Condition monitoring of wind-power units using the Derivative-free nonlinear Kalman Filter

Abstract

The article proposes a method for diagnosing faults and cyberattacks in electric power generation units that consist of a wind-turbine and of an asynchronous (DFIG) generator. The method relies on a differential flatness theory-based implementation of the nonlinear Kalman Filter, known as Derivative-free nonlinear Kalman Filter. The estimated outputs provided by the Kalman filter are subtracted from the real outputs measured from the power unit, thus generating the residuals sequence. It is proven that the sum of the squares of the residuals vectors, weighted by the inverse of the residuals covariance matrix, stands for a stochastic variable that follows the χ2 distribution. By exploiting the statistical properties of the χ2 distribution one can define confidence intervals which allow for deciding at a high certainty level about the appearance of a fault or cyberattack in the wind-power system.