Discrete Simulation Studies Research Articles

Integral methodology simulation support for the improvement of production systems job shop. Metalworking applications in SMES

Metalworking companies represent one of the strategic sectors in the regional economy of the Caldas department in Colombia; in fact, this sector is involved in 31% of the departments industrial establishments and 29% of industrial employment according to DANE (Colombian State Statistical Department) statistical data from 2005. The sector also exports to Andean countries. However, preliminary studies conducted with 57% of the entrepreneurs from this sector (excluding micro companies and family businesses) have revealed serious structural (technology, processing, installations) and infrastructure weaknesses (production planning, quality systems) in these organisations production systems. It is hoped that this paper will lead to disseminating the results amongst the academic community of implementing a comprehensive methodology for improving the production system of a pilot company from this particular sector. An experimental framework for improving the levels reached by the system regarding such priorities is proposed following universally accepted methodology in discrete simulation studies; it proposes using sequential bifurcation, factorial design and response surface experimentation based on defining and weighting the competing priorities which the company should achieve. The improvements in the pilot companys production system priorities are presented in terms of an effectiveness index (EI) which rose from 1.84 to 2.46 by the end of the study.

Using exact statistical distributions for truck shovel simulation studies

Abstract Several simulation packages exist for doing studies to determine the optimum number of trucks to have in a mine. These packages require the cycle times for trucks and times for the other equipment such as dumps and loaders to perform their various tasks. In most cases the times for trucks, shovels, etc are given only by some statistical distribution. The mean is either known or can be obtained from the statistics. The question arises whether one can simply use the mean times or should one use the exact statistical distribution for the simulation. A GPSS/H simulation is used to provide insight into this problem by performing discrete simulation studies to show the effect on using different statistical distributions for times in a mine. A simple cycling queueing theory problem is considered. First, exact times are used for a mining cycling problem; then variation in the times is introduced; and, finally, a model using exponential and normal distributions is used for the example. It is found that ev...

Antithetic Bias Reduction for Discrete-Event Simulations

This study presents a technique for reducing the bias induced by arbitrary initial conditions in some discrete simulation studies. The technique relies on compensating the existing bias in a run by purposely introducing a deviation in the counter-direction during the subsequent run. Specifically, after obtaining a sample with initial condition X0, an antithetic companion run is generated starting from (2X - X0). This introduces an adjustment equal and opposite to the indicated deviation, as measured by the distance between the current sample mean X and the initial condition X0. Then the overall mean has a significantly lower bias. Application of the technique to first-order autoregressive process and to a machine-repair system revealed that it is capable of reducing, and in most cases practically removing, the transient effects within moderate sample sizes.