scholarly journals Comparison of New Anomaly Detection Technique for Wind Turbine Condition Monitoring Using Gearbox SCADA Data

Energies ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 5152
Author(s):  
Conor McKinnon ◽  
James Carroll ◽  
Alasdair McDonald ◽  
Sofia Koukoura ◽  
David Infield ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Anomaly Detection ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Support Vector ◽  
Specific Training ◽  
Average Accuracy ◽  
Operations And Maintenance ◽  
Novel Method ◽  
Isolation Forest

Anomaly detection for wind turbine condition monitoring is an active area of research within the wind energy operations and maintenance (O & M) community. In this paper three models were compared for multi-megawatt operational wind turbine SCADA data. The models used for comparison were One-Class Support Vector Machine (OCSVM), Isolation Forest (IF), and Elliptical Envelope (EE). Each of these were compared for the same fault, and tested under various different data configurations. IF and EE have not previously been used for fault detection for wind turbines, and OCSVM has not been used for SCADA data. This paper presents a novel method of condition monitoring that only requires two months of data per turbine. These months were separated by a year, the first being healthy and the second unhealthy. The number of anomalies is compared, with a greater number in the unhealthy month being considered correct. It was found that for accuracy IF and OCSVM had similar performances in both training regimes presented. OCSVM performed better for generic training, and IF performed better for specific training. Overall, IF and OCSVM had an average accuracy of 82% for all configurations considered, compared to 77% for EE.

scholarly journals SCADA Data-Based Support Vector Machine Wind Turbine Power Curve Uncertainty Estimation and Its Comparative Studies

2020 ◽  
Vol 10 (23) ◽  
pp. 8685
Author(s):  
Ravi Pandit ◽  
Athanasios Kolios
Keyword(s):  
Support Vector Machine ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Offshore Wind ◽  
Data Driven ◽  
Accurate Estimation ◽  
Support Vector ◽  
Offshore Wind Turbine ◽  
Power Curve ◽  
Power Curves

Power curves, supplied by turbine manufacturers, are extensively used in condition monitoring, energy estimation, and improving operational efficiency. However, there is substantial uncertainty linked to power curve measurements as they usually take place only at hub height. Data-driven model accuracy is significantly affected by uncertainty. Therefore, an accurate estimation of uncertainty gives the confidence to wind farm operators for improving performance/condition monitoring and energy forecasting activities that are based on data-driven methods. The support vector machine (SVM) is a data-driven, machine learning approach, widely used in solving problems related to classification and regression. The uncertainty associated with models is quantified using confidence intervals (CIs), which are themselves estimated. This study proposes two approaches, namely, pointwise CIs and simultaneous CIs, to measure the uncertainty associated with an SVM-based power curve model. A radial basis function is taken as the kernel function to improve the accuracy of the SVM models. The proposed techniques are then verified by extensive 10 min average supervisory control and data acquisition (SCADA) data, obtained from pitch-controlled wind turbines. The results suggest that both proposed techniques are effective in measuring SVM power curve uncertainty, out of which, pointwise CIs are found to be the most accurate because they produce relatively smaller CIs. Thus, pointwise CIs have better ability to reject faulty data if fault detection algorithms were constructed based on SVM power curve and pointwise CIs. The full paper will explain the merits and demerits of the proposed research in detail and lay out a foundation regarding how this can be used for offshore wind turbine conditions and/or performance monitoring activities.

NUMERICAL SIMULATION AND VALIDITY OF A NOVEL METHOD FOR THE PREDICTION OF ARTERY STENOSIS VIA INPUT IMPEDANCE AND SUPPORT VECTOR MACHINE

2014 ◽  
Vol 26 (01) ◽  
pp. 1450002 ◽  
Author(s):  
Hanguang Xiao
Keyword(s):  
Support Vector Machine ◽  
Input Impedance ◽  
Recursive Algorithm ◽  
Artery Stenosis ◽  
Support Vector ◽  
Arterial Tree ◽  
Novel Method ◽  
The Mean ◽  
Fold Cross Validation ◽  
Systemic Arterial Tree

The early detection and intervention of artery stenosis is very important to reduce the mortality of cardiovascular disease. A novel method for predicting artery stenosis was proposed by using the input impedance of the systemic arterial tree and support vector machine (SVM). Based on the built transmission line model of a 55-segment systemic arterial tree, the input impedance of the arterial tree was calculated by using a recursive algorithm. A sample database of the input impedance was established by specifying the different positions and degrees of artery stenosis. A SVM prediction model was trained by using the sample database. 10-fold cross-validation was used to evaluate the performance of the SVM. The effects of stenosis position and degree on the accuracy of the prediction were discussed. The results showed that the mean specificity, sensitivity and overall accuracy of the SVM are 80.2%, 98.2% and 89.2%, respectively, for the 50% threshold of stenosis degree. Increasing the threshold of the stenosis degree from 10% to 90% increases the overall accuracy from 82.2% to 97.4%. Increasing the distance of the stenosis artery from the heart gradually decreases the overall accuracy from 97.1% to 58%. The deterioration of the stenosis degree to 90% increases the prediction accuracy of the SVM to more than 90% for the stenosis of peripheral artery. The simulation demonstrated theoretically the feasibility of the proposed method for predicting artery stenosis via the input impedance of the systemic arterial tree and SVM.

scholarly journals Value-Centric Approaches to Design, Operations, and Maintenance of Wind Turbines

2013 ◽  
Author(s):  
Madhur A. Khadabadi ◽  
Karen B. Marais
Keyword(s):  
Wind Turbine ◽  
Condition Monitoring ◽  
Wind Farm ◽  
Net Present Value ◽  
Operating Cost ◽  
Optimal Level ◽  
Two Dimensions ◽  
Alternative View ◽  
Operations And Maintenance ◽  
Farm Operators

Wind turbine maintenance is emerging as an unexpectedly high component of turbine operating cost and there is an increasing interest in managing this cost. Here, we present an alternative view of maintenance as a value-driver, and develop an optimization algorithm to maximize the value delivered by maintenance. We model the stochastic deterioration of the turbine in two dimensions: the deterioration rate, and the extent of deterioration, and view maintenance as an operator that moves the turbine to an improved state in which it can generate more power and so earn more revenue. We then use a standard net present value (NPV) approach to calculate the value of the turbine by deducting the costs incurred in the installation, operations and maintenance from the revenue due to the power generation. The application of our model is demonstrated using several scenarios with a focus on blade deterioration. We evaluate the value delivered by implementing blade condition monitoring systems (CMS). A higher fidelity CMS allows the blade state to be determined with higher precision. With this improved state information, an optimal maintenance strategy can be derived. The difference between the value of the turbine with and without CMS can be interpreted as the value of the CMS. The results indicate that a higher fidelity (and more expensive) condition monitoring system (CMS) does not necessarily yield the highest value, and, that there is an optimal level of fidelity that results in maximum value. The contributions of this work are twofold. First, it is a practical approach to wind turbine valuation and operation that takes operating and market conditions into account. This work should therefore be useful to wind farm operators and investors. Second, it shows how the value of a CMS can be explicitly assessed. This work should therefore be useful to CMS manufacturers and wind farm operators.

Sign in / Sign up

Export Citation Format

Share Document