Prediksi Trajectory Kapal Dan Critical Collision Zone Berbasis Data Automatic Identification System (Studi Kasus: Selat Sunda)

Situmorang, Andryan (2024) Prediksi Trajectory Kapal Dan Critical Collision Zone Berbasis Data Automatic Identification System (Studi Kasus: Selat Sunda). Diploma thesis, Institut Teknologi Sepuluh Nopember.

Text 2043201062-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2026. Download (3MB) | Request a copy

Abstract

Indonesia sebagai negara kepulauan dengan kondisi geografis yang sangat strategis membuat pelayaran nasional sangatlah krusial dalam sektor ekonomi. Kondisi pelayaran nasional Indonesia pada tahun 2021 menunjukkan peningkatan jumlah kunjungan kapal sebesar 5,26% juga berkorelasi positif terhadap potensi bahaya dan risiko terjadinya kecelakaan. Tragedi tubrukan kapal merupakan salah satu kategori teratas dari kecelakaan maritim dan umumnya lebih sering terjadi pada wilayah dengan lalu lintas kapal yang padat. Pemerintah dalam menjamin keselamatan pelayaran berupaya mengawasi kapal yang berlayar di perairan Indonesia menggunakan Automatic Identification System (AIS), sehingga dapat mengurangi risiko terjadinya tubrukan antar kapal. Dalam rangka mencapai tujuan ini, mengidentifikasi daerah perairan dengan kepadatan kapal yang tinggi sebagai Critical Collision Zone (CCZ) berdasarkan lintasan atau trajectory kapal dapat dilakukan sebagai langkah pencegahan. Data AIS pada setiap kapal yang berlayar di Selat Sunda diolah menggunakan algoritma Bidirectional Gated Recurrent Unit (Bi-GRU) membentuk model prediksi trajectory pergerakan kapal dengan nilai rata-rata eror sebesar 618,099 meter. Klasterisasi menggunakan Density-based Spatial Clustering of Application with Noise (DBSCAN) menghasilkan dua daerah CCZ berdasarkan kepadatan kapal. Monte Carlo Simulation (MCS) kemudian menyimulasikan trajectory pada masing-masing CCZ, kemudian dihitung peluang terjadinya critical distance dengan risiko tubrukan pada CCZ pertama sebesar 0,4383, serta pada CCZ kedua sebesar 0,6789. Hasil penelitian ini diharapkan menghasilkan model dengan nilai kepercayaan yang tinggi sehingga dapat membantu pengambilan tindakan preventif untuk menghindari terjadinya tubrukan kapal di Selat Sunda maupun laut lainnya di Indonesia.
================================================================================================================================
Indonesia as an archipelagic country with very strategic geographical conditions makes national shipping very crucial in the economic sector. The condition of Indonesian national shipping in 2021 shows an increase in the number of ship visits by 5.26%, which also has a positive correlation with potential dangers and the risk of accidents. Ship collision tragedies are one of the top categories of maritime accidents and generally occur more frequently in areas with heavy ship traffic. In ensuring shipping safety, the government is trying to monitor ships sailing in Indonesian waters using the Automatic Identification System (AIS), so as to reduce the risk of collisions between ships. In order to achieve this goal, identifying water areas with a high density of ships as Critical Collision Zones (CCZ) based on ship trajectories can be carried out as a preventive measure. AIS data on every ship sailing in the Sunda Strait is processed using the Bidirectional Gated Recurrent Unit (Bi-GRU) algorithm to form a prediction model for the trajectory of ship movements with an average error value of 618,099 meters. Clustering using Density-based Spatial Clustering of Application with Noise (DBSCAN) produces two CCZ regions based on ship density. Monte Carlo Simulation (MCS) then simulates the trajectory at each CCZ, then calculates the probability of a collision at the first CCZ as 0.4383, and at the second CCZ as 0.6789. It is hoped that the results of this research will produce a model with a high confidence value so that it can help take preventive action to avoid ship collisions in the Sunda Strait and other seas in Indonesia.

Item Type:	Thesis (Diploma)
Uncontrolled Keywords:	Automatic Identification System (AIS), Kecelakaan Maritim, Trajectory Kapal, Zona Kritis Tubrukan, Critical Collision Zone, Marine Accident, Ship Trajectory.
Subjects:	H Social Sciences > HA Statistics > HA31.7 Estimation H Social Sciences > HE Transportation and Communications > HE5614.3.N5 Traffic accidents Q Science > QA Mathematics > QA278.55 Cluster analysis Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Andryan Andryan
Date Deposited:	27 May 2024 08:01
Last Modified:	27 May 2024 08:01
URI:	http://repository.its.ac.id/id/eprint/107992

Actions (login required)

View Item