Prognostics and Health Management for Ships Machinery: A Review of Edge-Intelligence for Asset Integrity

Ship machinery running continuously and selling worldwide, it is crucial to maintain all machinery to protect ships, crew, environment and laws. The current preventive maintenance strategies not able to fulfilled requirement of sensible marine equipment maintenance and huge impact in unexpected breakdowns, operational delays, and significant financial losses. In the era of artificial intelligent (AI) enable Predictive Maintenance (PdM) by using ship machinery data analytics and emerged as a promising solution for forecasting equipment faults and enhancing maintenance operations. Edge computing (EC) model help to reducing computational time, communication delay, improving data secrecy, and minimizing dependence on centralized cloud-based (CB) computing. In this paper present various proposed PdM methods for specific maritime machinery, the existing literature lacks an extensive review of PdM approaches across different marine equipment. To address the gap of literature review, this paper provides an overview of state-of-the-art data-driven PdM techniques in the maritime industry, with particular emphasis on EC architectures. Furthermore, current research challenges, implementation barriers, and future research directions are discussed to advance the implementation of this technology in the field.