This paper presents an anomaly detection approach using machine learning to achieve condition monitoring for wind turbines. The approach applies the information in supervisory control and data acquisition systems as data input. First, machine learning is used to estimate the temperature signals of the gearbox component. Then the approach analyzes the deviations between the estimated values and the measurements of the signals. Finally, the information of alarm logs is integrated with the previous analysis to determine the operation states of wind turbines. The proposed approach has been tested with the data experience of a 2MW wind turbine in Sweden. The result demonstrates that the approach can detect possible anomalies before the failure occurrence. It also certifies that the approach can remind operators of the possible changes inside wind turbines even when the alarm logs do not report any alarms.

This paper presents an anomaly detection approach using artificial neural networks and the wavelet transform for the condition monitoring of wind turbines. The method aims to attain early anomaly detection and to prevent possible false alarms under healthy operations. In the approach, nonlinear autoregressive neural networks are used to estimate the temperature signals of the gearbox. The Mahalanobis distances are then calculated to measure the deviations between the current states and healthy operations. Next, the wavelet transform is applied to remove noisy signals in the distance values. Finally, the operation information is considered together with the refined distance values to detect potential anomalies. The proposed approach has been tested with the real data of three 2 MW wind turbines in Sweden. The results show that the approach can detect possible anomalies before failure events occur and avoid reporting alarms under healthy operations.

This paper presents an anomaly detection approach using artificial neural networks and the wavelet transform for the condition monitoring of wind turbines. The method aims to attain early anomaly detection and to prevent possible false alarms under healthy operations. In the approach, nonlinear autoregressive neural networks are used to estimate the temperature signals of the gearbox. The Mahalanobis distances are then calculated to measure the deviations between the current states and healthy operations. Next, the wavelet transform is applied to remove noisy signals in the distance values. Finally, the operation information is considered together with the refined distance values to detect potential anomalies. The proposed approach has been tested with the real data of three 2 MW wind turbines in Sweden. The results show that the approach can detect possible anomalies before failure events occur and avoid reporting alarms under healthy operations.

In this article, a parametric model for health condition monitoring of wind turbines is developed. The study is based on the assumption that a wind turbine’s health condition can be modeled through three features: rotor speed, gearbox temperature and generator winding temperature. At first, three neural network models are created to simulate normal behavior of each feature. Deviation signals are then defined and calculated as accumulated time-series of differences between neural network predictions and actual measurements. These cumulative signals carry health condition–related information. Next, through nonlinear regression technique, the signals are used to produce individual models for considered features, which mathematically have the form of proportional hazard models. Finally, they are combined to construct an overall parametric health condition model which partially represents health condition of the wind turbine. In addition, a dynamic threshold for the model is developed to facilitate and add more insight in performance monitoring aspect. The health condition monitoring of wind turbine model has capability of evaluating real-time and overall health condition of a wind turbine which can also be used with regard to maintenance in electricity generation in electric power systems. The model also has flexibility to overcome current challenges such as scalability and adaptability. The model is verified in illustrating changes in real-time and overall health condition with respect to considered anomalies by testing through actual and artificial data.

This paper proposes an approach for maintenancemanagement of wind turbines based on their life. The proposedapproach uses performance analysis and anomaly detection(PAAD) which can detect anomalies and point out the originof the detected anomalies. This PAAD algorithm utilizes neuralnetwork (NN) technique in order to detect anomalies in theperformance of the wind turbine (system layer), and then appliesprincipal component analysis (PCA) technique to uncover theroot of the detected anomalies (component layer). To validatethe accuracy of the proposed algorithm, SCADA data obtainedfrom online condition monitoring of a wind turbine are utilized.The results demonstrate that the proposed PAAD algorithm hasthe capability of exposing the cause of the anomalies. Reducingtime and cost of maintenance and increasing availability and inreturn profits in form of savings are some of the benefits of theproposed PAAD algorithm.

