1. Introduction
Wind turbines operate in harsh environments subjected to intense cyclic high- and low-frequency forces that can compromise their longevity and overall performance. Assessing the fatigue of these structures is crucial for ensuring their optimal operation and maintenance scheduling, determining their remaining useful lifetime, and considering potential lifetime extensions within the wind farm [
1,
2]. The assessment of fatigue damage accumulation in all components, based on measurements using sensors on a wind turbine, offers a solution. However, this approach requires a large array of sensors, leading to both logistical and financial constraints that are typically not employed on commercial machines [
3,
4,
5]. The use of aero-servo-elastic simulators has been proposed as an alternative solution. These simulators can generate vast amounts of data, which engineers and researchers can subsequently analyze to assess the fatigue life of wind turbines. However, while these simulations provide valuable insights, it is essential to recognize that they often do not align completely with a turbine’s actual environmental conditions and specific as-built characteristics. Thus, while simulators are a valuable tool, their results should be interpreted cautiously and supplemented with real-world data wherever possible to ensure accurate fatigue life assessments. Modern large wind turbines are equipped with Supervisory Control and Data Acquisition (SCADA) [
6]. SCADA systems typically collect over 200 variables, often recording and storing as 5- or 10-min averages along with basic statistics such as minimum (min), maximum (max), and standard deviation (STD) for each interval [
7]. However, SCADA has reliability and accuracy issues and typically does not include any data field directly related to loads [
8]. When load measurements are available from the SCADA system, they cannot be used directly for calculating the fatigue load. This is because the 10-min time scale is insufficient to capture a wind turbine’s dynamic behavior, which mainly requires high-resolution time series. Given all these factors and considerations, one potential solution is to use the SCADA environmental measurements as input for an aero-servo-elastic simulator to compute structural loads, in the absence of physical, e.g., strain gauge measurements. The output can then be utilized to construct a data-driven model capable of estimating and indicating Damage Equivalent Load (DEL) on turbine components.
The load assessment of a wind turbine is a complex task, whether it be in the design phase for a machine, layout optimization of a wind farm, or backing out from operational data. Therefore, many attempts have been made to simplify this task in the literature [
9,
10,
11,
12,
13]. Dimitrov et al. discussed five different methods, including Kriging and Polynomial Chaos Expansion (PCE), for load assessment using synthetic data [
14]. Their results indicate that the mean wind speed and turbulence intensity have the most significant effect on fatigue load estimation. In another study, Haghi and Crawford developed a PCE to map the random phases of synthetic wind to the loads on a wind turbine rotor [
15]. Most of the studies in the literature focus on the realm of Surrogate Model (SM)s, attempting to map wind speed by itself or combined with other relative variables to the fatigue or extreme loads of a wind turbine. In recent years, with the rapid growth of Machine Learning (ML) methods, there has been a shift towards using these methods for load assessment. Dimitrov et al. developed an Artificial Neural Network (ANN) to map different environmental conditions to the DEL on a turbine [
14]. Schröder et al. used ANN to develop a surrogate model capable of predicting the fatigue life of a wind turbine in a wind farm, considering changes in loads [
16]. More recently, Dimitrov and Göçmen developed a virtual sensor based on a sequential ML method that can provide load time series for different components of a wind turbine [
17].
Condition Monitoring (CM) for wind turbines is an activity that monitors the state of the turbine [
18]. CM is vital for wind turbines as it can reduce downtime, failure, and maintenance costs. There are various techniques available for the CM of wind turbines; however, many are either expensive or complex [
3,
8]. Consequently, utilizing data from SCADA for CM is appealing, as these data are available for the majority of turbines and do not incur additional costs [
19]. Tautz-Weinert and Watson provide an extensive review of the different CM methods that utilize data from SCADA. A few of these methods address damage modeling and fatigue of components. The concept behind damage modeling is to integrate measurements from SCADA with a physical model to understand better damage progression [
8]. Gray and Watson introduced a probability of failure methodology incorporating relatively simple failure models and successfully tested this method on a wind farm with a high rate of gearbox failure [
20]. Galinos et al. created a map of the fatigue life distribution for the Horns Rev 1 offshore wind farm turbines using SCADA wind speed measurements and aeroelastic simulations [
21]. Alvarez and Ribaric used SCADA to describe the wind turbine torque histogram and introduced a methodology for a physics-based gearbox fatigue failure prediction [
22]. Remigius and Natarajan utilized SCADA measurements to estimate the wind turbine main shaft using an inverse problem-based approach [
23]. The examples mentioned above are mainly based on a physics-driven approach.
