Turbine Failure Research Articles

Active learning-based wind turbine failure prediction with consideration of data from different wind farms

The SCADA system installed in each wind farm provides real-time and historical data required for fault diagnosis. However, labeling the data requires time and effort. Meanwhile, the performance of failure prediction and diagnostic relies on the volume of labeled failure data. Therefore, a fault diagnosis and prediction scheme for wind turbines based on active learning is proposed. Firstly, historical data from a selected wind turbine is screened out by residual analysis to set up the initial training data sets. Then a classifier is pre-trained by an improved active learning method. The active learning model based on the committee selection (QBC) sampling strategy and random forest (RF) learner is combined to realize the data labeling and, therefore, wind turbine fault detection. Afterward, the pre-trained classifier is applied to different wind turbines in the same/different wind farms to decide their operational status by labeling their operational data. Finally, the labeled data from different resources are fed back to retrain the classifier to improve its performance. Data from the SCADA system of wind turbines of different manufacturers in different wind farms are used as test cases, and simulation results show the effectiveness and feasibility of the proposed scheme.

Research on Fault Diagnosis of Wind Turbine Gearbox with Snowflake Graph and Deep Learning Algorithm

Wind power generation is one of the important development projects for renewable energy worldwide. As wind turbines operate in harsh environments, failure of the wind turbines often occurs, thus leading to lower power generation efficiency and high maintenance cost. Earlier detection of the fault type can reduce the maintenance cost. This study proposed a hybrid recognition algorithm based on the symmetrized dot pattern (SDP) and convolutional neural network (CNN) for wind turbine gearbox fault diagnoses. In addition to a fault-free type, four fault types were discussed in this paper, including gear rustiness, broken tooth, wear, and aging. A vibration sensor was used for measurement. The original vibration signals of the gearbox were captured by a NI-9234 high-speed data acquisition card, filtered by a fast Fourier transform, and imported into the SDP to create the snowflake image features. Afterward, CNN diagnosed the gearbox fault type. There were 1500 test data in this study. A total of 200 data items for each fault type were used as training samples, and 100 data of each type were used as test samples. The test result shows that the training accuracy was 98.8%. The proposed method can diagnose the fault condition of the gearbox effectively and identify the fault type of the gearbox accurately. This is favorable for the quick maintenance of wind turbines.

Wind Turbine Fault Detection With Multimodule Feature Extraction Network and Adaptive Strategy

Unexpected failures in wind turbines (WTs) lead to tremendous economic losses and safety hazards to wind farms. Intelligent condition monitoring and fault detection can prevent unscheduled downtime and improve reliability and efficiency. However, the variational external environments and operation states result in time-varying correlations and fluctuations of variables, which pose challenges to precise modeling and detection for WTs. This article proposes a dual-stage temperature monitoring and fault detection method, which can be applied to multiple key components in WTs. First, a novel multimodule feature extraction network (MMFENet) is designed to model the normal behavior of temperature data in the monitoring component. The proposed model decomposes the correlations into distinct patterns and devises different modules for quantification. Specifically, the static module aims to characterize the stationary correlations resulting from the inherent structure to provide reference expectations of fluctuations in the dynamic module and accelerate the model training. The dynamic module is devoted to depicting time-varying interdependence caused by variational operation states to pursue precise modeling. In addition, the proposed network also uses a heterogeneous data fusion module to use external information. Second, an adaptive detection strategy is devised for converting the prediction errors into detection results. Based on the evaluation results in the training procedure, parameter ranges during online detection can be adaptively determined to contain multiple rational values, which can enhance robustness and scalability. Experimental results using field data from real wind farms demonstrate the effectiveness and superiority of the proposed method.

Field‐data‐based reliability analysis of power converters in wind turbines: Assessing the effect of explanatory variables

AbstractFrequent failures of power converters affect the availability of wind turbines and cause considerable maintenance costs. To enhance the reliability of power converters in wind turbines, the prevailing causes and modes of failures have to be identified. This publication contributes to root‐cause analysis of the power‐converter failures in wind turbines from a statistical point of view. For this purpose, the failure behavior of power‐converters is modeled via lifetime models as well as repairable‐system models. By means of regression models, covariates are incorporated, including both design‐related and site‐specific covariates. The analysis is based on a worldwide extensive field‐data collection covering more than 9000 turbines, including different turbine designs, sites, and ages. The results obtained by means of the applied regression models indicate that the location of the power converter within the turbine, the cooling system, the converter rated power, the DC‐link voltage, the IGBT‐module manufacturer, and the commissioning date of the turbine as design‐related covariates have a significant effect on the phase‐module failure behavior and with that on converter reliability. Among the site‐specific covariates, the analysis results confirm humidity as a likely significant driver of failures.

