In an era where industries are increasingly prioritizing sustainability and efficiency, optimizing manufacturing processes is mandatory. Among these processes, lathe operations are widely used in industry and consume significant amount of energy. This research investigates the monitoring of a turning process, focusing on real-time data analysis with the final aim of achieving a more sustainable and energy efficient machining process. Using an integrated agent framework for monitoring of machining outputs, the machining parameters such as spindle speed, feed rate and depth of cut are optimized. A Multi-Agent Distributed System (MADS) is created and implemented for real-time data acquisition, filtering, storage and visualisation. Comprehensive analysis of energy consumption data during cutting intervals led to the identification of energy distribution patterns and inefficiencies. Additionally, insights into the progression of tool wear made it possible to identify consumption, specific to the cutting operations, in order to define predictive maintenance strategies and thereby reducing operational downtime. The results are contextualised with KPIs that provide information on process optimisation, including recommendations on energy saving parameters and cost reduction opportunities, thereby enhancing decision-making in machining operations.
Science Journal 