In recent years, with the emergence of data-driven methods, the integration of SCADA measurements with ML-based methods has become more popular among researchers. Pandit et al. provided an extensive review of data-driven CM approaches [
24]. More specifically, data-driven methods using SCADA measurements have been increasingly adopted for predicting fatigue life and damage. Vera-Tudela and Kühn employed ANN to map wind farm varying flow conditions to fatigue loads and demonstrated the robustness of this method by using data from two distinct wind farms [
25]. Natarajan and Bergami found that an ANN could predict turbulence and loads on the blade and tower by considering rotor speed, power production, and blade pitch angle from SCADA measurements, validating the loads using an instrumented turbine [
26]. Mylonas et al. developed a regenerative model based on a convolutional variational autoencoder, capable of predicting DEL on a wind turbine blade root and the uncertainty of loads using only 10-min average SCADA data [
27].
A Gaussian Process (GP) is a type of ML technique used for both regression and classification problems. It is a data-driven, non-parametric method that does not rely on a specific functional form. Instead, it focuses on a distribution of functions that align with the data it is analyzing [
28]. The application of GP in wind turbine research and engineering has grown due to the ease of implementation, versatility, and adaptability of the method, as well as its ability to provide uncertainty estimates. For instance, Pandit and Infield utilized GPR to capture failures due to yaw misalignment using SCADA [
29]. Li et al. employed Gaussian Process Classification (GPC) to detect and predict wind turbine faults from SCADA data, where the provided probabilistic knowledge aids in maintenance management [
30]. Herp et al. utilized GP to forecast wind turbine bearing failure a month in advance based on wind turbine bearing temperature residuals [
31]. Avendaño-Valencia et al. predicted wind turbine loads in downstream wakes, calibrating a GPR based on local or remote wind or load measurements [
32]. Wilkie and Galasso assessed the fatigue calculation reliability of offshore wind turbines using a GPR, where inputs consisted of site-specific environmental conditions and turbine structural dynamics [
33]. Singh et al. employed chained GP to derive the probability distribution function of offshore wind turbine loads based on stochastic synthetic loads [
34].
1.1. Motivation
In this manuscript, we aim to create a simple yet dependable probabilistic model for predicting damage using limited SCADA measurements and utilizing publicly available wind turbine models. The inflow turbulence is stochastic, leading to load responses that are aptly represented as random variables. The influence of these unpredictable factors on loads heavily depends on average environmental conditions and their variance. This variance in load response, known as heteroscedasticity in statistical terms, implies that at lower wind speeds, the inflow turbulence has a lesser impact on load variability compared to higher wind speeds [
34]. Heteroscedasticity directly affects the DEL of a wind turbine. The challenge is that to obtain an accurate distribution of the DELs for an operational turbine, we require many data points. Ideally, this could be achieved with an extensive array of sensors on wind turbines, which is not feasible. One approach involves running simulations to enrich the database and attain improved distributions. However, two primary challenges exist: (a) the models lack accuracy, and (b) wind turbine manufacturing companies view models as their intellectual property, making them generally inaccessible.
Given these challenges, our proposal is not for a highly accurate model to predict the DEL down to the minutest details. Instead, we advocate for a straightforward methodology to offer a probabilistic model built on hybrid SCADA and publicly available turbine models. This model can approximate the DEL distribution at each wind speed and demonstrate the trend of the DEL distribution as wind speed varies. Although this model might not be precise enough to indicate the remaining useful lifetime with high accuracy, it can roughly gauge the turbine fatigue health condition and relative damage of machines within a wind farm. Such a model can serve as a quick indicator to pinpoint turbines at risk, warranting further investigation. Additionally, it can assist in reducing the uncertainty of a turbine’s health condition for financial and banking purposes. This model demonstrates benefits for “asset reliability” and “asset health”, especially in mitigating investor risks when considering the purchase of operational wind farms.
1.2. Objective
For this research, we had access to a year’s worth of data from an undisclosed turbine in an undisclosed onshore wind farm’s SCADA system. The objectives of this manuscript are as follows:
Create a database of synthetic DEL based on publicly available turbine models with SCADA wind measurements as input.
