Advancing Hybrid Production Systems through Theoretical Frameworks and Stochastic Models for Performance Estimation

Contemporary research provides a solid foundation through the development of models and methodologies for analyzing performance indicators in single-machine production systems, with particular emphasis on exponentially distributed processing times. However, the transition to more complex and hybrid production systems, incorporating multiple machines operating in parallel, necessitates a new perspective in analyzing and optimizing their performance. This study fits within this context by proposing a new generation of mathematical and stochastic models for estimating the performance of such hybrid systems. The objective is twofold: on one hand, to provide a theoretical framework for understanding and predicting the behavior of more complex production systems; on the other hand, to offer practical tools for optimal work-in-process (WIP) sizing in relation to throughput objectives. Through the application of these models, this paper aims to facilitate the design of more efficient hybrid production lines capable of dynamically adapting to demand fluctuations and operational contexts, thereby maximizing productivity and responsiveness in the production system.