Approach to modeling the spray-forming process with artificial neural networks

M. Allen Matteson; R. D. Payne; Craig Madden; A. L. Moran

doi:10.1117/12.174079

1 May 1994 Approach to modeling the spray-forming process with artificial neural networks

M. Allen Matteson, R. D. Payne, Craig Madden, A. L. Moran

Proceedings Volume 2189, Smart Structures and Materials 1994: Smart Materials; (1994) https://doi.org/10.1117/12.174079
Event: 1994 North American Conference on Smart Structures and Materials, 1994, Orlando, FL, United States

Abstract

In this study artificial neural networks were used to model the spray forming process. Networks were developed and trained using process parameter and product quality data collected from a series of five spray forming runs. Process parameters of time into run, melt temperature, and gas to metal ratio were used as inputs and the networks were trained to predict the corresponding values of exhaust gas temperature, preform surface roughness, and porosity in the product. These networks were then tested with actual and hypothetical data. The results of the study showed that the networks can determine relationships between process parameters and the end product quality. It was also shown that the networks can be used to predict the effect on product quality from changes in process parameters. Additional work is in progress to create a larger data set for training over a broader region of the operating envelope. The result of this ongoing work will provide greater reliability in network prediction.

Citation Download Citation

M. Allen Matteson, R. D. Payne, Craig Madden, and A. L. Moran "Approach to modeling the spray-forming process with artificial neural networks", Proc. SPIE 2189, Smart Structures and Materials 1994: Smart Materials, (1 May 1994); https://doi.org/10.1117/12.174079

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available