The aim of this study was to benchmark novel lifetime assessment approach for green energy systems.

Dynamics model and vibrational response analysis of helical gear-rotor-bearing transmission system

As a core component of wind turbines, wind power gear speed increasers often work in harsh environments, so it is necessary to study the vibration characteristics of gear transmission systems. Taking a wind turbine gearbox high-speed stage helical gear transmission system as the research object, the dynamics model of multi-degree-of-freedom helical gear-rotor-bearing transmission system is established by the lumped parameter method and solved by Runge-Kutta method, taking into account the tooth side clearance of the gear, transmission error, eccentricity and support force of the nonlinear bearing. The effects of input torque, transmission error and tooth side clearance on the vibration characteristic response of the helical gear train were analyzed. The relationship between the trend of amplitude change in each direction of the gear and the trend of change in the major frequency components was analyzed under the conditions of changing internal and external excitation. The results show that torsional vibration dominates in the system. As the input torque increases, the vibration amplitude of the driving and driven gears decreases, and the frequency amplitude decreases significantly at multiple locations. Gear transmission errors and changes in tooth side clearance have significant effects on gear vibration amplitudes, but are sensitive only to the meshing frequency. The trend of gear vibration amplitude caused by the change of external excitation of the gear set is synchronized with the trend of main frequency amplitude in the corresponding direction, while the change of vibration amplitude caused by internal excitation is consistent with the trend of mesh frequency amplitude in the corresponding direction. The results of this paper can pave a certain foundation for the design and fault diagnosis of wind power gearbox transmission system.

Fault diagnosis of wind turbine gearbox under limited labeled data through temporal predictive and similarity contrast learning embedded with self-attention mechanism

Data-driven models for wind turbine (WT) gearbox health monitoring have garnered significant attention. However, these models usually depend on extensive manually labeled data, which is costly and time-consuming to obtain at industrial sites. The model performance is also heavily affected by volatile operating conditions of WT gearbox. To overcome these issues, this paper proposes a self-supervised fault diagnosis method based on temporal predictive and similarity contrast learning (TPSCL) embedded with self-attention mechanism. This method aims to extract latent fault features from unlabeled vibration signals, thereby improving diagnostic performance under limited labeled data and volatile working conditions. Firstly, a data augmentation combination strategy is proposed to improve the variety of input data and enhance the generalization. Furthermore, a temporal predictive and similarity contrastive learning model embedded with self-attention mechanism is proposed to extract representations related to WT gearbox health conditions. In this case, the intrinsic characteristics of unlabeled vibration signals are learned, and the operating environment disturbance can be eliminated. Finally, the fault separability is realized by fine-tuning the model with few labeled data, which can finally achieve accurate fault identification of WT gearbox. Compared with existing methods, the proposed method can fully utilize existing monitoring data and achieve better performance in WT gearbox status monitoring and diagnosis under limited labeled data and variable operating conditions, contributing to WT predictive maintenance and efficiency improvement.

A New Theory of Damage Estimation and Fatigue Life Prediction

There are a considerable number of fatigue damage estimation theories and fatigue life prediction of mechanical components. The most popular one is Palmgren-Minor (P-M) theory. This theory has been used in the standards for selecting the bearing –as a component subject to fatigue loading- and for expecting the bearings lives. In Wind Turbine Gearboxes (WTGs), the bearings were selected to be without maintenance for 20 to 25 years; however, in real service life, the bearing suffer from premature failure within a life span of quite less than the design life (1 to 5 years). A new applicable methodology and a procedure of calculation for damage estimation due to fatigue loading and predicting the life has been suggested and tested. Results of 20 rolling and sliding tests which conducted under severe contact loading are used to test this method. The suggested method depends on calculating the number of operating cycles under a specific contact loading level to an equivalent number of loading cycles under the average loading level. This method depends on the area under the S-N curve without any correction or loading factors and can be used to predict the WTG bearings failure to manage the maintenance because the current life prediction standards have very high percentages of error (> 400%). The reliability of this approach can be further verified by utilizing actual operational data from Supervisory Control and Data Acquisition (SCADA), used for overseeing wind turbine operations. Additional examinations are necessary to confirm the dependability of this novel method.