18th International-Federation-of-Automatic-Control (IFAC) Conference on Technology, Culture and International Stability (TECIS), Baku, Azerbaijan, 13 - 15 September 2018, vol.51, pp.77-82
In this study the innovation approach based model change detection algorithm with multiple system noise scale factors (MSNSF) is proposed. Model of the system with additive changes is considered. It is proved that, the additive changes in system model causes a change in the innovation mean of Kalman filter. For the detection of changes in the innovation mean the MSNSFs are used as the monitoring statistic. Proposed innovation approach based model change detection algorithm with MSNSF is applied for the model of dynamics of an UAV platform. The actuator/surface faults which cause the additive changes in the mathematical model of the UAV are considered. The proposed approach makes it possible to perform the actuator/surface fault detection and isolation operations simultaneously. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.