Generative Bayesian networks for conceptual aircraft design
Abstract/Contents
- Abstract
- Conceptual aircraft design, with its basis in engineering design, is an open-ended problem in which human designers synthesize solutions to meet a set of requirements. This open-ended prob- lem inherently necessitates an iteration process combining creation and testing. Designers approach these problems with their intuition, experience, and knowledge of physics to achieve this iteration process. However, future aircraft design requirements break away from traditional norms, leaving the seasoned human designer with little intuition. This work devises an architecture by taking cues from how human designers lead design pro- cesses. This architecture also becomes an iterative design loop with creation and testing. A prob- abilistic model, the generative Bayesian Network, suggests candidate designs for the architecture. The generative Bayesian Network decomposes the problem into physical components and finds the interactions between them, as a systems design. The generative Bayesian Network learns examples from a combination of historical data and generations analyzed with SUAVE, an aircraft conceptual design tool. SUAVE is especially suited for this process since it possesses the ability to analyze and optimize numerous types of aircraft. This architecture enables a human designer to consider concepts and configurations they might have otherwise not considered. Four test cases examine the effectiveness of this architecture that combines SUAVE with a gen- erative Bayesian Network. First, a simple beam design illustrates how multiple valid solutions may be found. Next, are two cases, that design with differing levels of complexity to compare against an existing medium-range airliner. Finally, an ultra-long-range aircraft is designed with mission requirements unprecedented today. The architecture returns feasible design concepts prepared for more in-depth design studies and development.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2019; ©2019 |
Publication date | 2019; 2019 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Botero, Emilio Matias |
---|---|
Degree supervisor | Alonso, Juan José, 1968- |
Thesis advisor | Alonso, Juan José, 1968- |
Thesis advisor | Kochenderfer, Mykel J, 1980- |
Thesis advisor | Kroo, Ilan |
Degree committee member | Kochenderfer, Mykel J, 1980- |
Degree committee member | Kroo, Ilan |
Associated with | Stanford University, Department of Aeronautics and Astronautics. |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Emilio M. Botero. |
---|---|
Note | Submitted to the Department of Aeronautics and Astronautics. |
Thesis | Thesis Ph.D. Stanford University 2019. |
Location | electronic resource |
Access conditions
- Copyright
- © 2019 by Emilio Matias Botero
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...