Optimizing Industrial Equipment Health: A Hybrid IoT and AI Framework for Predictive Maintenance Using the MOORA Method

The convergence of the Internet of Things (IoT) and Artificial Intelligence (AI) is fundamentally reshaping industrial maintenance paradigms. This research presents a comprehensive framework for advanced predictive maintenance (PdM) that leverages IoT sensors for real-time condition monitoring and AI-driven analytics for intelligent failure forecasting. The study addresses the critical challenge of selecting the optimal predictive model from a set of alternatives, each with varying strengths in key performance indicators such as cost savings, uptime, failure rate, and implementation time. To navigate this multi-criteria decision-making problem objectively, this paper employs the MOORA (Multi-Objective Optimization on the Basis of Ratio Analysis) method. The MOORA technique provides a robust, mathematically sound mechanism to rank competing AI models based on their aggregate performance across both beneficial and non-beneficial criteria. Our analysis utilizes a real-world dataset simulating the operational parameters of industrial equipment. The findings demonstrate that the proposed IoT-AI-MOORA hybrid approach effectively identifies the most balanced and advantageous predictive maintenance model. The results indicate a clear ranking, with one model (Model E) emerging as superior, achieving the highest score due to its exceptional cost-saving potential and low failure rate. This work concludes that integrating systematic multi-criteria decision-making tools like MOORA with technical IoT and AI solutions is essential for organizations seeking to implement truly optimized, data-driven, and cost-effective predictive maintenance strategies.