0382348 20240111140821.420121031235959.9 7 s. C cav_un_epca*0382347978-612-4057-71-71-7LimaTarea Asociación Gráfica Educativa, Lima, Peru2012 Fault detection and diagnosis nonlinear stochastic hybrid system B-spline functions probability density function(PDF) cav_un_auth*0284758 Nguyen H.Q. CZ cav_un_auth*0101074 Čelikovský Sergej Teorie řízení Department of Control Theory TŘ TR UTIA-B Department of Control Theory Ústav teorie informace a automatizace AV ČR, v. v. i. dokument 415 kB This paper studies the problem of the fault estimation for a class of time-varying faults using output probability density function (PDF). The system studied is a nonlinear stochastic hybrid system with time-dependent switchings. The measured output is viewed as a stochastic process and its PDF is modeled, which leads to a deterministic dynamical model including nonlinearities and uncertainties. A new adaptive fault diagnosis algorithm is proposed to improve the performance of the fault estimation. The proposed algorithm contains both the proportional and the integral term. The proportional term can improve the speed of the fault estimation, while the integral term can eliminate estimation error. Then, based on linear matrix inequality (LMI) technique, a feasible algorithm is explored to solve the designed parameters. Additionally, simulation results are given to show the e ciency of the proposed approach. cav_un_auth*0284759 15th Latinamerican Control Conference CLCA 2012 Lima 23.10.2012-26.10.2012 PE 2013 BC 2 PR RVO:67985556 http://hdl.handle.net/11104/0212588 2012 dokument 415 kB cav_un_epca*0382347 Memoria XV Congreso Latinoamericano de Control Automático CLCA 2012 Proceedings 978-612-4057-71-7 1 7 Memory XV Latin American Congress on Automatic Control CLCA 2012 Proceedings Lima Tarea Asociación Gráfica Educativa, Lima, Peru 2012 2012-12868