Hyperparameter Tuning of OC-SVM for Industrial Gas Turbine Anomaly Detection

Gas turbine failure diagnosis is performed in this work based on seven types of tag data consisting of a total of 7976 data. The data consist of about 7000 normal data and less than 500 abnormal data. While normal data are easy to extract, failure data are difficult to extract. So, this study mainly is composed of normal data and a one-class support vector machine (OC-SVM) is used here, which has an advantage in classification accuracy performance. To advance the classification performance, four hyperparameter tuning (manual search, grid search, random search, Bayesian optimization) methods are applied. To analyze the performance of each technique, four evaluation indicators (accuracy, precision, recall, and F-1 score) are used. As a result, about 54.3% of the initial failure diagnosis performance is improved up to 64.88% through the advanced process in terms of accuracy.

Pilot study on renovation, modernization and uprating of agricultural dependent power plant

Hydro energy is one of the most valuable, rich, pliable inexhaustible energy resources in the world. Furtherance to the India’s commitment and pledge at Conference of the Parties (COP) 26 at Glasgow in 2021 calls to cut emissions to net zero by 2070, reduce the carbon emission by one billion tonnes by 2030 and improve the share of renewables in the energy mix to 50 % among others. Scientists and researchers needs to play a major role in achieving net zero emission to reduce the climate change impacts. In India, the share of hydro power is 34.1 % among the overall renewable energy of 150 GW. Hence, hydro power is an important area for Renovation, Modernization and Uprating (RMU) of the existing hydro capacities and it leads to limiting considerable carbon emission to an extent. This research paper focuses on storage reservoir where irrigation to hydro power water transfer is important. A balance of power generation and irrigation is at the highest priority attaining optimum social benefits. The reaction turbines are operated at high flow and low/medium head conditions for agricultural dependant power plant with consideration to Irrigation, drinking, flora and fauna. The restrictions imposed on the reaction turbines while operation under low load and low flow conditions leads to cavitation. The operation conditions under low flow and low load of reaction turbines may lead to noise, vibration and directed to major catastrophic failure of turbines. The likely outcome of same leads to considerable loss of energy generation. In addition to the above, a typical hydro power plant consumes 0.3 to 0.5 % of maximum power capacity as an internal load for lighting and other auxiliary systems. This paper emphasizes in utilizing the unused energy potential during the low and high water releases from irrigation dependent hydro power plant on renovation, modernization and uprating (RMU) of existing hydropower station. An irrigation dependent hydropower plant Dhom (2X1 MW), MAHAGENCO, Satara, Maharastra has been considered for study in order to use the available energy potential optimally. The improvement of capacity factor from 0.315 to 0.46 and additional power generation of 300 kW creates the opportunity to apply RMU in existing hydropower plant successfully.

Assessment of Defects under Insulation Using K-Medoids Clustering Algorithm-Based Microwave Nondestructive Testing

Composite insulations, such as ceramics, are commonly utilized in the turbine system as a thermal coating barrier to protect the metal substrate against high temperatures and pressure. The presence of delamination in the composite insulations may cause turbine failure, leading to a catastrophic accident. Thus, regular non-destructive testing is required to detect and evaluate insulation defects. Among the non-destructive testing techniques, the microwave technique has emerged as a promising method for assessing defects in ceramic coatings. Although the method is promising, microwave non-destructive testing suffers from poor spatial imaging, making the defect assessment challenging. In this paper, a novel technique based on microwave non-destructive testing with a k-medoids clustering algorithm for delamination detection is proposed. The representative ceramic coating sample is scanned using a Q-band open-ended rectangular waveguide with 101 frequency points that operated between 33 to 50 GHz. The measured data is transformed from the frequency domain to the time domain using an inverse fast Fourier transform. The principal component analysis is then used to reduce the dimensionality of 101 time steps into only 3 dominant attributes. The attributes of each inspected location are classified as defect or defect-free using the k-medoids clustering algorithm for accurately detecting and sizing the defects in the ceramic insulation. The results reported in this paper highlight the superiority of the k-medoids clustering algorithm in delamination detection, with an accuracy rate of 95.4%. This is a significant step forward compared to earlier approaches for identifying ceramic defects.

Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines

In this paper, the time variation of signals from several SCADA systems of geographically closed turbines are analysed and compared. When operating correctly, they show a clear pattern of joint variation. However, the presence of a failure in one of the turbines causes the signals from the faulty turbine to decouple from the pattern. From this information, SCADA data is used to determine, firstly, how to derive reference signals describing this pattern and, secondly, to compare the evolution of different turbines with respect to this joint variation. This makes it possible to determine whether the behaviour of the assembly is correct, because they maintain the well-functioning patterns, or whether they are decoupled. The presented strategy is very effective and can provide important support for decision making in turbine maintenance and, in the near future, to improve the classification of signals for training supervised normality models. In addition to being a very effective system, it is a low computational cost strategy, which can add great value to the SCADA data systems present in wind farms.

Heat treatment optimization of 13Cr4Ni stainless alloy used as hydro turbine materials

In Nepal and the regions along with the Andes, sediment erosion is one of the major causes of the failure of hydro turbines. Every year lots of the components of turbines exposed to sediment-laden water got eroded resulting unexpected shutdown of the power plants. The cheapest method of repairing these eroded runners and other components of turbines are welding which may induce residual stress, embrittlement, and increase carbide content. Therefore, post welding heat treatment especially stress relieving annealing is always carried out to reduce the induced residual stresses, enhance strength and other mechanical properties as well as reduce the risk of cracking. As heating time is relative of low importance, great care should be taken during heat treatment to maintain the soaking time and cooling rate. Holding time for heat treatment will vary with the thickness of casting sections involved, but should be sufficiently long enough to heat all sections to a uniform temperature throughout. The cooling rate determines the material properties at room temperature and rapid cooling avoids the formation of chromium carbide. In this paper, the post-weld heat treatment used for repair and maintenance of turbines in Nepal is studied along with the investigation of heat treatment conditions on mechanical properties and microstructures of 13Cr4Ni stainless steel used as turbine materials to optimize the heat treatment itself. First of all relative analysis of five different heat treatment conditions with respect to ‘no heat treatment’ regarding mechanical properties i.e. toughness, hardness, and fatigue life was carried out. Heat treatments of the specimen were done in a muffle furnace. Hardness, toughness, and fatigue strength of the specimen using the Rockwell Hardness Test, Charpy Impact Test, and Fatigue Life Test were conducted respectively. Subsequently, microstructures of all the heat treatment conditions are closely examined using the metallurgical microscope. It was observed that holding time plays a great impact on improving mechanical properties.

Use of Markov Decision Model to Minimize Maintenance and Replacement Cost of Turbines in the Shiroro Hydro-Electric Power Station, Kaduna River, Niger State Nigeria

This paper presents the application of Markov decision model to minimize the maintenance and replacement cost of turbines in the Shiroro Hydro-Eletric Power Station, Kaduna River, Niger State, Nigeria. Data obtained reveals that minimum cost of equipment maintenance through the Markov reward model is achievable and able to ascertain long-run maintenance and the repair/replacement of turbine. Information obtained have the potential to assist engineers and utility staff to plan against turbine failure and hence, improve the stability of power generation which will in-turn lead to accelerate the economic growth of the nation.

Review of Tribological Failure Analysis and Lubrication Technology Research of Wind Power Bearings.

Wind power, being a recyclable and renewable resource, makes for a sizable portion of the new energy generation sector. Nonetheless, the wind energy industry is experiencing early failure of important components of wind turbines, with the majority of these issues also involving wind power bearings. Bearing dependability is directly tied to the transmission efficiency and work performance of wind turbines as one of its major components. The majority of wind turbine failures are due to bearings, and the vast majority of bearing failures are due to lubrication. The topic of improving the accuracy and life of wind power bearing motion is becoming increasingly essential as the wind power industry develops rapidly. This study examines the various constructions and types of wind turbines, as well as their bearings. We also examined the most typical causes of friction and lubrication failure. Furthermore, contemporary research on wind turbine bearings has been compiled, which mostly comprises the study and development of lubrication technology and other areas. Finally, a conclusion and outlook on current challenges, as well as future research directions, are offered.

A comparative study on class-imbalanced gas turbine fault diagnosis

Gas turbines are widely used in various fields, and the failure of gas turbines can cause catastrophic consequences. Health condition monitoring and fault diagnosis of gas turbines can detect faults timely, avoid serious faults, and significantly reduce maintenance costs. Thus, fault diagnosis of gas turbines has great significance. Current researches on gas turbine fault diagnosis mainly focus on the case of abundant fault samples. However, fault data are very rare and the number of normal samples is much larger than the number of fault samples in the industrial scene. This class-imbalance problem widely exists but is hardly focused in the field of gas turbine fault diagnosis. Aiming to solve this problem, this paper introduces the concept of class-imbalanced learning from the machine learning field, summarizes three kinds of class-imbalance addressment methods including oversampling, undersampling, and sample weighting, and proposes a new combination method of focal loss and random oversampling for addressing class-imbalance in deep neural networks, and performs a systematic comparative study on class-imbalanced gas turbine fault diagnosis. Experimental results show that class-imbalance can seriously reduce the fault diagnosis accuracy. Through these class-imbalance addressment methods, diagnosis accuracy is greatly improved. Comparative experiments also show that the proposed combination method can obtain the best diagnosis accuracy among all the compared methods in class-imbalanced situation. Through this comparative study, a detailed guideline for improving diagnosis accuracy under class-imbalanced circumstance is provided.

