Optimizing Predictive Maintenance in Industrial IoT Cloud Using Dragonfly Algorithm

– This study presents an optimized framework for predictive maintenance in Industrial Internet of Things (IIoT) cloud environments using the Dragonfly Algorithm (DA). With the rapid adoption of smart sensors and connected devices, industrial systems generate vast volumes of real-time data, making efficient maintenance strategies essential for minimizing downtime and operational costs. Traditional predictive models often struggle with high- dimensional data and dynamic system behavior. To address these challenges, the proposed approach leverages the swarm intelligence-based Dragonfly Algorithm to enhance feature selection and optimize model parameters. By mimicking the static and dynamic swarming behaviors of dragonflies, the algorithm effectively balances exploration and exploitation in the search space. The framework integrates DA with machine learning models to improve fault detection accuracy and prediction reliability. Experimental results demonstrate that the proposed method outperforms conventional optimization techniques in terms of prediction accuracy, computational efficiency, and robustness. Furthermore, the cloud-based deployment ensures scalability and real-time processing capabilities, making it suitable for large-scale industrial applications. This research highlights the potential of bio-inspired optimization techniques in advancing intelligent maintenance systems within IIoT ecosystems.