Using Taguchi design, regression analysis and simulation to study maintenance float systems

This paper proposes a new strategic approach for the maintenance float decision models. This new approach incorporates Taguchi experimental design, Taguchi’s ANOVA procedure and regression analysis. Taguchi experimental design is used to generate the input variables into the simulation program. The results are analysed using Taguchi’s ANOVA procedure. Input variables found significant are subsequently applied in a regression model. Predictor models for the system utilization are developed and their validity tested. Cost oriented decision models are further developed to show the applicability of the present models to decision situations. The major advantage of the strategic approach proposed here is that it saves time and reduces the cost of running simulation. This approach will also offer a decision support and improve the effectiveness of maintenance float decisions.