Asian Journal of Research in Computer Science

Predictive maintenance has emerged as a cornerstone of Industry 4.0, enabling manufacturers to proactively identify and address equipment failures, minimize unplanned downtime, and optimize operational costs. However, realizing effective predictive maintenance in smart manufacturing environments requires overcoming persistent challenges related to real-time data communication, cybersecurity vulnerabilities, and system scalability. This study addresses these gaps by investigating the integration of Artificial Intelligence (AI) and Internet of Things (IoT) technologies for predictive maintenance using the NASA C-MAPSS dataset. A quantitative methodology was employed, including transmission protocol analysis, cybersecurity assessment with an Isolation Forest-based Intrusion Detection System, scalability evaluation on edge and cloud infrastructures, and predictive modeling with Long Short-Term Memory (LSTM) networks. This research develops and empirically validates an integrated AI-IoT framework that unifies communication efficiency, cybersecurity resilience, and predictive modeling, representing a novel contribution to the state of the art. Results show MQTT achieved the lowest latency (50.21 ms), the IDS attained a Precision of 92.31%, edge systems supported up to 3352 MB before degradation, and the LSTM model outperformed linear regression with an RMSE of 14.25 and R² of 0.92. The study recommends that manufacturers adopt MQTT for efficient real-time communication, deploy AI-driven intrusion detection to safeguard predictive analytics, invest in scalable edge computing infrastructures, and implement deep learning models within hybrid edge-cloud architectures to enhance predictive maintenance reliability and support immediate, practical deployment in Industry 4.0 manufacturing systems.