A Two-step Empirical-analytical Optimization Scheme

Wa-Muzemba Tshibangu, Anselm Tshibangu

2013

Abstract

This paper presents a two-step optimization scheme developed to find the optimal operational settings of operational systems seeking to optimize their operations using multiple performance measures. The study focuses on two conflicting performance measures, the Throughput Rate (TR) and the Mean Flow Time (MFT). First an empirical approach is used to uncover the near optimal values of the performance measures using an experimental design procedure. Second, an analytical procedure is deployed to find the exact optima using values the near optima found in the first step as target. The analytical procedure uses a non-linear regression meta-model derived from simulation outputs and compromises the two conflicting targets while minimizing the loss incurred to the overall system. This loss is expressed in the form of a multivariate version of the Taguchi quadratic loss function. Although the framework as presented in this paper is derived by analyzing a manufacturing system through discrete-event simulation, the procedure however, can successfully be applied to any processing system in various industries including food production, financial institutions, warehouse industry, and healthcare.

Download


Paper Citation


in Harvard Style

Tshibangu W. and Tshibangu A. (2013). A Two-step Empirical-analytical Optimization Scheme.In Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8565-71-6, pages 558-565. DOI: 10.5220/0004489105580565


in Bibtex Style

@conference{icinco13,
author={Wa-Muzemba Tshibangu and Anselm Tshibangu},
title={A Two-step Empirical-analytical Optimization Scheme},
booktitle={Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2013},
pages={558-565},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004489105580565},
isbn={978-989-8565-71-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - A Two-step Empirical-analytical Optimization Scheme
SN - 978-989-8565-71-6
AU - Tshibangu W.
AU - Tshibangu A.
PY - 2013
SP - 558
EP - 565
DO - 10.5220/0004489105580565