Fuzzy Inference Based Monitoring Diagnostics and Prognostics

To date the majority of the research related to thedevelopment and application of monitoring diagnostic and prognosticsystems has been exclusive in the sense that only one of the threeareas is the focus of the work. While previous research progresses each ofthe respective fields the end result is a variable grab bag oftechniques that address each problem independently. Also the new field ofprognostics is lacking in the sense that few methods have beenproposed that produce estimates of the remaining useful life (RUL)of a device or can be realistically applied to real-world systems. Thiswork addresses both problems by developing the nonparametric fuzzyinference system (NFIS) which is adapted for monitoringdiagnosis and prognosis and then proposing the path classificationand estimation (PACE) model that can be used to predict the RUL of adevice that does or does not have a well defined failure threshold.