FUZZY ASSOCIATIVE MEMORIES FOR INSTRUMENT FAULT-DETECTION

A fuzzy logic instrument fault detection scheme is developed for syste ms having two or three redundant sensors. In the fuzzy logic approach the deviation between each signal pairing is computed and classified i nto three fuzzy sets. A rule base is created allowing the human percep tion of the situation to be represented mathematically. Fuzzy associat ive memories are then applied. Finally, a defuzzification scheme is us ed to find the centroid location, and hence the signal status. Real-ti me analyses are carried out to evaluate the instantaneous signal statu s as well as the long-term results for the sensor set. Instantaneous s ignal validation results are used to compute a best estimate for the m easured state variable. The long-term sensor validation method uses a frequency fuzzy variable to determine the signal condition over a spec ific period. To corroborate the methodology synthetic data representin g various anomalies are analyzed with both the fuzzy logic technique a nd the parity space approach.