Use of Hopfield networks for system identification and failure detection in autonomous underwater vehicles
Marsilio, Alan M.
Healey, Anthony J.
MetadataShow full item record
In the early 1980's John J. Hopfield developed a recurrent network based on a model of biological neurons. In his model, each neurons accepts inputs from all other neurons in the network, modifies each input with a weight and converts their sum to an output via the non-linear sigmoid transfer function. This output is then fed back to each of the input paths where the input signals are updated before the next summation. It has been proposed that this network can be successfully applied to the problem of system parameter identification where the weights are functions of the system states and the network, after being allowed to process a continuous block of system states, is guaranteed to converge to the system parameters. This thesis explored the concepts of network stability and solution existence for a time-invariant system. It is shown that the network will converge as expected provided the steady-state solutions falls within the range of values of the sigmoid transfer function. Experimentation with the network when not all system states are measurable revealed that knowledge of the actual system parameters is necessary to obtain convergence because of large error between the actual and estimated system states, showing that minimization of this error must take place before the network is integrated. Finally, it is shown that as system parameters vary, the Hopfield network will track the parameter changes provided the system remains persistently excited by the input.
RightsThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
Showing items related by title, author, creator and subject.
Naval Postgraduate School Center for Homeland Defense and Security (CHDS) (Monterey, California. Naval Postgraduate SchoolCenter for Homeland Defense and Security, 2006-07);July 2006. The July 2006 issue of Homeland Security Affairs offers articles about risk perception, domestic right wing extremist groups, social network analysis, and the impact of foreign policy on homeland security. It ...
Pietras, Christopher R. (Monterey, California. Naval Postgraduate School, 1993-09);The United States Coast Guard is upgrading communications equipment at remote sites in Alaska in support of the Coastal Voice Distress Network. The VHF-FM Search and Rescue sites are powered by a primary power system ...
Reinike, William J. (Monterey, CA; Naval Postgraduate School, 2020-06);This thesis builds a network representation of the U.S. financial system using data that is processed automatically from the U.S. Federal Reserve. We develop computational tools to import and clean the overall quarterly ...