Penerapan Bayesian Network untuk Penentuan Prioritas Perawatan dalam Metodologi Reliability Centered Maintenance

Ramdhani, Muhammad Fadli (2025) Penerapan Bayesian Network untuk Penentuan Prioritas Perawatan dalam Metodologi Reliability Centered Maintenance. Other thesis, Insitut Teknologi Sepuluh Nopember.

Text 5019201145_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (3MB) | Request a copy

Abstract

Penelitian ini mengembangkan kerangka kerja untuk memprioritaskan perawatan sistem maritim dengan mengintegrasikan Bayesian Networks (BN) ke dalam pendekatan Reliability-Centered Maintenance (RCM). Penelitian ini berfokus pada sistem propulsi kapal tunda, mengidentifikasi mode kegagalan kritis dan dampaknya. Temuan utama menunjukkan bahwa mode kegagalan paling kritis, yaitu "entangled mooring line", memiliki probabilitas yang diperbarui sebesar 18,27% dan dikategorikan sebagai "probable." Selain itu, "clogged lube oil filter" menunjukkan peningkatan signifikan dalam kemungkinan kegagalan, sehingga memerlukan tindakan perawatan yang lebih intensif. Melalui analisis logic tree, direkomendasikan 57 kegiatan perawatan, di mana 70% dari rekomendasi tersebut berfokus pada main engine sebagai komponen vital dalam sistem propulsi. Seluruh mode kegagalan yang dianalisis diklasifikasikan sebagai evident, yang berarti kegagalan dapat dengan mudah terdeteksi dalam kondisi normal. Dari total rekomendasi, 48% berupa perawatan scheduled on-condition yang menekankan inspeksi rutin terhadap potensi kegagalan seperti korosi dan kebocoran.
=================================================================================================================================
This research develops a framework for prioritising maritime system maintenance by integrating Bayesian Networks (BN) into the Reliability-Centered Maintenance (RCM) approach. The research focuses on tugboat propulsion systems, identifying critical failure modes and their impacts. The main findings show that the most critical failure mode, namely ‘entangled mooring line’, has an updated probability of 18.27% and is categorised as ‘probable.’ In addition, the ‘clogged lube oil filter’ showed a significant increase in the probability of failure, thus requiring more intensive maintenance measures. Through logic tree analysis, 57 maintenance activities were recommended, of which 70% focused on the main engine as a vital component in the propulsion system. All analysed failure modes were classified as evident, meaning that failures can be easily detected under normal conditions. Of the total recommendations, 48% were scheduled on-condition maintenance that emphasised regular inspections for potential failures such as corrosion and leaks.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Bayesian Networks (BN), Reliability-Centered Maintenance (RCM), Sistem Propulsi, FMECA, Scheduled On-Condition Maintenance.
Subjects:	V Naval Science > VC Naval Maintenance > VC 270-279 Equipment of vessels, supplier,allowances,etc V Naval Science > VC Naval Maintenance V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM464 Towboats. Tugboats V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM731 Marine Engines V Naval Science > VM Naval architecture. Shipbuilding. Marine engineering > VM753 Propellers
Divisions:	Faculty of Marine Technology (MARTECH) > Marine Engineering > 36202-(S1) Undergraduate Thesis
Depositing User:	Ramdhani Muhammad Fadli
Date Deposited:	04 Feb 2025 03:53
Last Modified:	04 Feb 2025 03:53
URI:	http://repository.its.ac.id/id/eprint/117966

Actions (login required)

View Item