ASCE will be sunsetting the Civil Engineering Database (CEDB) in the coming months. We encourage you to start using the ASCE Library to perform content searches. In the ASCE Library, you can save your search results as well as receive email content alerts when new content relevant to your area of interest is published. Try it out today at https://ascelibrary.org.

 

NETSYN: Neural Network-based Support for Synthesis

by Nanad Ivezic, Carnegie Mellon Univ, United States,
James H. Garrett, Jr., Carnegie Mellon Univ, United States,



Document Type: Proceeding Paper

Part of: Computing in Civil and Building Engineering

Abstract:

Our goal in applying machine learning for synthesis is to develop a tool that assists in acquiring the relationships between form, function, and behavior properties that can be used to more directly determine form attributes that satisfy design requirements. The proposed approach to synthesis knowledge acquisition described in this paper, called NETSYN, creates a function to estimate the probability of each possible value of each design property appearing in a given design context. NETSYN uses a connectionist learning approach to acquire and represent this probability estimation function. This paper presents the NETSYN approach for synthesis knowledge acquisition and an example of its ability to support engineering synthesis.

Subject Headings: Artificial intelligence (AI) | Probability | Systems engineering | Neural networks | Standards and codes

Services: Buy this book/Buy this article

 

Return to search