Degree Type

Thesis

Date of Award

2017

Degree Name

Master of Science

Department

Industrial and Manufacturing Systems Engineering

Major

Industrial and Manufacturing Systems Engineering

First Advisor

Cameron A. MacKenzie

Abstract

The aviation industry represents a complex system with low-volume high-value manufacturing, long lead times, large capital investments, and highly variable demand. Making important decisions with intensive capital investments requires accurate forecasting of future demand. However, this can be challenging because of significant variability in future scenarios. The purpose of this research is to develop an approach on making long-term production planning decision with appropriate demand forecasting model and decision-making theory.

The first study is focused on demand forecasting. Probabilistic models are evaluated based on the model assumptions and statistics test with historical data. Two forecasting models based on stochastic processes are used to forecast demand for commercial aircraft models. A modified Brownian motion model is developed to account for dependency between observations. Geometric Brownian motion at different starting points is used to accurately account for increasing variation. A comparison of the modified Brownian motion and Autoregressive Integrated Moving Average model is discussed.

The second study compared several popular decision-making methods: Expected Utility, Robust Decision Making and Information Gap. The comparison is conducted in the situation of deep uncertainty when probability distributions are difficult to ascertain. The purpose of this comparison is to explore under what circumstances and assumptions each method results in different recommended alternatives and what these results mean making good decisions with significant uncertainty in the long-term future.

Copyright Owner

Minxiang Zhang

Language

en

File Format

application/pdf

File Size

78 pages

Share

COinS