Wind Turbine Condition Monitoring Using SCADA Data and Data Mining Method

Wind turbine condition monitoring by the approach of SCADA data analysis

Chapter 2 - Wind turbine inspection and condition monitoring

Wind turbine condition monitoring is considered as a key task in wind power industry. A plethora of methodologies based on machine learning have been proposed but the absence of faulty data, at the amount and the variety needed, still set limitations. Therefore Anomaly Detection methodologies are proposed as alternatives for fault detection. Deep learning tools have been introduced in the research field of wind turbines’ monitoring for the purpose of higher detection accuracy. In this work, a deep learning-based anomaly detection method, the Deep Support Vector Data Description (Deep SVDD), is proposed for the monitoring of wind turbines. Compared to the classic SVDD anomaly detection approach, this method combines a deep network, more specifically a Convolutional Neural Network (CNN), with the SVDD detector in order to automatically extract effective features. To test and validate the effectiveness of the proposed method, the Deep SVDD method is applied on SCADA data from a real wind turbine use case, targeting to the ice detection on wind turbine blades. The experimental results show that the method can effectively detect the generation of ice on wind turbines’ blades with a successful detection rate of 91.45%.

As wind energy adoption is growing, ensuring the efficient operation and maintenance of wind turbines becomes essential for maximizing energy production and minimizing costs and downtime. Many AI applications in wind energy, such as in condition monitoring and power forecasting, may benefit from using operational data not only from individual wind turbines but from multiple turbines and multiple wind farms. Collaborative distributed AI which preserves data privacy holds a strong potential for these applications. Federated learning has emerged as a privacy-preserving distributed machine learning approach in this context. We explore federated learning in wind turbine condition monitoring, specifically for fault detection using normal behaviour models. We investigate various federated learning strategies, including collaboration across different wind farms and turbine models, as well as collaboration restricted to the same wind farm and turbine model. Our case study results indicate that federated learning across multiple wind turbines consistently outperforms models trained on a single turbine, especially when training data is scarce. Moreover, the amount of historical data necessary to train an effective model can be significantly reduced by employing a collaborative federated learning strategy. Finally, our findings show that extending the collaboration to multiple wind farms may result in inferior performance compared to restricting learning within a farm, specifically when faced with statistical heterogeneity and imbalanced datasets.

Deep Learning for fault detection in wind turbines

Gearbox oil temperature anomaly detection for wind turbine based on sparse Bayesian probability estimation

Availability and reliability are among the priority concerns for deployment of distributed generation (DG) systems, particularly when operating in a harsh environment. Condition monitoring (CM) can meet the requirement but has been challenged by large amounts of data needing to be processed in real time due to the large number of sensors being deployed. This paper proposes an optimal sensor selection method based on principal component analysis (PCA) for condition monitoring of a DG system oriented to wind turbines. The research was motivated by the fact that salient patterns in multivariable datasets can be extracted by PCA in order to identify monitoring parameters that contribute the most to the system variation. The proposed method is able to correlate the particular principal component to the corresponding monitoring variable, and hence facilitate the right sensor selection for the first time for the condition monitoring of wind turbines. The algorithms are examined with simulation data from PSCAD/EMTDC and SCADA data from an operational wind farm in the time, frequency, and instantaneous frequency domains. The results have shown that the proposed technique can reduce the number of monitoring variables whilst still maintaining sufficient information to detect the faults and hence assess the system’s conditions.

Condition monitoring of wind turbine for rotor fault detection under non stationary conditions

<p><span>This paper describes the design and implementation of Hardware in the Loop (HIL) system D.C. motor based wind turbine emulator for the condition monitoring of wind turbines. Operating the HIL system, it is feasible to replicate the actual operative conditions of wind turbines in a laboratory environment. This method simply and cost-effectively allows evaluating the software and hardware controlling the operation of the generator. This system has been implemented in the LabVIEW based programs by using Advantech- USB-4704-AE Data acquisition card. This paper describes all the components of the systems and their operations along with the control strategies of WTE such as Pitch control and MPPT. Experimental results of the developed simulator using the test rig are benchmarked with the previously verified WT test rigs developed at the Durham University and the University of Manchester in the UK by using the generated current spectra of the generator. Electric subassemblies are most vulnerable to damage in practice, generator-winding faults have been introduced and investigated using the terminal voltage. This wind turbine simulator can be analyzed or reconfigured for the condition monitoring without the requirement of actual WT’s.</span></p>

This paper proposes a two-stage data-driven methodology in condition monitoring (CM) of wind turbines (WTs). In the first stage, a fast and powerful network, namely a parallel generative adversarial network (PGAN) is proposed to resolve the problem of limited available information by generating artificial data. In the second stage, a robust deep network is designed based on a one-module Gabor filter oriented convolutional neural network and reformulation of a new loss function, namely robust deep Gabor network (RDGN). The experimental dataset of 3MW wind turbines in Ireland is used to verify the effectiveness of the proposed method and demonstrate the superiority of the proposed two-stage method in comparison with several state-of-the-art methods in terms of accuracy and reliability.

Some large wind turbines use a synchronous generator, directly-coupled to the turbine, and a fully rated converter to transform power from the turbine to the mains. This paper considers condition monitoring and diagnosis of mechanical and electrical faults in such a variable speed machine. A new condition monitoring technique is proposed in this paper, which removes the negative influence of variable wind in machine condition monitoring. This technique has a versatile function, able to detect both the mechanical and electrical faults in the wind turbine. Its effectiveness is validated by the experiments on a wind turbine condition monitoring test rig. Furthermore, a potential approach for diagnosing wind turbine drive-train mechanical faults using wind turbine generator electrical signals is introduced. The diagnosis of rotor imbalance in the wind turbine will be used as an illustrative example, heralding the detection of wind turbine electromechanical faults by power analysis. The paper offers a simpler and cheaper condition monitoring and fault diagnosis system for wind turbines.

A de-ambiguous condition monitoring scheme for wind turbines using least squares generative adversarial networks

Condition monitoring of wind turbine based on deep learning networks and kernel principal component analysis

The major wind turbine performance assessment methodology established in the field of wind energy is observing and comparing wind turbine power curves (WTPC) of multiple wind turbines. In this paper, adjustments to this method are proposed to improve overall accuracy of the assessment. While preprocessing the supervisory control and data acquisition (SCADA) data points, density peak clustering (DPC) filters out invalid points such as maintenance and peak-power limitation for a more accurate WTPC. This paper introduces a new variable, performance index "S", to evaluate both overall and segmented wind turbine performance without the influence of wind distribution. Further researches are also discussed in this paper.

This paper presents a data-driven approach to short-term wind turbine fault prediction and condition monitoring based on a hybrid architecture of recurrent neural network (RNN) and long short-term memory (LSTM). The proposed architecture is established by utilizing time series data from SCADA and a Bladed model of a 5 MW wind turbine to predict faults occurring to the wind generator. The RNN-LSTM training procedure is enhanced with self-organizing maps and LSTM auto encoder so as to describe the complex interaction between the mechanical system and unpredictable wind speed. To verify the performance of the proposed scheme, we conduct in-depth numerical experiments by applying the hybrid architecture to the Bladed 5 MW wind turbine model with rated wind speed of 11.8 m/s. Experiment results confirm that the proposed scheme has superior accuracy and practicality of fault prediction compared with eminent existing machine learning algorithms such as extreme gradient boost and random forest regressor.