Develop a probabilistic model based on the database that represents the distribution of the descriptive statistics and DEL at varying wind speeds.
Validate the probabilistic model by contrasting its output with the limited available measurements.
1.3. Paper Outline
The paper is organized as follows:
Section 2 starts with an overview of the methodology, depicted in
Figure 1, and continues with a description of the SCADA system used in the study, including data collection and processing methods. This is followed by an explanation of joint distributions and sampling in
Section 2.2, and the basics of aero-servo-elastic simulations and their post-processing.
Section 2.5 introduces the Gaussian Process Regression (GPR) methodology applied in this study and concludes
Section 2 with a definition of the error metrics used.
Section 3 begins with the conditions under which results are extracted and GPR models are trained, continuing with the validation of these models against empirical data. The accuracy of the trained GPR, using hybrid data, is compared with both simulations and SCADA data in
Section 3.1 and
Section 3.6.
Section 3 ends with proposed practical applications for the developed model. The manuscript concludes with
Section 4, summarizing the main findings and suggesting future research in using GPRs for wind turbine primary health assessment.
2. Methods
This section presents the methodology used to construct a GPR model using hybrid simulation and validate the GPR predictions against both hybrid simulation and SCADA measurements.
Figure 1 provides an overview of our approach, consisting of four blocks. The arrows illustrate the data flow between these blocks, databases, and processes. Hereafter, “wind speed” refers to the measured wind speed from SCADA, unless otherwise specified. It is worth mentioning that the wind speed sensor on a wind turbine is typically placed on top of the nacelle behind the rotor, and its readings differ from the true inflow wind speed.
The hybrid simulations generation block demonstrates the procedure for generating hybrid simulation data from SCADA measurements. Termed “hybrid”, this data combines SCADA measurements with synthetic data generation to create a comprehensive database. The SCADA data is binned to a resolution of 1 m/s, spanning the cut-in and cut-out wind speeds. The turbine in this study operates between 3 m/s and 25 m/s. For each bin, we establish a joint distribution of mean wind speed and STD of wind speed. The mean wind speed adheres to a uniform distribution between the bin’s upper and lower bounds, whereas the wind speed STD distribution sampling per bin is tested on both Weibull and uniform distributions separately.
Subsequently, using Sobol sampling, n samples are drawn from this joint distribution for each wind speed. Each sample, comprising a mean and STD of wind speed, generates a synthetic wind field. This results in a corresponding synthetic wind field per sample. These synthetic wind fields and the wind turbine model are inputs to the aero-servo-elastic simulator. The simulator outputs load time series for various components of the wind turbine model. These load time series are post-processed to extract statistical descriptions (minimum, maximum, mean, and STD) and the DEL for each component. In this manuscript, the post-processed outputs are termed Quantity of Interest (QoI). The QoI are stored in a database, referred to as the post-processing database.
The Gaussian Process Regression block outlines the technique employed to build the GPR model using hybrid simulation output. The post-processing database is initially scaled using the MinMax method to normalize all data fields between 0 and 1. The database is then divided into two non-overlapping datasets: Training and Testing. A separate GPR model is trained for each QoI for each wind turbine component load. The GPR model outputs the mean and STD of the QoI at each wind speed, representing the prediction data statistics. The testing data similarly provides the mean and STD of the QoI at each wind speed, known as the testing data statistics.
Figure 1 illustrates two validation blocks: Hybrid Validation and SCADA Validation. For Hybrid Validation, the testing data statistics are compared against the prediction data statistics. If the SCADA data include tower top acceleration or blade load statistics, the GPR prediction distribution for these is also validated.
In the following sections, we delve into the processes and steps depicted in
Figure 1 in greater detail.
2.1. Supervisory Control and Data Acquisition Measurement, Binning, and Scaling
The comprehensiveness of the collected SCADA data offers a wide range of insights for system analysis. Notably, the SCADA data encompasses numerous data fields, with our primary interest in wind speed statistics for hybrid simulation database generation, generated power for wind turbine model validation, and, if available, tower top acceleration and blade load statistics for measurement validation.
We binned the SCADA data based on mean wind speed to gain a broader perspective on wind turbine operation through the wind speed statistics. The bin center corresponds to an integer wind speed value, with the upper and lower bounds set at m/s of that value. For each bin, we calculated the mean of the measured mean wind speed, the mean of the STD of the wind speed, and the STD of the STD of the wind speed, resulting in three wind speed statistics for each bin.
