Accession Number : ADA256206


Title :   Neural Network Based Propulsion System Fault Diagnostics for the NPS AUV II


Descriptive Note : Master's thesis


Corporate Author : NAVAL POSTGRADUATE SCHOOL MONTEREY CA


Personal Author(s) : Navarrete, III, Juan A


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a256206.pdf


Report Date : Jun 1992


Pagination or Media Count : 68


Abstract : The use of artificial neural networks to provide a method of detecting and isolating impending failures in an autonomous underwater vehicle propulsion system has been studied. Two types of fault diagnostic systems, each capable of detecting different types of faults, were designed. The first system addresses the fault identification process by looking at the raw data available from system sensors. The second design processes sensor data with a Kalman filter before it is input to a neural network. The Kalman filter was designed to identify system parameters that characterize its dynamic response. These parameters serve as input to the network. This system is capable of fault detection, isolation, and seventy determination.


Descriptors :   *NEURAL NETS , *UNDERWATER VEHICLES , *UNDERWATER PROPULSION , INPUT , DETECTION , NETWORKS , DYNAMICS , PARAMETERS , DYNAMIC RESPONSE , FAILURE , ISOLATION , KALMAN FILTERING , THESES , IDENTIFICATION , PROPULSION SYSTEMS , RESPONSE , VEHICLES , FILTERS , DETERMINATION , UNDERWATER , FAULTS


Subject Categories : Submarine Engineering


Distribution Statement : APPROVED FOR PUBLIC RELEASE