Optimizing beverage manufacturing: integrating lean manufacturing and machine learning to enhance efficiency and reduce waste

• Autores: Mendoza Sotomayor, Raul, Sabogal Arias, Jose Antonio
• Formato: tesis de grado
• Fecha de Publicación: 2025
• Institución: Universidad de Lima
• Repositorio: ULIMA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.ulima.edu.pe:20.500.12724/23147
• Enlace del recurso: https://hdl.handle.net/20.500.12724/23147
• Nivel de acceso: acceso abierto
• Materia: Pendiente; https://purl.org/pe-repo/ocde/ford#2.11.04

The alcoholic and non-alcoholic beverage manufacturing sector faces persistent challenges that directly impact operational efficiency and business profitability. Recurrent problems in the equipment and sub-optimal practices of operators generate significant waste and production delays. Previous studies have explored methodologies such as Six Sigma, Lean Manufacturing and Kaizen to address these challenges, highlighting tools such as VSM, 5S and SMED. The sector urgently needs to improve operator training, implement advanced monitoring and control technologies to reduce equipment failures. This study proposes a model that integrates Lean Manufacturing and Machine Learning to optimize the production process, reduce line change times and reduce the percentage of waste. Key results showed a significant improvement in production efficiency, with a 42.4% reduction in quality control time thanks to the 5s methodology and a reduction in waste through preventive controls. The implementation of SMED managed to increase production efficiency 33.3%. The academic and socio-economic impact of this research is considerable, as it provides a practical and applicable framework for improving productivity and competitiveness in the beverage industry. It also promotes economic sustainability by optimizing resource use and reducing costs. It is imperative that future research explores new directions for the integration of emerging technologies in the field of Lean Manufacturing, encouraging academics and professionals to continue innovating in the improvement of industrial processes.