Scholarlink

The marine loading arm (MLA) is a critical component in fluid transfer operations at jetties, necessitating reliable operation for operational efficiency and safety. Ensuring MLA reliable operation is crucial for maintaining the efficiency and safety of the loading process. Unforeseen failures in the MLA can lead to significant disruptions, delays, and potential hazards. This paper presents an investigation study on the effect of metocean parameters to the MLA Failures. The study uses synthetic failures data collected from 29 MLAs across a period of seven years coincided with metocean data during the same period to derive hidden insights and future predictions of MLA failures to determine the feasibility of AI-driven failure prediction and smart monitoring for MLAs, including a detailed feasibility study and data quality assessment report. The obtained results show low to moderate correlation between MLA failures as well as metocean data, which can be further improved by considering more data from IOT sensors if installed at the proper locations in MLA.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Investigation of the Metocean Effects on Marine Loading Arms (MLA) Failures Using Machine Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Eddy A. Ariffin,
  • M. Sazli B. Ismail,
  • M. Khoushaini M. Naim,
  • M. Faieez B. M. Jupri,
  • Aizat Rasli,
  • Hitham Alhussian,
  • Izzatdin A. Aziz,
  • Nur Syakirah Mohd Jaafar,
  • Kamariah Abu Saed

摘要

The marine loading arm (MLA) is a critical component in fluid transfer operations at jetties, necessitating reliable operation for operational efficiency and safety. Ensuring MLA reliable operation is crucial for maintaining the efficiency and safety of the loading process. Unforeseen failures in the MLA can lead to significant disruptions, delays, and potential hazards. This paper presents an investigation study on the effect of metocean parameters to the MLA Failures. The study uses synthetic failures data collected from 29 MLAs across a period of seven years coincided with metocean data during the same period to derive hidden insights and future predictions of MLA failures to determine the feasibility of AI-driven failure prediction and smart monitoring for MLAs, including a detailed feasibility study and data quality assessment report. The obtained results show low to moderate correlation between MLA failures as well as metocean data, which can be further improved by considering more data from IOT sensors if installed at the proper locations in MLA.