Comparison of anomaly detection techniques for wind turbine gearbox SCADA data Article Swipe

View

Related Concepts

Anomaly detection Nonlinear autoregressive exogenous model Turbine Autoregressive model SCADA Anomaly (physics) Wind power Support vector machine Computer science Nonlinear system Artificial neural network Artificial intelligence Data mining Engineering Mathematics Econometrics Condensed matter physics Electrical engineering Physics Quantum mechanics Mechanical engineering

Conor McKinnon , James Carroll , Alasdair McDonald , Sofia Koukoura , Conaill Soraghan ·

YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.5281/zenodo.4550705 · OA: W2982345113

This analysis looks at the use of anomaly detection to assess the condition of wind turbine gearboxes based on data from a number of operational turbines. A comparison is made between various methods of anomaly detection, these being one class support vector machine (OCSVM), random forests, and nonlinear autoregressive neural networks with exogenous inputs (NARX).