Artificial Intelligence and Optimization Models for Agile and Resilient Production Planning and Control

[EN] The increasing uncertainty in the manufacturing industry, driven by disruptive events and market fluctuations, highlights the need for more agile and resilient Production Planning and Control (PPC) strategies. This research focuses on addressing the Capacitated Lot Sizing and Scheduling (CLSS)...

Descripción completa

Detalles Bibliográficos
Autores: Fiesco-Muñoz, Juan Pablo|||0009-0008-3369-4607, Esteso, Ana|||0000-0003-0379-8786, Poler, R.|||0000-0003-4475-6371
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:dnet:riunet______::3dbfc1d64f2b79c768aa373c480f8838
Acceso en línea:https://riunet.upv.es/handle/10251/235258
Access Level:acceso embargado
Palabra clave:Production planning and control
Capacitated lot sizing
Dynamic scheduling
Mathematical programming
Artificial intelligence
Smart manufacturing
Descripción
Sumario:[EN] The increasing uncertainty in the manufacturing industry, driven by disruptive events and market fluctuations, highlights the need for more agile and resilient Production Planning and Control (PPC) strategies. This research focuses on addressing the Capacitated Lot Sizing and Scheduling (CLSS) for medium-term planning and Dynamic Scheduling (DS) for short-term decision-making by integrating Mathematical Programming, Artificial Intelligence (AI), and Smart Manufacturing (SM) technologies. A systematic review of CLSS and DS models identifies gaps in modeling uncertainty and adapting to real-time disruptions. A conceptual framework is proposed to standardize CLSS characteristics, while a matheuristic approach combines metaheuristics and mathematical programming to optimize sustainability-driven lot sizing decisions. Additionally, an AI-based tool dynamically reschedules production in response to real-time factory data. The research further develops a scalable architecture for industrial implementation, leveraging IoT and AI for enhanced decision-making. Validation is conducted through real and synthetic case studies, assessing solution quality and computational efficiency. This work aims to bridge the gap between traditional optimization techniques and smart, data-driven SM environments.