Quantifying the fatigue life of wind turbines in cyclone-prone regions

Wind turbines are designed to harvest kinetic energy of the wind, which are more susceptible to the impact of tropical cyclones compared with other high-rise structures. Most of the existing research of cyclone (hurricane/typhoon) impacts on wind turbine merely concentrated on its short-term failure (strength or stability failure). However in this paper, it is evidently demonstrated that cyclones can also have a significant impact on the long-term failure (fatigue failure) of a wind turbine. In this study, a novel framework is developed in the fatigue life evaluation of a wind turbine, in which two external factors, i.e., the progressive change of cyclone direction and intensity observed at a specific site, combined with one internal factor, i.e., a parked wind turbine with feathered or unfeathered blades are considered. Subsequently, the effect of cyclone-normal-wind direction misalignment and cyclone average recurrence intervals are included to have a synthetic assessment on the damage potential of cyclones. The proposed fatigue analysis framework can be also extended to other structures, e.g., the hybrid wind-tidal energy conversion system in cyclone-prone regions.

A review on erosion and erosion induced vibrations in Francis turbine

Vibrations are one of the major issues observed during the operations of Francis turbine as they are frequently operated outside their optimal operating range, with rapid load changes. In hydropower plants, vibrations occur in various parts which can be classified as: hydraulic civil parts such as reservoir, intake, dam, tail race etc. mechanical parts such as penstock, turbine, draft tube and shaft, and electrical parts such as generator and transformer. However, due to the sediments and cavitation problems, the regions around rotating parts such as turbine experiences severe vibration. In the cases where the turbines need to be operated with high sediment load, the vibration problems could be further aggravated due to sediment carrying flow and declination of the surface morphology after erosion. This paper is based on a literature review to explore the characteristic effects of erosion and cavitation which could result in losses, vibrations, fatigues on the turbine materials and oblivious turbine failure. The study aims to correlate the erosion and cavitation due to abrasion with the pressure fluctuations resulting in vibrations.

Wind Turbine Gearbox Failure Detection Through Cumulative Sum of Multivariate Time Series Data

The wind energy industry is continuously improving their operational and maintenance practice for reducing the levelized costs of energy. Anticipating failures in wind turbines enables early warnings and timely intervention, so that the costly corrective maintenance can be prevented to the largest extent possible. It also avoids production loss owing to prolonged unavailability. One critical element allowing early warning is the ability to accumulate small-magnitude symptoms resulting from the gradual degradation of wind turbine systems. Inspired by the cumulative sum control chart method, this study reports the development of a wind turbine failure detection method with such early warning capability. Specifically, the following key questions are addressed: what fault signals to accumulate, how long to accumulate, what offset to use, and how to set the alarm-triggering control limit. We apply the proposed approach to 2 years’ worth of Supervisory Control and Data Acquisition data recorded from five wind turbines. We focus our analysis on gearbox failure detection, in which the proposed approach demonstrates its ability to anticipate failure events with a good lead time.

Multi-component fault classification of a wind turbine gearbox using integrated condition monitoring and hybrid ensemble method approach

Gearbox has a high failure rate and downtime per failure in a wind turbine. Condition monitoring (CM) helps in diagnosis and prognosis of the faults. CM uses sensors to acquire data from different components and these signals are processed to extract fault features. The extracted features are further used to train different data driven models to identify and quantify the faults. A single decision-making algorithm does not perform well in different scenarios. To overcome this limitation, ensemble methods are used to diagnose the faults. Bagging and boosting are the widely used ensemble methods. However, boosting algorithms performs well on a noise-free data compared to bagging and in noisy settings, bagging methods are much robust than boosting. For this reason, a hybrid ensemble method that combines boosting, bagging, and stacking techniques to identify faults in a gearbox is proposed. Random forest (RF), decision tress (DT), KNN, AdaBoost, and gradient booster were used to compare the fault classification performance of the developed method. Experiments were conducted on the gearbox considering multi-component faults and integrated condition monitoring scheme. Vibration and acoustic signals acquired for different fault cases were processed using discrete wavelet transform (DWT) and the feature extraction was performed to obtain Kurtosis and Shannon entropy. These features were used to classify the faults using aforementioned algorithms. Results indicate that the developed method has the highest fault classification accuracy of 92%. The proposed method can be further used to diagnose similar machine faults in the industries.

