DMAIC and Capability Analysis in Coffee Grinding Process: An SPC-Based Approach for Lavazza = DMAIC and Capability Analysis in Coffee Grinding Process: An SPC-Based Approach for Lavazza

The present thesis deals with some of the central themes of the Quality engineering, which represents a key discipline within the Supply Chain Management. The focus is on the analysis and improvement of the Nespresso Compatible Capsules (NCC) grinding process within Luigi Lavazza S.p.A. The objective was to evaluate process capability and strengthen process stability and centring through the integration of DMAIC methodology and Statistical Process Control (SPC) tools. SPC has been used not only to confirm that the process is under control but also to understand, analyse and continuously improve it, using statistical methodologies to take operative decisions. Initial trials without operating adjustments revealed a systematic dispersion in the start-up grinding phase, linked to roller adjustments and process flow inertia. Subsequent tests confirmed data stability over time and grinder stability without adjustments, while residual dispersion was attributed to an intrinsic machine characteristic still under investigation. The redefinition of specification limits and the introduction of grinder-specific recipes, derived from heatmaps constructed on recent data, reduced variability due to manual adjustments of the grinders and extended operational stability. The integration of DMAIC and SPC provided a structured and replicable framework for identifying variability sources, implementing corrective actions, and validating improvements. The results include improved process capability and strengthen support for operators. The project concludes with practical recommendations on standardization, operator training and continuous monitoring. Despite limitations related to environmental factors, dataset size, and operator influence, the methodology proved effective in promoting a data-driven and replicable process control approach. Future developments involve online sensors, predictive analytics, and semi-automatic control for enhanced process reliability and digital transformation.