Fiscal Year	2016
Division	Graduate School of Engineering & Applied Science
Department	Electrical & Computer Engineering
Investigator(s)	Yun, Xiaoping
Sponsor	Office of Naval Research (Navy)
Summary	The objective of this study is to investigate the feasibility of using nonlinear control system methods, artificial neural networks in particular, to estimate and predict ship magnetic sensor data without using any physical models. More specifically, the objective is to develop methods for estimating the amount of off-board magnetic field based measurements from an array of onboard magnetic sensors. A prior study suggests that neural networks can potentially be used in applications for estimating and predicting ship magnetic field without a ship model. Neural networks need to be trained using large amount of measurement or simulation data. Some training data are more accurate or more reliable than others. It is planned to investigate methods for properly representing training data with varying degrees of accuracy, and to investigate neural network training techniques that are able to accept training data of different accuracy.
Keywords	Control systems Magnetic sensors Neural networks
Publications	Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data	Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal