Abstract The rapid proliferation of cyber‐physical systems has marked the advent of Industry 4.0, transforming conventional production systems into intelligent, adaptive, and interconnected ecosystems. At the core of this revolution lies Artificial Intelligence (AI), enabling predictive analytics, adaptive optimization, and autonomous decision‐making that enhance both productivity and sustainability. This study proposes an AI‐driven smart factory framework that integrates industrial IoT, cloud‐based analytics, and supervisory control systems across production, maintenance, energy, and water management domains. The framework employs real‐time data acquisition, machine learning–based diagnostics, and optimization algorithms to improve operational reliability and resource efficiency. A case study conducted in a cement plant demonstrated tangible benefits from the AI–Industry 4.0 integration. Total production increased by 14.10%, OEE improved by 10.75%, while MTBF rose by 16.67% and MTTR decreased by 20.93%, indicating enhanced reliability and reduced downtime. Quality and customer‐related metrics also improved, with rejection and complaint rates dropping by 38% and 20%, respectively. From a sustainability perspective, specific energy consumption declined by 10.16%, specific carbon footprint reduced by 10.11% (recalculated using the CEA 2024 grid emission factor of 0.727 kg CO 2 /kWh), and specific water consumption decreased by 10.81%, confirming significant environmental gains. A brief cost–benefit evaluation revealed a 2.3‐year payback period, validating the framework's economic feasibility. The proposed architecture is scalable and transferable to other continuous‐process industries with minimal reconfiguration. Furthermore, the transition fostered human–machine collaboration, supported by operator retraining and digital upskilling, demonstrating that AI‐enabled sustainability can advance both industrial performance and social inclusivity.
Jena et al. (2026) studied this question.