<![CDATA[The rapid advancement of Industry 4.0 and Industry 5.0 technologies has accelerated the adoption of Artificial Intelligence (AI) in manufacturing environments, particularly in predictive maintenance applications aimed at improving the reliability and performance of production machines. This study analyzes the influence of AI on predictive maintenance strategies and evaluates its contribution to enhancing maintenance effectiveness and operational performance in modern manufacturing systems. A Systematic Literature Review (SLR) approach was employed to synthesize findings from peer-reviewed publications indexed in major scientific databases, including Scopus, Web of Science, ScienceDirect, IEEE Xplore, and SpringerLink. Relevant studies published between 2020 and 2026 were selected and analyzed using descriptive, thematic, and comparative analytical techniques. The findings reveal that various AI technologies, including Machine Learning, Deep Learning, Artificial Neural Networks, Random Forest, Support Vector Machines, Reinforcement Learning, and Internet of Things (IoT)-enabled systems, are widely applied in predictive maintenance to support machine condition monitoring, fault diagnosis, and failure prediction. The results indicate that AI significantly improves prediction accuracy through early fault detection, reduces unexpected downtime by enabling proactive maintenance interventions, lowers maintenance costs through optimized resource allocation and spare-part utilization, and enhances operational efficiency by improving machine availability and production continuity. Furthermore, AI contributes to real-time monitoring, faster decision-making, and improved asset management. However, several implementation challenges remain, including data quality issues, sensor reliability concerns, integration with legacy systems, shortages of AI expertise, high implementation costs, cybersecurity risks, and data privacy concerns.]]>