MinMax scaling is a common pre-processing step in data analysis and machine learning, involving transforming features to a specified range, often
[
35]. According to Rasmussen and Williams, scaling the data is recommended for GPR to ensure numerical stability [
28]. For the post-processing database, we scaled the data based on the minimum and maximum values in each wind turbine channel output, effectively constraining each scaled post-processed output to the
range. Additionally, if SCADA loads or acceleration measurements were available, they were scaled similarly to facilitate comparison with the GPR output. Furthermore, we adopted MinMax scaling for all output data in compliance with confidentiality requirements.
2.2. Joint Distributions and Sampling
Hybrid simulation data generation aims to build a comprehensive database of the loads on a wind turbine, closely resembling real-world conditions. This process, known as data assimilation [
36], merges observational data (in our case, SCADA data) with model predictions to produce a more complete estimate of the current state of the system and future evolution. One approach to account for measurement uncertainties is to define them as random variables with specific distributions. We utilized wind speed statistics extracted in
Section 2.1 to construct joint distributions of mean wind speed and the STD of wind speed for each bin. A uniform distribution was defined to cover the full range of the bin for the mean wind speed equally. Regarding the STD, we opted to test two alternatives: (a) fitting a Weibull distribution to the STD of wind speed, and (b) applying a uniform distribution to the STD, with bounds set at the minimum and maximum values per bin. The assumption of a uniform distribution for wind speed has been previously established in literature [
14,
16]. The choice of a Weibull distribution for the STD is based on data observations, and a uniform distribution is selected to encompass all possibilities, particularly when SCADA measurements in a bin are unavailable.
We employed the Quasi Monte Carlo (QMC) Sobol sampling technique, as detailed in [
37]. This method is preferred in our study for its reliability and computational efficiency, as noted in [
38]. Sobol’s technique is repeatable and ensures enhanced uniformity across sampled distributions, a feature emphasized in [
39]. Hereinafter, “the sample” refers to a two-data-point vector comprising mean wind speed and STD of wind speed. We took
n samples per bin, resulting in
n unique samples for
m bins, which are then used to generate
synthetic wind time histories.
2.3. Synthetic Wind Generation, Wind Turbine Models, and Aero-Servo-Elastic Simulations
To perform aero-servo-elastic simulations, we require synthetic wind time histories that closely resemble real-world wind conditions experienced by the turbine. To achieve this, we constructed joint distributions from the SCADA measurements and calculated statistics for each wind speed bin as explained in
Section 2.2. The objective was to generate synthetic wind time histories that faithfully replicate the actual wind conditions corresponding to the mean and STD of wind samples. To do so, we used the samples’ wind speed and STD as the input to TurbSim [
40]. The output of TurbSim is a “full-field” wind time history in TurbSim format. TurbSim, a synthetic wind generator, produces wind time histories with both spatial and temporal components for aero-servo-elastic simulators. A comprehensive explanation of this synthetic wind generator can be found in [
40].
The resulting
full-field synthetic wind time series are stored in the synthetic wind database. The full-field synthetic wind data serve as the environmental input for our aero-servo-elastic simulator. These simulations require synthetic wind time series and the integration of aerodynamic, aeroelastic, and controller models. Each wind turbine model encompasses modules for aerodynamics, aeroelasticity, and control. To conduct these simulations, we employed OpenFAST, an aero-servo-elastic solver developed by National Renewable Energy Lab (NREL) [
41]. The output from OpenFAST provides detailed load information for various wind turbine components, including blades, towers, and gear systems, spanning both time and space. Our simulations adhere to the IEC standards for energy production under Design Load Case (DLC) 1.2, as specified in the IEC standards [
42].
The provided SCADA data correspond to a year’s worth of data, which include loads and acceleration data. However, as the turbine models are the intellectual property of the wind turbine manufacturers, we did not have access to them. Therefore, we opted for the NREL 5MW turbine for the aero-servo-elastic simulations [
43] as this model is well established in the literature, demonstrates robustness against fluctuations in wind speed seed during simulations, the controller is well defined, and the rotor size is comparable with the turbine we have access to the SCADA measurements. Moreover, our tests indicate that the NREL 5MW model provides simulation results most similar to SCADA data at hand compared to other publicly available turbines [
44,
45,
46].
