Abstract:

Under most circumstances, it is most important to achieve fast and real-time fault detection. Regarding faults as dynamic modes which are observed through the multi-sensors, with probabilistic data association based on multi-sensor, the fault detection results are obtained according to the association probability and threshold values. Joint probabilistic data association (JPDA) algorithm is one of the effective ways for multi-sensor multi-target tracking, and the JPDA algorithm is here improved: first, an approximation method is proposed for constructing the confirmation matrix through removing the small probability events using the right threshold values; and then, the mathematical division of the confirmation matrix is presented according to the intersection area of the association gate of fault targets to be tracked; lastly, the association probability of fault target is computed through attenuating the value of the public measurement. The simulation results show preliminarily that the improved JPDA algorithm saves the computing time greatly, and effectively meets the requirements of fast and real-time fault detection.

Key words: fault , detection,  , data , association,  , confirmation , matrix,  , association , probability