Estudo e aplicação de filtragem estocástica utilizando o filtro de Kalman

Abstract

This work has as main objective to introduce the fundamental concepts of the theory and practice of the Kalman filter. For this purpose, the fundamental concepts of probability, random processes and recursive estimators necessary for the understanding of the Kalman filter were presented, as well as the theoretical deduction of its equations and examples of implementation. In addition, two variations of the Kalman filter known as Extended Kalman filter and Unscented Kalman filter were presented, which are used when the systems studied present nonlinear dynamics. Finally, the Kalman filter was applied to the problem of fault detection in induction motors, generating very promising results and opening research possibilities in the study of electric machines using stochastic filtering.