Artificial Intelligence for Constructing Accurate, Low-Cost Models and
Abstract
Modeling and Simulation is an important tool in product development. Current practice is to use an equation-based approach. Equation-based models can require extensive time and money to construct high fidelity models that accurately represent the real world. The primary goal of this research is to explore alternate methods of creating accurate models and simulations that can be done rapidly and at much lower. The research compared engineering modeling applications for time of construction and the accuracy between equation-based models and three methods of Bayesian network construction: human judgment, formulae and computer-generated. The derivative method, a multivariate approach to discretion continuous data was proposed and compared to four current search and score methods. The comparison found little difference in performance between different methods of discretion; however, the derivative method was faster than any of the iterative search and score techniques. The research software also integrated a neural network into the Bayesian network construction.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2005
- Accession Number
- ADA484107
Entities
People
- David P. Brown
Organizations
- Defense Acquisition University