Penilaian Risiko Pekerjaan Panas pada Kapal di Galangan Kapal menggunakan Metode HIRARC melalui Pendekatan Bayesian Network dan Fuzzy Inference System

Mardani, Dondi Perdana (2024) Penilaian Risiko Pekerjaan Panas pada Kapal di Galangan Kapal menggunakan Metode HIRARC melalui Pendekatan Bayesian Network dan Fuzzy Inference System. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5019201092-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (23MB) | Request a copy

Abstract

Pada abad ke – 20 ini, pekerjaan panas menjadi aktivitas penting dalam pembangunan dan perbaikan struktur logam kapal dalam mendukung aktivitas perdagangan muatan dan transportasi manusia. Penelitian ini bertujuan untuk mengidentifikasi potensi bahaya yang dapat menyebabkan risiko kecelakaan pada pekerjaan panas di kapal, dengan fokus pada tiga perusahaan galangan kapal. Metode Hazard Identification Risk Assessment and Risk Control (HIRARC) digunakan untuk mengidentifikasi dan mengevaluasi risiko, dengan menganalisis tingkat kemungkinan dan tingkat keparahan. Hasil identifikasi ini kemudian digunakan sebagai dasar pembuatan model Bayesian Network (BN) melalui root cause analysis menggunakan metode fishbone diagram. Perhitungan BN dalam mendapatkan hasil joint probability membutuhkan perhitungan Conditional Probability Table (CPT) yang didapatkan dengan konsep Weighted Sum Algorithm (WSA) dan Noisy OR – Gate. Joint probability hasil BN divalidasi dengan cara k – fold cross – validation untuk dapat menjadi masukan pendekatan Fuzzy Inference System bersama dengan nilai severity untuk mendapatkan penilaian risiko baru. Sebanyak 43 risiko pekerjaan panas yang pernah terjadi teridentifikasi dengan melibatkan 47 faktor dasar dengan nilai joint probability risiko yang bervariasi di tiga perusahaan. Pendekatan Bayesian Network - Fuzzy Inference System menghasilkan 31 kesamaan risiko dan 12 perbedaan risiko dibandingkan dengan metode HIRARC yang mana 4 risiko diantaranya berada di tingkat yang tidak dapat diterima. Pengendalian risiko dilakukan sebagai usaha dalam menurunkan risiko dengan mitigasi risiko yang dapat diterima pada setiap galangan kapal dalam bentuk analisis SOP standar ILO dan OSHAS.
=================================================================================================================================
In the 20th century, hot work has become an important activity in the construction and repair of ship metal structures to support cargo trade and human transportation. This study aims to identify potential hazards that may cause accident risks in hot work on ships, focusing on three shipbuilding companies. The Hazard Identification Risk Assessment and Risk Control (HIRARC) method is used to identify and evaluate risks, by analysing likelihood and severity. The results of this identification are then used as the basis for creating a Bayesian Network (BN) model through root cause analysis using the fishbone diagram method. BN calculations in obtaining joint probability results require Conditional Probability Table (CPT) calculations obtained with the Weighted Sum Algorithm (WSA) and Noisy OR - Gate concepts. The joint probability of BN results is validated by means of k - fold cross - validation to be able to input the Fuzzy Inference System approach along with the severity value to get a new risk assessment. A total of 43 hot work risks that have occurred were identified involving 47 basic factors with varying risk joint probability values in three companies. The Bayesian Network - Fuzzy Inference System approach resulted in 31 similar risks and 12 different risks compared to the HIRARC method of which 4 risks were at an unacceptable level. Risk control is carried out as an effort to reduce risk by mitigating acceptable risks at each shipyard in the form of standard ILO and OSHAS SOP analysis

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Bayesian Network, Fuzzy Inference System, Hot Work, Shipyard, Galangan Kapal, Pekerjaan Panas
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD61 Risk Management Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory. Q Science > QA Mathematics > QA9.64 Fuzzy logic V Naval Science > VK > VK200 Merchant marine--Safety measures V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering
Divisions:	Faculty of Marine Technology (MARTECH) > Marine Engineering > 36202-(S1) Undergraduate Thesis
Depositing User:	Dondi Perdana Mardani
Date Deposited:	19 Feb 2024 16:23
Last Modified:	19 Feb 2024 16:23
URI:	http://repository.its.ac.id/id/eprint/107560

Actions (login required)

View Item