Neural Network Predictive Control (NNPC) of a Deep Submergence Rescue Vehicle (DSRV)

Mohd Nor, Arfah Syahida and Abdullah, Shahrum Shah and Mohd Aras, Mohd Shahrieel and Ab Rashid, Mohd Zamzuri (2012) Neural Network Predictive Control (NNPC) of a Deep Submergence Rescue Vehicle (DSRV). In: 4th International Conference on Underwater System Technology: Theory and Application 2012 (USYS'12), 4-6 December 2012, Shah Alam.

[img] PDF
PAPER_5_Neural_Network_Predictive_Control_(NNPC)_of_a_Deep_S.pdf - Published Version

Download (1MB)


In this paper, the modeling and design of the depth control systems using Neural Network Predictive Control (NNPC)for a small unmanned underwater vehicle (UUV) will be described. Underwater vehicles consist of robotic vehicles that have been developed to reduce the risks of human life and to carry out tasks that would be impractical with a manned mission. The design of a depth control of an UUV is described in this paper. The main purpose of the underwater vehicle is that the vehicle must be stable over the entire range of operation. These techniques have the purpose of ensuring zero steady state error and minimum error in response to step commands in the desired depth.The depth performance for NNPC is discussed in terms of error and execution time. This NNPC will be compared with conventional controller such as PD controller and also by using the Fuzzy Logic Controller (FLC). For the comparison of computational time between this controllers, it can be observed that Fuzzy Logic is faster and neural network predictive controller is the slowest between them. It has been shown that the neural network predictive controller improved the transient response and error measure which shows the effectiveness of the designed controller.

Item Type: Conference or Workshop Item (Paper)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Electrical Engineering > Department of Diploma Studies
Date Deposited: 25 Jul 2013 21:57
Last Modified: 28 May 2015 03:59
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item