Uncertainty Propagation In Diagnostic Systems Based On Soft Computing Techniques

This paper presents the analysis of measurement uncertainty propagation in algorithms for the synthesis of one fault risk index for diagnostic applications. The reference application is non-invasive diagnostic of three-phase induction motor drives. This work focuses on algorithms for fault index calculation based on neuro-fuzzy networks and wavelet decomposition of acquired data. The impact on the index of the shape of fuzzy membership functions, the number of training epochs and is first analyzed. Then the propagation of uncertainty through the neuron-fuzzy network is assessed with a numerical approach.