Minyoung Lee, Yun-Young Hwang, Jiseong Son, Heemin Kim, Journal of Internet Computing and Services, Vol. 26, No. 1, pp. 171-180, Feb. 2025
10.7472/jksii.2025.26.1.171, Full Text:  HTML
Keywords: Weapon System Maintenance, Condition Based Maintenance Plus, predictive maintenance, Diagnostic, Prognostic, CBM+

Abstract

Efforts are underway to apply advanced technologies such as AI to weapon systems and achieve efficient management throughout their total life cycle, from design to disposal. Condition-Based Maintenance Plus (CBM+) serves as one of the logistics support tools for this purpose. Through the application of CBM+, it becomes possible to detect or predict conditions that could lead to failures and advance towards the concept of predictive maintenance, which involves performing maintenance prior to the occurrence of failures. To maximize the benefits of predictive maintenance, such as improving system availability and reducing costs, it is crucial to select algorithms that are suitable for the data characteristics and maintenance requirements. This study conducts research and analysis of predictive maintenance algorithms to facilitate optimal decision-making. For various weapon systems, the study investigates algorithms currently utilized for predictive maintenance, categorizes them based on analytical methods and data types, and presents the findings.

Statistics
Cite this article