Exploring Proactive Maintenance through Fault Detection Techniques for Rotating Machinery: A Systematic Review

Abstract

Rotating machinery plays a crucial role in industrial operations, but its reliability is frequently threatened by unexpected failures, leading to costly downtime and safety hazards. To address this problem, proactive maintenance strategies, underpinned by advanced fault detection techniques, have become essential for improving equipment performance and operational efficiency. This systematic review assesses different fault detection methods, such as vibration analysis, thermal imaging, acoustic emission monitoring, oil analysis, electrical signature analysis, and IoT-enabled real-time monitoring. It highlights their applications, strengths, limitations, and potential for integration across various industries, including oil and gas, manufacturing, aerospace, automotive, and power generation. The review followed the PRISMA 2020 framework, systematically analyzing 64 peer-reviewed studies published between 2013 and 2025. Findings reveal that vibration analysis remains the most researched and extensively applied technique, though emerging AI-driven models, IoT-based monitoring, and multimodal approaches are increasingly shaping predictive maintenance practices. Proactive maintenance was found to improve equipment reliability, reduce downtime by up to 50%, extend machinery lifespan, and enhance safety and cost efficiency. However, widespread adoption is hindered by high implementation costs, data management complexities, skill gaps, and the absence of standardized performance metrics. The study concludes by emphasizing the need for hybrid, AI-enabled, and Industry 5.0–aligned solutions, while providing recommendations for integrating fault detection methods to optimize proactive maintenance strategies and ensure resilient industrial operations.