ANALISA SISTEM KESEIMBANGAN VERTIKAL PADA WAHANA BAWAH AIR MENGGUNAKAN METODE ARTIFICIAL NEURAL NETWORK (ANN)

HAKIM, RAHMAN NUL and Zarkasi, Ahmad (2024) ANALISA SISTEM KESEIMBANGAN VERTIKAL PADA WAHANA BAWAH AIR MENGGUNAKAN METODE ARTIFICIAL NEURAL NETWORK (ANN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281924033.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281924033_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281924033_0225087902_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011281924033_0225087902_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (563kB) | Request a copy
	Text RAMA_56201_09011281924033_0225087902_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (92kB) | Request a copy
	Text RAMA_56201_09011281924033_0225087902_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (388kB) | Request a copy
	Text RAMA_56201_09011281924033_0225087902_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10kB) | Request a copy
	Text RAMA_56201_09011281924033_0225087902_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (84kB) | Request a copy
	Text RAMA_56201_09011281924033_0225087902_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (342kB) | Request a copy

Abstract

ABSTRACT The study analyzes the effectiveness of Artificial Neural Network (ANN) methods for vertical balance control in underwater vehicles (ROV). Traditional PID control methods were compared with ANN to evaluate performance differences. The research aims to identify the PID values required for training the ANN and to assess if ANN can achieve better balance control than PID in underwater systems. Data collection involved testing with sensors to gather a dataset comprising angular positions and control efforts. The ANN was trained using this dataset to predict and control the vehicle's balance more accurately.The results indicate that while PID control can stabilize the vehicle, it often results in oscillations around the zero angle before achieving balance. In contrast, ANN demonstrates superior performance by predicting and controlling motor actions more effectively, allowing the vehicle to reach and maintain the zero angle directly and accurately. The ANN's prediction and calculation capabilities enable smoother and more precise balance control compared to PID.However, implementing ANN on hardware like Arduino presents challenges due to memory limitations and slower processing speeds, which can hinder ANN's full potential. Despite these constraints, the study concludes that ANN offers a more accurate balancing process, with a standard deviation of 6.238 compared to PID's 7.545. The research highlights the potential of ANN in improving control systems for underwater vehicles, providing a foundation for further development in this field. Keywords: Artificial Neural Network (ANN), PID control, vertical balance, Remotely Operated Vehicle (ROV)

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Artificial Neural Network (ANN), kontrol PID, keseimbangan vertikal, Remotely Operated Vehicle (ROV).
Subjects:	T Technology > TJ Mechanical engineering and machinery > TJ1125-1345 Machine shops and machine shop practice > TJ1180 Machining, Ceramic materials--Machining-Strength of materials-Machine tools-Design and construction > TJ1180.I34 Machining-Machine tools-Numerical control-Computer integrated manufacturing systems-Artificial intelligence T Technology > TJ Mechanical engineering and machinery > TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Rahman Nul Hakim
Date Deposited:	15 Nov 2024 02:31
Last Modified:	15 Nov 2024 02:31
URI:	http://repository.unsri.ac.id/id/eprint/159367

Actions (login required)

View Item