Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.525880
Title: Improving operational effectiveness at vehicle inspection centres
Author: Samah, Azurah A.
Awarding Body: University of Salford
Current Institution: University of Salford
Date of Award: 2010
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
In this research, operational problems at vehicle inspection centres (VIC) are explored and investigated. Simulation is used in this new application area to improve operational effectiveness at the VIC. In particular, simulation is used to gain insights, model the interactions of operational activities and experiment with specific operational policies. Critical input random variables corresponding to service times and arrival patterns are modelled based upon empirical data collected at the VIC. Modelling the arrival process involves a thorough analysis of separate patterns of arrival for scheduled and non- scheduled vehicles at a typical VIC. Developing the most appropriate of several ideas, we generate methods for simulating typical streams of arrivals at the VIC. For non- scheduled arrivals, we adopt distinct beta distributions for morning and afternoon activities. For scheduled arrivals, this research demonstrates that customer punctuality varies according to planned appointment times, which leads to an adaptive model for customer punctuality that takes account of these appointment times. Specifically, we construct generalised beta distributions with parameters that evolve over time. In this research, we integrate the design of experiments within our simulation model. In particular, we propose a fractional factorial design matrix to replace traditional ways of planning simulation experiments. Further work involves incorporating blocking into our design matrix, which reduces the experimental size and provides a useful backup support feature for our VIC simulation. The proposed design matrix is then used in the output analysis along with other statistical methods, to determine factors that contribute significantly to specific performance measures. In this study, general linear models that link the control factors and the performance measures are developed. A major contribution of this research is its impact on simulation modelling, which helps us to characterize more realistic arrival patterns for customers compared with previous research techniques. Additionally, aspects of our research that include experimental design enrich the literature on simulation and modelling particularly in the application of simulation to service shop problems.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.525880  DOI: Not available
Share: