GONCALVES, I.M.P.UPADHYAYA, B.R.2014-11-172014-11-182015-04-022014-11-172014-11-182015-04-02GONCALVES, I.M.P.; UPADHYAYA, B.R. Multiple fault detection and isolation using GMDH model. In: CONGRESSO BRASILEIRO DE ENGENHARIA MECANICA, 16., 26-30 nov, 2001, Uberlandia, MG. Disponível em: http://repositorio.ipen.br/handle/123456789/15289.http://repositorio.ipen.br/handle/123456789/15289This study developed a Multiple Fault Detection algorithm using GMDH (Group Method for Data Handling) that is an algebraic model for system characterization. The GMDH provides a general framework for characterizing the relationship amonga set of state variables of a process and is used for generating estimates of critical variables in an optimal data-driven model form. It was developed a decision module that includes a rule-based logic for detecting two simultaneous faults in sensors and actuators (valves, controllers, pumps, etc.). The effectiveness of the method developed in this research was demonstrated through simulation and by implementation to an experimental control loop. The test loop consisted of a level control system; flow, pressure, level and temperature measuring sensors, motor operated valves, and a pump. The simulation model of the experimental control loop was implemented in Matlab-Simulink.openAccessreactor monitoring systemsalgorithmscontrol equipmentdata acquisitionmathematical modelscomputerized simulationTexto completo de evento