2.4. Post-Processing Database
We have compiled a comprehensive database incorporating all time series data from the simulation outputs. Following its creation, the data underwent post-processing to derive simulation QoI, namely, descriptive statistics and DEL for assessing loads and fatigue. Additionally, DEL computation adheres to the Palmgren–Miner linear damage rule, as elaborated in [
47,
48]. The DEL can be expressed as follows:
Here,
m represents the Wöhler slope, while
and
pertain to load ranges and the corresponding number of cycles, respectively. The DEL outcome is derived through rainflow counting of the load time series [
47,
49].
denotes the equivalent number of load cycles, typically equivalent to the length of the simulations in seconds. The post-processing database encompassed all calculated descriptive statistics and DELs from every simulation output.
Subsequently, the post-processing database is subjected to MinMax scaling and binning, which were explained in
Section 2.1.
2.5. Gaussian Process Regression
GPR is a non-parametric Bayesian method widely used for regression tasks [
28]. At the core of GPR lies its assumption that observed target values follow a multivariate Gaussian distribution. One of its notable features is its ability to provide probabilistic predictions, offering both mean and variance functions to quantify prediction uncertainty. Given a dataset
, a Gaussian Process defines a distribution over functions characterized by a mean function
and a covariance (kernel) function
. The GPR can be expressed as:
where,
represents the mean function, and
is the covariance function, capturing the data point relationships. Predictions
at new data points
are expressed as predictive mean
and variance
:
where
K is the covariance matrix for the training data,
represents the covariance matrix between training and test data, and
is the covariance matrix for the test data.
y is the vector of training targets, and
is the noise variance. Typically, noise variance and other hyperparameters of GPR and kernel function parameters are estimated from the data, often using techniques like maximum likelihood estimation. The log-likelihood of observations conditioned on hyperparameters is expressed as:
where
y represents the vector of observed target values,
is the covariance matrix calculated using the kernel function for training inputs, and
denotes the noise variance.
signifies the determinant of the matrix, and
N is the dataset size. Maximum likelihood estimation aims to determine the hyperparameters
that maximize this log-likelihood.
For the problem at hand, the
x values are the wind speeds, and the
y values are the QoI. Recalling the number of bins
m and the number of samples
n, we have
data points, which can result in a large number of data. Moreover, the target data
y is a heteroscedastic variable. In our case, it means the data variance is not constant across wind speeds. Due to these two characteristics of the data at hand, standard GPR formulation is ineffective for our purpose. The standard GPR method implementations require
computation, where
n is the number of data samples [
50]. Furthermore, standard GPR assumes the variance across the data is constant. [
51]. To tackle these two, we used Approximate Gaussian Process Regression (AGPR) for the large-size dataset challenge with “inducing points” [
50] and Predictive Log Likelihood (PLL) for the heteroscedasticity challenge [
52]. AGPR introduces a set of inducing points or pseudo-inputs representing a subset of the training data. The GP is conditioned on these inducing points rather than the entire dataset, reducing computational complexity [
50]. The standard likelihood tries to maximize the posterior estimation, while PLL, instead of estimating the posterior, directly aims for the posterior distribution estimation [
52]. Both of these methods have been thoroughly explained in various literature. For a deeper understanding of these methods, readers are encouraged to refer to [
50,
52,
53]. In this work, we utilized
GPyTorch for building the GPR models [
54].
2.6. Measurement Statistics and Error Metrics
If the SCADA measurement data include loads or tower top acceleration information, it offers an opportunity to compare these data points with the AGPR output. Given that the output from AGPR is probabilistic, processing the SCADA measurement data to extract relevant statistics becomes necessary. This procedure mirrors the one detailed in
Section 2.1. Initially, we scale the measurements using MinMax scaling. Subsequently, we categorize the scaled SCADA measurement loads and acceleration data based on SCADA wind speed measurements and then calculate the mean and STD of acceleration and loads within each bin.
