Rancang Bangun Prototipe Remotely Operated Vehicle (ROV) untuk Inspeksi Biofouling Kapal saat Sandar

Azhary, Sutan (2021) Rancang Bangun Prototipe Remotely Operated Vehicle (ROV) untuk Inspeksi Biofouling Kapal saat Sandar. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 04111740000060-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (8MB) | Request a copy

Abstract

Biofoulingpada kapal adalah akumulasi mikroorganisme, tanaman, ganggang, atau hewan kecil pada permukaan basah yang menyebabkan defisiensi kapal saat berlayar. Adanya biofoulingpada lambung kapal diperkirakan menambah lebih dari 20 persen biaya bahan bakar pelayaran komersial. Biofoulingpada kapal umumnya diatasi dengan menggunakan cat anti-foulingpada lambung kapal dan melakukan pembersihan di atas dok menggunakan air bertekanan tinggi. Dengan perkembangan teknologi Remotely Operated Vehicle(ROV) yang ada saat ini, inspeksi biofoulingdapat dilakukan pada saat kapal melakukan bongkar muat dan tanpa harus menaikkan kapal ke atas dok. Penelitian ini bertujuan untuk merancang prototipe ROV beserta sistem yang dibutuhkan untuk mampu melakukan inspeksi biofoulingpada lambung kapal saat sandar. Kemampuan inspeksi dirancang dengan mengimplementasikan metode peningkatan citra bawah air dan deteksi objek menggunakan machinelearning. Didapatkan desain prototipe dengan panjang 42,9cm, lebar 18,7cm, dan tinggi 11,7cm. Dalam meningkatkan citra bawah air digunakan model FUnIE-GAN dengan hasil rerata nilai PSNR sebesar 28,6dB dan rerata nilai SSIM sebesar 0,798. Secara rata-rata, kemampuan wahana dalam mendeteksi objek biofoulingmeningkat 155%.
================================================================================================
Biofouling on ships is the accumulation of microorganisms, plants, algae, orsmall animals on wet surfaces which causes the ship to be deficient while sailing. The presence of biofouling in the hull of ships is estimated to add more than 20 percent to the fuel cost of commercial shipping. Biofouling in ships is generally treated by using anti-fouling paint on the hull and cleaning on the dock using high-pressure water. With the current development of Remotely Operated Vehicle (ROV) technology, biofouling inspectioncan be done when the ship is loading and unloading and without having to dry-dock. This study aims to design an ROV prototype and the system required to perform biofouling inspection on the hull of a ship when berthing. The inspection capability is designed by implementing underwater image enhancement and object detection methods using machine learning. Obtained prototype design with a length 42,9cm, width 18,7cm and 11,7cm high. In improving the underwater image, the FUNIE-GAN model results in an average PSNR value of 28.6dB and an average SSIM value of 0.798. On average, the vehicle's ability to detect biofouling objects increased by 155%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Remotely Operated Vehicle, Inspection, Biofouling, Machine Learning, Underwater Image Enhancement, Object Detection
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA336 Artificial Intelligence T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM365 Remote submersibles. Autonomous vehicles.
Divisions:	Faculty of Marine Technology (MARTECH) > Naval Architecture and Shipbuilding Engineering > 36201-(S1) Undergraduate Thesis
Depositing User:	Sutan Azhary
Date Deposited:	02 Sep 2021 06:08
Last Modified:	02 Sep 2021 06:08
URI:	http://repository.its.ac.id/id/eprint/91282

Actions (login required)

View Item