Engineering Commons^™

Deep Reinforcement Learning For The Design Of Structural Topologies, Nathan Brown

All Dissertations

Advances in machine learning algorithms and increased computational efficiencies have given engineers new capabilities and tools for engineering design. The presented work investigates using deep reinforcement learning (DRL), a subset of deep machine learning that teaches an agent to complete a task through accumulating experiences in an interactive environment, to design 2D structural topologies. Three unique structural topology design problems are investigated to validate DRL as a practical design automation tool to produce high-performing designs in structural topology domains.

The first design problem attempts to find a gradient-free alternative to solving the compliance minimization topology optimization problem. In the proposed …

An Evaluation Of Function-Based Representations And Information Archival In Engineering Design, Benjamin Caldwell

All Theses

Recent research in function-based design includes the development of a vocabulary of functions, the Functional Basis, and a repository of products and their functions. Many design tools are being developed around this vocabulary and repository to support conceptual design. The usefulness of these tools, however, is dependent on the quality of the vocabulary and the information contained in the repository. In this research, both the vocabulary and the repository are empirically evaluated to understand their strengths and limitations. A statistical analysis is performed on function models in the repository to determine the frequency of usage of Functional Basis terms. It …