Approximations for dynamic multi-class manufacturing systems with priorities and finite buffers

Abstract

Capacity planning models for tactical to operational decisions in manufacturing systems require a performance evaluation component that relates demand processes with production resources and system state. Steady-state queueing models are widely used for such performance evaluations. However, these models typically assume stationary demand processes. With shorter new product development and life cycles, increasing customization, and constantly evolving customer preferences the assumption of stationary demand processes is not always reasonable. Nonstationary demand processes can capture the dynamic nature of modern manufacturing systems. The ability to analyze dynamic manufacturing systems with multiple products and finite buffers is essential for estimating throughput rates, throughput times, and work-in-process levels as well as evaluating the impact of proposed capacity plans and resource allocations. In this article, we present computationally efficient numerical approximations for the performance evaluation of dynamic multi-product manufacturing systems with priorities and finite buffers. The approximation breaks time into short periods, estimates throughput and arrival rates based on system status and current arrival processes, and then pieces the periods together through flow balance equations. The dynamic nature of product demands is modeled through non-homogeneous Poisson processes. The performance of these approximations is presented for practically sized flowshops and jobshops.