A Review on Failure Analysis of Turbine Blades of Aero Gas Turbine Engine

Almost all commercial electrical power on earth is generated with a turbine, driven either by wind, water, steam or burning gas. Turbine blades are subjected to very strenuous environments inside a gas turbine. They face high temperatures, high stresses, and a potentially high vibration environment. All these factors can lead to blade failure, resulting in catastrophic failure of turbine. In the event of turbine blade failure, turbine does not work and this leads to shutdown of power plant from one to four weeks or longer, depending on the extent of the damage and the procedure used to make the machine operational again, which results in economic loss and service to mankind also stops. For each day of a forced outage, a utility could lose hundreds of thousands of rupees in electrical power. The external and internal surface damages include corrosion, oxidation, crack formation, erosion, foreign object damage and fretting. The internal damage of microstructure include γ’ phase, CoNi3 [(Al, Ti)] phase aging (rafting), grain growth, brittle phases formation, carbides precipitation, creep and grain boundary void formation. These damages produce dimensional change which results in increase in operational stress that leads to deterioration in turbine efficiency. The deterioration of blade material is related to the high gas temperature, high steady state load levels (centrifugal load) and high thermal transient load (trips, start-ups, start downs). In this research, a review of common failures due to metallurgical defects found in gas turbine discussed is presented.

Sensitivity analysis of geometrical design parameters on the performance of conical plain bearings for use as main bearings in wind turbines

The failure of a wind turbine’s main bearing causes very high repair costs, as the entire drivetrain has to be disassembled with the help of an external crane. Just the costs for a crane for an offshore turbine can sum up to 200.000€ per day [1]. In contrast, segmented hydrodynamic plain bearings offer the advantage that individual bearing segments can be replaced on the tower without the use of an external crane, which offers great potential for savings in repair costs. However, this application requires new, innovative plain bearing concepts for which the current design guidelines are not applicable. This paper presents a simulation-based design approach for a plain bearing concept with conical sliding surfaces. Such a simulation-based approach with a multi-objective optimization is necessary, because due to the geometric complexity the manual, iterative design process is not efficient. In this paper, a bearing geometry optimized in terms of load distribution and friction losses was developed by applying this approach.

Experimental Analysis of Planet Carrier Bearing Loads under Torque and Bending Moment in a Four-Point-Suspension Drive Train

Bearing failures in wind turbine gearboxes still occur which results in downtimes and hence leads to an increase in the levelized cost of energy. One of these affected bearings are the planet carrier bearings as they are still subject to unexpected fatigue related failure modes, like pitting and spalling, which are mainly influenced by the load distribution in the bearing. Hence it is necessary to determine the influence of torque and bending moment loads onto the planet carrier bearings. In this work the generator sided planet carrier bearing load distribution is investigated. Therefore, strain gauges are applied onto the circumference of that bearing of the gearbox of a 1 MW wind turbine four-point-suspension drive train. The loading is measured while testing at the 4 MW wind turbine test bench at CWD. The relevant loading for the investigated generator sided planet carrier bearing is torque which leads to a tilting of the gearbox leading to two load zones in the bearing. Bending moments at the hub of the drive train do not influence the bearing load distribution as they are absorbed by the main bearing.

SCADA Data-Driven Wind Turbine Main Bearing Fault Prognosis Based on Principal Component Analysis

Condition monitoring for wind turbines is essential for the further development of wind farms. Currently, many of the works are focused on the installation of new sensors to predict turbine failures, which raises the cost of wind projects. Wind turbines operate in a wide variety of environmental conditions, such as different temperatures and wind speeds that vary throughout the year season. Typically, most or all of the data available in a turbine is healthy data (operation without failure), so data-driven supervised classification methods have data imbalance problems (more data from one class). Also, when historical pre-failure data do not exist, those methods cannot be used. Taking into account the aforementioned difficulties, the stated strategy in this work is based on a principal component analysis anomaly detector for main bearing failure prognosis and its contributions are: i) this methodology is based only on healthy SCADA data, ii) it works under different seasons of the year providing its usefulness, iii) it is based only on external variables and one temperature related to the element under diagnosis, thus avoiding data containing information from other fault types, iv) it accomplishes the main bearing failure prognosis (several months beforehand), and v) the performance of the proposed strategy is validated on a real in production wind turbine.