During the past decade wind turbines have proven to be a promising source of renewable power. Wind turbines are generally placed in remote locations and are subject to harsh environmental conditions throughout their lifetimes. Consequently, the failures in wind turbines are expensive to repair and cause loss of revenue due to long down times. Asset management in wind turbines can aid in assessing and improving the reliability and availability of wind turbines, thereby making them more competitive. Maintenance policies play an important role in asset management and different maintenance models have been developed for wind turbine applications. Typically, mathematical models for maintenance optimization provide either an age based or a condition based preventive maintenance schedule. Age based preventive maintenance schedules provide the owner with the possibility to financially plan for maintenance activities for the entire lifetime of the wind turbine by providing the expected number of replacements for each component. However, age based preventive maintenance schedule may not consume the operating life of the wind turbine components to the maximum. Condition based maintenance scheduling has the advantage of better utilizing the operating life of the components. This paper proposes a wind turbine maintenance management framework which utilizes operation and maintenance data from different sources to combine the benefits of age based and condition based maintenance scheduling. This paper also presents an artificial neural network (ANN) based condition monitoring method which utilizes data from supervisory control and data acquisition (SCADA) system to detect failures in wind turbine components and systems. The procedures to construct ANN models for condition monitoring application are outlined. In order to demonstrate the effectiveness of the ANN based condition monitoring method it is applied to case studies from real wind turbines. Furthermore, a mathematical model called preventive maintenance schedule with interval costs (PMSPIC) is discussed and its application to a case study within the maintenance management framework is presented. The case study demonstrates the advantage of combining both the age based and condition based maintenance scheduling methods. 

The issue of applying high performance computing (HPC) techniques to computation-intensive probabilistic optimal power flow has not been well discussed in literature. In this paper, the probabilistic convex AC OPF based on second order cone programming (P-SOCPF) is formulated. The application of P-SOCPF is demonstrated by accounting uncertainties of loads. To estimate the distributions of nodal prices calculated from PSOCPF, two point estimation method (2PEM) is deployed. By comparing with Monte Carlo (MC) method, the accuracy of 2PEM is proved numerically. The computation efficiency of 2PEM outperforms MC significantly. In the context of large scale estimation, we propose to apply high performance computing (HPC) to P-SOCPF. The HPC accelerated P-SOCPF is implemented in GAMS grid computing environment. A flexible parallel management algorithm is designed to assign execution threads to different CPUs and then collect completed solutions. Numerical results from IEEE 118-bus and modified 1354pegase case network demonstrate that grid computing is effective means to speed up large scale P-SOCPF computation. The speed up of P-SOCPF computation is approximately equal to the number of cores in the computation node.

This paper proposes an approach for stress condition monitoring and maintenance assessment in wind turbines (WTs) through large amounts of collected data from the supervisory control and data acquisition (SCADA) system. The objectives of the proposed approach are to provide a stress condition model for health monitoring, to assess the WT’s maintenance strategies, and to provide recommendations on current maintenance schemes for future operations of the wind farm. At first, several statistical techniques, namely principal component analysis, Pearson, Spearman and Kendall correlations, mutual information, regressional ReliefF and decision trees are used and compared to assess the data for dimensionality reduction and parameter selection. Next, a normal behavior model is constructed by an artificial neural network which performs condition monitoring analysis. Then, a model based on the mathematical form of a proportional hazards model is developed where it represents the stress condition of the WT. Finally, those two models are jointly employed in order to analyze the overall performance of the WT over the study period. Several cases are analyzed with five-year SCADA data and maintenance information is utilized to develop and validate the proposed approach.

Gearbox has proven to be a major contributor toward downtime in wind turbines. The majority of failures in the gearbox originate from the gearbox bearings. An early indication of possible wear and tear in the gearbox bearings may be used for effective predictive maintenance, thereby reducing the overall cost of maintenance. This paper introduces a self-evolving maintenance scheduler framework for maintenance management of wind turbines. Furthermore, an artificial neural network (ANN)-based condition monitoring approach using data from supervisory control and data acquisition system is proposed. The ANN-based condition monitoring approach is applied to gearbox bearings with real data from onshore wind turbines, rated 2 MW, and located in the south of Sweden. The results demonstrate that the proposed ANN-based condition monitoring approach is capable of indicating severe damage in the components being monitored in advance.

This paper consolidates the data, analysis andobservations from a case study conducted in cooperation withthe Smart Grid Gotland project. The analysis identifies howelectrical power consumption interacts with distributedelectricity generation such as wind and solar power andpresents how it correlates to weather data and smart gridsolutions. The analysis model developed based on the Gotlandnetwork is generic and hence can be functional in investigatingother power networks of different size, voltage level andstructures. The key observations from the study of smart gridsolutions such as dynamic load capacity and energy storagesolutions are specified. Based on the project, an overview offuture risks and opportunities of smart grid systems is presented.