Fault diagnosis in autonomous underwater vehicle propulsion system: a systematic review

Autonomous Underwater Vehicles (AUVs) are essential for marine exploration, environmental monitoring, and underwater operations Operational reliability and fault diagnosis are key to mission success. This paper systematically reviews research progress and core technologies in AUV propulsion system fault diagnosis. First, it outlines the development history and typical application of AUVs, highlighting the importance of fault diagnosis in maintaining system stability. Then, based on methodological perspectives, existing studies are categorized into model-based, data-driven, knowledge-based, and hybrid-based approaches, with a comparative analysis of their principles, applications, and advantages and limitations. Representative fault diagnosis datasets and summarized their practical applicability evaluated. Finally, key challenges, such as data scarcity, insufficient adaptability to complex environments, and real-time processing requirements are discussed. The paper also explores future directions including intelligent sensing, deep learning, and cross-platform transfer learning. This review provides theoretical support and practical reference for advancing fault diagnosis in AUV propulsion systems.