We assess the disparity between the SCADA measurement and AGPR output, or between the AGPR output and the testing datasets, using Kullback-Leibler (KL) divergence. The KL divergence is formulated as:
where, in (
6),
G represents the AGPR output with mean
and variance
, and
M signifies the measurement or simulation data with mean
and variance
. This comparison involves computing the KL divergence, with the testing database and SCADA measurement serving as the reference or “ground truth”. In cases where we have samples from both AGPR and SCADA, the KL divergence is formulated as:
where
and
are the probability distributions at bin
i for the two distributions, respectively. The bins are set identically for both distributions. The KL divergence has the minimum value of zero and no upper bound. If the KL divergence is zero, it indicates that the two distributions being compared are identical. Therefore, smaller values are preferable. For a more detailed discussion of this topic, interested readers are referred to Murphy [
55].
4. Conclusions
This work emphasizes the crucial need for assessing the structural health of wind turbines, given their operation in harsh environmental conditions. This assessment is vital for ensuring the longevity and optimal performance of wind turbines. The focus is on understanding the fatigue damage accumulation in these structures and the importance of advanced methods for accurate prediction and monitoring of their structural health. The methodology section details the construction of a AGPR model using a combination of the SCADA wind measurement and simulations utilizing Sobol’s sampling method. It presents a systematic method involving the generation of hybrid simulation, followed by its use in modeling and validation. The final section first explains the conditions under which the results were generated, followed by a presentation and discussion of these findings. Then, it shows the accuracy of the utilized model by comparing the simulation output and SCADA measurement for the generated power and rotor speed. Afterwards, the section shows how a AGPR trained on the hybrid simulations database accurately predicts the testing dataset and the SCADA acceleration and loads data fields. It also explores the model’s accuracy, reliability, and ability to predict potential structural issues. The results are not just numerical outputs; they are interpreted to provide insights into the overall effectiveness of the AGPR model in real-world scenarios.
This research conclusively demonstrates the efficacy and robustness of AGPR in the realm of wind turbine asset reliability. The research underscores the advanced predictive capabilities of AGPR, particularly in handling the heteroscedasticity inherent in wind turbine operational data. The ability of AGPR to accurately model and predict loads and accelerations based on a range of inputs, especially those derived from SCADA systems, while it is trained on the publicly available models and methodology is a noticeable development. It is worth noting that our tests have revealed that the choice of publicly available wind turbine model impacts the accuracy and compatibility of the trained AGPR model with the SCADA measurements. This study elaborates on how AGPR is effectively trained on hybrid simulation datasets, blending real-world measurements with simulated data to create a comprehensive model. This approach allows a better understanding of the data and enhances the model’s predictive accuracy. The research highlights the validation processes the AGPR model underwent, affirming its reliability and accuracy. The performance of the AGPR models in predicting the loads under various operational scenarios showcases its practical applicability in real-world settings. The paper points out the potential for AGPR to serve as a standard tool in the predictive maintenance of wind turbines.
While the AGPR model demonstrates promising capabilities in predicting DEL, it is important to recognize the challenges faced in this study. The lack of data about the measurement of turbine natural frequencies, dependence on specific data fields, and the limitations posed by the unavailability of the measurement wind turbine model are notable challenges. Furthermore, the transferability of the model and whether the model can be applied to various turbine types and operational scenarios, including extreme events, remains to be tested.
4.1. Future Work
Considering the fact that the model employed in this study is publicly available, and the turbine manufacturer’s model is not accessible, the performance of the AGPR for the purposes of this work is promising. For future research, there is an ambition to extend this study and test the hypothesis mentioned in
Section 3.8 on a turbine equipped with sensors. Additionally, having access to more extensive and varied data fields in SCADA would be beneficial. This would help in reducing measurement uncertainties, particularly at higher wind speeds, and in fine-tuning the model for outputs that more closely reflect reality. Ideally, access to the actual wind turbine model would substantially enrich this research. Moreover, it is important to demonstrate the generalizability of this approach by implementing it on an offshore wind turbine in future work.
In the realm of data-driven modeling, we employed AGPR for this study with remarkable results. Nevertheless, exploring other methods, such as probabilistic neural networks or Bayesian neural networks, is crucial. Another avenue could involve moving away from probabilistic models and experimenting with ANNs to map environmental inputs to loads. Additionally, considering SCADA data as a time series and employing a transformer, as discussed in [
60], could provide a novel approach to building a data-driven model that predicts loads based on a limited series of environmental and controller inputs.
In this study, our focus was primarily on data from power production DLCs. However, other significant events, such as shutdowns, gusts, and faults during a wind turbine’s lifetime, can impact its structural integrity. These scenarios are crucial and should be considered in future studies.