Model-based fault diagnosis of a DC motor

The main goals of the fault diagnosis methods are reliability and robustness, because they allow these methods to be implemented in industrial systems. The uncertainty of the system models, the presence of noise and the stochastic behaviour of several variables make it hard to reach these goals. To tackle this kind of problems, this paper presents a decision-making module based on fuzzy logic for model-based fault diagnosis applications. The fuzzy rules use the concept of fault possibility and the knowledge of the sensitivities of the residual equations. A fault detection and isolation system, based on the input-output model parity equations approach, with this decision-making module has been applied successfully in laboratory equipment, resulting in a reduction of the uncertainty due to disturbances and modeling errors. Furthermore, the fault sizes have been estimated with sufficient accuracy.