Neural network course changing and track keeping controller for a submarine.

Dur Muhammad Pathan; Abdul Fatah Abbassi; Zeeshan Ali Memon

No Detail Found!

Neural network course changing and track keeping controller for a submarine.

Author(s)

Dur Muhammad Pathan Department of Mechanical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan

Abdul Fatah Abbassi Department of Mechanical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan

Zeeshan Ali Memon Department of Mechanical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan

Abstract

This paper presents the performance of ANN (Artificial Neural Networks) technique for the development of controller for heading motions of submarine. A MLP (Multi-Layer Preceptron) FINN (Feed-Forward Neural Network) is used for development of controller. Supervised type of learning is used for training of network by using back-propagation Algorithm. The training is performed by providing a nonlinear sliding mode controller as a supervisor. The development of controller is based on nonlinear decoupled heading model of a submarine without consideration of external environmental disturbances. To demonstrate the robustness of controller the performance of controller is tested in different operating conditions: course changing, track keeping and under the influence of sea currents. Simulations results show that in all cases, the heading error comes to zero, which indicates that the actual heading converges to the desired heading in finite time. The maximum error is observed 0.5° for 45° command angle, in presence of sea currents. The result demonstrates that the performance neural network controller has been robust.

Publication Details

Page(s) 711-722

DOI DOI not available

Published Journal: Mehran University Research Journal of Engineering and Technology, Volume: 31, Issue: 4, Year: 2012

Request the full text from PASTIC

Citations

Downloads

Views