Artificial Intelligence Integration in Naval Material Maintenance: A Qualitative NVivo and SWOT Analysis of SIGMA-Class Corvette

Abstract

Integrating Artificial Intelligence (AI) into naval material maintenance represents a vital strategic imperative to enhance technical readiness and operational reliability across warship fleets. This research examines the implementation of AI-based early fault detection systems for Caterpillar AR3406C diesel generators on SIGMA-class corvettes within Satkor Koarmada II. Utilizing a qualitative descriptive methodology, the study integrates in-depth interviews with key naval leadership and technical stakeholders, direct engine room observations, policy document analysis, and qualitative thematic coding via NVivo 15 software combined with IFAS-EFAS SWOT matrices, Reliability-Centered Maintenance, and the Technology Acceptance Model. The empirical findings identify critical technological bottlenecks, establish an AI-driven predictive maintenance architecture, and formulate a structured strategic implementation roadmap. This study confirms that AI-based predictive maintenance serves as a vital cornerstone for modern naval material logistics, minimizing downtime and effectively safeguarding national maritime sovereignty.